🚨 ML for Gas Sensors: Anomaly Detection & Domain-Aware Modeling

About This Course

“ML for Gas Sensors: Anomaly Detection & Domain-Aware Modeling” is a cutting-edge 3-week course that integrates the nanomaterial science of graphene with AI, machine learning (ML), and IoT analytics. Graphene-based sensors, known for their ultra-sensitivity, are ideal for applications in biomedicine, environmental monitoring, chemical detection, and flexible electronics. However, effectively using these sensors at scale requires sophisticated data processing pipelines.

In this course, participants will learn the fundamentals of graphene-based sensor mechanisms and build practical workflows using tools like Python, pandas, scikit-learn, TensorFlow, MATLAB, and real-time signal analysis libraries. The course focuses on processing, classifying, and predicting sensor responses for real-world applications.

Aim

This course aims to equip participants with the knowledge and practical skills needed to analyze, interpret, and model data generated by graphene-based sensors. By using modern data analytics and machine learning frameworks, participants will be prepared to apply these techniques to real-world applications in sensing technologies.

Course Objectives

• Bridge the gap between sensor hardware innovation and intelligent data use

• Promote cross-disciplinary learning between nanoscience and AI

• Empower participants to contribute to next-gen sensor networks and smart systems

• Foster innovation in sustainable, scalable, and real-time sensing platforms

• Prepare researchers to publish or commercialize sensor-based data solutions

Course Structure

📅 Module 1: Signal Preprocessing for SAW Gas Sensors

Theme: Understanding and Preparing Sensor Signals for Analysis

• Introduction to SAW Gas Sensors

  • Working principles and real-world applications

  • Common signal characteristics and noise sources

• Signal Preprocessing Techniques

  • Filtering: Low-pass, band-pass, and median filters

  • Baseline correction and normalization

• Feature Extraction & Dimensionality Reduction

  • Time-domain and frequency-domain features

  • PCA, FFT, and wavelet transforms for SAW data

Hands-On Lab:

• Implementing signal preprocessing techniques with Python

📅 Module 2: Anomaly Detection Using Autoencoders

Theme: Detecting Anomalies in Sensor Data

• Basics of Autoencoders

  • Architecture: Encoder, bottleneck, decoder

  • Training for reconstruction accuracy

• Autoencoders for Anomaly Detection

  • Loss-based detection of anomalous gas responses

  • Performance evaluation metrics (AUC, precision-recall)

Hands-On Lab:

• Building and training an autoencoder model in Python (Keras/PyTorch)

• Analyzing real SAW data with labeled anomalies

📅 Module 3: Transfer Learning for New Analytes

Theme: Expanding Model Applicability Across Different Sensor Data

• Introduction to Transfer Learning

  • What is transfer learning and why it matters

  • Types: Feature-based, fine-tuning, domain adaptation

• Applying Transfer Learning to Sensor Data

  • Transferring models across sensor types or analyte classes

  • Handling distribution shift and domain generalization

• Advanced Techniques & Future Directions

  • Meta-learning, few-shot learning, and continual learning

  • Preparing models for deployment in dynamic environments

Hands-On Lab:

• Implementing transfer learning for sensor data analysis

Who Should Enrol?

• Nanotechnology researchers and material scientists

• Sensor engineers and IoT hardware developers

• AI/ML professionals working in biomedical or environmental sensing

• Researchers in wearable and flexible electronics

• UG/PG/PhD students in physics, electronics, materials, or data science