1. A system (100) for real-time cognitive state classification during yoga practice, the system (100) comprising: a multi-channel electroencephalography headset (102) wearably positioned on the head of a user, configured to acquire brain activity signals of the user during yoga practice; an inertial measurement unit sensor (104) attached to at least one body segment of the user including the torso, waist, wrist, or ankle, configured to capture body posture, motion, and orientation associated with yoga postures; a respiration monitoring sensor (106) positioned around the chest or abdominal region of the user configured to monitor breathing patterns of the user; a communication network (108) connected to electroencephalography headset (102), the IMU sensor, and the respiration monitoring sensor, the communication network (108) being configured to transmit data between the several components of the system (100); a processing unit (110) operationally coupled the electroencephalography headset (102), the inertial measurement unit sensor (104), and the respiration monitoring sensor through the communication network (108), the processing unit (110) configured to process physiological data in real time, the processing unit (110) comprises: an input module (112) configured to receive physiological signals including electroencephalography signals, motion data, and respiration signals from electroencephalography headset (102), the inertial measurement unit sensor (104), and the respiration monitoring sensor (106); a signal processing module (114) configured to preprocess the acquired electroencephalography signals using band-pass filtering, independent component analysis, and motion artifact removal using inertial measurement unit (104) data; a feature extraction module (116) configured to derive neural features including spectral band power in delta, theta, alpha, beta, and gamma frequency bands, and nonlinear features including entropy and fractal dimension; a machine learning classification module (118) employing deep learning architectures including convolutional neural networks (CNN), long short-term memory (LSTM) networks, or hybrid models for classification of cognitive states; an integration module (120) configured to synchronize electroencephalography headset (102) signals with posture data from the inertial measurement unit sensor (104) and respiration data to generate a temporally aligned cognitive-state representation; an output module (122) configured to present the classified cognitive state and provide adaptive neurofeedback to the user through visual, auditory, or haptic feedback interfaces; and an user interface (124) linked with the output module (122) to provide real-time neurofeedback to guide the user toward an optimal cognitive state during yoga practice.

2. The system (100) as claimed in claim 1, the system (100) is connected to a cloud database (126) to store and retrieve physiological signal data and cognitive state analysis results for remote monitoring, data analytics, and model improvement.

3. The system (100) as claimed in claim 1, wherein the inertial measurement unit sensor (104) comprises accelerometer, gyroscope, and magnetometer sensors configured to detect yoga posture, orientation, and motion dynamics.

4. The system (100) as claimed in claim 1, wherein the respiration monitoring sensor (106) measures breathing rate and breathing variability associated with yogic breathing techniques.

5. The system (100) as claimed in claim 1, wherein the signal processing module (114) utilizes inertial measurement unit sensor (104) derived motion information to identify and eliminate motion artifacts from electroencephalography signals during dynamic yoga movements.

6. The system (100) as claimed in claim 1, wherein the feature extraction module (116) is configured to compute spectral power of electroencephalography (EEG) signals across predefined frequency bands, including delta (0.5–4 Hz), theta (4–8 Hz), alpha (8–13 Hz), beta (13–30 Hz), and gamma frequencies above 30 Hz, for analysis of neural activity associated with different cognitive states.

7. The system (100) as claimed in claim 1, wherein the machine learning classification module (118) utilizes a pose-aware deep learning architecture combining convolutional neural networks (CNN) for spatial feature extraction and long short-term memory (LSTM) networks for temporal pattern recognition.

8. The system (100) as claimed in claim 1, wherein the integration module (120) synchronizes electroencephalography, posture data from the inertial measurement unit sensor (104), and respiration signals to generate a temporal cognitive-state profile during yoga practice.

9. The system (100) as claimed in claim 1, wherein a feedback module (128) is configured to provide real-time feedback to the user through visual displays, auditory signals, or haptic stimulation to guide the user toward an optimal cognitive state.

10. A method (200) for real-time cognitive state mapping during yoga practice, the method (200) comprising: acquiring physiological data from a user through an electroencephalography headset (102), an inertial measurement unit sensor (104), and a respiration monitoring sensor (106); transmitting the acquired physiological data through a communication network (108) to an input module (112) for real-time analysis; preprocessing the electroencephalography headset (102) signals using a signal processing module (114) by applying band-pass filtering, independent component analysis (ICA), and motion artifact removal based on inertial measurement unit (104) motion data; extracting neural features from the pre-processed electroencephalography headset (102) signals using a feature extraction module (116), the neural features comprising spectral band power in delta, theta, alpha, beta, and gamma frequency bands and nonlinear features including entropy and fractal dimension; classifying cognitive states of the user using a machine learning classification module (118) employing deep learning architectures including convolutional neural networks, long short-term memory networks, or hybrid models; synchronizing multi-modal physiological data using an integration module (120) by aligning electroencephalography signals with posture data obtained from the inertial measurement unit sensor (104) and respiration data to generate a temporally aligned cognitive-state representation; generating cognitive state outputs corresponding to mental states including focused attention, relaxation, mind wandering, or stress; and providing adaptive neurofeedback to the user through a user interface (124) via visual, auditory, or haptic feedback based on the classified cognitive state to assist the user in achieving an optimal mental state during yoga practice.

