1. A wearable device (100) for detecting and classifying a user’s emotional state in real time, comprising: i) a sensor block (110) including a photoplethysmography (PPG) sensor (111) for heart rate and heart rate variability detection, a galvanic skin response (GSR) sensor (112), a skin temperature sensor (113), and optionally a SpO₂ sensor (114); ii) a microcontroller unit (120) configured with embedded machine learning processing to receive, preprocess, and classify bio-signal data into predefined emotional states; iii) a wireless communication module (130) configured for data transfer via at least one of Bluetooth Low Energy (BLE) or Wi-Fi; iv) a rechargeable battery (140) powering the device; v) a status indicator (150) comprising at least one of an LED or haptic feedback motor; and vi) a social plugin interface module (160) configured to embed classified emotional metadata into digital communication platforms.

2. The wearable device as claimed in claim 1, wherein the microcontroller unit (120) comprises an adaptive thresholding engine (121) configured to learn a user-specific physiological baseline to improve classification accuracy.

3. The wearable device as claimed in claim 1, wherein the wireless communication module (130) is configured to connect with a mobile companion application (170) for local inference, visualization of emotional states, and user-specific calibration.

4. The wearable device as claimed in claim 1, wherein the social plugin interface module (160) is implemented as an API or browser extension (161) configured to integrate emotion tags into social media posts and messaging applications.

5. The wearable device as claimed in claim 1, wherein the status indicator (150) provides stress or anxiety alerts through vibration feedback when classified emotional states exceed a threshold.

6. The method (200) for detecting and classifying emotional states using a wearable device as claimed in claim 1, comprising: i) capturing physiological signals using the PPG sensor (111), GSR sensor (112), and skin temperature sensor (113); ii) preprocessing the captured signals to remove noise and extract features; iii) calibrating signals against a user baseline using an adaptive thresholding engine (121); iv) classifying the emotional state into one of a plurality of categories using a trained machine learning model; and v) transmitting the classified emotional state as metadata to a digital communication platform.

7. The method as claimed in claim 5, wherein the classified emotional state is represented as an emoji overlay (210) in messaging applications or as an emotion tag (220) in social media posts.

8. The method as claimed in claim 5, wherein the wearable device provides real-time stress or anxiety alerts via the status indicator (150).

9. The wearable device as claimed in claim 5, wherein the data transmission from the wireless module (130) to external platforms is secured using end-to-end encryption (180) and complies with GDPR or medical device data privacy standards.

10. The wearable device of claim 1, wherein the form factor (190) is a wristband or clip-on housing configured to be lightweight, water-resistant, and sweat-resistant.

