Description:FIELD OF THE INVENTION
This invention relates to a system of Real-Time Mental Health Tracking via an AI-Integrated Wearable Sensor Platform
BACKGROUND OF THE INVENTION
In today’s world where the concerns of psychological health and real-time mental health tracking are continuously growing, now there is need for systems that are wearable and capable of real-time monitoring using wireless communications. This patent frameworks an AI-enabled wristband that reads psychological well-being by collecting and gathering data through attached sensors like Skin Conductance sensors named GSR, Heart Rate Variability (HRV) Sensors and Accelerometers to track the sleep schedule, level of activity, sleep cycles. Using AI algorithms, the signals from the sensors of the device proceed and generated psychological health insights that are real- time. The processed results from the device are collected and transmitted to connected mobile applications and the cloud for further processing using Wi-Fi. This invention ensures both mental health professionals and users get notifications in case any patterns are abnormal. Moreover, a collection of the patterns of a patient’s health will now be available for studying and personalizing treatment to be given.
Regardless of various upgradations and innovations in wearable health monitoring technologies in recent years, there is still presence of underserved and underexplored in the field of real-time psychological health assessment. Even if there are various devices that are wearable and are available to track physical health through parameters like number of steps, sleep cycle, heart rate, there are very few technologies that are qualified and equipped to read and interpret the psychological signal associated with mental states such as depression, stress or anxiety. Single-sensor input or exclusively relaying on generalized activity-set data are keys that are present on the existing systems, which are not sufficient for responding or diagnosing complex cognitive changes or complex emotional rush. Existing systems fail to combine data from multi-sensors .
There is a presence of gap as there is lack of intelligent integration of multiple physiological signals such as movement patterns, heart rate variability (HRV), conductance through skin; a proper, well designed AI model is required to process all these. Wearable would be unable to produce results that would be accurate, and personalized if such multi-model data fusion is not used through the process.
Another limitation in the existing system’s current devices is their inefficiency of personalized and dynamic feedback or continuous monitoring giving timely alerts. Well, there are presence of fitness trackers that give basic notifications, but they do not adapt to personalized psychological patterns that could be tailored to user’s lifestyles and needs.
Another challenge lies in privacy and data security for the user. For developing a comprehensive, wearable device that is AI driven, and not only gathers various physiological signals but also analyzes them and reports insights to users and professionals in a secure and user-friendly manner, is the aim of this innovation.
Thus, there is a clear research gap in present in the existing system and thus this AI powered device that is also wearable combines detecting psychological stress in real-time, personalized interventions, tracking mental health over time, and secure communications while also being compatible with clinical world.
AU2020213416B2 Disclosed herein is a system and a method for generating stress level information for an individual and stress level resilience information for an individual, which includes a stress information processing module configured to process stress information for the individual, the stress information for the individual comprising at least two of psychometric information for the individual, physiological information for the individual, behavioral information for the individual, and cognitive function information for the individual 1/4 LIL 00
RESEARCH GAP: The previous systems rely on complex psychometric or cognitive tests, while this invention uses only easy, real-time body signals—like skin response, heart rate, temperature and motion—all through a wearable wristband. It does not need user input. Moreover, it offers instant alerts, does stress detection and generates AI-powered advice and recommendations directly on the device and mobile app.
US7785257B2 A system and method for detecting, monitoring and analyzing physiological characteristics. Signals from a subject are acquired from a suite of sensors, such as temperature, carbon dioxide, humidity, light, movement, electromagnetic and vibration sensors, in a passive, non-invasive manner. The signals are processed and physiological characteristics are isolated for analysis. The system and method are to analyze sleep patterns, as well as to prevent bed sores or detect conditions such as illness, restless leg syndrome, periodic leg movement, sleep walking, or sleep apnea. However, numerous other applications of the invention are also disclosed.
RESEARCH GAP: This system uses wearable biosensors that are intended for ongoing use to specifically check for emotions and levels of stress. This wristband monitors personal health signals such as heart rate, GSR, motion, and the temperature, but unlike systems designed for sleep or bed monitoring with environmental sensors, it provides real-time emotional insights, warnings, and personal wellness direction through mobile apps and displays.
None of the prior art indicate above either alone or in combination with one another disclose what the present invention has disclosed. This invention relates to
SUMMARY OF THE INVENTION
