Description:A) TECHNICAL FIELD
[0001] The present invention is generally related to the field of sleep monitoring systems. The present invention is particularly related to a system and method for sleep quality monitoring using a multi-sensor integrated mattress.

B) BACKGROUND OF THE INVENTION
[0002] Sleep plays a vital role in human health, with poor sleep quality being linked to a wide range of health issues including cardiovascular disease, diabetes, obesity, and cognitive impairment. Existing solutions for sleep monitoring, such as wearable devices and polysomnography (PSG), suffer from certain limitations. Wearable devices often cause discomfort and compliance issues during prolonged use, while PSG systems are expensive, require a clinical setup, and are impractical for continuous long-term monitoring in real-life conditions. These methods are often intrusive, expensive, and unable
to accurately reflect an individual’s habitual sleep patterns in
real-life conditions.
[0003] In addition to clinical methods, portable devices such as the
Watch PAT have been introduced for at-home sleep assessment. However,
these systems require the user to wear the device throughout the
night, which can cause discomfort and interfere with natural sleep
behavior. Further, existing solutions often lack affordability and
scalability, making them less accessible for continuous long-term
monitoring across diverse populations.
[0004] Quality sleep is closely linked to mental and physical
well-being, as disruptions in the sleep cycle can lead to conditions
such as anxiety, depression, cardiovascular issues, and metabolic
disorders. A variety of internal and external factors—including mental
health conditions, physiological changes, and environmental factors
such as temperature, humidity, noise levels, and comfort—can
significantly influence sleep quality. Existing tools to monitor these
parameters are often fragmented, complex to operate, and fail to
provide an integrated, intelligent, and cost-effective monitoring
approach.
[0005] ] Contact-free sleep monitoring technologies have emerged as a promising alternative, enabling the acquisition of physiological signals without interfering with the user’s natural sleep environment. However, many such systems face challenges in accuracy, robustness under varying sleeping conditions, and integration with user-friendly data analysis platforms.
[0006] Recent advancements in Internet of Things (IoT) technologies
have opened opportunities for the development of efficient, scalable,
and low-cost systems for sleep monitoring. However, many of the
available IoT-based solutions remain prohibitively expensive, overly
complex, or limited in functionality, and do not offer advanced
analysis of sleep bio-signals with high accuracy in a contact-free and
non-intrusive manner.
[0007] Hence, there exists a need for a system and method for
sleep quality monitoring using a multi-sensor integrated mattress providing continuous, contact-free monitoring of sleep quality, that is affordable, intelligent, accurate, and capable of operating in real-life conditions without disrupting the
user’s natural sleep.
[0008] The abovementioned shortcomings, disadvantages and problems are addressed herein, which will be understood by reading and studying the following specification.

C) OBJECT OF THE INVENTION
[0009] The primary object of the present invention is to provide a system and method for sleep quality monitoring using a multi-sensor integrated mattress.
[0010] Another object of the present invention is to provide a system that acquires and processes physiological sleep signals with high accuracy and minimal user inconvenience.
[0011] Yet another object of the present invention is to enable detection of heart rate, respiration rate, blood pressure, body movements, turning over, sleep posture, leaving bed events, and other physiological indicators without requiring the user to wear any sensors.
[0012] Yet another object of the present invention is to detect game elements such as the ball, players, goal lines, and court markings.
[0013] Yet another object of the present invention is to provide precise extraction of bio-signals in real-life sleeping conditions using advanced signal processing methods, including wavelet transforms, empirical mode decomposition (EEMD), and dynamic smoothing.
[0014] Yet another object of the present invention is to accurately determine sleep parameters including sleep-wake cycles, REM cycles, deep and light sleep phases, sleep latency, apnea-hypopnea events, snoring, breathing disturbances, tossing and turning, sleep duration, and to compute an overall Sleep Score.
[0015] Yet another object of the present invention is to securely transmit the processed sleep data and analysis reports to a mobile application and/or cloud dashboard, while providing data privacy and integrity.
[0016] Yet another object of the present invention is to provide a modular system that is scalable and compatible with both edge-based and cloud-based deployments, enabling real-time monitoring, population-scale analytics, and integration with third-party healthcare platforms.
[0017] Yet another object of the present invention is to provide a system that is adaptable for both personal and clinical use, enabling long-term health monitoring and aiding in the diagnosis and management of sleep disorders.
[0018] These and other objects and advantages of the present invention will become readily apparent from the following detailed description taken in conjunction with the accompanying drawings.

D) SUMMARY OF THE INVENTION
[0019] The various embodiments of the present invention provide a system and method for sleep quality monitoring using a multi-sensor integrated mattress.
