Systems and methods for intelligent, cloud-based real-time health surveillance using an IOT-enabled wearable device

Abstract

The present disclosure describes an intelligent, cloud-based, wearable IoT-enabled device for real-time ECG monitoring and cardiovascular health assessment. It tracks ECG, heart rate, respiration, SpO2, skin temperature, and activity using integrated biosensors, a central microprocessor, and wireless transceivers (Wi-Fi, Bluetooth, 3G–6G). The device supports GPS tracking and local ECG analysis, including noise filtering, R-peak detection, and arrhythmia identification. An AI module detects cardiac events such as AFib and PVCs, with data visualized through a personalized dashboard. Additional features include fall detection, pacemaker signal filtering, voice messaging, and modular support for external biosensors. Data is securely transmitted to a cloud-based platform for AI-driven analytics, remote access, and proactive medical alerts. The ergonomic, standalone design suits both clinical monitoring and everyday wellness tracking.

Description

SYSTEMS AND METHODS FOR INTELLIGENT, CLOUD-BASED REAL-TIME HEALTH SURVEILLANCE USING AN IOT-ENABLED WEARABLE DEVICECROSS-REFERENCE TO RELATED APPLICATION

[0001] The present disclosure application claims priority from pending IR Patent Application Serial No 140350140003000392, filed on April 13, 2024, entitled “Intelligent IOT & Cloud-Based, real-time, smart vital signs surveillance system, for cardiovascular patients”, which is incorporated by reference herein in its entirety.TECHNICAL FIELD

[0002] The present disclosure relates to systems and methods for real-time cardiovascular health surveillance, specifically to a system and method for integrating multiple biosensors within a wearable, loT-enabled device to monitor vital signs such as, but not limited to, heart rate, oxygen saturation, respiration rate, faint detection and stress levels.BACKGROUND

[0003] Millions of people worldwide suffer from cardiovascular illnesses, which continue to be one of the main causes of death and have a substantial social and financial impact. The frequency and extent of patient evaluation are limited by traditional monitoring guidelines for such illnesses, which frequently call for sporadic or clinic -based examinations. This places a significant burden on healthcare systems. Acute events can be prevented and early intervention chances lost when patients with chronic illnesses, such as heart disease or hypertension, do not have continuous surveillance.

[0004] Numerous wearable gadgets that can monitor blood oxygen levels, heart rates, and other related characteristics have been developed in an effort to improve patient outcomes.Many of these devices are limited, nevertheless, by their incapacity to deliver real-timeautonomous analytics or to measure many vital signs at once. These technologies' ability to analyze data and produce actionable insights is often dependent on external devices ’s processors, such cellphones or personal computers, which limits their usefulness in situations when resources are scarce or important.

[0005] Other sensors or functionalities, such as voice modules for audio communication or accelerometers for step counting, are included into some suggested systems. However, these methods usually don't have the strong, centralized platform required to integrate respiration rate, oxygen saturation levels, ECG data, and other important metrics into a coherent monitoring system. Furthermore, a lot of the current solutions lack predictive analytics or alarm systems that may quickly identify changing cardiac risks and notify family members or emergency services without the need for direct doctor supervision.

[0006] Therefore, a wearable device that is portable, intelligent, and all-inclusive and that can track a variety of cardiovascular and general health markers in real time is still desperately needed. In addition to tracking a variety of metrics, such as blood pressure, stress levels, and ECG, such a system would also evaluate data in real time — a system and method to do analysis on the local board's processor and then transmitting data to a computing device, which processes data not only in the local memory but also in the cloud, for further analysis to reduce the computational time cost is necessary — forecast potential health risks, and notify caregivers or medical experts as necessary. By suggesting an Internet of Things-enabled wearable gadget that can collect, analyze, and send physiological data on its own, the current disclosure fills this demand and offers integrated, affordable, and user-friendly health monitoring options.SUMMARY

[0007] This summary is intended merely to introduce certain concepts of the invention disclosed herein. It is not intended to identify key or essential features of the claimed subject matter, nor is it intended to limit the scope of the claimed subject matter. The proper scope of the present disclosure can be ascertained from the claims set forth below, in view of the detailed description and accompanying drawings.

[0008] In one general aspect, the present disclosure provides a wearable health-monitoring device configured to collect, analyze, and transmit multiple physiological signals relevant to cardiovascular well-being. The device may incorporate an ECG module, a heart rate sensor, an oxygen saturation sensor, and additional biosensors to generate a comprehensive view of the user’s health status. In certain embodiments, the system further includes communication modules, such as a Global Positioning System (GPS) receiver and a cellular SIM card interface, enabling the device to operate autonomously — communicating urgent alerts or vital data to healthcare providers and designated caregivers in real time.

[0009] By integrating advanced sensing technology with artificial intelligence or cognitive computing techniques, the system may predict potential health risks and issue timely recommendations. The disclosed device may function independently, without requiring constant connection to external smart devices since all the analysis related to the cardiovascular system can be done on a local processor, and may present alerts or warnings through visual, auditory, or haptic interfaces by an external computing device, which processes data not only in the local memory but also in the cloud. In some implementations, the system supports voice messaging between patients and clinicians, automatic fall detection, and environmental sensing (such as ambient temperature) to provide a more complete understanding of user well-being.