Description:TECHNICAL FIELD
[0001] The present invention relates to the field of wearable electronic devices and biometric signal processing, and more particularly to systems and methods for real-time detection and classification of emotional states using physiological sensors and embedded machine learning. The invention further pertains to context-aware computing, affective computing, and emotion-based human-computer interaction, including the integration of emotional metadata into digital communication platforms such as messaging and social media applications.
BACKGROUND ART
[0002] Background description includes information that may be useful in understanding the present invention. It is not an admission that any of the information provided herein is prior art or relevant to the presently claimed invention, or that any publication specifically or implicitly referenced is prior art.
[0003] In recent years, there has been growing interest in technologies that can detect and interpret human emotions for applications in mental health monitoring, human-computer interaction, and context-aware computing. Emotional states influence cognitive processes, decision-making, social interaction, and overall well-being. As such, the ability to monitor emotional states in real time can provide significant benefits in both personal and professional domains.
[0004] Traditional approaches to emotional monitoring rely heavily on subjective self-reporting, questionnaires, or visual observation—methods that are inherently intrusive, intermittent, and prone to bias. Some modern solutions utilize camera-based facial recognition or speech analysis to infer emotional states, but these methods raise privacy concerns and typically require controlled environments, making them unsuitable for continuous or mobile use.
[0005] Wearable devices offer a promising alternative by enabling continuous, non-invasive monitoring of physiological signals that correlate with emotional responses. Metrics such as heart rate variability (HRV), galvanic skin response (GSR), and skin temperature have been shown to provide reliable indicators of stress, arousal, and affective states. However, existing wearable solutions often suffer from limitations such as:
[0006] Limited sensor integration (e.g., relying on a single physiological input);
[0007] Lack of real-time, on-device processing, requiring cloud connectivity;
[0008] Inflexibility in adapting to individual physiological variations;
[0009] Poor integration with digital communication platforms;
[0010] Insufficient feedback mechanisms for real-time emotional awareness.
[0011] WO2023216680A1 The present invention relates to a digital biomarker and a brain health evaluation system based on same. Initial data of the digital biomarker at least come from behavior data of a user when the user uses a digital chess and card (1); the initial data can be sent to a server (2) and/or an analysis unit (103) and processed and analyzed by the server (2) and/or the analysis unit (103) to calculate the digital biomarker capable of characterizing the cognitive ability of the user. The digital biomarker obtained in the present invention can mark real-time data collected in real time when the user uses a digital prop, and the cognitive ability of the user can be evaluated by means of marking.
[0012] US8449471B2 A heart monitoring system for a patient includes one or more wireless nodes forming a wireless network; a wearable appliance having a wireless transceiver to communicate with the one or more wireless nodes; and an analyzer to determine vital signs, the analyzer coupled to the wireless transceiver to receive patient data over the wireless network.
[0013] Moreover, many current devices are primarily fitness-oriented and do not include embedded machine learning models capable of classifying complex emotional states. They also fail to contextualize emotional data in social or digital environments in a meaningful or privacy-preserving manner.
[0014] Accordingly, there exists a need for an improved wearable system that can accurately detect and classify emotional states in real time, adapt to individual physiological baselines, provide actionable feedback, and integrate emotional metadata into digital communication platforms—all while ensuring data privacy, security, and user comfort.
[0015] The present invention addresses these needs by providing a comprehensive, sensor-rich, and intelligent wearable device that enables real-time emotion classification and interaction, both for personal insight and enhanced digital communication.
[0016] OBJECTS OF THE INVENTION
[0017] The principal object of the present invention is to overcome the disadvantages of the prior art.
[0018] The primary objective of the present invention is to provide a wearable device capable of real-time detection and classification of a user’s emotional state through physiological signal monitoring and embedded machine learning.
[0019] Another objective of the present invention is to provide a multi-sensor wearable platform that non-invasively captures physiological signals such as heart rate, heart rate variability, galvanic skin response, skin temperature, and optionally blood oxygen saturation, for use in emotional state analysis.
[0020] Another objective of the present invention is to enable accurate classification of emotional states using embedded machine learning models operating locally on the device, thereby minimizing latency and preserving user privacy.
[0021] Another objective of the present invention is to implement an adaptive thresholding engine that learns and adjusts to user-specific physiological baselines, improving the accuracy and personalization of emotional state classification over time.
[0022] Another objective of the present invention is to facilitate real-time feedback to the user through visual (LED) and/or haptic alerts when stress, anxiety, or other predefined emotional thresholds are detected.
[0023] Another objective of the present invention is to enable seamless wireless communication of classified emotional data to companion mobile applications or cloud services via Bluetooth Low Energy (BLE) or Wi-Fi.
[0024] Another objective of the present invention is to provide a secure and privacy-compliant data pipeline, using end-to-end encryption and conforming to relevant data protection standards such as GDPR.
[0025] Another objective of the present invention is to offer a mobile companion application for visualization, calibration, and local inference of emotional state trends, enhancing user engagement and control.
[0026] Another objective of the present invention is to integrate classified emotional states into digital communication platforms, such as messaging and social media, through a social plugin interface implemented as an API or browser extension.
[0027] Another objective of the present invention is to provide emotion-aware enhancements to online communication by embedding emotion metadata as emoji overlays or emotion tags in digital content.
[0028] Another objective of the present invention is to deliver the functionality in a compact, wearable form factor, such as a wristband or clip-on device, designed for continuous wear, comfort, and durability in everyday environments.
[0029] Another objective of the present invention is to support applications in mental health, wellness monitoring, and human-computer interaction, by enabling context-aware, emotion-driven interactions and insights.
SUMMARY
[0030] The present invention relates to a wearable device designed to detect and classify a user's emotional state in real time through the integration of multiple physiological sensors, embedded machine learning, and connectivity features. The device enables seamless emotional awareness and contextual interaction within digital communication platforms.

