ECG Inner Speech Recognition With Low-Channel Wearable Sensing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies struggle to accurately and cost-effectively classify inner speech or human thinking using electroencephalography (EEG) due to high costs and poor accuracy, and no studies have explored electrocardiography (ECG) for this purpose.
Innovation Solution
A low-cost, low-channel ECG system with electrodes placed on the forehead and neck is used to collect heart electrical activity, combined with feature extraction methods like autoregressive coefficients, Shannon entropy, and multiscale wavelet variance estimation, followed by a support vector machine (SVM) classification to interpret inner speech.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If EEG-based BCI systems are used to record brain electrical activities for inner speech recognition, then the ability to detect inner speech is improved, but the cost and device complexity increase significantly
Solution Approach 1:
The patent extracts and utilizes only the necessary components for inner speech detection by focusing on specific EEG frequency bands (alpha, beta, gamma) rather than processing all brain signals. This selective extraction reduces computational complexity and processing requirements while maintaining detection accuracy.
Solution Approach 2:
The patent employs inexpensive disposable electrodes instead of expensive reusable medical-grade sensors. These disposable electrodes significantly reduce system cost while providing sufficient signal quality for inner speech recognition, making the technology accessible for broader applications.
2Measurement precision
If multimodal physiological signals (EEG, EMG, GSR, BVP, PPG, ECG) are combined for affective computing and inner speech detection, then the accuracy of emotion and inner speech recognition is improved, but the device complexity and cost increase
Solution Approach 1:
The patent merges multiple physiological signal types (EEG, ECG, EMG, GSR) into a unified processing framework that leverages the complementary information from each modality. By integrating these signals through a common analytical approach, the system achieves high recognition accuracy without requiring separate complex processing pipelines for each sensor type.
Solution Approach 2:
The patent develops a universal processing framework that handles multiple physiological signal types using the same feature extraction and classification algorithms. This multi-functional approach allows the system to process different signal modalities through a single unified system, reducing overall complexity while maintaining high accuracy for both emotion and inner speech detection.
3Measurement precision
If high-cost, high-channel EEG headsets are used for inner speech recognition, then measurement precision is improved, but ease of manufacture and accessibility worsen
Solution Approach 1:
The patent employs inexpensive disposable electrodes instead of expensive reusable medical-grade sensors. These disposable electrodes significantly reduce system cost while providing sufficient signal quality for inner speech recognition, making the technology accessible for broader applications.
Solution Approach 2:
The patent changes the operational parameters of the EEG system by focusing on specific frequency bands and using simplified feature extraction methods. This parameter optimization allows the system to achieve high accuracy with fewer channels and lower-cost hardware, improving manufacturability and accessibility.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system achieves high accuracy in distinguishing inner speech commands, reducing data complexity and cost, enabling effective interaction for individuals with speech disabilities.
Implementation Method 1
The electrical field generated by the heart is monitored and measured through a process called electrocardiogra which records it in an ECG graph illustrating the variation in voltage versus time
Data Source
AI summary
The present disclosure relates to methods and apparatuses for classifying internalized speech using a heart-computer interface. In particular, disclosed herein is a method for interpreting electrocardiogram (ECR) signals in an individual using electrodes placed on the individual's skin. The method disclosed herein may be performed using a low-cost, low-channel ECG apparatus, such as by placing three sensors on the individual's skin and which may be wearable and portable to facilitate its use. The sensors may be placed on the left and right sides of the individual's forehead and on the left side below the individual's neck to collect ECG signals, although other placements are possible. features. Autoregressive coefficient (AR), Shannon entropy, fractal measures, and multiscale wavelet variance estimation may then be applied to the collected ECG signals to determine the individual's internalized speech.