[0010] The present disclosure thereby addresses the shortcomings of existing wearable and clinic -based solutions by offering real-time data analysis on the local processors, multipleparameter integration, and immediate emergency alert capabilities which can be done by an external computing device. Additional features and exemplary embodiments will be apparent from the following description, which, together with the accompanying drawings, illustrate certain principles of the disclosed innovations.

[0011] In one exemplary embodiment, the wearable health-monitoring system described here, in one illustrative form, does away with the need for external devices like smartphones, tablets, or PCs to process data. Instead, the system runs independently thanks to an internal battery and inbuilt electronics that locally evaluate important electrocardiogram (ECG) data and transform analog impulses into digital form. To detect any cardiac abnormalities in real time, the device may in some implementations detect and interpret waveform components such as P, Q, R, S, T, or U waves and evaluate intervals like RR and ST. However, furthere analysis like health-report writing, alerting, comparing with public datasets’ features, and storing personalized data can be done through a web application, personal dashboard, using an external device In the early phases of diagnosis, this method lessens the requirement for ongoing medical supervision while maintaining the capacity to elevate alarms when required.

[0012] The system may be configured as an Internet of Things (loT)-based, cloud-enabled wearable device that supports continuous surveillance of multiple physiological parameters. In various implementations, the device can simultaneously measure parameters such as ECG signals, respiration rate, oxygen saturation, and body temperature, among others. Certain configurations permit real-time analysis of these metrics so that, upon detecting an imminent cardiac emergency, the device can automatically transmit the patient’s location via a globalpositioning service (GPS) and forward a message through available data networks to emergency responders, healthcare centers, or the user’s family.

[0013] In another exemplary embodiment, the disclosed wearable device is designed to acquire data from multiple biosensors in parallel, thereby enabling simultaneous monitoring of heart activity, blood oxygen levels, respiratory patterns, and potential faint or fall events. The device further supports advanced detection of life-threatening conditions such as strokes, cardiac arrhythmias, or other high-risk events, providing timely notifications through a built- in communication module. Moreover, the system may incorporate an internal mechanism to disregard pacemaker artifact signals and verify the correctness of ECG electrode connections in both wearable and stationary use cases (e.g., in hospital environments).

[0014] The device may be configured to connect wirelessly to external computing devices, such as blood pressure cuffs or blood glucose sensors, thereby expanding its functionality and offering a comprehensive health-monitoring system. Collected data can be stored locally, streamed to a central server, or both. In certain implementations, a cloud-based dashboard or dedicated software application may enable healthcare providers, patients, and authorized family members to access historical records, visualize trends, and utilize advanced analytics, powered by algorithms and artificial intelligence, to predict health risks or recommend preventive measures. This infrastructure may also facilitate lifestyle coaching by evaluating parameters such as step counts, estimated caloric expenditure, and sleep quality.

[0015] The current invention's robust, multi-parameter monitoring, real-time warnings, autonomous local analysis for cardiovascular data, and thorough cloud integration set it apart from other wearable or clinic-based monitoring systems. The invention's adaptive sampling approach, which may modify measurement frequency in response to past readings or individual clinical histories in order to save battery life, is another feature that sets it apart. Because itfacilitates early intervention, lowers needless hospital stays, and encourages safer, more active lifestyles outside of formal care facilities, this real-time and predictive capabilities is especially beneficial for individuals with chronic cardiac diseases.

[0016] In an additional aspect, the present disclosure contemplates a method for real-time electrocardiogram (ECG) analysis on a local processor using a wearable loT-enabled device. The method may include providing an electronic assembly on a flexible support structure, which comprises a modular architecture that permits modules and sensors to be configured and implemented on the board in a systematic, scalable, and robust manner, receiving and digitizing ECG signals from at least two electrical leads, filtering out high-frequency and baseline noise, and segmenting the resulting data into sequential time windows. Each segmented time window can then be examined to identify cardiac wave components, such as R peaks, for calculating heart rate or other relevant clinical metrics. By employing local signal processing in tandem with cloud-based servers, this method offers a robust blend of autonomous operation and large- scale data storage.

[0017] In certain implementations, the method may further include adjusting sampling or segmentation parameters based on user-specific histories or previously recorded intervals, thereby optimizing power consumption and reducing redundant measurements. The method may also provide continuous comparisons of detected ECG intervals against established thresholds, enabling the system to trigger alerts or share processed data with remote healthcare professionals whenever anomalous patterns arise. These capabilities facilitate timely interventions and reduce the burden on clinical resources, particularly in regions where access to specialized cardiac care may be limited.

