A New Neuromorphic Computing Approach for Epileptic Seizure Prediction
This work addresses the challenge of implementing seizure prediction on wearable devices for epilepsy patients by offering an energy-efficient solution, though it is incremental as it builds on existing CNN and SNN methods.
The paper tackles the problem of computationally expensive seizure prediction methods by proposing a neuromorphic computing approach using a spiking convolutional neural network (Spiking-CNN), which reduces computation complexity by 98.58% while maintaining sensitivity at 95.1%, specificity at 99.2%, and AUC at 0.912.
Several high specificity and sensitivity seizure prediction methods with convolutional neural networks (CNNs) are reported. However, CNNs are computationally expensive and power hungry. These inconveniences make CNN-based methods hard to be implemented on wearable devices. Motivated by the energy-efficient spiking neural networks (SNNs), a neuromorphic computing approach for seizure prediction is proposed in this work. This approach uses a designed gaussian random discrete encoder to generate spike sequences from the EEG samples and make predictions in a spiking convolutional neural network (Spiking-CNN) which combines the advantages of CNNs and SNNs. The experimental results show that the sensitivity, specificity and AUC can remain 95.1%, 99.2% and 0.912 respectively while the computation complexity is reduced by 98.58% compared to CNN, indicating that the proposed Spiking-CNN is hardware friendly and of high precision.