Description:FIELD OF DISCLOSURE
[0001] The present disclosure generally relates to neurotechnology and wearable sensing systems, more specifically, relates to a system for real-time cognitive state classification during yoga practice using electroencephalography signal processing, inertial measurement unit-based motion sensing, respiration monitoring, and machine learning models to provide adaptive neurofeedback for improved mindfulness and mental well-being during yoga practice.
BACKGROUND OF THE DISCLOSURE
[0002] Mind–body practices such as yoga and meditation are widely used for improving mental well-being, stress management, and cognitive performance. In recent years, there has been increasing interest in using physiological sensing technologies to objectively monitor mental states during such practices. Among these technologies, electroencephalography (EEG) has been widely adopted for detecting brainwave patterns associated with cognitive states such as attention, relaxation, and stress.
[0003] Several prior inventions and research efforts have proposed systems for monitoring brain activity and providing neurofeedback. These systems demonstrate the feasibility of EEG-based neurofeedback and cognitive state monitoring, they are primarily designed for stationary activities such as seated meditation or clinical neurofeedback training. These prior approaches generally do not consider the challenges associated with dynamic body movements that occur during yoga practice, where postures (asanas) and transitions between poses introduce significant motion artifacts in EEG signals.
[0004] A number of commercial products are currently available that attempt to provide brain monitoring and meditation assistance. Examples include the Muse 2 Headband, Muse S headband, Emotiv Insight 2 headset, BrainBit EEG headband, NeuroSky MindWave, and research platforms such as OpenBCI. These devices are capable of capturing EEG signals and providing limited forms of neurofeedback. Some products also include additional sensors for breathing or motion detection. However, most of these systems are designed primarily for meditation, relaxation training, or simple attention monitoring, rather than for full-body practices such as yoga.
[0005] Existing solutions suffer from several limitations such as most EEG-based meditation devices assume minimal user movement, making them susceptible to motion artifacts when used during dynamic yoga postures. Second, current systems typically analyze brain activity independently, without proper synchronization with body posture or breathing patterns, both of which are essential elements of yoga practice. Third, available systems often provide generic feedback that is not tailored to individual users or specific yoga poses, thereby limiting their effectiveness in accurately identifying cognitive states. In addition, many high-fidelity EEG systems used for research or clinical applications are expensive, bulky, or not suitable for everyday use by yoga practitioners.
[0006] The present invention overcomes the limitations of the prior art by providing a system for real-time cognitive state classification during yoga practice capable of accurately monitoring and mapping cognitive states during dynamic yoga practice by integrating brain activity, body posture, and breathing information. The system should be capable of reducing motion artifacts, synchronizing multi-modal physiological signals, and providing adaptive real-time neurofeedback to help practitioners achieve improved focus, relaxation, and mindfulness.
[0007] Thus, in light of the above-stated discussion, there exists a need for a system for real-time cognitive state classification during yoga practice.
SUMMARY OF THE DISCLOSURE
[0008] The following is a summary description of illustrative embodiments of the invention. It is provided as a preface to assist those skilled in the art to more rapidly assimilate the detailed design discussion which ensues and is not intended in any way to limit the scope of the claims which are appended hereto in order to particularly point out the invention.
[0009] According to illustrative embodiments, the present disclosure focuses on a system for real-time cognitive state classification during yoga practice which overcomes the above-mentioned disadvantages or provides the users with a useful or commercial choice.
[0010] An objective of the present disclosure is to provide a real-time cognitive state mapping system for yoga practice using multi-sensor physiological monitoring and machine learning techniques.
[0011] Another objective of the present disclosure is to simultaneously acquire brain activity, body movement, and respiration data for mapping the cognitive state in real-time.
[0012] Another objective of the present disclosure is to improve the quality of EEG signals during yoga movements by removing motion-related disturbances.
[0013] Another objective of the present disclosure is to analyze brainwave patterns by extracting important EEG features such as delta, theta, alpha, beta, and gamma frequency bands, along with advanced features like entropy and fractal dimension.
[0014] Another objective of the present disclosure is to automatically classify cognitive states like focus, relaxation, stress, and mind wandering for for enabling real-time assessment of the user’s mental condition and providing personalized feedback to improve concentration, mindfulness, and overall mental well-being during yoga practice.
[0015] Another objective of the present disclosure is to provide real-time feedback to the user through visual displays, audio signals, or haptic vibrations to help the user improve concentration, relaxation, and mindfulness.
