Course Overview

This course introduces EEG (Electroencephalography) and EGG (Electrogastrography) signals and their applications in human-centric robotics, including brain-computer interfaces (BCI), bio-signal processing, and intelligent robotic control systems.

---

📅 Week-wise Course Content

---

🔹 Week 1: Introduction to Human-Centric Robotics & Bio-Signals

Topics Covered:

• What is Human-Centric Robotics?
• Role of bio-signals in robotics
• Introduction to EEG & EGG signals
• Human nervous system basics
• Sensors and data acquisition overview

Practical:

• Familiarization with EEG/EGG devices (simulated or real)
• Understanding signal visualization

Outcome:

• Understand how human signals can control robotic systems

---

🔹 Week 2: EEG Signal Fundamentals

Topics Covered:

• EEG signal generation (brain activity basics)
• Brain waves: Alpha, Beta, Gamma, Theta, Delta
• EEG electrode placement (10–20 system)
• Noise and artifacts in EEG signals

Practical:

• EEG data collection (using datasets or hardware)
• Visualization using Python (Matplotlib)

Tools:

• Python, NumPy, Matplotlib

Outcome:

• Ability to interpret basic EEG signals

---

🔹 Week 3: EGG Signal Fundamentals

Topics Covered:

• Digestive system basics
• EGG signal generation and characteristics
• Differences: EEG vs EGG
• Medical and robotic relevance of EGG

Practical:

• EGG dataset analysis
• Filtering and smoothing signals

Tools:

• Python, SciPy

Outcome:

• Understand gut-brain interaction and EGG signal behavior

---

🔹 Week 4: Signal Processing & Feature Extraction

Topics Covered:

• Signal preprocessing (filtering, denoising)
• Time-domain & frequency-domain analysis
• Feature extraction techniques:
  • Mean, variance
  • FFT (Fast Fourier Transform)
  • Power spectral density

Practical:

• Implement filtering (band-pass filter)
• Extract features from EEG/EGG signals

Tools:

• Python (SciPy, Pandas)

Outcome:

• Ability to clean and prepare bio-signals for ML models

---

🔹 Week 5: Machine Learning for Bio-Signals

Topics Covered:

• Introduction to BCI (Brain-Computer Interface)
• Classification of EEG signals
• ML algorithms:
  • KNN, SVM, Decision Trees
• Pattern recognition for robotic control

Practical:

• Train a model to classify EEG signals
• Simple command detection (e.g., left/right movement)

Tools:

• Scikit-learn, Python

Outcome:

• Build ML models for interpreting human signals

---

🔹 Week 6: Human-Centric Robotics Application & Final Project

Topics Covered:

• EEG-based robot control systems
• EGG-based health monitoring robots
• Integration with robotics (Arduino / ROS basics)
• Ethics & future scope

Final Project:

👉 Build a mini project such as:

• EEG-based robotic arm control (simulation)
• Mind-controlled cursor/robot movement
• Health monitoring system using EGG

Tools:

• • Python + Arduino / ROS (optional)

  Outcome:

  • Real-world implementation of human-centered robotic system

  ---

  🎯 What You Will Learn

  • Basics of EEG & EGG signals
  • Signal processing & feature extraction
  • Machine learning for bio-signals
  • Brain-computer interface concepts
  • Real-world robotics integration

  ---

  🛠️ Tools & Technologies

  • Python (NumPy, Pandas, Matplotlib, SciPy)
  • Scikit-learn
  • Arduino / ROS (optional)
  • EEG datasets (OpenBCI, PhysioNet)

  ---

  🏆 Certification Criteria

  • Weekly assignments
  • Final project submission
  • Attendance & participation