Smart interactive shirt system for real-time multi-modal pain and fatigue monitoring using embedded IoT sensors

Abstract

The Smart Interactive Shirt System is an advanced wearable biosensing platform engineered for real-time, multi-modal monitoring and predictive management of pain, fatigue, and physiological stress. Embedded within a flexible textile, the system integrates 15 specialized IoT sensors—spanning biochemical, biomechanical, thermal, and neurophysiological domains—to deliver continuous high-resolution insight into the wearer's physiological state. Key innovations include plasmonic nano-optical modules for real-time cortisol and CRP detection, EMG-based neuromuscular sensing, and thermopile arrays for deep-tissue inflammation mapping. A hybrid AI engine combining convolutional and recurrent neural networks (CNN-LSTM) processes incoming data locally, enabling early prediction of acute fatigue and pain episodes 10–15 minutes before physiological onset. The system incorporates triboelectric nanogenerators (TENGs) that harvest kinetic energy from body motion, minimizing reliance on external power sources and supporting extended autonomous operation. Validated through pilot deployments in elite European sports organizations, the shirt also features screen-printed electronic circuits, vibrotactile feedback mechanisms, and seamless Bluetooth Low Energy (BLE) integration with mobile interfaces. This invention marks a significant advancement over conventional wearables by offering proactive, data-driven physiological management, setting a new benchmark in intelligent, AI-powered textile systems.

Description

[0001] Smart Interactive Shirt System for Real-Time Multi-Modal Pain and Fatigue Monitoring Using Embedded loT Sensors

[0002] Summary

[0003] The Smart Interactive Shirt System is a next-generation wearable biosensing innovation designed to dynamically assess pain, fatigue, and physiological stress in real-time. It integrates 15 advanced loT-based sensors embedded in a textile platform to monitor biochemical (e.g., cortisol and CRP via plasmonic nano-optical detection), biomechanical (muscle strain gauges with 0.5% error), and neurophysiological (EMG-derived neural signals) indicators.

[0004] The system is powered by triboelectric nanogenerators (TENGs) that harvest kinetic energy during motion, ensuring uninterrupted operation without external power. A hybrid Al model (CNN+LSTM) enables early prediction of fatigue and pain episodes 10-15 minutes before onset, using both real-time and historical data.

[0005] • Developed using screen-printed textile electronics, the shirt is lightweight, moistureresistant, and shock-absorbent, ideal for high-performance and clinical environments. It has advanced from prototype to commercial-scale manufacturing, with initial adoption interest from leading European football leagues. These engagements validate the system’s technical novelty, predictive accuracy and real-world applicability, validated in elite sports teams.

[0006] Invention Background

[0007] In recent years, the demand for intelligent wearable systems capable of detecting and analyzing pain and physiological fatigue in motion-intensive environments, such as elite sports, military operations and industrial fieldwork has significantly increased. However, current wearable devices, including popular commercial models, lack the ability to dynamically interpret neuromuscular strain and molecular-level inflammatory responses associated with pain and fatigue. These solutions often rely on superficial metrics and do not provide real-time, high-resolution analysis of complex physiological signals. Moreover, they are generally not equipped to integrate multi-modal signal acquisition, including biochemical, thermal, biomechanical and neurophysiological data, with adaptive Al algorithms that learn and adjust to individual baselines. This has created a clear and unmet need for an integrated system capable of capturing and analyzing micro-level indicators of pain and fatigue in real time during physical activity — a need that remains unfulfilled by any known solution to date. General Description of the Invention

[0008] This invention pertains to the field of intelligent wearable technologies and introduces a novel integrated system for real-time monitoring and analysis of physical pain, neuromuscular fatigue and physiological stress during movement in dynamic environments. It marks a significant departure from conventional wearables by enabling high-resolution, multi-dimensional biosensing with adaptive artificial intelligence.

[0009] The system is embedded within a smart textile garment and comprises 15 advanced loT-enabled sensors, including nano-optical, biochemical, thermal, biomechanical and neurophysiological sensors. These components collectively capture detailed biological, mechanical and neural signals related to inflammatory changes, muscle strain, neural responses and key biochemical markers such as cortisol, CRP and lactate.

[0010] A central processing unit interprets this data using a hybrid artificial intelligence model (CNN + LSTM), enabling real-time predictive analytics for early detection of acute fatigue and pain episodes — typically 10 to 15 minutes prior to physiological onset. The system communicates via a mobile application and provides instant vibrotactile alerts, enabling users or clinicians to respond proactively and reduce injury risk.

[0011] Key distinguishing features include:

[0012] • Multi-modal sensor fusion combining biochemical, thermal, and neural data streams.

[0013] • Closed-loop haptic feedback for real-time physiological guidance.

[0014] • Energy autonomy through embedded triboelectric nanogenerators (TENGs) that harvest kinetic energy, reducing dependence on charging.

[0015] • Industrial scalability via screen-printed electronic textiles, validated in elite sports.

[0016] What sets this invention apart is its capacity not only to monitor physiological changes, but also to manage them proactively. It offers continuous adaptation to individual baselines, supports long-term wear in sports, occupational and military use, and enables performance optimization and injury prevention at scale.

[0017] A fully functional prototype has been developed, tested and validated by leading European sports institutions. Commercial production is underway, positioning this system as a foundational platform in a new category of intelligent, Al-driven biosensing wearables, making it a strong candidate for patent protection under national and international intellectual property laws.