[0016] Yet another objective of the present disclosure is to synchronize brain signals with body posture and breathing patterns to better understand the relationship between the mind and body during different yoga poses.
[0017] In light of the above, in one aspect of the present disclosure, a system for real-time cognitive state classification during yoga practice is disclosed herein. The system comprises a multi-channel electroencephalography headset wearably positioned on the head of a user, configured to acquire brain activity signals of the user during yoga practice, an inertial measurement unit sensor attached to at least one body segment of the user including the torso, waist, wrist, or ankle, configured to capture body posture, motion, and orientation associated with yoga postures, and a respiration monitoring sensor positioned around the chest or abdominal region of the user configured to monitor breathing patterns of the user. The system includes a communication network connected to EEG headset, the IMU sensor, and the respiration monitoring sensor, the communication network being configured to transmit data between the several components of the system. The system also includes a processing unit operationally coupled the EEG headset, the IMU sensor, and the respiration monitoring sensor through the communication network, the processing unit configured to process physiological data in real time. The processing unit also includes an input module configured to receive physiological signals including electroencephalography signals, motion data, and respiration signals from electroencephalography headset, the inertial measurement unit sensor, and the respiration monitoring sensor, a signal processing module configured to pre-process the acquired electroencephalography signals using band-pass filtering, independent component analysis, and motion artifact removal using inertial measurement unit data, a feature extraction module configured to derive neural features including spectral band power in delta, theta, alpha, beta, and gamma frequency bands, and nonlinear features including entropy and fractal dimension, a machine learning classification module () employing deep learning architectures including convolutional neural networks (CNN), long short-term memory (LSTM) networks, or hybrid models for classification of cognitive states, an integration module configured to synchronize electroencephalography headset signals with posture data from the inertial measurement unit sensor and respiration data to generate a temporally aligned cognitive-state representation, an output module configured to present the classified cognitive state and provide adaptive neurofeedback to the user through visual, auditory, or haptic feedback interfaces, and an user interface linked with the output module to provide real-time neurofeedback to guide the user toward an optimal cognitive state during yoga practice.
[0018] In one embodiment, the system is connected to a cloud database to store and retrieve physiological signal data and cognitive state analysis results for remote monitoring, data analytics, and model improvement.
[0019] In one embodiment, the inertial measurement unit sensor comprises accelerometer, gyroscope, and magnetometer sensors configured to detect yoga posture, orientation, and motion dynamics.
[0020] In one embodiment, the respiration monitoring sensor measures breathing rate and breathing variability associated with yogic breathing techniques.
[0021] In one embodiment, the signal processing module utilizes inertial measurement unit sensor-derived motion information to identify and eliminate motion artifacts from electroencephalography signals during dynamic yoga movements.
[0022] In one embodiment, the feature extraction module is configured to compute spectral power of electroencephalography (EEG) signals across predefined frequency bands, including delta (0.5–4 Hz), theta (4–8 Hz), alpha (8–13 Hz), beta (13–30 Hz), and gamma frequencies above 30 Hz, for analysis of neural activity associated with different cognitive states.
[0023] In one embodiment, the machine learning classification module utilizes a pose-aware deep learning architecture combining convolutional neural networks (CNN) for spatial feature extraction and long short-term memory (LSTM) networks for temporal pattern recognition.
[0024] In one embodiment, the integration module synchronizes electroencephalography, posture data from the inertial measurement unit sensor, and respiration signals to generate a temporal cognitive-state profile during yoga practice.
[0025] In one embodiment, a feedback module is configured to provide real-time feedback to the user through visual displays, auditory signals, or haptic stimulation to guide the user toward an optimal cognitive state.
[0026] In light of the above, in one aspect of the present disclosure, a method for real-time cognitive state mapping during yoga practice is disclosed herein. The method includes acquiring physiological data from a user through an electroencephalography headset, an inertial measurement unit sensor, and a respiration monitoring sensor. The method also includes transmitting the acquired physiological data through a communication network to an input module for real-time analysis. The method also includes pre-processing the electroencephalography headset signals using a signal processing module by applying band-pass filtering, independent component analysis (ICA), and motion artifact removal based on inertial measurement unit motion data. The method also includes extracting neural features from the pre-processed EEG signals using a feature extraction module, the neural features comprising spectral band power in delta, theta, alpha, beta, and gamma frequency bands and nonlinear features including entropy and fractal dimension. The method also includes classifying cognitive states of the user using a machine learning classification module employing deep learning architectures including convolutional neural networks (CNN), long short-term memory (LSTM) networks, or hybrid models. The method also includes synchronizing multi-modal physiological data using an integration module by aligning electroencephalography signals with posture data obtained from the inertial measurement unit sensor and respiration data to generate a temporally aligned cognitive-state representation. The method also includes generating cognitive state outputs corresponding to mental states including focused attention, relaxation, mind wandering, or stress. The method also includes providing adaptive neurofeedback to the user through a user interface via visual, auditory, or haptic feedback based on the classified cognitive state to assist the user in achieving an optimal mental state during yoga practice.