[0018] This Summary may introduce a number of concepts in a simplified format; the concepts are further disclosed within the “Detailed Description” section. This Summary is notintended to configure essential / key features of the claimed subject matter, nor is intended to limit the scope of the claimed subject matter.BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The novel features which are believed to be characteristic of the present disclosure, as to its structure, organization, use, and method of operation, together with further objectives and advantages thereof, will be better understood from the following drawings in which a presently preferred embodiment of the present disclosure will now be illustrated by way of example. It is expressly understood, however, that the drawings are for the purpose of illustration and description only and are not intended as a definition of the limits of the present disclosure;

[0020] FIG. 1 illustrates a block diagram of an exemplary system for real-time monitoring of electrocardiogram (ECG) signals using a wearable Internet of Things (loT)-enabled device, consistent with one or more exemplary embodiments of the present disclosure. The system initiates by positioning the wearable device on the user, followed by verifying sensor lead connection to ensure proper signal acquisition. Once validated, the system begins acquiring multiple physiological signals, including ECG data. The acquired data undergoes in-device electrocardiogram analysis to extract relevant features. The processed data is then transmitted to an external computing device, which processes data not only in the local memory but also in the cloud, where extended signal processing is conducted for further health assessment. Finally, the system issues user alerts and notifications based on the analyzed data, allowing timely intervention in case of detected abnormalities;

[0021] FIG. 2 illustrates a block diagram of an exemplary method for analyzing electrocardiogram (ECG) data, consistent with one or more exemplary embodiments of the present disclosure. The method includes recording raw ECG data, applying band-pass filteringto remove noise, segmenting the filtered ECG data, subdividing each segment, and analyzingECG data in each sub-window to identify key features such as R-peaks and RR intervals for further evaluation.

[0022] FIG. 3 illustrates a flowchart of an exemplary method for analyzing noise-removed ECG data, consistent with one or more exemplary embodiments of the present disclosure. The process begins with analyzing noise-removed ECG data and creating incremental and decremental tables. It then involves differentiating consecutive samples to populate the respective tables. Next, peak values are sorted and compared with a threshold to identify R peaks. The method proceeds by determining R peak positions, calculating RR intervals, and estimating heart rate, before concluding the analysis;

[0023] FIG. 4 illustrates a block diagram of an exemplary method for ECG data processing. The method includes transmitting and storing analyzed ECG data in an external device, detecting arrhythmia and trends, segmenting noise-removed ECG data, comparing with historical records to identify abnormalities, and evaluating cardiac risk to send alerts to patients or doctors;

[0024] FIG. 5 illustrates a block diagram of the electronic components within the wearable device, consistent with exemplary embodiments of the present disclosure.

[0025] FIG. 6 illustrates a front view of the wearable device, consistent with exemplary embodiments of the present disclosure;

[0026] FIG. 7 illustrates a back view of the wearable device, showing the sensor interface, ECG electrodes, and attachment mechanism for direct contact with the user’s skin, ensuring accurate data acquisition;

[0027] FIG. 8 illustrates a user wearing the wearable device, demonstrating its placement, fit, and interaction with the body for continuous physiological monitoring;DETAILED DESCRIPTION

[0028] In the following detailed description, various specific details are provided as examples to facilitate a comprehensive understanding of the disclosed embodiments. However, it should be understood that these teachings can be implemented without incorporating every specific detail mentioned. In some instances, well-established techniques, components, and methodologies have been described in a more general manner to avoid overcomplicating the explanation of key aspects of the present disclosure.

[0029] This detailed description is intended to guide those skilled in the field in implementing and utilizing the methods and devices disclosed in exemplary embodiments of this disclosure. For clarity, specific terminology has been used to enhance comprehension. However, it will be evident to those familiar with the subject matter that these precise details are not strictly necessary for the practical application of the disclosed embodiments. The descriptions of particular implementations serve as illustrative examples rather than definitive limitations. Modifications and adaptations will be apparent to those skilled in the art, and the underlying principles described herein may be extended to various other implementations without deviating from the essence of this disclosure. Accordingly, the present disclosure should not be interpreted as being confined solely to the described implementations but should be regarded in the broadest sense, consistent with the fundamental concepts and features presented.

[0030] The present disclosure pertains to exemplary embodiments of a wearable Internet of Things (loT)-enabled health monitoring system designed for real-time acquisition and analysis of physiological signals. The disclosed system improves continuous health tracking's accuracy and efficiency by combining biosensors with an electronic assembly. In order toidentify abnormalities and provide processed data to an external computer device, this wearable gadget tracks electrocardiogram (ECG) signals, heart rate (HR), blood oxygen saturation (SpCh), body temperature, respiration rate, and other critical parameters such as blood pressure and blood sugar (via a connected wireless accessory device), step counter, calorie meter, sleep quality measurement, fall detection, stress level monitoring, voice messaging between patient and doctor, and recording and transmitting heart sounds. The system also supports early diagnosis and proactive healthcare management by enabling real-time alerts, predictive analytics, and Al-driven health evaluations through connection with cloud-based systems.

[0031] An exemplary wearable health monitoring system may comprise a multi-board electronic assembly, a microprocessor unit, and a set of integrated biosensors for real-time physiological signal processing. The system may have temperature sensors, SpCh sensors, ECG sensors, and other health-tracking modules that are electrically connected to the local processor. Additionally, the gadget may have wireless connectivity modules for data transfer to other computing devices, allowing for remote monitoring and sophisticated health analytics.

