Efficient Patient Fine-Tuned Seizure Detection with a Tensor Kernel Machine

TL;DR

This paper introduces a transfer learning method using tensor kernel machines for seizure detection in wearable devices, enabling efficient patient-specific model fine-tuning with reduced model size.

Contribution

It proposes a novel tensor kernel machine approach that allows efficient updating of patient-independent models with patient-specific data, reducing model size.

Findings

Patient fine-tuned models match patient-specific SVM performance.

Model size is halved compared to patient-specific models.

Achieves high accuracy with significantly smaller models.

Abstract

Recent developments in wearable devices have made accurate and efficient seizure detection more important than ever. A challenge in seizure detection is that patient-specific models typically outperform patient-independent models. However, in a wearable device one typically starts with a patient-independent model, until such patient-specific data is available. To avoid having to construct a new classifier with this data, as required in conventional kernel machines, we propose a transfer learning approach with a tensor kernel machine. This method learns the primal weights in a compressed form using the canonical polyadic decomposition, making it possible to efficiently update the weights of the patient-independent model with patient-specific data. The results show that this patient fine-tuned model reaches as high a performance as a patient-specific SVM model with a model size that is twice as small as the patient-specific model and ten times as small as the patient-independent model.