[0027] These and other advantages will be apparent from the present application of the embodiments described herein.
[0028] The preceding is a simplified summary to provide an understanding of some embodiments of the present invention. This summary is neither an extensive nor exhaustive overview of the present invention and its various embodiments. The summary presents selected concepts of the embodiments of the present invention in a simplified form as an introduction to the more detailed description presented below. As will be appreciated, other embodiments of the present invention are possible utilizing, alone or in combination, one or more of the features set forth above or described in detail below.
[0029] These elements, together with the other aspects of the present disclosure and various features are pointed out with particularity in the claims annexed hereto and form a part of the present disclosure. For a better understanding of the present disclosure, its operating advantages, and the specified object attained by its uses, reference should be made to the accompanying drawings and descriptive matter in which there are illustrated exemplary embodiments of the present disclosure.
BRIEF DESCRIPTION OF THE DRAWINGS
[0030] To describe the technical solutions in the embodiments of the present disclosure or in the prior art more clearly, the following briefly describes the accompanying drawings required for describing the embodiments or the prior art. Apparently, the accompanying drawings in the following description merely show some embodiments of the present disclosure, and a person of ordinary skill in the art can derive other implementations from these accompanying drawings without creative efforts. All of the embodiments or the implementations shall fall within the protection scope of the present disclosure.
[0031] The advantages and features of the present disclosure will become better understood with reference to the following detailed description taken in conjunction with the accompanying drawing, in which:
[0032] FIG. 1 illustrates a block diagram of a system for real-time cognitive state classification during yoga practice, in accordance with an exemplary embodiment of the present disclosure; and
[0033] FIG. 2 illustrates a method for real-time cognitive state mapping during yoga practice, in accordance with an exemplary embodiment of the present disclosure.
[0034] Like reference, numerals refer to like parts throughout the description of several views of the drawing.
[0035] The system for real-time cognitive state classification during yoga practice is illustrated in the accompanying drawings, which like reference letters indicate corresponding parts in the various figures. It should be noted that the accompanying figure is intended to present illustrations of exemplary embodiments of the present disclosure. This figure is not intended to limit the scope of the present disclosure. It should also be noted that the accompanying figure is not necessarily drawn to scale.
DETAILED DESCRIPTION OF THE DISCLOSURE
[0036] The following is a detailed description of embodiments of the disclosure depicted in the accompanying drawings. The embodiments are in such detail as to communicate the disclosure. However, the amount of detail offered 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 spirit and scope of the present disclosure.
[0037] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. It may be apparent to one skilled in the art that embodiments of the present disclosure may be practiced without some of these specific details.
[0038] Various terms as used herein are shown below. To the extent a term is used, it should be given the broadest definition persons in the pertinent art have given that term as reflected in printed publications and issued patents at the time of filing.
[0039] The terms “a” and “an” herein do not denote a limitation of quantity, but rather denote the presence of at least one of the referenced items.
[0040] The terms “having”, “comprising”, “including”, and variations thereof signify the presence of a component.
[0041] Referring now to FIG. 1 and FIG. 2 to describe various exemplary embodiments of the present disclosure. FIG. 1 illustrates a block diagram of a performance measuring system 100, in accordance with an exemplary embodiment of the present disclosure.
[0042] The system 100 includes a multi-channel electroencephalography headset 102 wearably positioned on the head of a user. The headset 102 is configured to acquire brain activity signals of the user during yoga practice.
[0043] In one embodiment of the present invention, the headset 102 has multiple electrodes positioned at different locations on the scalp. These electrodes detect very small electrical signals produced by neurons in the brain when they communicate with each other. The headset 102 may also include signal acquisition circuitry, such as amplifiers and analog-to-digital converters that amplify and digitize the brain signals before transmitting for processing.
[0044] An inertial measurement unit sensor 104 is attached to at least one body segment of the user including the torso, waist, wrist, or ankle, configured to capture body posture, motion, and orientation associated with yoga postures.
[0045] In one embodiment of the present invention, the inertial measurement unit (IMU) sensor 104 comprises accelerometer, gyroscope, and magnetometer sensors configured to detect yoga posture, orientation, and motion dynamics. The accelerometer measures linear acceleration and movement of the body, enabling the system 100 to detect changes in speed or direction and determine whether the user is moving, bending, or remaining still during a yoga posture. The gyroscope measures angular velocity, which indicates the rotational movement of a body segment, thereby helping determine how the body or limb rotates or tilts while performing different yoga poses. The magnetometer measures the Earth’s magnetic field and assists in determining the absolute orientation or directional heading of the body, similar to the function of a digital compass. By combining the data obtained from the accelerometer, gyroscope, and magnetometer, the IMU sensor 104 accurately determines the user’s posture, body orientation, and motion dynamics during yoga practice, allowing the system 100 to analyze yoga poses, detect posture correctness, and track movement transitions between poses.