[0032] An exemplary wearable health monitoring system may incorporate a set of biosensors configured to capture various physiological signals from the user’s body. At least one heart rate sensor, blood oxygen (SpO?) sensor to track oxygen saturation levels, and ECG electrodes positioned to detect cardiac activity may all be part of the system. To continuously monitor skin temperature, a temperature sensor array may also be incorporated. A local processor electrically connected to these biosensors, processing and analyzing the collected data in real time.

[0033] The microprocessor may be configured to perform signal filtering, segmentation, and feature extraction, ensuring accurate health assessments. Furthermore, the system may include wireless communication modules, such as Wi-Fi, Bluetooth, or cellular connectivity,to facilitate real-time data transmission to external computing devices, enabling remote monitoring and diagnostics.

[0034] This exemplary wearable health monitoring system provides a compact, efficient, and versatile solution for continuous health tracking. Its integration of multiple sensing modalities, combined with advanced data processing capabilities, ensures real-time analysis and proactive healthcare management, supporting early detection of potential health risks.

[0035] The present disclosure further describes a method integrated within the wearable health monitoring system, specifically for the acquisition, processing, and transmission of electrocardiogram (ECG) signals to support real-time cardiac assessment. Continuous ECG waveform recording, cardiac anomaly detection, and analysis of important signal components, such as P, Q, R, S, T, and U waves, as well as critical intervals, such as RR and ST segments, are all features of the wearable device. Locally processing ECG data, the system filters out pacemaker signals and detects anomalies including arrhythmias and premature ventricular contractions (PVCs). Additionally, the device facilitates bidirectional audio contact between patients and medical professionals, allowing ECG data to be transmitted in real time for remote assessment. Additionally, the system offers wireless connection to external devices, including portable ECG printers, allowing for real-time visualization and documentation of cardiac data. Integrated with advanced analytical software, the system leverages Al-based algorithms to assess ECG patterns, predict potential cardiovascular risks, and provide automated alerts for critical conditions. This method is primarily designed for continuous cardiac monitoring in individuals with heart conditions, facilitating early diagnosis and intervention while reducing the need for hospital-based monitoring. However, it may also be utilized by healthy individuals for routine cardiac assessments and proactive heart health management.

[0036] An exemplary wearable health monitoring system may include a self-contained processing unit configured to operate independently without requiring external computing devices. The system may be powered by an internal rechargeable battery, enabling continuous monitoring. It may incorporate an advanced signal processing module capable of converting analog ECG signals into digital form, extracting key waveform components such as P, Q, R, S, T, and U waves, and measuring critical intervals including RR and ST segments. The device may support real-time analysis of ECG signals to detect cardiac abnormalities, such as arrhythmias, atrial fibrillation (AFib), and premature ventricular contractions (PVCs).

[0037] An exemplary method for identifying the R wave in an electrocardiogram (ECG) signal may include analyzing the sequence of increasing and decreasing waves within a predefined time window. The system may evaluate waveform characteristics and detect the R wave based on predefined criteria, such as the steepest positive and negative slopes, the highest peak, and the most significant drop in amplitude.The method may further include comparing multiple R wave candidates within the time window to ensure accurate detection. If more than one potential R wave is identified, the system may analyze the second-highest peak and determine its classification based on its amplitude relative to the primary R wave. If the secondary peak is at least 30% lower than the primary R wave, it may be excluded as a non-R wave, possibly a T or U wave. The identified R wave may then serve as the reference point for further waveform analysis within the cardiac cycle. The method may also dynamically adjust the time window size based on detected wave characteristics, optimizing segmentation for subsequent pulses. The total number of R waves detected within one minute may be used to estimate the patient’s heart rate by counting R peaks within a 10-second interval and multiplying the count by six.

[0038] An exemplary method for identifying additional waves in a cardiac cycle may involve determining the QRS complex based on the position and magnitude of the reference R wave. It is possible to identify the Q wave as the lowest dip that comes before the R wave and the S wave as the lowest point that comes after the R wave. Following the classification of the QRS complex, the P and T wave detection process may begin. The greatest peak before the Q wave may be the P wave, which indicates atrial depolarization, while the most noticeable peak after the S wave may be the T wave, which indicates ventricular repolarization. By monitoring the time disparities between observed wave locations, the system can also calculate crucial time intervals for the ST segment, P-QRS duration, and R-S duration. Wave amplitudes and time intervals are among the data that may be saved for further analysis.

[0039] An exemplary method for detecting the U wave within a cardiac cycle may include analyzing waveform characteristics following the T wave. The system may identify the U wave based on its relative amplitude and location. To ensure correct classification, the method may compare the detected wave with the P wave. If the candidate U wave has an amplitude within 50% of the P wave, it may be excluded as a potential U wave. Otherwise, if it meets the amplitude threshold, it may be classified as the U wave. Following U wave detection, the system may store extracted waveform position in time axis, including peak positions, amplitudes, and time intervals. Temporary processing variables may be cleared while the ECG waveform is retained for visualization. The processed ECG data will be transmitted to a cloud server for further analysis and long-term storage.