[0031] A microcontroller unit with an embedded machine learning model processes the acquired data, applying signal preprocessing, feature extraction, and classification into predefined emotional categories. The system further includes an adaptive thresholding engine that calibrates responses based on individual physiological baselines, thereby improving classification accuracy over time.
[0032] The device features a wireless communication module (e.g., Bluetooth Low Energy or Wi-Fi) for data transmission to a mobile companion application, which provides local inference, visualization, and user-specific calibration. A status indicator (LED or haptic motor) offers real-time feedback, such as alerts for stress or anxiety.

[0033] An integrated social plugin interface enables classified emotional states to be embedded into digital communication platforms, such as messaging applications or social media, in the form of emotion tags or emoji overlays. All transmitted data is secured via end-to-end encryption, ensuring compliance with privacy regulations such as GDPR.
[0034] The present invention relates to a compact, wearable device designed to detect and classify a user's emotional state in real-time by analyzing multiple physiological signals such as heart rate, oxygen saturation levels, galvanic skin response (GSR), and skin temperature. The device employs machine learning algorithms trained on multimodal bio-signal data to recognize and interpret emotional states accurately. It integrates with digital communication platforms, allowing emotional feedback to be visually or textually embedded into messaging environments. A key feature of the invention is its ability to tag emotional context in social media posts through a dedicated plugin, thereby enhancing the emotional transparency of online content. This system enables more authentic and empathetic digital interactions by bridging the gap between a user's internal emotional state and their digital expressions.

[0035] The invention also includes a method for emotional state detection comprising signal acquisition, preprocessing, baseline calibration, classification via machine learning, and transmission of emotional metadata. The wearable is implemented in a compact, water-resistant form factor (e.g., wristband or clip-on), suitable for continuous use in daily environments.

[0036] This invention provides a novel, real-time solution for emotion-aware personal feedback and communication, bridging physiological sensing with intelligent digital interaction.

[0037] These and other features will become apparent from the following detailed description of illustrative embodiments thereof, which is to be read in connection with the accompanying drawings. While the invention has been described and shown with reference to the preferred embodiment, it will be apparent that variations might be possible that would fall within the scope of the present invention.

