Description:FIELD OF THE INVENTION
This invention relates to Probabilistic Hybrid Classification for Real-Time SSVEP-Based Hands-Free Wheelchair Control in Brain-Computer Interface Systems
BACKGROUND OF THE INVENTION
SSVEP-based Brain-Computer Interface (BCI) systems for hands-free wheelchair control struggle with accurate signal classification due to EEG noise, inter-subject variability, and overlapping frequency clusters, resulting in unreliable navigation and delayed responses.
EXISTING SOLUTIONS / PRIOR ART/RELATED APPLICATIONS & PATENTS
• Indirect Control of an Autonomous Wheelchair Using SSVEP BCI
• CN114652532B - Multifunctional Brain-Controlled Wheelchair System Based on SSVEP and Attention Detection
• CN209695601U - System Based on SSVEP Brain Control Wheelchair Indoor Controlled Training
• CN112370259A - Control System of Brain-Controlled Wheelchair Based on SSVEP
The existing models have the following limitations:
 do not effectively integrate probabilistic methods to handle uncertainties, resulting in unreliable control outputs.
 require intensive computations, making them unsuitable for real-time BCI applications like wheelchair control.
 lack robust adaptive mechanisms, leading to inconsistent performance across different users and environments.
 classifiers like SVM, LDA, and CCA struggle with noisy EEG data and overlapping frequency clusters, reducing classification accuracy.
Criteria Existing Approaches Proposed PHC
Real-Time Processing & Adaptability Often optimized for offline analysis and lacks adaptability to different users and conditions. Designed for real-time SSVEP classification with dynamic scalability to handle varying EEG patterns.
Handling Noise & Overlapping Classes Struggles with noisy EEG signals and overlapping frequency clusters, reducing accuracy. Utilizes probabilistic modeling and wavelet denoising to enhance classification in complex environments.
Performance & Feature Extraction Rely on basic feature extraction methods, leading to lower accuracy and reliability. Integrates frequency-time domain features, PCA-based dimensionality reduction, and advanced data augmentation for superior accuracy.
Classification & Decision-Making Uses single classifiers (e.g., SVM, LDA) with static decision boundaries, leading to misclassifications. Combines multiple classifiers with adaptive probabilistic decision-making for robust real-time classification.

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 proposed innovation PHC-based BCI system is designed to provide hands-free control of a motorized wheelchair for individuals with motor disabilities by accurately classifying SSVEP signals from EEG data. The proposed innovation major components and methodology is illustrated in Fig. 1.
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: SYSTEM ARCHITECTURE
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 proposed innovation PHC-based BCI system is designed to provide hands-free control of a motorized wheelchair for individuals with motor disabilities by accurately classifying SSVEP signals from EEG data. The proposed innovation major components and methodology is illustrated in Fig. 1.
EEG Signal Acquisition: The system records brain activity using a multi-channel EEG headset, which captures SSVEP signals when the user visually focuses on flickering stimuli (LEDs or monitor screens) at distinct frequencies. Each frequency corresponds to a specific wheelchair movement command (e.g., forward, left, right, stop).
Signal Preprocessing: Raw EEG signals contain artifacts such as eye blinks, muscle movements, and electrical noise. To enhance signal quality, preprocessing techniques include:
• Bandpass Filtering (e.g., 8–30 Hz): Isolates SSVEP-relevant frequencies.
• Common Average Referencing (CAR): Reduces background noise and improves signal clarity.
• Independent Component Analysis (ICA): Identifies and removes non-neural artifacts.
PHC Approach: The PHC method integrates probabilistic modeling with multiple base classifiers to improve SSVEP classification accuracy. The key steps are:
a. Feature Extraction
• Power Spectral Density (PSD) Analysis: Extracts dominant frequency components.
• Canonical Correlation Analysis (CCA): Identifies the strongest correlation between EEG data and predefined SSVEP templates.
• Wavelet Transform (WT): Captures transient features for better classification in noisy environments.
b. Hybrid Classification
PHC utilizes a combination of classifiers to enhance robustness:
• Support Vector Machine (SVM): Separates signal classes using a hyperplane for improved generalization.
• Convolutional Neural Networks (CNNs): Detects complex nonlinear patterns in EEG signals.
• Random Forest (RF): Improves classification by aggregating multiple decision trees.
• Probabilistic Bayesian (PB) Model: Assigns probabilistic confidence scores to classifications for better decision-making under uncertain conditions.
The final classification decision is made using a probabilistic fusion mechanism, which assigns weights to each classifier’s prediction and selects the most probable command.
Control Interface and Wheelchair Navigation: Once the PHC system classifies the SSVEP signals, the output is sent to the wheelchair control module. The system maps detected SSVEP signals to specific movement commands, such as:
• Move Forward (MF) → 10 Hz flicker
• Turn Left (TL)→ 12 Hz flicker
• Turn Right (TR)→ 15 Hz flicker
• Stop (ST)→ 20 Hz flicker
The wheelchair responds in real-time, allowing users to navigate efficiently with minimal cognitive effort and low latency.
The PHC approach significantly enhances SSVEP-based BCI classification by integrating probabilistic modeling with multiple base classifiers, ensuring higher accuracy, faster response time, and better adaptability in real-world hands-free wheelchair control applications. This innovation improves mobility and independence for individuals with motor impairments, making BCI-based assistive technologies more practical and efficient.
NOVELTY:
This invention presents a unique combination of probabilistic decision-making, adaptive mechanisms, and advanced data enhancement techniques, making it a groundbreaking approach for SSVEP signal classification in BCI systems. Its ability to handle noise, overlapping classes, and real-time processing distinguishes it from existing methods, establishing a new benchmark for performance in practical BCI deployments.

 
, Claims:1. A Probabilistic Hybrid Classification for Real-Time SSVEP-Based brain-computer interface (BCI) system, comprising: An EEG signal acquisition module, A signal preprocessing module, A feature extraction module, A probabilistic hybrid classification (PHC) module and a control unit.
2. The system as claimed as claim 1, wherein the system enables individuals with motor disabilities to control a motorized wheelchair using Steady-State Visual Evoked Potentials (SSVEPs) captured via EEG signals.
3. The system as claimed as claim 1, wherein the EEG signal acquisition module configured to capture multi-channel EEG signals from a user in response to visual stimuli flickering at predefined frequencies.
4. The system as claimed as claim 1, wherein the feature extraction module configured to extract features from the pre- processed EEG signals using: power spectral density (PSD) analysis, canonical correlation analysis (CCA), and wavelet transform (WT).
5. The system as claimed as claim 1, wherein the control interface configured to map the classified command to corresponding wheelchair navigation actions, including at least: move forward, turn left, turn right, and stop.
6. The system as claimed as claim 1, wherein the system enhances the accuracy, robustness, and responsiveness of SSVEP signal interpretation in real-time.