[0018] Detailed Description of the Invention The present invention discloses a Smart Interactive Shirt System, a groundbreaking advancement in wearable biosensing technology that enables real-time, multi-dimensional monitoring and predictive analysis of pain, fatigue and physiological stress during physical activity. Unlike conventional wearables limited to superficial metrics (e.g. heart rate, motion) this system integrates 15 specialized loT sensors embedded within a functional textile to capture and correlate biochemical, biomechanical and neurophysiological data with unprecedented precision.

[0019] 1. Field of the Invention

[0020] This invention pertains to the advanced field of smart wearable technologies, specifically focusing on the real-time, dynamic assessment and management of pain, fatigue and physiological stress through an interactive loT sensor-integrated garment.

[0021] 2. Background of the Invention

[0022] Conventional wearable technologies provide mostly superficial, static physiological data. They often lack comprehensive, multi-dimensional sensing and real-time predictive analysis. This limits their effectiveness in physically demanding environments such as elite sports, military operations and industrial work. Thus, there remains a critical unmet need for an integrated system that provides continuous, dynamic biosensing and proactive health management.

[0023] 3. Summary of the Invention

[0024] The invention introduces a wearable biosensing system embedded in an intelligent textile platform. It comprises 15 highly specialized loT sensors capable of capturing physiological, biochemical, thermal and mechanical signals in real time. The data is processed by a low-power microcontroller and interpreted by adaptive machine learning algorithms that predict pain and fatigue episodes, provide instant haptic feedback and communicate with a mobile interface. This system enables proactive physiological management and injury prevention.

[0025] 4. System Architecture and Components

[0026] 4.1 The garment integrates 15 loT advanced biosensors (explained in details in Figurel, Figure!, Figure5, Figure6, Figure?, Figure8)

[0027] 1. Nano-Optical Sensors Detect biochemical markers such as cortisol and CRP using plasmonic nanostructures. These sensors enable real-time, motion-resistant molecular analysis — unprecedented in commercial wearables.

[0028] 2. MIP Sensors (Molecularly Imprinted Polymer)

[0029] Measure lactate and inflammatory cytokines using synthetic polymer receptors that mimic biological affinity. Highly selective and rarely integrated in smart garments.

[0030] 3. Thermal Imaging Sensors

[0031] Use electromagnetic thermopile-based detection to map deep-tissue inflammation with high resolution (±0.1 °C). Enable detection of microinflammatory patterns not accessible to surface sensors.

[0032] 4. Neurophysiological Sensor (EMG)

[0033] Monitor electrical muscle activity, neural delay, and neuromuscular stress. Critical for detecting fatigue before it manifests physically.

[0034] 5. Muscle Strain Sensor

[0035] Measure real-time contraction force, mechanical fatigue, and load dynamics. Provide biomechanical workload analysis vital to athletic and rehab applications.

[0036] 6. Muscle Pressure Sensors

[0037] Sense mechanical compression or tension across muscle groups. Complement strain sensors in assessing mechanical overload or imbalance.

[0038] 7. TENG Energy Harvester

[0039] Triboelectric nanogenerators convert body motion into usable electrical power. Innovative for self-sustaining operation in high-mobility environments.

[0040] 8. Motion Sensor (IMU)

[0041] Inertial Measurement Unit (accelerometer + gyroscope) tracks posture, gait, and movement for biomechanical context.

[0042] 9. Lactate Sensor

[0043] Biochemical sensor tracking sweat-based lactate accumulation. Complements cortisol and strain data to triangulate fatigue levels.

[0044] 10. SpO2Sensor Measures blood oxygen saturation using photoplethysmography (PPG). Useful for monitoring aerobic exertion and oxygen efficiency.

[0045] 11. Respiratory Sensor

[0046] Tracks breath rate and rhythm via impedance or stretch sensors. Adds respiratory insight during exertion or recovery.

[0047] 12. Vital Sign Sensors: covering heart rate, respiratory rate, and SpCh, offering foundational physiological context.

[0048] 4.1.1 Expanded Sensor Hardware Description and Communication Architecture (explained in details in Figure 2)

[0049] The Smart Interactive Shirt’s integrated biosensing infrastructure is anchored in a sophisticated multi-sensor network combining nanotechnology, biocompatible materials, and intelligent signal transmission. Figure 2 (System Architecture and Power-Communication Flow) complements this section by illustrating the interconnection of the nano-sensor modules, the central microcontroller, power regulation circuits, and wireless transmission pathways.

[0050] Nano-Optical Detection Module (P-NODM-1)

[0051] This sensor harnesses plasmonic nanostructures to detect stress-induced biomarkers such as cortisol and C-reactive protein (CRP) in sweat with extremely high sensitivity. Key characteristics include:

[0052] • Detection Range: 500-900 nm (NIR spectrum)

[0053] • Optical Gain: 60 dB

[0054] • Power Consumption: 500 pW @ 3.3V

[0055] • Interface: SPI-based digital transmission to nRF52840 MCU

[0056] • Construction: Flexible, biocompatible encapsulation (0.5 mm thick)

[0057] This module enables real-time biochemical analysis previously unattainable in commercial wearables, supporting accurate, motion-resistant tracking of stress physiology.