This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention.
This summary is neither intended to identify key or essential inventive concepts of the invention and nor is it intended for determining the scope of the invention.
To further clarify advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which is illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail with the accompanying drawings.
The wearable wristband helps user to keep the check of their mental health and emotional wellbeing in real-time. It is light weight, user-friendly device that can easily be everyday gadget. The device collects physiological signals such as body movement, skin conductivity, heart rate. The data from these signals are processed using AI algorithms. This results in getting the insights of if the user is suffering from any anxiety, stress, depression or any emotional disbalance. It connects to the mobile applications Blynk and to the cloud through Wi-Fi, and here insights, personalized suggestions and timely alerts are provided. This help in the revolution in the mental well-being grounds, proactively enabling healthcare providers to remotely monitor patients whenever needed.
BRIEF DESCRIPTION OF THE DRAWINGS
The illustrated embodiments of the subject matter will be understood by reference to the drawings, wherein like parts are designated by like numerals throughout. The following description is intended only by way of example, and simply illustrates certain selected embodiments of devices, systems, and methods that are consistent with the subject matter as claimed herein, wherein:
FIGURE 1: FLOW CHART
FIGURE 2: SYSTEM ARCHITECTURE
FIGURE 3: DATA FLOW FROM BLYNK WEBHOOKS TO CLOUD STORAGE AND USE CASES
The figures depict embodiments of the present subject matter for the purposes of illustration only. A person skilled in the art will easily recognize from the following description that alternative embodiments of the structures and methods illustrated herein may be employed without departing from the principles of the disclosure described herein.
DETAILED DESCRIPTION OF THE INVENTION
The detailed description of various exemplary embodiments of the disclosure is described herein with reference to the accompanying drawings. It should be noted that the embodiments are described herein in such details as to clearly communicate the disclosure. However, the amount of details provided herein is not intended to limit the anticipated variations of embodiments; on the contrary, the intention is to cover all modifications, equivalents, and alternatives falling within the scope of the present disclosure as defined by the appended claims.
It is also to be understood that various arrangements may be devised that, although not explicitly described or shown herein, embody the principles of the present disclosure. Moreover, all statements herein reciting principles, aspects, and embodiments of the present disclosure, as well as specific examples, are intended to encompass equivalents thereof.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments. As used herein, the singular forms “a",” “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and/or “including,” when used herein, specify the presence of stated features, integers, steps, operations, elements and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components and/or groups thereof.
It should also be noted that in some alternative implementations, the functions/acts noted may occur out of the order noted in the figures. For example, two figures shown in succession may, in fact, be executed concurrently or may sometimes be executed in the reverse order, depending upon the functionality/acts involved.
In addition, the descriptions of "first", "second", “third”, and the like in the present invention are used for the purpose of description only, and are not to be construed as indicating or implying their relative importance or implicitly indicating the number of technical features indicated. Thus, features defining "first" and "second" may include at least one of the features, either explicitly or implicitly.
Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which example embodiments belong. It will be further understood that terms, e.g., those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The wearable wristband helps user to keep the check of their mental health and emotional wellbeing in real-time. It is light weight, user-friendly device that can easily be everyday gadget. The device collects physiological signals such as body movement, skin conductivity, heart rate. The data from these signals are processed using AI algorithms. This results in getting the insights of if the user is suffering from any anxiety, stress, depression or any emotional disbalance. It connects to the mobile applications Blynk and to the cloud through Wi-Fi, and here insights, personalized suggestions and timely alerts are provided. This help in the revolution in the mental well-being grounds, proactively enabling healthcare providers to remotely monitor patients whenever needed.
When the user wears the Wristband, it is comfortably worn and its passive sensors begins to monitor the applicant. The data collection is through various sensors such as
1) HRV Sensor: for measuring the variation of time between the heartbeats. It detects stress, anxiety and overall nervous response.
2) GSR sensors: For measuring sweat response or skin conductivity of the user. It indicates stress spikes and emotional arousal.
3) Accelerometer: for measuring the overall physical activity, Movements, and restlessness. It identifies inactivity that can have connects to depression or in some cases of hyperactivity.
4) Temperature Sensor: for measuring the skin temperature as it can fluctuates during stress.