[0040] An exemplary method for evaluating ECG waveform characteristics may include comparing key ECG parameters against established clinical thresholds. Major waveform components, including the R wave, PR interval, QRS complex, ST segment, T wave, and QT interval, may be evaluated for amplitude and duration. If any of these parameters deviate fromnormal reference ranges, the system may produce a preliminary diagnostic alert. For example, an elevated ST segment may suggest a potential myocardial infarction, whereas a prolonged QT interval may suggest an increased risk of arrhythmia. The method may also analyze arrhythmia risks by evaluating waveform characteristics, such as missing P waves in atrial fibrillation or prolonged QRS duration in bundle branch blocks. To enhance diagnostic accuracy, the method may analyze ECG signals over a predefined time frame, such as 30 seconds, and compare findings against historical patient data. If a potential cardiac event is detected, alerts may be issued for further medical evaluation. All collected data may be securely tramsmitted to a cloud-based system, allowing healthcare professionals to track long-term patient trends. It is noted that while this system provides early cardiac abnormality detection, it serves as an assistive tool and does not replace professional medical diagnosis.

[0041] An exemplary wearable health monitoring system may include wireless communication modules configured to support real-time data transmission via Wi-Fi or 4G LTE networks. A GPS module may be integrated to enable location tracking, facilitating emergency alert when necessary. To ensure precise ECG signal gathering, the system may also include an inbuilt algorithm intended to identify and fix lead connection issues. Furthermore, motion sensors can be used to identify fainting or collapse occurrences by detecting abrupt changes in movement.

[0042] An exemplary system may support external ECG lead configurations, allowing for up to 12-lead setups to enhance diagnostic capabilities. Real-time processing and interpretation of ECG data by an Al-powered analytical module can identify patterns suggestive of possible heart problems. Additionally, the system may have a cloud-based data storage component that would give authorized users and medical professionals safe access to recorded health information. Additionally, by minimizing needless data collecting while preserving highdiagnostic accuracy, an efficient query-processing method may be used to increase power efficiency.

[0043] An exemplary wearable health monitoring system may include a high-capacity NAND memory module configured for storing extensive health data records, along with an SD-RAM module designed for rapid data processing, particularly in Al-driven analytical tasks. These memory components may be permanently embedded within the device, ensuring secure and reliable data retention without the need for removal or external storage. These memory elements may be permanently included inside the gadget, guaranteeing safe and dependable data preservation without requiring removal or external storage. Real-time monitoring and retrospective health evaluations can be supported by optimizing the memory system for effective storage and retrieval. By combining cloud-based analytics, Al-assisted diagnostics, and multi-modal sensing, the system may offer a complete answer for preventative and ongoing healthcare management.

[0044] In accordance with one or more example implementations of the current disclosure, FIG. 1 depicts a block diagram 100 of an exemplary wearable health monitoring system. The system may proceed in a structured order, as shown in FIG. 1, starting with Positioning the Wearable Device 101, which entails positioning the device appropriately on the user's body. Verifying Sensor Lead Connection 102, the following step, makes sure that all electrodes and biosensors are positioned appropriately for precise physiological signal capture. After verification, the system moves on to Acquiring Multiple Physiological Signals 103, where a number of biometric parameters are continually captured, including electrocardiogram (ECG) data. The signals are then processed by performing In-Device Electrocardiogram Analysis 104, which allows for the local computation of ECG waveforms and the identification of possible cardiac irregularities; transmitting Processed Data to External Computing Device105, which permits the safe transfer of analyzed health data to cloud-based platforms or remote monitoring systems; conducting Extended Signal Processing 106, which refines the acquired data with additional computational algorithms to improve accuracy; and, finally, facilitating user engagement and safety measures by issuing User Alerts and Notifications 107, which offers real-time health insights and emergency warnings when needed.

[0045] FIG. 2 illustrates a block diagram 200 of an exemplary method for analyzing electrocardiogram (ECG) data, consistent with one or more exemplary embodiments of the present disclosure. As shown in FIG. 2, the procedure starts with Recording Raw ECG Data 201, in which the user provides the system with raw electrocardiographic signals. After data is acquired, the technique continues on to Performing Band-Pass Filtering 202, which improves signal clarity by eliminating undesirable frequency components and noise. After the ECG data has been filtered, it is put into Segmenting Noise-Removed ECG Data 203, which separates the signal into useful parts for additional examination. Subdividing Each Segment 204 allows for better granularity in signal assessment by facilitating in-depth analysis of each segment. Analyzing ECG Data in Each Sub-window 205, the method's conclusion, identifies important characteristics like R-peaks and RR intervals for additional clinical assessment and possible arrhythmia identification.

