Binary Single-dimensional Convolutional Neural Network for Seizure Prediction
This work addresses the challenge of implementing seizure prediction in implantable or wearable devices by reducing hardware and power consumption, though it is incremental in optimizing existing deep learning methods for specific constraints.
The authors tackled the problem of epileptic seizure prediction by proposing a hardware-friendly binary single-dimensional convolutional neural network (BSDCNN) that achieves high performance with reduced computational and storage requirements, reaching AUCs of 0.915 and 0.970 on two datasets while reducing parameter size by 7.2 times and computation by 25.5 times.
Nowadays, several deep learning methods are proposed to tackle the challenge of epileptic seizure prediction. However, these methods still cannot be implemented as part of implantable or efficient wearable devices due to their large hardware and corresponding high-power consumption. They usually require complex feature extraction process, large memory for storing high precision parameters and complex arithmetic computation, which greatly increases required hardware resources. Moreover, available yield poor prediction performance, because they adopt network architecture directly from image recognition applications fails to accurately consider the characteristics of EEG signals. We propose in this paper a hardware-friendly network called Binary Single-dimensional Convolutional Neural Network (BSDCNN) intended for epileptic seizure prediction. BSDCNN utilizes 1D convolutional kernels to improve prediction performance. All parameters are binarized to reduce the required computation and storage, except the first layer. Overall area under curve, sensitivity, and false prediction rate reaches 0.915, 89.26%, 0.117/h and 0.970, 94.69%, 0.095/h on American Epilepsy Society Seizure Prediction Challenge (AES) dataset and the CHB-MIT one respectively. The proposed architecture outperforms recent works while offering 7.2 and 25.5 times reductions on the size of parameter and computation, respectively.