Chapter
1.2. Human Biological Systems
1.3. Neural Interfaces and Devices
Chapter 2: State-of-the-Art
2.1. Neuromuscular Signal
2.1.1. EMG Signal Acquisition
2.1.2. EMG Signal Processing
2.1.3. Applications of Neuromuscular Signal
Discrete Movement Recognition
Continuous Movement Recognition
2.2.1. Fundamentals of EEG Electrophysiology
2.2.2. Composition and Characteristics of EEG Signals
Spontaneous and Rhythmic Properties of EEG
EEG Has Small Amplitude and Low Frequency
EEG Signal Source Has High Internal Resistance and Randomness
2.2.3. Types and Characteristics of EEG Signals
Alpha Waves Produced by Eye Movements
EEG Signals Based on Motor Imagery
2.3. Neural Modeling and Interfaces
Chapter 3: Neuromuscular Signal Acquisition and Processing
3.1.1. Production of sEMG Signal
3.1.2. Characteristics of sEMG Signals
3.2. sEMG Acquisition Devices
3.2.1. Requirement of sEMG Acquisition
3.2.2. Wired sEMG Acquisition Device
Design and Implementation of Acquisition Device
3.2.3. WiFi-Based sEMG Acquisition Device
Design and Implementation of Acquisition Device
3.2.4. Bluetooth-Based sEMG Acquisition Device
Design and Implementation of the Acquisition Device
3.3. sEMG Signal Preprocessing
3.3.1. Wavelet Analysis-Based sEMG Denoising
Best Wavelet Packet Adaptive Threshold Denoising
Comparison Between Methods
3.3.2. Singular Spectrum-Based sEMG Denoising
Chapter 4: sEMG-Based Motion Recognition
4.1. sEMG Feature Extraction and Classification
4.1.1. sEMG Feature Extraction Methods
Frequency Domain Analysis
Time-Frequency Domain Analysis
High-Order Spectral Analysis
Nonlinear Dynamic Analysis
4.1.2. sEMG Pattern Recognition Methods
Artificial Neural Networks
Fuzzy Pattern Recognition
4.2. Hand Gesture Recognition
4.2.1. Best Wavelet Package Denoising for Preprocessing
4.2.2. Wavelet Coefficient and LLE for Feature Extraction
Extraction of Wavelet Coefficients
Construction of Joint Feature
4.2.3. BP Neural Network for Classification
4.2.4. Experimental Results Analysis
4.3. Ankle Motion Recognition
4.3.1. Feature Extraction and Selection
4.3.2. LS_SVM for Classification
4.3.3. Experimental Results and Analysis
Experiment Results and Analysis
4.4. Continuous Motion Recognition of Wrist Joint
4.4.1. Experimental Protocol
4.4.2. Signal Preprocessing
4.4.3. NMF for Extracting Muscle Synergies
Determination of Number of Muscle Synergies
Analysis of Muscle Synergies
An Improved Neural Network Model
Force Prediction Model Based on Motion Recognition
Analysis of Force Prediction Results
Chapter 5: Brain Signal Acquisition and Preprocessing
5.1. Research Background and Significance
5.2. SSVEP/P300/Motor Imagery Signal
5.2.1. P300 Signal and Its Processing Method
5.2.2. SSVEP Signal and Processing Method
5.2.3. Motor Imagery Signal and Processing Method
5.3. Stimulators and Acquisition Devices
5.3.1. Current Status of EEG Signal Acquisition Device
5.3.2. Design of an EEG Acquisition Device
Hardware Design of EEG Acquisition Device
Software Design of EEG Acquisition Device
Test Experiment of EEG Acquisition Device
5.4. Signal Preprocessing
5.4.1. P300 Signal Preprocessing Algorithm
Optimal Weighted Averaging Filtering Preprocessing
5.4.2. SSVEP Signal Preprocessing Algorithm
Adaptive Filtering Based on Gaussian White Noise
Chapter 6: EEG-Based Brain Intention Recognition
6.1. EEG Feature Extraction and Classification
6.1.1. Feature Extraction
Canonical Correlation Analysis
6.1.2. Feature Classification
6.2. SSVEP-Based Intent Recognition
6.2.1. MestCCA-MSI for Feature Extraction
6.2.2. MUSIC for Classification
6.3. P300-Based Intention Recognition