[0058] Fluorescence-Based Microfluidic Sensor (FMS-100)

[0059] A drug-level detection module using fluorescence transducers embedded in microfluidic channels, this sensor enables continuous non-invasive pharmacokinetic monitoring. It operates by UV excitation (365 nm) and detects drug concentrations in the 10 nM-100 pM range.

[0060] • Signal-to-Noise Ratio: 80 dB

[0061] • Power Consumption: 1 mW per reading • Communication Interface: I2C for loT gateway compatibility

[0062] • Packaging: PDMS coating; IP67 water resistance

[0063] This sensor adds functionality for patients or athletes on medication requiring dynamic dosage evaluation or safety compliance monitoring.

[0064] Molecularly Imprinted Polymer Sensor (MLP-200)

[0065] This biological particle sensor is designed to detect lactate and pro-inflammatory cytokines, using synthetic polymer structures that mimic antibody binding.

[0066] • Detection Range: 5 ng / mL to 200 pg / mL

[0067] • Output: Analog (0.5V - 2.5V), 16-bit ADC compatibility

[0068] • Power Consumption: 400 pW @ 2.7V

[0069] • Interface: UART

[0070] • Material: Thin-film polymer (0.8 mm), sweat-permeable channels

[0071] This sensor is highly selective and responsive, enabling early detection of inflammation or anaerobic thresholds during exertion.

[0072] 4.1.2 Smart Shirt System Communication and Power Design (explained in Figure 2)

[0073] The sensors described above (El: Nano-Optical, E2: Fluorescent, E3: MIP) are integrated with the following processing and communication framework:

[0074] • Microcontroller: Nordic Semiconductor nRF52840 o Dual SPI / I2C interface support o Real-time signal preprocessing and Al execution (Kalman Filter + CNN-LSTM) o Bluetooth Low Energy (BLE) communication

[0075] • Support Sensors: o ADS 1192: Biopotential front-end (ECG / EMG), 16-bit SPI interface o SHT4xI: Temperature and humidity sensor via I2C o MS5837-30BA: Pressure sensor for pain-related respiratory stress markers via I2C

[0076] • Power Supply & Regulation: o Rechargeable LiPo battery (3.7V nominal) o LDO regulator ensures stable 3.3V delivery o Optional TENG (Triboelectric Nanogenerator) harvests motion-based energy (~5 mW / cm2)

[0077] Each sensor and component is mapped to the system’s SPI or I2C bus via standardized pinouts (e.g., SDA, SCL, MISO, MOSI), regulated by the central MCU. For example: ADS 1192 is configured on SPI and initiated via a dedicated GPIO (START pin) Environmental sensors (SHT4xI, MS5837) share the I2C bus with unique addresses

[0078] 4.1.3 Data Acquisition and Processing Flow (explained in Figure 3)

[0079] The architecture operates under a layered structure that includes:

[0080] • Sensor Polling: Initiated by nRF52840 at scheduled intervals

[0081] • Preprocessing: Includes denoising, normalization, and signal conditioning

[0082] • Edge-Level Analysis: CNN-LSTM-based fatigue / stress prediction

[0083] • Data Output: BLE streaming to mobile apps or healthcare dashboards

[0084] This detailed architecture not only supports multi-modal signal acquisition and processing, but also showcases how nanotechnology, biochemical sensing, and embedded Al are harmonized to create a real-time intelligent biosensing platform.

[0085] 4.2 Embedded Microcontroller Unit (MCU) (Explained in Figure 7)

[0086] The system utilizes a Nordic Semiconductor nRF52840 microcontroller, which functions as the central processing unit. It is responsible for:

[0087] • Real-time acquisition and synchronization of multi-modal sensor data;

[0088] • Initial signal filtering and preprocessing using embedded Kalman filtering algorithms;

[0089] • Executing a hybrid Al model (CNN + LSTM) for fatigue and stress prediction directly at the edge;

[0090] • Bluetooth Low Energy (BLE) wireless communication for seamless data transmission to connected mobile interfaces.

[0091] 4.3 Power Management System

[0092] The garment incorporates a hybrid power solution consisting of:

[0093] • A lithium-polymer (LiPo) rechargeable battery integrated with a low-dropout (LDO) voltage regulator providing a stable 3.3V supply; Triboelectric nanogenerators (TENGs) woven into motion-prone areas of the textile, capable of harvesting kinetic energy at rates up to ~5 mW / cm2during motion (~3 Hz), thereby reducing reliance on external charging.

[0094] 5. Advanced Artificial Intelligence and Data Analytics

[0095] 5.1 Real-Time Predictive Algorithms

[0096] The onboard Al engine executes a hybrid convolutional neural network-long short-term memory (CNN-LSTM) model trained to:

[0097] • Detect fatigue and pain-related patterns across sensor inputs in real time;

[0098] • Predict physiological risk events 10-15 minutes before onset;

[0099] • Adapt continuously to individual user baselines through federated edge learning.

[0100] The predictive engine directly interfaces with embedded haptic actuators to deliver vibrotactile alerts when threshold levels are exceeded.

[0101] 5.2 Cloud-Based Deep Analytics

[0102] In parallel with edge processing, the system supports optional data upload to a secure cloud infrastructure for:

[0103] • Longitudinal tracking of physiological metrics and performance over time;

[0104] • Comparative Al-driven insights across sessions or cohorts;

[0105] • Personalized, data-informed recommendations for therapeutic or performance applications.