[0046] A respiration monitoring sensor 106 is positioned around the chest or abdominal region of the user configured to monitor breathing patterns of the user. The respiration monitoring sensor 106 continuously monitors the breathing patterns of the user, which include how frequently the user breathes and how the breathing rhythm changes during yoga practice. Monitoring respiration is particularly important in yoga because many yoga practices involve controlled breathing techniques that influence relaxation, concentration, and physiological balance.
[0047] In one embodiment of the present invention, the respiration monitoring sensor 106 measures breathing rate and breathing variability associated with yogic breathing techniques. The respiration monitoring sensor 106 measures the breathing rate, which refers to the number of breaths taken per minute and breathing variability, which refers to the variation or rhythm in the breathing cycle, including the duration and consistency of inhalation and exhalation phases. These measurements are useful for analyzing yogic breathing techniques, where practitioners intentionally regulate their breath to achieve relaxation, improved focus, and better control of the mind and body.
[0048] A processing unit 110 is operationally coupled the EEG headset 102, the IMU sensor 104, and the respiration monitoring sensor 106 through the communication network 108, the processing unit 110 configured to process physiological data in real time
[0049] In an exemplary embodiment, the processing unit 110 may be a microcontroller configured to execute program instructions stored in memory, process the physiological data received from the EEG headset 102, the IMU sensor 104, and the respiration monitoring sensor 106, perform signal conditioning and feature extraction, and generate processed outputs indicative of the user's physiological state in real time.
[0050] In an exemplary embodiment, the processing unit 110 may be a microprocessor configured to execute program instructions stored in memory, process the physiological data received from the EEG headset 102, the IMU sensor 104, and the respiration monitoring sensor 106, perform signal conditioning and feature extraction, and generate processed outputs indicative of the user's physiological state in real time.
[0051] In an exemplary embodiment, the processing unit 110 may be a central processing unit (CPU) configured to execute program instructions stored in memory, process the physiological data received from the EEG headset 102, the IMU sensor 104, and the respiration monitoring sensor 106, perform signal conditioning and feature extraction, and generate processed outputs indicative of the user's physiological state in real time.
[0052] A communication network 108 is provided connected to EEG headset 102, the IMU sensor 104, and the respiration monitoring sensor 106, the communication network 108 being configured to transmit data between the several components of the system 100
[0053] In one embodiment of the present invention, the communication network 108 may be both wired and wireless.
[0054] In one embodiment of the present invention, the communication network 108 may include, Wi-Fi, Bluetooth, Ethernet, cellular networks such as 2G, 3G, 4G, and 5G, Wide Area Network (WAN), Local Area Network (LAN), and Virtual Area Network (VAN), serial communication protocols, and universal serial bus (USB) interfaces for an input/output connectivity.
[0055] In one embodiment of the present invention, the communication network 108 may include an antenna supporting long-range wireless communication.
[0056] In one embodiment of the present invention, the system 100 is connected to a cloud database 126 to store and retrieve physiological signal data and cognitive state analysis results for remote monitoring, data analytics, and model improvement.
[0057] The processing unit 110 includes several modules including:
[0058] An input module 112 is configured to receive physiological signals including electroencephalography (EEG) signals, inertial measurement unit (IMU) motion data, and respiration signals from the multi-sensor physiological data acquisition unit. These diverse physiological signals are processed and analyze multiple aspects of a person’s physical and neurological state in real time.
[0059] A signal processing module 114 is configured to pre-process the acquired EEG signals using band-pass filtering, independent component analysis (ICA), and motion artifact removal using IMU data. EEG signals recorded from the scalp are often noisy and may contain unwanted interference caused by muscle activity, environmental noise, or body movements during yoga practice. Therefore, the signal processing module 114 applies several techniques to clean and refine the EEG data.
[0060] First, band-pass filtering is applied to allow only a specific range of frequencies associated with brain activity to pass through while removing very low-frequency and high-frequency noise. This helps isolate meaningful brainwave signals such as those related to attention, relaxation, or meditation. Second, the system 100 applies Independent Component Analysis (ICA), which is a computational technique used to separate mixed signals into independent components. ICA helps isolate true brain activity from other interfering signals such as eye blinks, muscle movements, or electrical noise.
[0061] In one embodiment of the present invention, the signal processing module 114 utilizes IMU-derived motion information to identify and eliminate motion artifacts from EEG signals during dynamic yoga movements. This improves the reliability of subsequent analysis related to mental state, concentration, or relaxation during yoga practice.