5) SpO2 sensor : It measures the level of oxygen saturation in the body thus measuring the physical stress and reading the breathing patterns.
These sensors are regulated from battery, and are powered by a 3.3V line. The processing layer consists of Computing Unit that reads all the sensors at different intervals and known as Smart numeric sensory data collector. GSR is read its data at every 10s, HRV at every 5s, Temperature at every 10-30s, Motion at every 2s. It uses Deep Sleep mode to save power then the sensors are not in the use. All this data is send via Wi-Fi to mobile app to cloud directly. To ensure potability, stable power and for the sake of battery management we are using Li-Po Battery (3.7V) for the main source of power. It is small, rechargeable and perfect for devices that need to be wearable. There is use of TP4056 charger module that charges the battery safely using Micro-USB port. It acts as the interface for charging by power bank or USB adaptor. It provides undervoltage, overcharge and short-circuit protection. There is use of MT3608 Boost convertor which ensures that there is always stable output voltage of 3.3V. Computing Unit, Sensors, OLED Display are all power consumers and all of them need a common ground and regulated 3.3V to ensure their performance to be consistent. Micro-USB charging port on the wristband ensures connection directly to the TP4056.
Computing Unit connects to Blynk Cloud by Wi-Fi and it periodically sends data to the dashboard of Blynk. As Blynk dashboard is used as the mobile app widgets like Notification Widgets for mobile alerts, SuperChart for Live graphs, GSR, Temperature, HRV and motion, Label Display – for showing current state, and different tabs for trends, advice and insights. As we are using Blynk only for UI, advanced machine learning is done separately on the cloud server. It receives data using Blynk HTTP/Webhook and then it applies different algorithms like Random Forest for Emotion classification, LSTM for Mood prediction, K-means for Behaviour patterns, and Thresholds for Stress/emergency alerts. This then sends insights to: Blynk app (via virtual pins) and Computing Unit. Thus, we can say that for all the visualisation we are using a Mobile app Dashboard (Blynk) that includes the features of giving real-time alerts, showing Heart Rate, SpO2, GSR, Temp, showing weekly treads and much more. Then there is OLED Display on the wristband that shows HR and alerts and also support offline usage. Notifications are sent by Blynk’s push notification widget.
for long term analysis and research, all the incoming data from the sensor, are saved in the cloud server in the CSV file structure. Blynk HTTP Webhooks are used to receive the data. And these data are necessary for model training, Daily and weekly exports and Manual analytics.
For the enclosure design, different components used are- the material to be TPU strap and PLA/ABS case for components; for the Sensor Window- Flush-fitting lens/ opening for MAX30102 sensor, OLED for Transparent window or cutout, a Charging port that uses Micro-USB hole for TP4056 access (Charging Point), a Battery Slot that fits 150–300 mAh Li-Po with foam protection, and a strap Design that can be Velcro band or watch type.
To understand psychological state of the user and make sense of the sensors used, the following system utilizes different algorithm, each helping in different ways. For instance, some algorithm helps learn how there are changes in the mood of user over time, while other detect the level of stress. While coming all together, these algorithms gives alert, predictions and suggestions through the device about the mental health of the user. Below explained algorithms are chosen on the basis of the ability to emotion classification, pattern detection, and handling time-series data in behaviour of the user.
Random Forest algorithm is specifically used for classification of emotions. It is like a forest full of decision tress. Individual tree give its decision on what the result should be like stress, anxiety, calm etc. The final answer depends on the majority result. For the sake of understanding lets say the unit of tree says “No movement + Low temperature = depression”
Another tree says “ High GSR + fast heart = anxiety”, while another tree says “GSR + HRV = stress”, all tress gives their vote and the most common results is chosen as the final. It is based on the multiple sensor input at once, thus is great for classifying emotions.
K-Means group algorithm is used when grouping of behaviour is required. It groups data based on the basis of similarity and calls is “clusters”, and not labeling things like stress or clam, it just find patterns. This algorithm helps when we just need to find the common patterns in the behaviour of the applicant.
LSTM – Long Short-Term Memory is a algorithm that is good for reading patterns and behaviour that happens in the time series or over time. It is a type of deep learning model. For instance, over time changing situations can be read through LSTM and thus help predict mental health state before it turns out to be wild.
Threshold-Based Rules are for alerts that are needed in the real-time. The are utilised for decision making that to be done instantly, like recommending breathing exercises, alert triggering. These are simple if-else rule based on fixed numbers. They are reliable and very fast and there is no learning required.
Algorithms Used:
// =====================
// 1. SYSTEM INITIALIZATION
// =====================
Setup Serial Monitor
Initialize I²C bus (for MAX30102, MPU6050, MAX30205)
Initialize OneWire bus (if using DS18B20)
Initialize analog input pin for GSR (GPIO34)
Initialize OLED display (via I²C)
Connect to Wi-Fi using SSID & Password
Initialize Blynk with Auth Token