[0020] According to one embodiment of the present invention, a system for sleep quality monitoring and analysis is provided. The system comprises a multi-sensor integrated mattress embedded with a plurality of sensors configured to continuously capture physiological parameters including body movements, respiration rate, heart rate, snoring, and blood pressure and environmental parameters including temperature, humidity, carbon dioxide levels, and ambient light conditions. The system further comprises a signal conditioning and preprocessing module configured to amplify, filter, and digitize the acquired bio-signals for noise reduction and feature enhancement. A processing and control module processes the conditioned signals using wavelet analysis, ensemble empirical mode decomposition (EEMD), and dynamic smoothing to detect events including sleep apnea, leaving the bed, and turning over. A machine learning module evaluates sleep parameters including REM cycles, apnea-hypopnea index (AHI), sleep score, and sleep stages, generating detailed quality metrics. A communication module transmits analyzed results to an application for real-time alerts, comprehensive reporting, and long-term statistical analysis.
[0021] According to one embodiment of the present invention, a method for sleep quality monitoring and analysis is provided. The method comprises continuously capturing physiological parameters using a multi-sensor integrated mattress; conditioning and preprocessing the captured signals using a signal conditioning and preprocessing module; detecting sleep-related bio-signals and events by applying wavelet analysis, EEMD, and dynamic smoothing; evaluating sleep quality parameters, including REM cycles, AHI, and sleep score; and transmitting the evaluated results to an application via a communication module for generating real-time alerts and detailed sleep reports. The method supports both real-time analysis for immediate notifications and batch processing for long-term statistical evaluation, enabling accurate, affordable, and non-intrusive sleep quality assessment over extended durations.
[0022] These and other aspects of the embodiments herein will be better appreciated and understood when considered in conjunction with the following description and the accompanying drawings. It should be understood, however, that the following descriptions, while indicating the preferred embodiments and numerous specific details thereof, are given by way of illustration and not of limitation. Many changes and modifications may be made within the scope of the embodiments herein without departing from the spirit thereof, and the embodiments herein include all such modifications.

E) BRIEF DESCRIPTION OF THE DRAWINGS
[0023] The other objects, features and advantages will occur to those skilled in the art from the following description of the preferred embodiment and the accompanying drawings in which:
[0024] FIG. 1 illustrates the overall block diagram of the system for sleep quality monitoring using a multi-sensor integrated mattress, according to one embodiment of the present invention.
[0025] Although the specific features of the present invention are shown in some drawings and not in others. This is done for convenience only as each feature may be combined with any or all of the other features in accordance with the present invention.
F) DETAILED DESCRIPTION OF THE INVENTION
[0026] In the following detailed description, a reference is made to the accompanying drawings that form a part hereof, and in which the specific embodiments that may be practiced is shown by way of illustration. These embodiments are described in sufficient detail to enable those skilled in the art to practice the embodiments and it is to be understood that other changes may be made without departing from the scope of the embodiments. The following detailed description is therefore not to be taken in a limiting sense.
[0027] The various embodiments of the present invention provide a system and method for sleep quality monitoring using a multi-sensor integrated mattress.
[0028] According to one embodiment of the present invention, a system is provided for sleep quality monitoring using a multi-sensor integrated mattress. The system comprising: a mattress, configured to support a user in a sleeping position; a sensor module integrated within or beneath the mattress, acquiring physiological signals and environmental parameters associated with the user during sleep; a signal conditioning and preprocessing module, operatively coupled to the sensor module, amplify the analog signals received from the sensor module, filter the signals using low-pass and band-pass filters; digitize the filtered signals using a plurality of analog-to-digital converters (ADCs); and preprocess the digitized signals for removal of baseline drift and noise artifacts; a processing and control module extracting the physiological and environmental features from the preprocessed signals, coordinate data flow across system modules, and manage transitions between real-time and batch operational modes; a machine learning module embedded within the processing and control module further comprising a trained classifier configured to receive the extracted features as input, classify the sleep quality level of the user based on the extracted features; and provide a classification selected from a plurality of sleep quality categories; a communication interface module configured to facilitate wireless data transmission between the system and one or more external devices, and further configured to support secure data exchange, device pairing, remote access, and firmware updates; an application module further comprising a mobile application module and a cloud dashboard module, wherein the mobile application module is configured to display real-time and historical sleep-related data on a smartphone or tablet, and the cloud dashboard module is configured to provide centralized access, remote monitoring, and aggregated analytics for multiple users in institutional settings; and a power management module configured to receive electrical input from an alternating current (AC) mains or battery supply and deliver regulated power to all functional modules of the system, wherein the power management module is further configured to enable low-power operational modes during sleep periods and provide protection against overcurrent, voltage fluctuation, and thermal overload conditions.