BRIEF DESCRIPTION OF DRAWINGS
[0038] The accompanying illustrations are incorporated into and form a part of this specification in order to aid in comprehending the current disclosure. The pictures demonstrate exemplary implementations of the current disclosure and, along with the description, assist to clarify its fundamental ideas.
[0039] Fig.1 shows the flow chart of process of the invention.
[0040] Fig 2 shows the System Architecture Diagram.
[0041] Fig 3 shows the Detail Process diagram.
[0042] Fig 4 shows the Signal Flow Diagram.
[0043] Fig 5 shows the Wearable Device Hardware Layout Diagram.
[0044] Fig 6 shows the Working Model with MAX30100 Sensor.
[0045] Fig 7 shows the Hardware Layout with MAX30100 Sensor.
[0046] Fig 8 shows the Proposed device.
[0047] It should be noted that the figures are not drawn to scale, and the elements of similar structure and functions are generally represented by like reference numerals for illustrative purposes throughout the figures. It should be noted that the figures do not illustrate every aspect of the described embodiment sand do not limit the scope of the present disclosure.
[0048] Other objects, advantages, and novel features of the invention will become apparent from the following detailed description of the present embodiment when taken in conjunction with the accompanying drawings.
DETAILED DESCRIPTION OF THE INVENTION
[0049] While the present invention is described herein by way of example using embodiments and illustrative drawings, those skilled in the art will recognize that the invention is not limited to the embodiments of drawing or drawings described and are not intended to represent the scale of the various components. Further, some components that may form a part of the invention may not be illustrated in certain figures, for ease of illustration, and such omissions do not limit the embodiments outlined in any way. It should be understood that the drawings and the detailed description thereto are not intended to limit the invention to the particular form disclosed, but on the contrary, the invention is to cover all modifications, equivalents, and alternatives falling within the scope of the present invention as defined by the appended claim.
[0050] As used throughout this description, the word "may" is used in a permissive sense (i.e. meaning having the potential to), rather than the mandatory sense, (i.e. meaning must). Further, the words "a" or "an" mean "at least one” and the word “plurality” means “one or more” unless otherwise mentioned. Furthermore, the terminology and phraseology used herein are solely used for descriptive purposes and should not be construed as limiting in scope. Language such as "including," "comprising," "having," "containing," or "involving," and variations thereof, is intended to be broad and encompass the subject matter listed thereafter, equivalents, and additional subject matter not recited, and is not intended to exclude other additives, components, integers, or steps. Likewise, the term "comprising" is considered synonymous with the terms "including" or "containing" for applicable legal purposes. Any discussion of documents acts, materials, devices, articles, and the like are included in the specification solely for the purpose of providing a context for the present invention. It is not suggested or represented that any or all these matters form part of the prior art base or were common general knowledge in the field relevant to the present invention.
[0051] In this disclosure, whenever a composition or an element or a group of elements is preceded with the transitional phrase “comprising”, it is understood that we also contemplate the same composition, element, or group of elements with transitional phrases “consisting of”, “consisting”, “selected from the group of consisting of, “including”, or “is” preceding the recitation of the composition, element or group of elements and vice versa.
[0052] The present invention is described hereinafter by various embodiments with reference to the accompanying drawing, wherein reference numerals used in the accompanying drawing correspond to the like elements throughout the description. This invention may, however, be embodied in many different forms and should not be construed as limited to the embodiment set forth herein. Rather, the embodiment is provided so that this disclosure will be thorough and complete and will fully convey the scope of the invention to those skilled in the art. In the following detailed description, numeric values and ranges are provided for various aspects of the implementations described. These values and ranges are to be treated as examples only and are not intended to limit the scope of the claims. In addition, several materials are identified as suitable for various facets of the implementations.
[0053] The present invention relates to a wearable device capable of detecting, classifying, and communicating a user’s emotional state in real time. The device is designed for continuous physiological monitoring, advanced on-device processing, and seamless integration with digital communication platforms.
[0054] In an embodiment of the present invention a wearable device (100) for detecting and classifying a user’s emotional state in real time, comprising: a sensor block (110) including a photoplethysmography (PPG) sensor (111) for heart rate and heart rate variability detection, a galvanic skin response (GSR) sensor (112), a skin temperature sensor (113), and optionally a SpO₂ sensor (114); a microcontroller unit (120) configured with embedded machine learning processing to receive, preprocess, and classify bio-signal data into predefined emotional states; a wireless communication module (130) configured for data transfer via at least one of Bluetooth Low Energy (BLE) or Wi-Fi; a rechargeable battery (140) powering the device; a status indicator (150) comprising at least one of an LED or haptic feedback motor; and a social plugin interface module (160) configured to embed classified emotional metadata into digital communication platforms.