[0062] A feature extraction module 116 is configured to derive neural features including spectral band power in delta, theta, alpha, beta, and gamma frequency bands, and nonlinear features including entropy and fractal dimension.
[0063] In one embodiment of the present invention, the feature extraction module 116 is configured to compute spectral power of electroencephalography (EEG) signals across predefined frequency bands, including delta (0.5–4 Hz), theta (4–8 Hz), alpha (8–13 Hz), beta (13–30 Hz), and gamma frequencies above 30 Hz, for analysis of neural activity associated with different cognitive states.
[0064] A machine learning classification module 118 is employing deep learning architectures including convolutional neural networks (CNN), long short-term memory (LSTM) networks, or hybrid models for classification of cognitive states.
[0065] In one embodiment of the present invention, the machine learning classification module 118 utilizes a pose-aware deep learning architecture combining convolutional neural networks (CNN) for spatial feature extraction and long short-term memory (LSTM) networks for temporal pattern recognition.
[0066] An integration module 120 is configured to synchronize EEG signals with posture data from the IMU and respiration data to generate a temporally aligned cognitive-state representation. Each of these sensors captures different types of physiological or movement-related data. The EEG headset 102 records brain activity signals, the IMU sensor 104 captures posture, body motion, and orientation, and the respiration sensor measures breathing patterns. However, these signals may be collected at slightly different times or sampling rates. The integration module 120 therefore synchronizes these data streams in time, ensuring that the signals from all sensors correspond to the same moment during the user’s yoga practice.
[0067] In one embodiment of the present invention, the integration module 120 synchronizes EEG, posture data from the IMU, and respiration signals to generate a temporal cognitive-state profile during yoga practice. After synchronization, the integration module 120 generates a temporally aligned cognitive-state representation. The synchronized data is then used to generate a temporal cognitive-state profile. This profile represents how the user’s mental and physiological states change over time while performing yoga. For example, it may show variations in concentration, relaxation level, breathing rhythm, and body posture stability throughout the session. Such a temporal profile allows the system 100 to track the progression of the user’s cognitive and physiological responses during yoga practice, enabling more accurate analysis, feedback, or performance evaluation of the yoga session.
[0068] An output module 122 is configured to present the classified cognitive state and provide adaptive neurofeedback to the user through visual, auditory, or haptic feedback interfaces.
[0069] An user interface 124 is linked with the output module 122 to provide real-time neurofeedback to guide the user toward an optimal cognitive state during yoga practice.
[0070] In one embodiment of the present invention, a feedback module 128 is configured to provide real-time feedback to the user through visual displays, auditory signals, or haptic stimulation to guide the user toward an optimal cognitive state.
[0071] In an exemplary embodiment of the present invention, the visual feedback might involve displaying colors, graphs, or animations on a screen or wearable device to represent levels of focus or relaxation. For example, during yoga practice, the system 100 could show calming blue hues or dynamic bar graphs that rise as the user reaches a more relaxed state, providing clear and immediate visual cues without disrupting the flow.
[0072] In an exemplary embodiment of the present invention, auditory feedback uses sounds or tones to guide the user’s mental state. This could include soothing music, nature sounds, or specific audio signals like chimes or beeps whose pitch or rhythm changes in response to the user’s brain activity. Such sounds help create an immersive environment that encourages concentration and calmness, supporting the user’s mindfulness during practice.
[0073] In an exemplary embodiment of the present invention, haptic feedback delivers information through vibrations or tactile sensations via wearable devices such as wristbands or smart watches. Different vibration patterns or intensities signals the user to adjust their breathing or focus without needing to look at a screen or listen to sounds. For example, a gentle pulse might indicate an optimal cognitive state, while a stronger vibration could remind the user to refocus, providing subtle but effective guidance throughout the yoga session.
[0074] FIG. 2 illustrates a method 200 for real-time cognitive state mapping during yoga practice, in accordance with an exemplary embodiment of the present disclosure.
[0075] The method 200 may include the following steps:
[0076] At 202, acquiring physiological data from a user through an electroencephalography headset 102, an inertial measurement unit sensor 104, and a respiration monitoring sensor 106.
[0077] At 204, transmitting the acquired physiological data through a communication network 108 to an input module 112 for real-time analysis.
[0078] At 206, pre-processing the EEG signals using a signal processing module 114 by applying band-pass filtering, independent component analysis (ICA), and motion artifact removal based on IMU motion data.
[0079] At 208, extracting neural features from the pre-processed EEG signals using a feature extraction module 116, the neural features comprising spectral band power in delta, theta, alpha, beta, and gamma frequency bands and nonlinear features including entropy and fractal dimension.