[0029] According to one embodiment of the present invention, the sensor module further comprises a plurality of sensors including a piezoelectric sensor configured to detect cardiac activity, respiratory motion, and body movements of the user; a pulse oximeter configured to measure oxygen saturation level and pulse rate of the user; HR Variations configured to detect posture changes and motion intensity of the user during sleep; a microphone configured to detect snoring patterns of the user; and a temperature sensor, a humidity sensor, a carbon dioxide (CO₂) sensor, and a light-dependent resistor (LDR) configured to measure ambient environmental parameters surrounding the user during sleep.
[0030] According to one embodiment of the present invention, the signal conditioning and preprocessing module comprises a plurality of amplification circuits configured to enhance low-amplitude analog signals received from the sensor module, and a plurality of filtering circuits configured to remove noise components from the amplified signals. The digitized signals are preprocessed using a preprocessing microcontroller configured to remove baseline drift and package the signal data for transfer to the processing and control module.
[0031] According to one embodiment of the present invention, the processing and control module comprises a multiple microcontroller architecture including a plurality of microcontrollers configured to extract physiological and environmental features from the digitized signal data, and to coordinate real-time and batch operations, data routing, and system-wide control functions. The extracted features include heart rate, respiratory rate, motion intensity, snoring events, SpO₂ variation, and ambient environmental trends.
[0032] According to one embodiment of the present invention, the machine learning module comprises a firmware-embedded classifier based on a trained Machine Learning algorithm configured to generate a sleep quality classification selected from a pre-determined set of sleep categories, generating classification outputs at periodic intervals for either live or retrospective analysis. The machine learning module is further configured to analyze and quantify a plurality of sleep parameters including: sleep timing metrics such as time of sleep onset, wake-up time, and total sleep duration; sleep stage tracking including Wake, N1, N2, N3, N4, N5 and REM phases, and the identification and analysis of complete sleep cycles throughout the night; REM cycle monitoring including detection of physiological changes and brain activity variations characteristic of REM sleep; sleep apnea detection through continuous monitoring of respiratory patterns, including identification of apneas, hypopneas, and abnormal snoring behavior, and computation of an Apnea-Hypopnea Index (AHI); ) detection and logging of snoring intensity, frequency, and temporal patterns; detection and logging of breathing disturbances indicative of partial airway obstruction or disrupted airflow; body movement analysis including tracking of tossing and turning, posture changes, and restlessness during sleep; calculation of sleep scores based on cumulative analysis of duration and quality of sleep. The score reflects sleep sufficiency and restoration potential; generation of daily sleep quality summaries, including sleep latency, number and duration of interruptions, and sleep consistency; generation of graphical sleep insights and trends across multiple nights to help users assess sleep improvement or deterioration over time; capturing and interpreting sleep diary inputs and subjective feedback from users regarding lifestyle factors, sleep perception, and contributing variables; and transmit the analyzed data and parameters to the application module for real-time display and historical analytics.
[0033] According to one embodiment of the present invention, the communication interface module comprises a Bluetooth Low Energy (BLE) communication unit configured to facilitate short-range wireless data transmission to a mobile device, and further comprises a Wi-Fi communication unit configured to establish secure long-range connectivity with a remote cloud platform. The communication interface module is also configured to support bi-directional data exchange, over-the-air firmware updates, and communication protocol switching based on user preferences or network availability. The communication interface module further comprises a security module comprising a hardware-based cryptographic authentication chip performing secure key management, encrypting data packets transmitted through the communication interface module, validating firmware integrity during system startup, and preventing unauthorized access to stored or transmitted sensor data, thereby providing end-to-end data security and compliance with healthcare data protection standards.
[0034] According to one embodiment of the present invention, the application module comprises a mobile application module and a cloud dashboard module. The mobile application module is configured to operate on a smartphone or tablet and pair with the communication interface module via Bluetooth Low Energy (BLE), receive sleep classification results and physiological metrics in real-time, generate alerts or notifications based on anomalous sleep events including low oxygen saturation or abnormal motion activity, allow configuration of user preferences and alert thresholds, and display sleep quality trends, nightly summaries, and historical analytics in graphical and tabular formats. The cloud dashboard module is configured to be accessed via a web-based administrative interface, receive sleep data transmitted from a plurality of user devices via the Wi-Fi communication unit, display long-term health trends and sleep metrics across users, and provide secure login-based access to caregivers, clinicians, or institutional administrators, support centralized user and device management, remote firmware update scheduling, and anonymized data analytics for monitoring population-level sleep health trends in clinical, residential, or assisted living environments.