[0106] 6. User Interface and Interaction

[0107] A custom mobile application is integrated with the system to provide:

[0108] • Real-time visualization of biosensor outputs and Al-derived predictions; Configurable alerts and feedback thresholds;

[0109] Recommendations for recovery, performance optimization, or clinical follow-up.

[0110] Vibrotactile feedback mechanisms embedded in the garment are triggered based on both real-time sensor analysis and Al inference outcomes, completing the closed-loop intervention cycle. dustrial and Practical Applications Athletic Performance Optimization

[0111] • Real-time tracking of pain, fatigue, inflammation and effort.

[0112] • Proactive management to prevent overexertion and injury. Military and Emergency Use

[0113] • Enhances soldier resilience and reduces operational fatigue-related risks. Occupational Health and Ergonomics

[0114] • Real-time pain and strain alerts in high-repetition or high-load environments. Clinical and Rehabilitation Settings

[0115] • Personalized recovery insights and Al-assisted therapy optimization. istinctive Novelty, Differentiation and Technical Superiority

[0116] • First wearable to combine biochemical, biomechanical, thermal and neural monitoring.

[0117] • Enables proactive — not reactive — physiological management.

[0118] • Powered by integrated Al, motion energy harvesting and real-time feedback loops.

[0119] • Compatible with scalable screen-printing manufacturing. 9. Comparative Superiority Over Prior Art

[0120] This invention demonstrates clear technical superiority over conventional wearable technologies in several key aspects:

[0121] • Biochemical Detection: Unlike existing wearables that do not support biochemical sensing — specifically lacking the ability to detect biomarkers such as cortisol or CRP — this invention integrates plasmonic nano-sensors capable of real-time, motion-resistant detection of these markers in sweat.

[0122] • Deep-Tissue Imaging: Conventional solutions are limited to surface-level physiological data and cannot capture internal inflammatory dynamics. In contrast, this system incorporates deep-tissue thermal and electromagnetic profiling, allowing for precise identification of microinflammatory hotspots.

[0123] • Predictive Capability: Existing systems typically provide reactive monitoring, issuing alerts only after fatigue or stress has already occurred. This invention utilizes a hybrid Al model (CNN + LSTM) to predict acute pain and fatigue episodes 10-15 minutes before onset, allowing for preemptive intervention.

[0124] • Power Efficiency: Traditional wearables require frequent recharging, often daily. The present system eliminates this limitation by using triboelectric nanogenerators (TENGs) woven into the garment, harvesting kinetic energy to enable self-sustaining operation.

[0125] • Integration Scope: Whereas most wearables rely on single-mode sensing (e.g. only heart rate or motion), this invention features a multi-modal biosensing platform that simultaneously integrates biochemical, biomechanical, thermal and neurophysiological data streams — an unprecedented level of fusion in wearable technology.

[0126] 10. Manufacturing and Commercial Feasibility

[0127] • Modular architecture compatible with mass textile production.

[0128] • Fully functional prototype tested in collaboration with European football organizations.

[0129] • Commercial rollout underway, backed by industry partnerships.

[0130] Figures Section

[0131] Figure 1 : System Overview Diagram

[0132] Figure 2: System Architecture and Power-Communication Flow (Nano-Optical Sensors, Fluorescent Sensor for Measuring Drug Levels, Fluorescent Sensor for Measuring Drug Levels)

[0133] Figure 3: Closed-Loop System Architecture for Physiological Monitoring and Feedback

[0134] Figure 4: Sensor Architecture Cross-Section

[0135] Figure 5: Functional Block Diagram of Integrated Temperature and Humidity Sensor Module (SHT4xl) - 4th Gen., High-Accuracy, 16-bit, Industrial Grad, Relative Humidity and Temperature Sensor)

[0136] Figure 6: Functional Block Diagram of Integrated Pain level monitoring (Pressure and Temperature Sensor Module)-MS5837-30BA high-resolution pressure and temperature sensor

[0137] Figure 7 : Functional Block Diagram of the Embedded Microcontroller Unit (MCU) for Sensor Integration and Wireless Communication

[0138] Figure 8 - Functional Block Diagram of the Biopotential Measurement Front-End Using ADS1192(TX ADS1192 - Low-Power, 2-Channel, 16-Bit Analog Front-End for Biopotential Measurements)

[0139] Figure 1 : System Overview Diagram

[0140] A smart shirt with all sensor positions and system components (MCU, cloud, energy, app.).

[0141] Description

[0142] 1. Nano-Optical Sensors

[0143] Detect biochemical markers such as cortisol and CRP using plasmonic nanostructures. These sensors enable real-time, motion-resistant molecular analysis — unprecedented in commercial wearables.

[0144] 2. MIP Sensors (Molecularly Imprinted Polymer)

[0145] Measure lactate and inflammatory cytokines using synthetic polymer receptors that mimic biological affinity. Highly selective and rarely integrated in smart garments.

[0146] 3. Neurophysiological Sensor (EMG)

[0147] Monitor electrical muscle activity, neural delay, and neuromuscular stress. Critical for detecting fatigue before it manifests physically.

[0148] 4. Motion Sensor (IMU)

[0149] Inertial Measurement Unit (accelerometer + gyroscope) tracks posture, gait, and movement for biomechanical context.