[0046] FIG. 3 illustrates a flowchart 300 of an exemplary method for analyzing noise- removed electrocardiogram (ECG) data, consistent with one or more exemplary embodiments of the present disclosure. The procedure starts with Start Analyzing Noise-Removed ECG Data 301, where the system starts analyzing filtered ECG signals, as shown in FIG. 3. By organizing the data into an Incremental Table 303 and a Decremental Table 304, the procedure moves on to Creating Two Tables Containing ECG Data Samples 302. In order to fill these tables, the system differentiates successive ECG samples using Filling the Incremental Table 305, addingvalues to the incremental table if the difference is positive. Filling up Decremental Table 306, which records negative differences, is a step in the procedure that is done concurrently. After the technique is filled, signal peaks are ranked and assessed in relation to a predetermined threshold in the Sorting Peak Values and Comparing with Threshold to Identify R Peaks 307 step. The algorithm may then pinpoint the exact positions of the selected peaks by mapping them using Finding R Peaks Positions 308. Calculating RR Intervals in Each Sub-window 309, which calculates the time intervals between subsequent R peaks, comes after peak identification. The procedure concludes with Finish Analyzing Noise-Removed ECG Data 311 after completing Estimating Heart Rate Based on RR Intervals 310 to evaluate cardiac rhythm.

[0047] FIG. 4 illustrates a block diagram 400 of an exemplary method for processing and analyzing electrocardiogram (ECG) data, consistent with one or more exemplary embodiments of the present disclosure. As depicted in FIG. 4, the process begins with Transmitting and Storing Analyzed ECG Data into an External Computing Device 401, where the system securely transfers processed ECG signals to an external computing platform for further evaluation. The system uses signal processing methods to detect irregular heart rhythms and patterns suggestive of cardiac problems in Analyzing ECG Data to Detect Arrhythmia and Trends 402. The system then divides the filtered ECG signals into meaningful portions for accurate analysis via a process called Segmenting Noise-Removed ECG Data 403. Comparing ECG Data with Historical Records to Identify Abnormalities 404 is the next step in the process, which enables the system to evaluate departures from the patient's baseline and find early indicators of possible health issues. The final step involves Evaluating Cardiac Risk and Sending Alerts to Patients or Doctors 405, where detected abnormalities trigger notifications to healthcare providers or patients, enabling timely medical intervention if necessary.

[0048] FIG. 5 illustrates a block diagram 500 of the electronic components within the wearable health monitoring device, consistent with one or more exemplary embodiments of the present disclosure. As depicted in FIG. 5, the system includes a Communication Interface 501, centrally positioned to facilitate bidirectional data exchange between various internal components and external networks. Real-time data transfer is ensured by the Network Interface 502, which permits access to cellular, Bluetooth, and Wi-Fi networks. Cellular connectivity capabilities are offered via the SIM Module 503 for emergency alerts and remote monitoring. For sophisticated data processing, an Al & Machine Learning Module 504 is included, allowing for predictive study of health patterns and automatic diagnosis of cardiac problems. For healthcare workers, a Cloud Server 505 component guarantees safe data storage and makes remote access easier. Users and medical professionals can check recorded health data and get alarms using an interface provided by a Web Dashboard / App 506. The Display Unit 507 provides customers with real-time visual feedback by displaying device status and important health parameters. The system has Local Storage 508 for managing local data, which permits short-term data holding prior to synchronization with cloud services. The Central Processor 509 is in charge of overseeing the activities of signal collecting, processing, and communication, making sure the device runs well. In order to help with fall detection and altitude adjustments, the wearable system incorporates a number of biosensors, such as an ECG Module 510 for acquiring electrocardiogram signals, a SpCh Sensor 511 for tracking blood oxygen saturation levels, a Temperature Sensor 512 for tracking changes in body temperature, and a Pressure Sensor 513 for detecting changes in environmental pressure. A Gyroscope & Accelerometer 514 module is included for motion analysis, enabling activity tracking and fall detection. Additionally, an Audio Module 515 is incorporated, featuring a microphone andspeaker for bidirectional voice communication between patients and healthcare providers, as well as for transmitting heart sound recordings.

[0049] FIG. 6 illustrates a front view 600 of an exemplary wearable health monitoring device, consistent with one or more exemplary embodiments of the present disclosure. As depicted in FIG. 6, the system includes a Display 601, which provides real-time feedback on health metrics, device status, and notifications. A number of physical keys 602 are incorporated beneath the display, each with a unique purpose. In an emergency, users may instantly notify emergency contacts by pressing the first key, which is designated as an SOS button. Regardless of the device's Al-driven monitoring or scheduled measures, users may manually start a thorough health check using the second key, a self-test button. In order to avoid needless alarms, the third key is a sport mode button that lets the system know that the user is exercising. This lowers sensitivity to brief spikes in heart rate and movement. The last key is a user-defined button that may be tailored to do particular tasks like calling a pre-defined contact or leaving a voicemail. On the left and right sides of the housing are belt attachment placeholders 603 and 606, which enable users to firmly fasten a belt or strap for enhanced wearability. The gadget has an inbuilt SIM Module 604 that allows for cellular access for communication and remote health monitoring. To continually check blood oxygen saturation levels, a SpCh Sensor 605 is included. The gadget has a microphone port 607 to improve audio performance. It is positioned to maximize sound quality for voice communication and heart sound recordings. Furthermore, a ventilation hole 608 is incorporated to reveal the ambient pressure sensor, which supports functions like altitude -based activity analysis and fall detection (faint detection).