[0035] According to one embodiment of the present invention, a method is provided for sleep quality monitoring using a multi-sensor integrated mattress, the method includes: supporting a user in a sleeping position on a mattress integrated with one or more sensors; acquiring a plurality of physiological signals including cardiac activity, respiratory motion, body movement, blood oxygen saturation, pulse rate, and snoring sounds, and environmental parameters including temperature, humidity, carbon dioxide levels, and ambient light conditions, associated with the user during sleep by the sensor module; amplifying, filtering, digitizing, and preprocessing the acquired analog signals, including removal of baseline drift and noise artifacts using the signal conditioning and preprocessing module; extracting a set of physiological and environmental features from the preprocessed signals, managing data flow across system modules, and coordinating between real-time and batch modes of operation using the processing and control module; classifying a sleep quality level of the user based on the extracted features, wherein the classification is selected from a plurality of predefined sleep quality categories using the machine learning module; transmitting the classified sleep quality level and associated metrics to an external device, enabling secure data exchange, device pairing, remote access, and firmware updates using the communication interface module; displaying real-time and historical sleep-related data, generating alerts based on anomalous events, and allowing user preference configuration using the application module; storing and managing sleep data from a plurality of users, providing centralized access and analytics to caregivers or institutional administrators using a cloud dashboard module; and regulating the power supply to each functional module of the system, including enabling low-power operation during sleep and protecting against electrical faults using a power management module.
[0036] According to one embodiment of the present invention, the method for sleep quality monitoring using a multi-sensor integrated mattress further comprising, detecting and analyzing a plurality of sleep bio-signals in a continuous and contact-free manner using a piezoelectric sensor integrated within or beneath the mattress; collecting mechanical signals generated by thoracic and abdominal movements of the user during sleep using piezoelectric ceramic elements embedded in the sensor module; extracting raw signal data corresponding to cardiac cycles and respiratory waves from the piezoelectric sensor output; performing multi-level signal decomposition using wavelet transform techniques to isolate relevant bio-signal components; enhancing signal fidelity and separation using ensemble empirical mode decomposition (EEMD) and dynamic smoothing algorithms; deriving instantaneous heart rate and respiratory rate values by computing inter-beat intervals and breath cycle durations from the processed bio-signals; detecting variations in mattress pressure patterns corresponding to user movement, body displacement, and weight redistribution to identify turning-over events and leaving-bed events; estimating blood pressure trends based on piezoelectric-derived pulse wave amplitude and timing characteristics using calibrated signal models; and  transmitting the extracted bio-signal metrics and event detections to the processing and control module for real-time analysis and subsequent classification by the machine learning module.
[0037] According to one embodiment of the present invention, a method for sleep quality monitoring using a multi-sensor integrated mattress further comprising, receiving a plurality of analog bio-signals and environmental signals from the sensor module; amplifying low-amplitude analog signals using one or more amplification circuits configured to increase signal strength without distortion; removing high-frequency and low-frequency noise components using a combination of low-pass and band-pass filtering circuits tailored to the expected physiological signal bands; converting the filtered analog signals into digital format using a plurality of analog-to-digital converters (ADCs) with high-resolution sampling capability; preprocessing the digitized signals using a preprocessing microcontroller to remove baseline drift, suppress motion artifacts, and correct signal non-linearities; segmenting the digital data stream into time-stamped packets corresponding to individual sensor sources; standardizing the signal units and applying normalization algorithms providing uniformity across different sensing channels; performing outlier rejection and signal smoothing to enhance the reliability of extracted physiological features; identifying abnormal or missing signal intervals and applying interpolation techniques where necessary to preserve signal continuity; and  transmitting the preprocessed and formatted signal data to the processing and control module for downstream feature extraction and sleep classification.
[0038] According to one embodiment of the present invention, a method for sleep quality monitoring using a multi-sensor integrated mattress further comprising, extracting a plurality of physiological and environmental features from the preprocessed signals, including heart rate, respiratory rate, motion intensity, SpO₂ levels, snoring patterns, and ambient conditions such as temperature, humidity, and CO₂ levels; feeding the extracted features as input to a firmware-embedded machine learning module comprising a trained classifier based on a algorithm; computing intermediate statistical and time-domain representations of the features, including averages, standard deviations, frequency bands, and event counts over defined time windows; generating a sleep quality classification based on the combined analysis of individual and aggregate features, wherein the classification is selected from a plurality of categories comprising Very Peaceful, Peaceful, Medium, Unpeaceful, and Very Unpeaceful; periodically updating the sleep quality classification in real time or in scheduled post-processing intervals based on newly acquired and processed data; analyzing temporal trends in the classified results to detect deterioration or improvement in sleep patterns across multiple nights; computing sleep quality scores based on a weighted aggregation of classification results, sensor metrics, and signal stability indices;  annotating the classified results with potential physiological or behavioral causes based on correlation with environmental parameters and movement patterns; generating explanatory insights including snoring severity, sleep phase consistency, sleep latency, and apnea indicators as contributing factors to sleep quality; and transmitting the classification outcomes, insights, and trend analytics to the application module for display, logging, and alert generation.