6.3.1. OWAF for Preprocessing
6.3.2. PCA for Feature Extraction
6.3.3. msw-SVM for Classification
6.4. Motor Imagery-Based Intention Recognition
6.4.1. CSP-LCD for Feature Extraction
6.4.2. FA-LA for Feature Selection
Parameter Adaptive Adjustment Based on Learning Automata
Experimental Results and Analysis
Chapter 7: Neuromuscular Modeling
7.1. Biological Organisms
7.1.1. Neuromuscular System
7.1.2. Skeletal Muscles of the Lower Limb
7.2. sEMG-Driven Musculoskeletal Model
7.2.1. sEMG Preprocess and Muscle Activation
7.2.2. Hill-Type Muscle-Tendon Model
7.2.3. Musculoskeletal Geometry
7.2.4. Experiments and Results
7.3. Muscle Force Estimation
7.3.1. The Study on the Relationship Between sEMG and Muscle Force
7.3.2. Muscle Force Estimation of Static Force Contraction Mode
7.3.3. Muscle Force Prediction Based on Muscle Activity
7.3.4. Muscle Force Estimation of Dynamic Contraction Mode
7.4. Neuromuscular Models in Robotic Rehabilitation
7.4.1. Assist-As-Needed Lower Limb Rehabilitation
7.4.2. Muscle Force-Based Adaptive Impedance Control
Chapter 8: Neural Interface
8.1. Neuromuscular Interface
8.1.1. Man-Robot Interface
Interface Design of Lower Limbs Signal and Robot
sEMG Signal Acquisition and Processing
Communication Between sEMG Processing System and Robot
System Application Test and Result Analysis
Upper Limbs and Robot Interface With EMG-Based Force Prediction
Software System Based on Motion Discrimination and Force Prediction
Control Robot Based on Force Prediction
Experimental Scheme and Result Analysis
8.1.2. Man-Mechanical Arm Interface
Design of Elbow Joint Angle Recognition Control Software Based on MFC
Simplified Mechanical Arm Angle Control Experiment Based on sEMG Real-Time Control
8.2. Brain-Computer Interface
8.2.1. BCI Based on SSVEP Signal
Design of SSVEP Vision Stimulator
Data Acquisition Module Design
System Testing and Result Analysis
8.2.2. BCI Based on SSVEP and P300
Visual Stimulator Design of Hybrid EEG Signals
Hybrid EEG Signal Acquisition
System Testing and Result Analysis
Software Design of BCI System Based on MI
Experimental Design of BCI System Based on MI
8.3. Interactive Control Interface
8.3.1. Interactive Signals Processing
Interactive Force Prediction Based on SVR Model
Interactive Motion Recognition Based on AR Model and SVM
8.3.2. Interactive Impedance Control Interface
Position-Based Interactive Impedance Control Interface
Adaptive Interactive Impedance Control Interface
8.3.3. Experimental Results and Analysis
Experiment on Force Prediction and Interactive Control Interface
Experiment on EMG Recognition and Interactive Control Interface
Chapter 9: Conclusion and Future Prospects
9.1.1. Effective Neuromuscular Interfaces
sEMG Signal Acquisition Devices
EMG Processing and Features Extraction
Human Intention Recognition Methodologies
9.1.2. Brain-Computer Interfaces
SSVEP Signals Acquisition and Processing
Recognition of Human Motor Imagery
Hybrid Brain-Computer Interfacing Approaches
9.1.3. Human Biomechanics Modeling
EMG-Driven Musculoskeletal Model
Estimation of Muscle Force and Joint Torque
9.1.4. Interfaces and Devices
Neural Interfaces in Robotic Rehabilitation
9.2. Outlook and Future Prospects
9.2.1. Future Neural Interfaces
Intelligent Brain/Neural Signal Processing Methods
Interfaces Based on Advanced Sensing Technology
Development of More Patient-Specific Models
9.2.2. Bioinspired Rehabilitation Devices
Wearable Actuators, Sensors, and Devices
Biomechatronic Integrated Rehabilitation
Advanced Rehabilitative Technology
：Neural Interfaces and Devices
Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.