[0080] At 210, classifying cognitive states of the user using a machine learning classification module 118 employing deep learning architectures including convolutional neural networks (CNN), long short-term memory (LSTM) networks, or hybrid models.
[0081] At 212, synchronizing multi-modal physiological data using an integration module 120 by aligning EEG signals with posture data obtained from the IMU and respiration data to generate a temporally aligned cognitive-state representation.
[0082] At 214, generating cognitive state outputs corresponding to mental states including focused attention, relaxation, mind wandering, or stress.
[0083] At 216, providing adaptive neurofeedback to the user through a user interface 124 via visual, auditory, or haptic feedback based on the classified cognitive state to assist the user in achieving an optimal mental state during yoga practice.
[0084] In the best mode of operation, the system 100 for real-time cognitive state classification during yoga practice includes the multi-channel electroencephalography (EEG) headset 102 positioned on head of the user to acquire brain activity signals, while the inertial measurement unit (IMU) sensor 104 is attached to at least one body segment such as the torso, waist, wrist, or ankle to capture body posture, orientation, and motion dynamics associated with yoga movements. Additionally, the respiration monitoring sensor 106 is positioned around the chest or abdominal region to measure breathing patterns, including breathing rate and breathing variability during yogic breathing techniques. During operation, the physiological signals acquired from the EEG headset 102, IMU sensor 104, and respiration monitoring sensor 106 are continuously transmitted through the communication network 108 to the processing unit 110 that includes the input module 112 for receiving the sensor data in real time. The system 100 then pre-processes the EEG signals using the signal processing module 114 that performs band-pass filtering to isolate relevant neural frequency bands, applies independent component analysis (ICA) to separate neural signals from noise components, and removes motion artifacts using motion information derived from the IMU sensor 104. This pre-processing stage improves the quality and reliability of the EEG signals during dynamic yoga movements.
[0085] Following pre-processing, the feature extraction module 116 extracts neural features from the cleaned EEG signals. These features include spectral band power across delta, theta, alpha, beta, and gamma frequency bands, as well as nonlinear characteristics such as entropy and fractal dimension that represent the complexity and variability of brain activity. The extracted features are then provided to the machine learning classification module 118 configured to determine the cognitive state of the user. The classification module 118 employs deep learning architectures such as convolutional neural networks (CNN), long short-term memory (LSTM) networks, or hybrid CNN–LSTM models to identify patterns in the neural signals corresponding to different mental states. Simultaneously, the integration module 120 synchronizes the multi-modal physiological signals by temporally aligning EEG signals with posture data obtained from the IMU sensor 104 and respiration signals from the breathing sensor. This synchronization enables the system 100 to generate the comprehensive and temporally aligned cognitive-state representation reflecting the relationship between brain activities, body posture, and breathing behaviour during yoga practice. Based on the classification results and synchronized physiological data, the system 100 generates cognitive state outputs representing mental states such as focused attention, relaxation, mind wandering, or stress. These outputs are then used to provide adaptive neurofeedback to the user through the user interface 124.
[0086] While the invention has been described in connection with what is presently considered to be the most practical and various embodiments, it will be understood that the invention is not to be limited to the disclosed embodiments, but on the contrary, is intended to cover various modifications and equivalent arrangements included within the scope of the appended claims.
[0087] A person of ordinary skill in the art may be aware that, in combination with the examples described in the embodiments disclosed in this specification, units and algorithm steps may be implemented by electronic hardware, computer software, or a combination thereof.
[0088] The foregoing descriptions of specific embodiments of the present disclosure have been presented for purposes of illustration and description. They are not intended to be exhaustive or to limit the present disclosure to the precise forms disclosed, and many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described to best explain the principles of the present disclosure and its practical application, and to thereby enable others skilled in the art to best utilize the present disclosure and various embodiments with various modifications as are suited to the particular use contemplated. It is understood that various omissions and substitutions of equivalents are contemplated as circumstances may suggest or render expedient, but such omissions and substitutions are intended to cover the application or implementation without departing from the scope of the present disclosure.
[0089] In a case that no conflict occurs, the embodiments in the present disclosure and the features in the embodiments may be mutually combined. The foregoing descriptions are merely specific implementations of the present disclosure, but are not intended to limit the protection scope of the present disclosure. Any variation or replacement readily figured out by a person skilled in the art within the technical scope disclosed in the present disclosure shall fall within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.