[0039] According to one embodiment of the present invention, the method of analyzing sleep quality using the processing and control module and the machine learning module (105), comprising: recording sleep onset and wake-up times, and classifying sleep phases into deep and light sleep stages based on heart rate variability and motion intensity using the processing and control module; detecting and recording Rapid Eye Movement (REM) cycles by monitoring irregular breathing patterns, elevated heart rates, and specific waveform features extracted from piezoelectric sensor signals using the processing and control module; continuously monitoring breathing patterns during sleep to detect irregularities, pauses, or abnormal snoring indicative of sleep apnea, and flagging potential apnea events using the processing and control module; calculating a sleep score based on the duration and quality of recorded sleep, wherein the score is generated on a scale of 0 to 100, and transmitted to the mobile application module via the communication interface module; detecting and recording snoring events by analyzing audio signals captured by the microphone sensor and classifying them as minor or persistent using the machine learning module; identifying breathing disturbances by analyzing airflow irregularities and correlating them with motion and snoring data to infer possible respiratory obstructions using the processing and control module; tracking multiple sleep cycles and their progression through the stages Wake, N1, N2, N3, N4 , N5 and REM, with each cycle comprising approximately with respect to 30-1440 minutes, and logging the frequency and duration of each stage; computing daily sleep quality metrics and generating comprehensive sleep reports based on the data from overnight monitoring sessions, including sleep duration, restlessness, and sleep efficiency; recording body movement patterns throughout the night to assess restlessness and postural changes, and correlating this information with other physiological signals to determine overall sleep stability; determining the sleep stage at each time interval by analyzing piezoelectric signal patterns, classifying them into NREM and REM categories, and visualizing their temporal distribution using the application module; calculating the Apnea-Hypopnea Index (AHI) by detecting the frequency of apneas and hypopneas per hour and transmitting the computed AHI to the mobile application module for user review; identifying tossing and turning behavior during sleep based on HR Variations from piezoelectric sensor signals, and associating high movement intensity with poor sleep quality; logging the overall sleep state of the user, classified into wakefulness, light sleep, deep sleep, and REM sleep, and updating the classification dynamically through the machine learning module; collecting and storing data from a user-maintained sleep diary entered through the mobile application module, including sleep latency, interruptions, naps, perceived quality, and behavioral factors such as caffeine intake and medication; estimating total sleep duration using muscle activity signals and motion tracking data, and validating it with user-reported entries from the sleep diary; determining the time taken to fall asleep (sleep latency) by analyzing the time interval between reduced motion and physiological stabilization, and displaying the result to the user via the mobile application module; and generating sleep insights by summarizing all recorded data, including sleep cycles, apnea events, motion disturbances, sleep scores, and environmental trends, and providing graphical analytics and recommendations through the cloud dashboard module.
[0040] FIG. 1 illustrates the overall block diagram of the system for sleep quality monitoring using a multi-sensor integrated mattress, according to one embodiment of the present invention.
[0041] Although the embodiments herein are described with various specific embodiments, it will be obvious for a person skilled in the art to practice the embodiments herein with modifications.

G) ADVANTAGES OF THE INVENTION
[0042] The various embodiments of the present invention provide a system and method for sleep quality monitoring using a multi-sensor integrated mattress, providing a contact-free, multi-sensor based sleep monitoring system that enhances accuracy, user comfort, and applicability compared to conventional wearable or clinical-only solutions. The system offers a comprehensive monitoring capability by capturing a wide range of physiological parameters, including heart rate, respiration rate, blood pressure, and sleep stage data, without requiring the user to wear intrusive devices. The use of piezoelectric ceramic sensors integrated into the mattress enables continuous, non-intrusive monitoring that preserves the natural sleep environment while maintaining high signal fidelity.
[0043] Advanced signal processing algorithms, including wavelet transforms, EEMD, and dynamic smoothing, improve accuracy in detecting sleep stages and identifying sleep disorders even in noisy, real-life conditions. The system securely transmits data to a mobile application and cloud dashboard, providing users and healthcare providers with real-time insights, historical trends, and personalized recommendations, supported by hardware-based cryptographic authentication for privacy and security. The modular architecture allows scalability and integration with edge or cloud computing platforms, enabling deployment across home and healthcare environments, as well as large-scale population health monitoring programs. The system further facilitates early detection of sleep disorders such as sleep apnea and provides actionable data that can improve clinical decision-making, patient compliance, and overall sleep health.
[0044] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such as specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modifications. However, all such modifications are deemed to be within the scope of the claims.