[0150] 5. Thermal Imaging Sensors

[0151] Use electromagnetic thermopile-based detection to map deep-tissue inflammation with high resolution (±0.1 °C). Enable detection of microinflammatory patterns not accessible to surface sensors.

[0152] 6. Muscle Strain Sensor

[0153] Measure real-time contraction force, mechanical fatigue, and load dynamics. Provide biomechanical workload analysis vital to athletic and rehab applications.

[0154] 7. Muscle Pressure Sensors Sense mechanical compression or tension across muscle groups. Complement strain sensors in assessing mechanical overload or imbalance.

[0155] 8. TENG Energy Harvester

[0156] Triboelectric nanogenerators convert body motion into usable electrical power. Innovative for self-sustaining operation in high-mobility environments.

[0157] 9. Lactate Sensor

[0158] Biochemical sensor tracking sweat-based lactate accumulation. Complements cortisol and strain data to triangulate fatigue levels.

[0159] 10. SpO2 Sensor

[0160] Measures blood oxygen saturation using photoplethysmography (PPG). Useful for monitoring aerobic exertion and oxygen efficiency.

[0161] 11. Respiratory Sensor

[0162] Tracks breath rate and rhythm via impedance or stretch sensors. Adds respiratory insight during exertion or recovery.

[0163] 12. Vital Sign Sensors: covering heart rate, respiratory rate, and SpO2, offering foundational physiological context.

[0164] Figure 2: System Architecture and Power-Communication Flow (Nano-Optical Sensors, Fluorescent Sensor for Measuring Drug Levels, Fluorescent Sensor for Measuring Drug Levels)

[0165] Description:

[0166] This figure illustrates the integrated system architecture of the smart garment, showing the interaction between the rechargeable battery, low-dropout (LDO) voltage regulator, nano-sensor modules (including Nano-Optical, MIP, and EMG components), and key physiological sensors (ADS1192, SHT4xI, MS5837-30BA). The diagram highlights power distribution, data transmission over SPI and I2C buses, and Bluetooth-based wireless communication. It also maps biopotential inputs (ECG / EMG) and shows the central role of the nRF52840 module in coordinating sensor polling, data fusion, and Bluetooth output.

[0167] Component 1: Plasmonic-Based Nano-Optical Detection Module (P-NODM-1)

[0168] SPECIFICATIONS:

[0169] * Core Detection Technology: Piasmonic nanostructures for enhanced optica i detection of protein biomarkers.

[0170] • Detection Capability: Sensitivity to pain and stress-associated proteins (e.g„ cortisol, CRP).

[0171] ® Low Power Operation: o Power Consumption: 500 pW o Voltage: 3.3V

[0172] * Wavelength Sensitivity: o Detection Range: 500 nm --- 900 nm (near-infrared range) o Signal Amplification: 60 dB optical gain

[0173] • Integrated Signal Amplifier: Converts optical signals into electrical signals for processing.

[0174] * Communication Interface: SPI-compatible interface for transmitting data to the central controller,

[0175] ® Operating Conditions: o Temperature Range: -20°C to +70°C o Humidity: Lip to 90% RH (non-condensing)

[0176] • Material: Flexible, biocompatible encapsulation with a thickness of 0.5 mm.

[0177] Component 2: Fluorescence-Based Microfluidic Sensor Module (FMS-100)

[0178] SPECIFICATIONS:

[0179] • Core Detection Technology: fluorescence transducers integrated with microfluidic channels

[0180] • Sampling Medium: Non-invasive collection through sweat or interstitial fluids

[0181] • Excitation Source: Embedded UV LED (365 nm) for fluorescence activation.

[0182] * Detection Range: o Drug Concentration Sensitivity: 10 nM to 100 pM o Signa I -to - Noise Ratio: 80 dB

[0183] ® Power Requirements: o Operating Voltage: 3.3V o Power Consumption: 1 mW per reading.

[0184] • Output Signal: Digital signal compatible with ADC (Analog-to-Digitai Converter),

[0185] * Communication Interface: i2C for low-speed transmission to the ioT Gateway.

[0186] ® Encapsulation Material: PDMS coating for biocompatibility and water resistance.

[0187] « Environmental Tolerance: o Operating Temperature: -10°C to +50°C o Water Resistance: IP67 certified.

[0188] Components: Fluorescent Sensor for Measuring Drug Levels

[0189] MQLeculadmpn^

[0190] SPECIFICATIONS:

[0191] • Core Technology: Molecularly imprinted polymers (MIPs) designed to detect key biomarkers for injuries or pain (e.g., lactate or inflammatory markers).

[0192] ® Sensitivity Range: o Biomarker Detection: 5 ng / mL to 200 pg / mL o Detection Time: 2 seconds per sample,

[0193] ■> Integrated Amplification: Built-in low-noise amplifier for signal processing.

[0194] * Power Specifications: o Operating Voltage: 2.7V o Power Consumption: 400 pW in active mode.

[0195] ® Output Signal: o Analog Output: 0.5V -- 2.5V (proportional to biomarker concentration). o ADC Compatibility: 16-bit resolution. • Communication Protocol: UART interface for serial communication with the processing unit.

[0196] * Environmental Resilience: o Operating Temperature: -30”C to -r85°C o Humidity: 20% - 95% RH.