, Claims:I/We Claim:
1. A system (100) for real-time cognitive state classification during yoga practice, the system (100) comprising:
a multi-channel electroencephalography headset (102) wearably positioned on the head of a user, configured to acquire brain activity signals of the user during yoga practice;
an inertial measurement unit sensor (104) attached to at least one body segment of the user including the torso, waist, wrist, or ankle, configured to capture body posture, motion, and orientation associated with yoga postures;
a respiration monitoring sensor (106) positioned around the chest or abdominal region of the user configured to monitor breathing patterns of the user;
a communication network (108) connected to electroencephalography headset (102), the IMU sensor, and the respiration monitoring sensor, the communication network (108) being configured to transmit data between the several components of the system (100);
a processing unit (110) operationally coupled the electroencephalography headset (102), the inertial measurement unit sensor (104), and the respiration monitoring sensor through the communication network (108), the processing unit (110) configured to process physiological data in real time, the processing unit (110) comprises:
an input module (112) configured to receive physiological signals including electroencephalography signals, motion data, and respiration signals from electroencephalography headset (102), the inertial measurement unit sensor (104), and the respiration monitoring sensor (106);
a signal processing module (114) configured to preprocess the acquired electroencephalography signals using band-pass filtering, independent component analysis, and motion artifact removal using inertial measurement unit (104) data;
a feature extraction module (116) configured to derive neural features including spectral band power in delta, theta, alpha, beta, and gamma frequency bands, and nonlinear features including entropy and fractal dimension;
a machine learning classification module (118) employing deep learning architectures including convolutional neural networks (CNN), long short-term memory (LSTM) networks, or hybrid models for classification of cognitive states;
an integration module (120) configured to synchronize electroencephalography headset (102) signals with posture data from the inertial measurement unit sensor (104) and respiration data to generate a temporally aligned cognitive-state representation;
an output module (122) configured to present the classified cognitive state and provide adaptive neurofeedback to the user through visual, auditory, or haptic feedback interfaces; and
an user interface (124) linked with the output module (122) to provide real-time neurofeedback to guide the user toward an optimal cognitive state during yoga practice.
2. The system (100) as claimed in claim 1, the system (100) is connected to a cloud database (126) to store and retrieve physiological signal data and cognitive state analysis results for remote monitoring, data analytics, and model improvement.
3. The system (100) as claimed in claim 1, wherein the inertial measurement unit sensor (104) comprises accelerometer, gyroscope, and magnetometer sensors configured to detect yoga posture, orientation, and motion dynamics.
4. The system (100) as claimed in claim 1, wherein the respiration monitoring sensor (106) measures breathing rate and breathing variability associated with yogic breathing techniques.
5. The system (100) as claimed in claim 1, wherein the signal processing module (114) utilizes inertial measurement unit sensor (104) derived motion information to identify and eliminate motion artifacts from electroencephalography signals during dynamic yoga movements.
6. The system (100) as claimed in claim 1, wherein the feature extraction module (116) is configured to compute spectral power of electroencephalography (EEG) signals across predefined frequency bands, including delta (0.5–4 Hz), theta (4–8 Hz), alpha (8–13 Hz), beta (13–30 Hz), and gamma frequencies above 30 Hz, for analysis of neural activity associated with different cognitive states.
7. The system (100) as claimed in claim 1, wherein the machine learning classification module (118) utilizes a pose-aware deep learning architecture combining convolutional neural networks (CNN) for spatial feature extraction and long short-term memory (LSTM) networks for temporal pattern recognition.
8. The system (100) as claimed in claim 1, wherein the integration module (120) synchronizes electroencephalography, posture data from the inertial measurement unit sensor (104), and respiration signals to generate a temporal cognitive-state profile during yoga practice.
9. The system (100) as claimed in claim 1, wherein a feedback module (128) is configured to provide real-time feedback to the user through visual displays, auditory signals, or haptic stimulation to guide the user toward an optimal cognitive state.
10. A method (200) for real-time cognitive state mapping during yoga practice, the method (200) comprising:
acquiring physiological data from a user through an electroencephalography headset (102), an inertial measurement unit sensor (104), and a respiration monitoring sensor (106);
transmitting the acquired physiological data through a communication network (108) to an input module (112) for real-time analysis;
preprocessing the electroencephalography headset (102) signals using a signal processing module (114) by applying band-pass filtering, independent component analysis (ICA), and motion artifact removal based on inertial measurement unit (104) motion data;
extracting neural features from the pre-processed electroencephalography headset (102) signals using a feature extraction module (116), the neural features comprising spectral band power in delta, theta, alpha, beta, and gamma frequency bands and nonlinear features including entropy and fractal dimension;
classifying cognitive states of the user using a machine learning classification module (118) employing deep learning architectures including convolutional neural networks, long short-term memory networks, or hybrid models;
synchronizing multi-modal physiological data using an integration module (120) by aligning electroencephalography signals with posture data obtained from the inertial measurement unit sensor (104) and respiration data to generate a temporally aligned cognitive-state representation;
generating cognitive state outputs corresponding to mental states including focused attention, relaxation, mind wandering, or stress; and
providing adaptive neurofeedback to the user through a user interface (124) via visual, auditory, or haptic feedback based on the classified cognitive state to assist the user in achieving an optimal mental state during yoga practice.