, Claims:We Claim:
1. A system for sleep quality monitoring using a multi-sensor integrated mattress, the system comprises:
a mattress (101), wherein the mattress (101) is configured to support a user in a sleeping position;
a sensor module (102) integrated within or beneath the mattress (101), wherein the sensor module (102) acquires physiological signals and environmental parameters associated with the user during sleep;
a signal conditioning and preprocessing module (103), wherein the signal conditioning and preprocessing module (103), operatively coupled to the sensor module (102), amplify the analog signals received from the sensor module (102), filter the signals using low-pass and band-pass filters; digitize the filtered signals using a plurality of analog-to-digital converters (ADCs); and preprocess the digitized signals for removal of baseline drift and noise artifacts;
a processing and control module (104), wherein the processing and control module (104) extracts physiological and environmental features from the preprocessed signals, coordinate data flow across system modules, and manage transitions between real-time and batch operational modes;
a machine learning module (105) embedded within the processing and control module (104), wherein the machine learning module (105) comprises a trained classifier configured to receive the extracted features as input, classify the sleep quality level of the user based on the extracted features; and provide a classification selected from a plurality of sleep quality categories;
a communication interface module (106), wherein the communication interface module (106) is configured to facilitate wireless data transmission between the system and one or more external devices, and further configured to support secure data exchange, device pairing, remote access, and firmware updates;
an application module (107), wherein the application module (107) further comprises a mobile application module and a cloud dashboard module, wherein the mobile application module is configured to display real-time and historical sleep-related data on a smartphone or tablet, and the cloud dashboard module is configured to provide centralized access, remote monitoring, and aggregated analytics for multiple users in institutional settings; and
a power management module (108), wherein the power management module (108) is configured to receive electrical input from an alternating current (AC) mains or battery supply and deliver regulated power to all functional modules of the system, wherein the power management module (108) is further configured to enable low-power operational modes during sleep periods and provide protection against overcurrent, voltage fluctuation, and thermal overload conditions.
2. The system as claimed in claim 1, wherein the sensor module (102) further comprises a plurality of sensors including a piezoelectric sensor configured to detect cardiac activity, respiratory motion, and body movements of the user; a pulse oximeter configured to measure oxygen saturation level and pulse rate of the user; HR Variations configured to detect posture changes and motion intensity of the user during sleep; a microphone configured to detect snoring patterns of the user; and a temperature sensor, a humidity sensor, a carbon dioxide (CO₂) sensor, and a light-dependent resistor (LDR) configured to measure ambient environmental parameters surrounding the user during sleep.
3. The system as claimed in claim 1, wherein the signal conditioning and preprocessing module (103) comprises a plurality of amplification circuits configured to enhance low-amplitude analog signals received from the sensor module (102), and a plurality of filtering circuits configured to remove noise components from the amplified signals, wherein the digitized signals are preprocessed using a preprocessing microcontroller configured to remove baseline drift and package the signal data for transfer to the processing and control module (104).
4. The system as claimed in claim 1, wherein the processing and control module (104) comprises a multiple microcontroller architecture including a plurality microcontrollers configured to extract physiological and environmental features from the digitized signal data, and to coordinate real-time and batch operations, data routing, and system-wide control functions, wherein the extracted features include heart rate, respiratory rate, motion intensity, snoring events, SpO₂ variation, and ambient environmental trends.
5. The system as claimed in claim 1, wherein the machine learning module (105) comprises a firmware-embedded classifier based on a trained Machine Learning algorithm configured to generate a sleep quality classification selected from a pre-determined set of sleep categories, generating classification outputs at periodic intervals for either live or retrospective analysis, and wherein the machine learning module (105) is further configured to analyze and quantify a plurality of sleep parameters including: sleep timing metrics such as time of sleep onset, wake-up time, and total sleep duration; sleep stage tracking including Wake, N1, N2, N3, N4, N5 and REM phases, and the identification and analysis of complete sleep cycles throughout the night; REM cycle monitoring including detection of physiological changes and brain activity variations characteristic of REM sleep; sleep apnea detection through continuous monitoring of respiratory patterns, including identification of apneas, hypopneas, and abnormal snoring behavior, and computation of an Apnea-Hypopnea Index (AHI); ) detection and logging of snoring intensity, frequency, and temporal patterns; detection and logging of breathing disturbances indicative of partial airway obstruction or disrupted airflow; body movement analysis including tracking of tossing and turning, posture changes, and restlessness during sleep; calculation of sleep scores based on cumulative analysis of duration and quality of sleep, wherein the score reflects sleep sufficiency and restoration potential; generation of daily sleep quality summaries, including sleep latency, number and duration of interruptions, and sleep consistency; generation of graphical sleep insights and trends across multiple nights to help users assess sleep improvement or deterioration over time; capturing and interpreting sleep diary inputs and subjective feedback from users regarding lifestyle factors, sleep perception, and contributing variables; and transmit the analyzed data and parameters to the application module (107) for real-time display and historical analytics.