[0050] FIG. 7 illustrates a back view 700 of an exemplary wearable health monitoring device, consistent with one or more exemplary embodiments of the present disclosure. As depicted in FIG. 7, the back panel of the device is designed for direct contact with the user’sbody, integrating multiple biosensors for continuous health monitoring. ECG Leads 1 704 and2701 are part of the device and are positioned to record electrocardiogram (ECG) signals from the user's body. Furthermore, multi-lead ECG monitoring is supported by the integration of ECG Leads 3 708 and 4 710, improving the precision of cardiac evaluations. The gadget has three separate temperature sensors (702, 703, and 709) to measure skin temperature at several points of contact, guaranteeing accurate and consistent temperature readings. Belt attachment placeholders 705 and 706 are situated on the left and right sides of the device to secure it to the user and enable comfortable use. In order to provide sophisticated acoustic health analysis, a contact microphone 707 is included into the rear panel. It is intended to record body -generated sounds, such as heartbeats and respiration noises.

[0051] FIG. 8 illustrates an exemplary representation 800 of a user wearing the wearable health monitoring device 801, consistent with one or more exemplary embodiments of the present disclosure. Belts 802 are used to firmly tie the device to the user's body, as shown in FIG. 8, guaranteeing appropriate sensor contact for precise physiological monitoring. The data transmission procedure, in which the device connects wirelessly to an external system 804 — which might include cloud-based processing and storage servers — is further depicted in the figure. Real-time health data analysis, remote medical professional monitoring, and safe storing of physiological signal recordings for later study are all made possible by this link.

[0052] The foregoing description presents exemplary embodiments of the disclosed wearable health monitoring system. However, it is understood that modifications, adaptations, and variations may be made without departing from the underlying principles of the invention. The disclosed technology may be implemented in different forms and applied in a variety of scenarios beyond those explicitly described. The following claims are intended to cover allmodifications, alternatives, and equivalent implementations that fall within the scope of the disclosed concepts.

[0053] Unless explicitly stated otherwise, all numerical values, measurements, dimensions, magnitudes, and other specifications mentioned throughout this document, including in the claims that follow, are approximate and not intended to be exact. These values allow for reasonable variations within the practical limits of their intended function and within the standard practices of the relevant field.

[0054] The scope of protection for this invention is defined solely by the claims that follow. The claims should be interpreted as broadly as possible while remaining consistent with the language used, the disclosure in this specification, and the historical context of the prosecution. However, no claim is intended to encompass subject matter that does not comply with statutory patentability requirements under applicable laws, including Sections 101, 102, and 103 of the Patent Act. Any inadvertent inclusion of such non-patentable subject matter is expressly disclaimed.

[0055] Except where explicitly stated otherwise, nothing in the specification or figures should be interpreted as dedicating any feature, component, step, or advantage of the disclosed invention to the public domain, regardless of whether or not it is explicitly mentioned in the claims.

[0056] The terminology used in this disclosure is intended to be understood with its ordinary meaning within the relevant technical fields unless a specific definition is provided. Relational terms such as “first” and “second” are used for differentiation purposes and do not imply a specific sequence or hierarchy unless explicitly stated. Additionally, the use of "a" or "an" should not be interpreted as limiting the invention to a single instance of the element unless specifically restricted.

[0057] The Abstract of this disclosure is provided solely for informational purposes to summarize key aspects of the invention. It should not be used to define or limit the scope of the claims. Furthermore, while various features and components are grouped together in the detailed description for clarity, this should not be interpreted as requiring all such features to be included in every embodiment. Each claim should be treated independently, reflecting distinct aspects of the disclosed invention.

[0058] While multiple embodiments and implementations have been described, they are intended to be illustrative rather than restrictive. Those skilled in the art will recognize that numerous modifications and variations may be introduced without deviating from the fundamental principles of the invention. Any feature described herein may be combined with others in different configurations unless explicitly stated otherwise. The disclosed embodiments should not be seen as limiting, and all modifications and equivalents that fall within the scope of the following claims are intended to be covered.