[0197] • Packaging: Thin-f iim polymer (0.8 mm thick), integrated into modular compartments within the shirt.

[0198] System Overview and Connections

[0199] Smart Shirt integrates the following components:

[0200] 1. ADS1192 (Biopotential Measurements): Measures and digitizes ECG signals. o Interface: SPI. o Power Supply: 3.3V. o Outputs: 16-bit digitized data for processing.

[0201] 2. SHT4xl (Humidity and Temperature Sensor): Measures environmental conditions. o Interface: l2C. o Power Supply: 3.3V.

[0202] 3. MS5837-30BA (Pressure and Temperature Sensor): Measures pressure and additional temperature data. o Interface: l2C. o Power Supply: 3.3V.

[0203] 4. nRF52840 (Bluetooth Transmitter): Acts as the central processing unit and transmits data to a smartphone or other devices. o Interfaces: SPI / I2C for sensor communication, GPIO for control. o Power Supply: 3.3V.

[0204] 5. Nano Sensors E1 / E2 / E3

[0205] Connections

[0206] 1. ADS1192: o SPI interface (MISO, MOSI, SCLK, CS) connected to the nRF52840. o VDD and GND connected to the regulated 3.3V and GND rails. o START pin controlled by GPIO from nRF52840.

[0207] 2. SHT4xl and MS5837-30BA: o Both sensors share the l2C bus (SDA, SCL) with pull-up resistors. o VDD and GND connected to the 3.3V and GND rails. o l2C addresses configured uniquely for both sensors.

[0208] 3. nRF52840: o Communicates with the ADS1192 via SPI and the SHT4xl / MS5837-30BA via l2C. o GPIOs for controlling peripherals. o Transmits sensor data via Bluetooth to paired devices.

[0209] 4. Battery and Power Management: o LiPo battery connected to an LDO regulator. o Battery charging circuit (e.g., TP4056) for recharging via USB.

[0210] Above is a detailed circuit diagram for the Smart Shirt system. Each sensor is connected to the nRF52840 microcontroller using the appropriate communication protocol (SPI for ADS1192 and l2C for SHT4xl and MS5837). The system is powered by a battery with an LDO regulator providing stable 3.3V.

[0211] Data Flow Explanation

[0212] 1. Data Acquisition: o The nRF52840 initializes and configures the ADS1192, SHT4xl, and MS5837-30BA. o Periodically polls the sensors for data over SPI (ADS1192) and l2C (SHT4xl and MS5837-30BA).

[0213] 2. Data Processing: o Raw data from sensors are collected and pre-processed by the nRF52840 (e.g., filtering ECG signals).

[0214] 3. Data Transmission: o The processed data is packaged and transmitted via Bluetooth Low Energy (BLE) using nRF52840. o BLE packets include timestamped readings for heart rate, humidity, temperature, and pressure.

[0215] 4. Data Reception: o A paired smartphone or device receives the BLE data stream. o Data is displayed or logged via a custom mobile app or a compatible BLE application.

[0216] Data Assimilation and Calibration for Pain and Stress

[0217] 1. Data Assimilation:

[0218] • Biopotential Data (ADS1192): Captures ECG or EMG signals, indicating muscle activity, heart rate, or stress-induced irregularities. Data is processed in the nRF52840 to calculate metrics like heart rate variability (HRV), a key indicator of stress.

[0219] • Humidity and Temperature Data (SHT4xl): Monitors skin temperature and sweat levels, correlating to physiological stress responses. • Pressure Data (MS5837): Measures chest pressure during breathing, identifying irregular patterns linked to pain or anxiety.

[0220] All data streams are synchronized and transmitted over Bluetooth using the nRF52840 to a paired device for processing and visualization.

[0221] 2. Data Processing for Pain and Stress Calibration:

[0222] • Heart Rate Variability Analysis: Low HRV is strongly associated with stress and pain.

[0223] • Thermal and Humidity Patterns: Sudden increases in temperature or sweat levels can indicate acute pain or stress episodes.

[0224] • Breathing Irregularities: Pressure sensor data identifies shallow or rapid breathing, typical in pain or high stress.

[0225] 3. Machine Learning Calibration:

[0226] • Data is fed into a machine learning model trained on patterns correlating physiological data with reported pain and stress levels.

[0227] • The model learns individual baselines and deviations, adapting to unique physiological responses for personalized stress and pain assessment.

[0228] Data Flow Explanation

[0229] The smart shirt system is designed to capture, process, and transmit real-time physiological data through an efficient flow between edge devices and cloud infrastructure. The process can be outlined as follows:

[0230] 1. Edge Layer o Devices and Sensors:

[0231] The smart shirt is embedded with advanced sensors (Explained earlier above) that monitor physiological signals such as heart rate, body temperature, and movement. These sensors detect and capture raw data continuously while being non-intrusive to the user. o Data Transmission to loT Gateway:

[0232] The collected data is transmitted to an loT gateway, which acts as an intermediary to preprocess and securely route the data for further analysis.

[0233] 2. Cloud loT Layer o loT Gateway to Cloud:

[0234] The loT gateway sends the preprocessed data to a cloud-based data system over a secure connection. The cloud platform offers robust infrastructure for storing, processing, and analyzing large-scale data. o Data System:

[0235] The cloud data system applies advanced analytics, machine learning, and Al algorithms to interpret the data, identify patterns, and generate meaningful insights such as health alerts or performance metrics.