[0055] In an embodiment of the present invention the method (200) for detecting and classifying emotional states using a wearable device comprising: capturing physiological signals using the PPG sensor (111), GSR sensor (112), and skin temperature sensor (113); preprocessing the captured signals to remove noise and extract features; calibrating signals against a user baseline using an adaptive thresholding engine (121); classifying the emotional state into one of a plurality of categories using a trained machine learning model; and transmitting the classified emotional state as metadata to a digital communication platform.
[0056] In an aspect of the present invention offers a comprehensive, real-time solution to the emotional disconnect in digital communication by combining wearable physiological sensing, machine learning, and social media integration. Here's how it works:
[0057] Wearable Device: A compact wearable equipped with biosensors — including heart rate (PPG), oxygen saturation, galvanic skin response (GSR), and skin temperature sensors — is worn by the user. These sensors continuously monitor physiological changes that correlate with emotional arousal.
[0058] Real-Time Data Processing: The physiological signals are pre-processed and transmitted to a real-time database hosted at cloud solutions via Bluetooth or Wi-Fi.
[0059] Machine Learning Model: The system utilizes a trained ML model to classify the emotional state based on signal patterns. A novel adaptive thresholding algorithm fine-tunes the detection by learning the user's personal physiological baseline, ensuring greater accuracy over time. The output of this trained model is the prediction of one’s psychological state in terms of labels like “Happy”, “Sad”, “Angry”, “Frustrated”, “Tired” etc.
[0060] Emotion Integration into Digital Platforms: In chat/messaging apps, the predicted emotion by the machine learning model is represented via emoji overlays. In social media apps, the Social Post Context Plugin allows emotional tagging of posts based on the user’s real-time emotion.
[0061] In an aspect of the present invention the diagram represents the data flow and system architecture of the wearable emotion detection device, illustrating how physiological information is captured, processed, classified, and interfaced with external digital platforms for real-time emotional state communication.
[0062] Sensors (PPG, GSR, Temp): These include the photoplethysmography (PPG) sensor (111) for cardiac metrics, galvanic skin response (GSR) sensor (112) for electrodermal activity, and skin temperature sensor (113) for monitoring thermoregulatory status. Each sensor is strategically placed to optimize signal fidelity and user comfort by continuously extracting physiological parameters indicative of affective state.
[0063] The microcontroller unit is embedded with real-time signal processing and machine learning capabilities. It performs the following functions:
[0064] Signal acquisition and preprocessing: Raw data from the sensors are filtered and denoised using standard preprocessing techniques (e.g., moving average filters, band-pass filters).
[0065] Feature extraction: Time-domain and frequency-domain features are extracted from each biosignal, including HRV metrics (e.g., RMSSD, LF/HF ratio), GSR peak frequency, and temperature trends.
[0066] Baseline calibration: An adaptive thresholding engine is configured to establish and continuously update a user-specific physiological baseline. This allows the system to dynamically adjust sensitivity and improve classification accuracy across varying individuals and conditions.
[0067] Emotion classification: Extracted features are input into a pre-trained machine learning model (e.g., a decision tree, SVM, or neural network) stored locally on the microcontroller. The model classifies the emotional state into predefined categories such as calm, happy, stressed, anxious, sad, or excited.
[0068] The wireless communication module provides secure, low-latency data transmission to external devices and platforms via: i) Bluetooth Low Energy (BLE) or ii) Wi-Fi (depending on configuration).
[0069] The device includes a status indicator comprising one or more of: An LED to display device status or emotional state colors (e.g., green for calm, red for stressed); A haptic feedback motor that delivers discreet vibration alerts when certain emotional thresholds are exceeded—such as high stress or anxiety levels.
[0070] The invention features a social plugin interface module, which allows classified emotional states to be embedded into digital communication platforms. This module may be implemented as: A browser extension or an API for integration into messaging and social media platforms.
[0071] In an embodiment of the present invention the method for detecting and classifying emotional states comprises the following steps: i) Signal acquisition: Physiological data is continuously collected using the PPG sensor, GSR sensor, and skin temperature sensor; ii) Preprocessing: Signals are filtered and normalized to reduce noise and artifacts; iii) Adaptive calibration: Captured data is compared against a dynamically updated baseline via the adaptive thresholding engine; iv) Emotion classification: Using a trained machine learning model embedded in the microcontroller, the emotional state is classified into one of several predefined categories; v) Metadata generation and communication: The classified emotion is transmitted as metadata to digital communication platforms using the wireless module. This metadata may be visualized as emoji overlays or emotion tags, enhancing the context of social interactions; vi) Real-time alerting: If emotional states like stress or anxiety exceed predefined thresholds, the status indicator activates to notify the user via visual or haptic signals.
[0072] Data Privacy and Compliance: To ensure user trust and regulatory compliance, all data transmitted from the device is encrypted using end-to-end encryption. Additionally, the system is designed to adhere to privacy standards such as the General Data Protection Regulation (GDPR) and medical device data security protocols.
[0073] The wearable device is housed in a compact and ergonomic enclosure, which may be implemented as: a wristband form suitable for continuous wear, a clip-on module for attachment to clothing.
