Multimodal Pain Classification (m-PainAttnNet)

Automated pain assessment using physiological signals offers an objective alternative to self-reporting. m-PainAttnNet extends PainAttnNet to a multimodal setting, fusing ECG, EMG, and EDA signals through attention mechanisms to classify pain into 5 intensity levels. Evaluated on the BioVid Heat Pain Database (87 participants).

Key result: 98.8% accuracy on 5-class pain intensity classification, with cross-session robustness >75%.

Architecture

The model stacks three learned components:

1. Multi-Scale CNN (MSCN) — extracts temporal features at short, medium, and long scales from 1D physiological signals; dropout 0.4–0.5 for regularisation.
2. Squeeze-and-Excitation ResNet (SEResNet) — channel-wise attention recalibrates feature importance; residual connections maintain gradient flow; output dimensionality reduced to 30 channels.
3. Transformer Encoder — 2-layer encoder, 6 attention heads; captures long-range temporal dependencies with layer normalisation and feed-forward networks.

Multimodal Fusion Strategies

Three fusion points were evaluated:

• Early fusion: concatenate modalities before MSCN
• Late fusion: process each modality independently, combine at the final layer
• Attention fusion: learn weighted modality combinations (best results)

Results

Ablation over architecture components

SEResNet’s channel attention provided the single largest accuracy jump (~28 pp). The full model trades a marginal accuracy drop for better generalisation.

Modality ablation (full model)

Dataset

BioVid Heat Pain Database — 87 participants, 5 pain levels (0–4: none to very high), synchronised ECG, EMG (trapezius, corrugator, zygomaticus), and EDA recordings across multiple sessions.

Technical Stack

PyTorch · NumPy · SciPy · Scikit-learn · K-fold cross-validation · Google Colab (GPU)

Project Report

Download PDF · Presentation slides

Course: CS6530 — Advanced Topics in AI, IIT Hyderabad (Jan–Apr 2024) · Supervised by Prof. Nagarajan Ganapati