[0236] 3. Signal View and User Interface o Smartphone Application:

[0237] The processed insights are made accessible to users through a smartphone app. The app provides real-time visualizations and alerts based on the data received from the cloud, enabling users to monitor their health or activity on the go. o Medical Facility Processing Server:

[0238] For scenarios requiring professional monitoring, the data can also be transmitted to a processing server at a medical facility. This enables healthcare professionals to view the signals in real-time and make informed decisions.

[0239] Figure 3 - Closed-Loop System Architecture for Physiological Monitoring and Feedback

[0240] General Description:

[0241] FIG. 4 illustrates the closed-loop system architecture of the smart interactive shirt, showcasing the flow of physiological sensor data through the edge processing pipeline and the feedback mechanism. The 15 biosensor data streams — including biochemical, neurophysiological, and vital sign inputs — are filtered via embedded Kalman algorithms and analyzed using deep signal processing (CNN + LSTM). If a pain or fatigue risk is detected, the system triggers vibrotactile feedback and sends alerts to the mobile application. The system supports federated learning for continuous adaptation and includes optional cloud upload for extended analytics. Energy harvesting via TENG technology supports autonomous operation.

[0242] Figure 4 - Sensor Architecture Cross-Section

[0243] • Show internal structure of Nano-Optical Sensor and MIP Sensor: o Substrate o Functional layers (e.g., AuNPs, polymer) o Sweat interface o Signal output layer Figure 5: Functional Block Diagram of Integrated Temperature and Humidity Sensor Module (SHT4xI) (4th Gen., High-Accuracy, 16-bit, Industrial Grad, Relative Humidity and Temperature Sensor)

[0244] Figure 5 illustrates the functional architecture of the integrated SHT4xI sensor module used within the smart interactive shirt system. This industrial-grade, fourth-generation module provides continuous measurement of ambient temperature and relative humidity, enhancing the accuracy of biosignal interpretation under varying environmental conditions.

[0245] SPECIFICATIONS

[0246] • Accuracies ARH = ±2.0 %RH, AT = ±0.2 °C

[0247] • Fully functional in condensing environment

[0248] • Supply voltage VDD = 2.3 V...5.5 V

[0249] • Average current: 21 pA (at meas. rate 1 Hz)

[0250] • I2C FM+, CRC checksum, multip. I2C addr.

[0251] • Operating range: 0...100 %RH, -40...125 °C

[0252] • Variable power heater

[0253] The system includes:

[0254] • RH Sensor (Relative Humidity) and T Sensor (Temperature), which capture environmental data.

[0255] • An Analog-to-Digital Converter (ADC) digitizes analog sensor outputs.

[0256] • A Data Processing Unit, supported by Calibration Memory, applies compensation algorithms using factory-calibrated coefficients.

[0257] • A Heater ensures stable operation even in high-humidity or condensing environments.

[0258] • Reset and Register blocks maintain operational integrity and buffer sensor data.

[0259] • An integrated I2C Interface with SDA (data) and SCL (clock) lines transmits readings to the central microcontroller unit (MCU).

[0260] • VDD and VSS lines provide regulated power input (2.3-5.5V).

[0261] This sensor module is permanently embedded in the textile structure and has been fully integrated into the wearable system’s architecture. It plays a critical role in providing environmental compensation, which supports the precision of real-time physiological monitoring and fatigue prediction. Figure 6: Functional Block Diagram of Integrated Pain level monitoring (Pressure and Temperature Sensor Module): MS5837-30BA high- resolution pressure and temperature sensor

[0262] SPECIFICATIONS

[0263] • Ceramic and metal package: 3.3 x 3.3 x 2.75mm

[0264] • High resolution module: 0.2 cm (in water)

[0265] • Supply voltage: 1.5 to 3.6 V

[0266] • Low power: 0.6 pA (standby < 0.1 pA at 25°C)

[0267] • Integrated digital pressure sensor (24-bit Al ADC)

[0268] • Operating range: 0 to 30 bar, -20 to +85 °C

[0269] • I2C interface

[0270] • No external components (internal oscillator)

[0271] • Water resistant sealing with 1.8 x 0.8mm O-ring

[0272] • High chemical endurance

[0273] • Shielded metal lid

[0274] Figure 7 - Functional Block Diagram of the Embedded Microcontroller Unit (MCU) for Sensor Integration and Wireless Communication

[0275] This figure illustrates the internal architecture of the nRF52840-based microcontroller used in the smart garment system. It highlights the integration of Bluetooth Low Energy communication, ARM Cortex-M33 processor, RISC-V coprocessor, and secure memory blocks essential for processing multi-sensor data, executing edge Al models, and transmitting physiological metrics to external devices.

