PaperNet: Efficient Temporal Convolutions and Channel Residual Attention for EEG Epilepsy Detection

TL;DR

PaperNet is a lightweight hybrid deep learning model that effectively classifies EEG signals for epilepsy detection by combining temporal convolutions, channel attention, and recurrent modules, achieving high accuracy with low computational cost.

Contribution

The paper introduces PaperNet, a novel compact architecture that integrates temporal convolutions, residual channel attention, and bidirectional recurrent units for efficient EEG classification.

Findings

Achieves macro-F1 of 0.96 on EEG epilepsy dataset

Uses approximately 0.6 million parameters, suitable for resource-limited systems

Demonstrates the effectiveness of combining temporal, attention, and recurrent modules

Abstract

Electroencephalography (EEG) signals contain rich temporal-spectral structure but are difficult to model due to noise, subject variability, and multi-scale dynamics. Lightweight deep learning models have shown promise, yet many either rely solely on local convolutions or require heavy recurrent modules. This paper presents PaperNet, a compact hybrid architecture that combines temporal convolutions, a channel-wise residual attention module, and a lightweight bidirectional recurrent block which is used for short-window classification. Using the publicly available BEED: Bangalore EEG Epilepsy Dataset, we evaluate PaperNet under a clearly defined subject-independent training protocol and compare it against established and widely used lightweight baselines. The model achieves a macro-F1 of 0.96 on the held-out test set with approximately 0.6M parameters, while maintaining balanced performance across all four classes. An ablation study demonstrates the contribution of temporal convolutions, residual attention, and recurrent aggregation. Channel-wise attention weights further offer insights into electrode relevance. Computational profiling shows that PaperNet remains efficient enough for practical deployment on resource-constrained systems through out the whole process. These results indicate that carefully combining temporal filtering, channel reweighting, and recurrent context modeling can yield strong EEG classification performance without excessive computational cost.