[0074] The proposed invention introduces several unique and novel features that distinguish it from existing technologies in emotion recognition, wearable health monitoring, and digital communication enhancement.
[0075] Real-Time Emotion Detection Using Multimodal Physiological Signals: Utilizes a combination of heart rate, oxygen saturation, galvanic skin response (GSR), and skin temperature to detect emotional states; These signals are processed continuously in real-time through a compact wearable, enabling moment-to-moment emotional monitoring.
[0076] Adaptive Thresholding for Personalized Emotion Classification: A novel machine learning model dynamically adjusts emotion detection thresholds based on the user's unique physiological baseline; This ensures personalized, context-aware emotional feedback—unlike existing systems that use static thresholds or generic training data.
[0077] Social Post Context Plugin for Emotion Tagging: A dedicated software plugin allows users to embed real-time emotional states into social media posts, enabling emotional transparency in digital self-expression; This feature provides emotion-based prompts, mood tagging, or suggestions to revise emotionally intense content, improving digital empathy.
[0078] Emotion-Adaptive Digital Interfaces: Emotion classification output is visually represented in messaging or chat apps using dynamic elements such as: i) Adaptive keyboard colors or emojis. ii) Emotion-linked auto-suggestions. iii) Real-time emotional status indicators.
[0079] Privacy-Preserving Architecture: The system prioritizes on-device or edge inference, minimizing data transfer to protect sensitive physiological and emotional data; Emotion sharing is user-controlled and consent-based, addressing privacy concerns associated with emotion detection technologies
[0080] Integration of Wearable Technology with Communication Platforms: Unlike fitness trackers or emotion-recognition tools, this device is explicitly designed for enhancing the emotional richness of digital communication, making it uniquely application-focused.
[0081] Further, the operations need not be performed in the disclosed order, although in some examples, an order may be preferred. Also, not all functions need to be performed to achieve the desired advantages of the disclosed system and method, and therefore not all functions are required.
[0082] Various modifications to these embodiments are apparent to those skilled in the art from the description and the accompanying drawings. The principles associated with the various embodiments described herein may be applied to other embodiments. Therefore, the description is not intended to be limited to the embodiments shown along with the accompanying drawings but is to be providing the broadest scope consistent with the principles and the novel and inventive features disclosed or suggested herein. Accordingly, the invention is anticipated to hold on to all other such alternatives, modifications, and variations that fall within the scope of the present invention and appended claims.
, Claims:I/We Claim:
1. A wearable device (100) for detecting and classifying a user’s emotional state in real time, comprising:
i) a sensor block (110) including a photoplethysmography (PPG) sensor (111) for heart rate and heart rate variability detection, a galvanic skin response (GSR) sensor (112), a skin temperature sensor (113), and optionally a SpO₂ sensor (114);
ii) a microcontroller unit (120) configured with embedded machine learning processing to receive, preprocess, and classify bio-signal data into predefined emotional states;
iii) a wireless communication module (130) configured for data transfer via at least one of Bluetooth Low Energy (BLE) or Wi-Fi;
iv) a rechargeable battery (140) powering the device;
v) a status indicator (150) comprising at least one of an LED or haptic feedback motor; and
vi) a social plugin interface module (160) configured to embed classified emotional metadata into digital communication platforms.
2. The wearable device as claimed in claim 1, wherein the microcontroller unit (120) comprises an adaptive thresholding engine (121) configured to learn a user-specific physiological baseline to improve classification accuracy.
3. The wearable device as claimed in claim 1, wherein the wireless communication module (130) is configured to connect with a mobile companion application (170) for local inference, visualization of emotional states, and user-specific calibration.
4. The wearable device as claimed in claim 1, wherein the social plugin interface module (160) is implemented as an API or browser extension (161) configured to integrate emotion tags into social media posts and messaging applications.
5. The wearable device as claimed in claim 1, wherein the status indicator (150) provides stress or anxiety alerts through vibration feedback when classified emotional states exceed a threshold.
6. The method (200) for detecting and classifying emotional states using a wearable device as claimed in claim 1, comprising:
i) capturing physiological signals using the PPG sensor (111), GSR sensor (112), and skin temperature sensor (113);
ii) preprocessing the captured signals to remove noise and extract features;
iii) calibrating signals against a user baseline using an adaptive thresholding engine (121);
iv) classifying the emotional state into one of a plurality of categories using a trained machine learning model; and
v) transmitting the classified emotional state as metadata to a digital communication platform.
7. The method as claimed in claim 5, wherein the classified emotional state is represented as an emoji overlay (210) in messaging applications or as an emotion tag (220) in social media posts.
8. The method as claimed in claim 5, wherein the wearable device provides real-time stress or anxiety alerts via the status indicator (150).
9. The wearable device as claimed in claim 5, wherein the data transmission from the wireless module (130) to external platforms is secured using end-to-end encryption (180) and complies with GDPR or medical device data privacy standards.
10. The wearable device of claim 1, wherein the form factor (190) is a wristband or clip-on housing configured to be lightweight, water-resistant, and sweat-resistant.