6. The system as claimed in claim 1, wherein the communication interface module (106) comprises a Bluetooth Low Energy (BLE) communication unit configured to facilitate short-range wireless data transmission to a mobile device, and further comprises a Wi-Fi communication unit configured to establish secure long-range connectivity with a remote cloud platform, wherein the communication interface module (106) is further configured to support bi-directional data exchange, over-the-air firmware updates, and communication protocol switching based on user preferences or network availability, and wherein the communication interface module (106) further comprises a security module comprising a hardware-based cryptographic authentication chip performing secure key management, encrypting data packets transmitted through the communication interface module (106), validating firmware integrity during system startup, and preventing unauthorized access to stored or transmitted sensor data, thereby providing end-to-end data security and compliance with healthcare data protection standards.
7. The system as claimed in claim 1, wherein application module (107) comprises a mobile application module and a cloud dashboard module, wherein the mobile application module is configured to operate on a smartphone or tablet and pair with the communication interface module (106) via Bluetooth Low Energy (BLE), receive sleep classification results and physiological metrics in real-time, generate alerts or notifications based on anomalous sleep events including low oxygen saturation or abnormal motion activity, allow configuration of user preferences and alert thresholds, and display sleep quality trends, nightly summaries, and historical analytics in graphical and tabular formats, and wherein the cloud dashboard module is configured to be accessed via a web-based administrative interface, receive sleep data transmitted from a plurality of user devices via the Wi-Fi communication unit, display long-term health trends and sleep metrics across users, and provide secure login-based access to caregivers, clinicians, or institutional administrators, support centralized user and device management, remote firmware update scheduling, and anonymized data analytics for monitoring population-level sleep health trends in clinical, residential, or assisted living environments.
8. A method for sleep quality monitoring using a multi-sensor integrated mattress, the method includes:
supporting a user in a sleeping position on a mattress (101) integrated with one or more sensors;
acquiring a plurality of physiological signals and environmental parameters associated with the user during sleep by the sensor module (102), the physiological signals including cardiac activity, respiratory motion, body movement, blood oxygen saturation, pulse rate, and snoring sounds, and the environmental parameters including temperature, humidity, carbon dioxide levels, and ambient light conditions;
amplifying, filtering, digitizing, and preprocessing the acquired analog signals, including removal of baseline drift and noise artifacts using the signal conditioning and preprocessing module (103);
extracting a set of physiological and environmental features from the preprocessed signals, managing data flow across system modules, and coordinating between real-time and batch modes of operation using the processing and control module (104);
classifying a sleep quality level of the user based on the extracted features, wherein the classification is selected from a plurality of predefined sleep quality categories using the machine learning module (105);
transmitting the classified sleep quality level and associated metrics to an external device, enabling secure data exchange, device pairing, remote access, and firmware updates using the communication interface module (106);
displaying real-time and historical sleep-related data, generating alerts based on anomalous events, and allowing user preference configuration using the application module (107);
storing and managing sleep data from a plurality of users, providing centralized access and analytics to caregivers or institutional administrators using a cloud dashboard module; and
regulating the power supply to each functional module of the system, including enabling low-power operation during sleep and protecting against electrical faults using a power management module (108)
9. The method as claimed in claim 8, wherein the method for sleep quality monitoring further comprises, detecting and analyzing a plurality of sleep bio-signals in a continuous and contact-free manner using a piezoelectric sensor integrated within or beneath the mattress (101); collecting mechanical signals generated by thoracic and abdominal movements of the user during sleep using piezoelectric ceramic elements embedded in the sensor module (102); extracting raw signal data corresponding to cardiac cycles and respiratory waves from the piezoelectric sensor output; performing multi-level signal decomposition using wavelet transform techniques to isolate relevant bio-signal components; enhancing signal fidelity and separation using ensemble empirical mode decomposition (EEMD) and dynamic smoothing algorithms; deriving instantaneous heart rate and respiratory rate values by computing inter-beat intervals and breath cycle durations from the processed bio-signals; detecting variations in mattress pressure patterns corresponding to user movement, body displacement, and weight redistribution to identify turning-over events and leaving-bed events;  estimating blood pressure trends based on piezoelectric-derived pulse wave amplitude and timing characteristics using calibrated signal models; and  transmitting the extracted bio-signal metrics and event detections to the processing and control module (104) for real-time analysis and subsequent classification by the machine learning module (105).
10. The method as claimed in claim 8, wherein the method for sleep quality monitoring further comprises, receiving a plurality of analog bio-signals and environmental signals from the sensor module (102); amplifying low-amplitude analog signals using one or more amplification circuits configured to increase signal strength without distortion; removing high-frequency and low-frequency noise components using a combination of low-pass and band-pass filtering circuits tailored to the expected physiological signal bands; converting the filtered analog signals into digital format using a plurality of analog-to-digital converters (ADCs) with high-resolution sampling capability; preprocessing the digitized signals using a preprocessing microcontroller to remove baseline drift, suppress motion artifacts, and correct signal non-linearities; segmenting the digital data stream into time-stamped packets corresponding to individual sensor sources; standardizing the signal units and applying normalization algorithms providing uniformity across different sensing channels; performing outlier rejection and signal smoothing to enhance the reliability of extracted physiological features; identifying abnormal or missing signal intervals and applying interpolation techniques where necessary to preserve signal continuity; and  transmitting the preprocessed and formatted signal data to the processing and control module (104) for downstream feature extraction and sleep classification.