Claims

What is claimed is:

1. A method for real-time monitoring of electrocardiogram (ECG) signals using a wearable Internet of Things (loT)-enabled device, the method comprising: providing a multi-board electronic assembly comprising a flexible support structure with at least one microprocessor in electrical communication with a plurality of biosensors, the at least one microprocessor configured to receive and process real-time sensor data, wherein providing the multi-board electronic assembly comprising the flexible support structure with the at least one microprocessor in electrical communication with the plurality of biosensors comprises providing the multi-board electronic assembly comprising the flexible support structure with the at least one microprocessor in electrical communication with at least one ECG sensor, the at least one ECG sensor comprising at least two leads, wherein the at least one microprocessor is configured to check if the at least two leads are connected to a user's skin; receiving ECG data by the at least one microprocessor; and performing a real-time ECG analysis on the received ECG data via the at least one microprocessor comprising: generating a noise-removed ECG signal by performing at least one low-pass and at least one high-pass filtering on the received ECG data; segmenting the noise-removed ECG signal into a plurality of sequential time windows followed by subdividing each respective time window of the plurality of sequential time windows to a plurality of sub windows with a predetermined time duration, wherein each sub window of the plurality of sub windows comprises a plurality of signal samples; and estimating beats-per-minute (BPM) metric of the user comprising: identifying a maximum amplitude value and a minimum amplitude value within the each sub window of the plurality of sub windows by comparing amplitude values of the plurality of signal samples with each other; designating the maximum amplitude value as an R peak when the associated slope value exceeds a predefined threshold, and recording a timestamp of the R peak in a reference table;designating the maximum amplitude value in the each sub window of the plurality of sub windows as a respective R peak, followed by recording a respective timestamp corresponding to the respective R peak of the each sub window in a reference table; obtaining a plurality of R-R intervals by calculating a respective time difference between each two consecutive R peaks; storing the plurality of R-R intervals in a non-transitory memory; transmitting the received ECG data and the plurality of R-R intervals to a remote server of the external computing device; and determining a heart rate value of the user via the at least one microprocessor, comprising counting a respective R peak within the each sub window of the plurality of sub windows, and scaling the counted respective R peak within the each sub window to the BPM metric.

2. the method of claim 1, wherein the wearable loT-enabled device further comprises: at least one cardiac module comprising at least one cardiac sensor for monitoring ECG signals, heartbeat, and respiration, and providing pacemaker functionality; at least one blood oxygen sensor; at least one body temperature sensor; at least one environmental pressure sensor for measuring air pressure and detecting fainting; at least one inertial sensor, including a gyroscope and an accelerometer, for detecting angular orientation and physical motion; and at least one voice messaging module comprising at least one speaker, at least one microphone, and at least one amplifier for exchanging voice messages and transmitting heart sound data.

3. the method of claim 1, further comprising: at least one central processor configured for managing and processing data and exchanging data with an external server;at least one communication module for establishing a cellular connection (3G / 4G / 5G / 6G), data transfer, and GPS tracking; at least one charging module for charging the system’s battery and powering the system; at least one communication module for enabling Wi-Fi and Bluetooth communication.

4. the method of claim 1, wherein if no R peak is detected within the sub-window, the method further comprises applying a secondary peak detection algorithm to identify at least one of a P wave, T wave, or U wave.

5. the method of claim 1, wherein the step of transmitting the ECG data and the plurality of R-R intervals to a computing device further comprises transmitting said data to a computing device that comprises at least one database configured to store the user's data and at least one server configured to perform further analysis of the transmitted data.

6. The method of claim 1, further comprising: using at least one feedback system disposed within the wearable device to provide alerts or guidance to the user upon detection of critical physiological conditions, wherein the feedback system includes at least one of visual indicators, haptic actuators, or auditory alarms.

7. The method of claim 1, further comprising: a module providing a personalized user dashboard, wherein each user has access to a display interface that presents real-time and long-term physiological data, including analyzed trends and patterns. The dashboard further comprises an artificial intelligence(Al) system configured to analyze the data for abnormalities, detect potential health issues,and generate alerts.

8. The internal combustion engine of claim 1, wherein the at least one first crankpin comprises two crankpins disposed on opposite ends of the crankshaft.

8. The method of claim 1, wherein the step of transmitting the ECG data and the plurality of R-R intervals to a computing device further comprises transmitting said data to a computing device that comprises at least one database configured to store the user's data and at least one server configured to perform further analysis of the transmitted data.

9. The method of claim 1, further comprising a noise suppression circuit configured to detect and delete pacemaker-induced noise artifacts and other movement artifacts due to daily usage, in cases where the user employs a pacemaker, the noise suppression circuit comprising a detection module that distinguishes between intrinsic cardiac signals and pacemaker-generated pulses, and a filtering module that selectively removes the pacemaker noise from the ECG data prior to the signal analysis.

10. The method of claim 1, further comprising a removeable display unit located on a front-facing portion of the wearable device, the display unit configured to show real-time physiological data, system status, and user notifications.

11. The method of claim 1, further comprising four physical keys integrated into the wearable device, wherein one key is designated for SOS activation, one key is designated for initiating a self-test function, one key is designated for enabling sport mode, and one key is designated for creating a call shortcut.

12. The method of claim 1, further comprising temperature sensors, wherein the wearable device includes three temperature sensors positioned in three distinct locations on the board for monitoring localized temperature variations.

13. The method of claim 1, further comprising a microphone integrated into the wearable device, the microphone configured to capture ambient audio for voice messaging and other audio-based functionalities.

14. The method of claim 1, further comprising a pressure sensor integrated into the wearable device, wherein the pressure sensor is configured to measure environmental pressure variations and is utilized for detecting fainting events.

Images