// === Variable Definitions ===
Define variables for: heart_rate, spo2, hrv, gsr_value, body_temp, motion_data, stress_level
Initialize timers for each sensor's interval

// =====================
// 2. MAIN LOOP – CONTINUOUS OPERATION
// =====================
Loop Forever:

// ---------- SENSOR READINGS ----------

// Every 2 seconds → Motion Detection
If (millis - last_motion_read >= 2000 ms):
Read MPU6050 for acceleration and gyro
Calculate orientation and activity level
Store as motion_data
Update last_motion_read

// Every 5 seconds → Heart Rate and SpO₂
If (millis - last_hr_read >= 5000 ms):
Read raw IR and RED light data from MAX30102
Calculate HR from pulse peaks
Calculate SpO₂ using RED/IR ratio
Calculate HRV (RR intervals from pulse timings)
Update heart_rate, spo2, hrv
Update last_hr_read

// Every 10 seconds → GSR
If (millis - last_gsr_read >= 10000 ms):
Read analog signal from GSR sensor
Apply smoothing filter (moving average)
Convert to resistance or conductance value
Update gsr_value
Update last_gsr_read

// Every 10–30 seconds → Temperature
If (millis - last_temp_read >= temp_interval):
If using DS18B20:
Request and read temperature via OneWire
Else If using MAX30205:
Read temperature via I²C
Update body_temp
Update last_temp_read

// ---------- DATA PREPROCESSING ----------

Normalize all sensor values
Calculate estimated stress level from:
- GSR trends
- HRV drop
- Motion pattern
- Temperature rise
Classify emotion (e.g., calm, tense, anxious) using simple rule or ML model (optional)

// ---------- OLED DISPLAY ----------
Display on OLED:
HR: heart_rate bpm
SpO₂: spo2 %
Temp: body_temp °C
Status: stress_level or emotion_state

// ---------- DATA TRANSMISSION ----------

// Send to Blynk (Mobile App)
Blynk.virtualWrite(V1, heart_rate)
Blynk.virtualWrite(V2, spo2)
Blynk.virtualWrite(V3, body_temp)
Blynk.virtualWrite(V4, gsr_value)
Blynk.virtualWrite(V5, stress_level)

// Optional → Send to Cloud Server
If (cloud_logging_enabled):
Format data as JSON or CSV string:
timestamp, HR, SpO₂, Temp, GSR, Motion
Send via HTTP POST or MQTT to AI backend
Server stores in CSV or database

// ---------- ALERT HANDLING ----------
If (heart_rate > threshold_HR or stress_level == "High"):
Blynk.notify(" Stress or High HR detected!")
Show alert on OLED: “Take a break ”

// ---------- POWER MANAGEMENT ----------
If (no significant motion for X minutes AND stress_level == "Normal"):
Display: “Entering sleep mode”
Turn off OLED
Enter Deep Sleep for Y minutes
Wake on motion interrupt or timer

// =====================
// 3. BATTERY & CHARGING MANAGEMENT
// =====================
// TP4056 handles charging logic (hardware level)
// Optional: Read battery voltage using ADC pin + resistor divider
If (battery_monitoring_enabled):
Read battery voltage
Display battery % on OLED and Blynk

// =====================
// 4. END LOOP
// =====================
ADVANTAGES OF THE INVENTION:
• Combines heart rate variability, GSR (stress), SpO₂, temperature, and motion sensing in a single wristband to offer comprehensive physical and emotional state monitoring — previously fragmented across separate devices.
• The invention uses machine learning algorithms like LSTM, Random Forest to read physiological signals and provide personalised prediction of mood and alerts for prevention.
• Insights can be seen on an onboard OLED, and data is transferred in real time to a cloud server and a mobile app (Blynk), ensuring that the user receives alerts even if their phone is unavailable.
• Makes it feasible to easily collect raw bio signals in CSV format for further academic research, emotion-model training, or medical diagnosis — with timestamped data appropriate for retrospective analysis.
• Integrates Deep Sleep, adaptive sensor sampling, and optimized voltage regulation (via MT3608) to significantly extend battery life in wearable applications — making it ideal for continuous daylong use.
 
, Claims:1. A wearable AI-based psychological health monitoring system comprising: physiological sensors, a computing unit, a power management system, a wireless communication module, a machine learning module and a user interface.
2. The system as claimed in claim1, wherein the system provides real-time insights, alerts, and personalized suggestions based on the physiological and behavioral state of the user.
3. The system as claimed in claim1, wherein the physiological sensors configured to measure at least heart rate variability (HRV), galvanic skin response (GSR), motion activity, skin temperature, and blood oxygen saturation (SpO2).
4. The system as claimed in claim1, wherein the power management system comprising a rechargeable Li-Po battery, a charging module, and a voltage regulation circuit to maintain consistent operation at 3.3V.
5. The system as claimed in claim1, wherein the machine learning module deployed on said cloud server, configured to analyze said sensor data using one or more algorithms selected from: Random Forest for emotion classification, Long Short-Term Memory (LSTM) for mood prediction, K-Means clustering for behavioral pattern recognition, and threshold-based rules for real-time alerts.
6. The system as claimed in claim1, wherein the user interface comprising a mobile application and an OLED display on the device, for displaying sensor readings, emotional insights, historical trends, and notifications.
7. The system as claimed in claim1, wherein the computing unit operatively connected to said sensors, configured to collect sensor data at predefined intervals.