11. The method as claimed in claim 8 the method for sleep quality monitoring further comprises, extracting a plurality of physiological and environmental features from the preprocessed signals, including heart rate, respiratory rate, motion intensity, SpO₂ levels, snoring patterns, and ambient conditions such as temperature, humidity, and CO₂ levels; feeding the extracted features as input to a firmware-embedded machine learning module (105) comprising a trained classifier based on a algorithm; computing intermediate statistical and time-domain representations of the features, including averages, standard deviations, frequency bands, and event counts over defined time windows; generating a sleep quality classification based on the combined analysis of individual and aggregate features, wherein the classification is selected from a plurality of categories comprising Very Peaceful, Peaceful, Medium, Unpeaceful, and Very Unpeaceful; periodically updating the sleep quality classification in real time or in scheduled post-processing intervals based on newly acquired and processed data; analyzing temporal trends in the classified results to detect deterioration or improvement in sleep patterns across multiple nights; computing sleep quality scores based on a weighted aggregation of classification results, sensor metrics, and signal stability indices;  annotating the classified results with potential physiological or behavioral causes based on correlation with environmental parameters and movement patterns; generating explanatory insights including snoring severity, sleep phase consistency, sleep latency, and apnea indicators as contributing factors to sleep quality; and transmitting the classification outcomes, insights, and trend analytics to the application module (107) for display, logging, and alert generation.
12. The method as claimed in claim 8 wherein the method of analyzing sleep quality using the processing and control module (104) and the machine learning module (105), comprising:
recording sleep onset and wake-up times, and classifying sleep phases into deep and light sleep stages based on heart rate variability and motion intensity using the processing and control module (104);
detecting and recording Rapid Eye Movement (REM) cycles by monitoring irregular breathing patterns, elevated heart rates, and specific waveform features extracted from piezoelectric sensor signals using the processing and control module (104);
continuously monitoring breathing patterns during sleep to detect irregularities, pauses, or abnormal snoring indicative of sleep apnea, and flagging potential apnea events using the processing and control module (104);
calculating a sleep score based on the duration and quality of recorded sleep, wherein the score is generated on a scale of 0 to 100, and transmitted to the mobile application module (107) via the communication interface module (106);
detecting and recording snoring events by analyzing audio signals captured by the microphone sensor and classifying them as minor or persistent using the machine learning module (105);
identifying breathing disturbances by analyzing airflow irregularities and correlating them with motion and snoring data to infer possible respiratory obstructions using the processing and control module (104);
tracking multiple sleep cycles and their progression through the stages Wake, N1, N2, N3, N4 , N5 and REM, with each cycle comprising approximately 30–1440 minutes, and logging the frequency and duration of each stage;
computing daily sleep quality metrics and generating comprehensive sleep reports based on the data from overnight monitoring sessions, including sleep duration, restlessness, and sleep efficiency;
recording body movement patterns throughout the night to assess restlessness and postural changes, and correlating this information with other physiological signals to determine overall sleep stability;
determining the sleep stage at each time interval by analyzing piezoelectric signal patterns, classifying them into NREM and REM categories, and visualizing their temporal distribution using the application module (107);
calculating the Apnea-Hypopnea Index (AHI) by detecting the frequency of apneas and hypopneas per hour and transmitting the computed AHI to the mobile application module (107) for user review;
identifying tossing and turning behavior during sleep based on HR Variation from piezoelectric sensor signals, and associating high movement intensity with poor sleep quality;
logging the overall sleep state of the user, classified into wakefulness, light sleep, deep sleep, and REM sleep, and updating the classification dynamically through the machine learning module (105);
collecting and storing data from a user-maintained sleep diary entered through the mobile application module (107), including sleep latency, interruptions, naps, perceived quality, and behavioral factors such as caffeine intake and medication;
estimating total sleep duration using muscle activity signals and motion tracking data, and validating it with user-reported entries from the sleep diary;
determining the time taken to fall asleep (sleep latency) by analyzing the time interval between reduced motion and physiological stabilization, and displaying the result to the user via the mobile application module (107); and
generating sleep insights by summarizing all recorded data, including sleep cycles, apnea events, motion disturbances, sleep scores, and environmental trends, and providing graphical analytics and recommendations through the cloud dashboard module.