[0276] Nordic Semiconductor nRF52840 : Multiprotocol 2.4 GHz radio supporting Bluetooth Low Energy, 802.15.4-2020, and 2.4 GHz proprietary modes (up to 4 Mbps)

[0277] SPECIFICATIONS

[0278] « Bluetooth 6.0, IEEE 802.15.4-2020, and 2.4 GHz enabled transceiver

[0279] « -96 dBm sensitivity in 1 Mbps Bluetooth Low Energy mode, 0.1% bit error rate

[0280] ® -104 dBm sensitivity in 125 kbps Bluetooth Low Energy mode (long range) with a 0.1% bit error rate

[0281] • -102 dBm typical sensitivity in IEEE 802.15.4

[0282] ® Up to +8 dBm configurable output power; 1 dB step size from -8 dBm to +8 dBm

[0283] ® Supported data rates:

[0284] ® Bluetooth 6.0 - 2 Mbps, 1 Mbps, 500 kbps, and 125 kbps « IEEE 802.15.4-2020 - 250 kbps

[0285] • Proprietary 2.4 GHz - 4 Mbps, 2 Mbps, and 1 Mbps

[0286] ® Single-ended antenna output (on-chip balun)

[0287] « 128-bit AES / ECB / CCM / AAR coprocessor (on-the-fly operation)

[0288] ® RSSi (1 dB resolution)

[0289] » 1.7 V to 3,6 V supply and I / O voltage

[0290] ® Single 32 MHz crystal operation

[0291] « Optional 32.768 kHz clock

[0292] ® Operating temperature from -40°C to 105°C

[0293] Figure 8 - Functional Block Diagram of the Biopotential Measurement Front-End Using ADS1192( TX ADS1192 - Low-Power, 2-Channel, 16-Bit Analog Front-End for Biopotential Measurements)

[0294] General Description:

[0295] This figure illustrates the internal architecture and functional workflow of the ADS 1192, a low- power, 2-channel, 16-bit analog front-end (AFE) used for biopotential measurements in the smart wearable system. The block diagram shows how the MUX, low-noise amplifiers (Al, A2), analog-to-digital converters (ADC1, ADC2), and right leg drive amplifier (RLD) are integrated to acquire and process electrophysiological signals such as ECG or EMG. The system also includes SPI-compatible digital output, internal oscillator, programmable gain control, and a reference generator, making it ideal for wearable physiological sensing applications.

[0296] SPECIFICATION

[0297] • Two Low-Noise PGAs and 23 Two High-Resolution ADCs (ADS1192)

[0298] • Low Power: 335 pW / channel

[0299] • Input-Referred Noise: 24 pVPP (150-Hz BW, G = 6)

[0300] • Input Bias Current: 1 nA

[0301] • Data Rate: 125 SPS to 8 kSPS • CMRR:-95dB

[0302] • Programmable Gain: 1, 2, 3, 4, 6, 8, or 12

[0303] • Supplies: Unipolar or Bipolar- Analog: 2.7 V to 5.25 V- Digital: 1.7 V to 3.6 V

[0304] • Built-In Right Leg Drive Amplifier, Lead-Off Detection, Test Signals

[0305] • Built-In Oscillator and Reference • Flexible Power-Down, Standby Mode

[0306] • SPI™-Compatible Serial Interface

[0307] • Operating Temperature Range:-40°C to +85°C

Claims

ClaimsClaim 1 (Independent Claim - Smart Wearable System):A smart interactive garment system for real-time physiological monitoring and fatigue management, comprising:• a flexible textile substrate configured to conform to a user’s body;• a sensor suite comprising at least 15 embedded sensors selected from biochemical, thermal, biomechanical, and neurophysiological categories, including: o nano-optical sensors configured to detect biochemical markers in sweat; o thermal sensors configured to monitor deep-tissue temperature gradients; o strain gauges configured to measure muscle fatigue or exertion; and o bioelectrical sensors configured to monitor neural or muscular activity;• a processing unit embedded within the garment configured to: o collect and preprocess sensor data; o execute a machine learning model to predict pain or fatigue events in real time; and o initiate a feedback response;• a haptic feedback mechanism integrated within the textile;• and a wireless communication interface configured to transmit real-time data to a companion mobile application.Claim 2:The system of claim 1, wherein the biochemical sensors comprise plasmonic nano-optical elements for detecting cortisol and CRP levels in sweat.Claim 3:The system of claim 1 , wherein the thermal sensors comprise thin-film thermopiles with a resolution of at least ±0.1 °C.Claim 4:The system of claim 1, wherein the processing unit implements a hybrid machine learning model combining convolutional neural networks (CNN) and long short-term memory (LSTM) networks to generate predictive alerts for fatigue or stress events.Claim 5:The system of claim 1, wherein the haptic feedback mechanism is configured to provide vibrotactile alerts in response to predicted thresholds of pain or physiological stress.Claim 6:The system of claim 1, wherein the wireless interface uses Bluetooth Low Energy (BLE) to transmit sensor data to a mobile device.Claim 7:The system of claim 1, wherein the textile substrate is manufactured using screen-printed electronic components for sensor integration and connectivity.Claim 8:The system of claim 1, further comprising an energy management unit configured to support integrated power delivery from a rechargeable battery and / or motion-based energy harvesting elements embedded in the fabric.Claim 9:The system of claim 1, wherein the mobile application is configured to display real-time data, predictive analytics, and configurable alerts for user guidance.Claim 10 (Method Claim):A method for providing real-time physiological monitoring using a smart interactive shirt, comprising:• acquiring multi-modal physiological data from sensors embedded in a textile garment;• preprocessing the data using an onboard processing unit;• analyzing the data using a machine learning model trained to predict pain or fatigue episodes; and• generating real-time feedback via integrated actuators and / or mobile interface.

Images