Development of an epileptic seizure prediction algorithm using R–R intervals with self-attentive autoencoder

Epilepsy is a neurological disorder that may affect the autonomic nervous system (ANS) from 15 to 20 min before seizure onset, and disturbances of ANS affect R–R intervals (RRI) on an electrocardiogram (ECG). This study aims to develop a machine learning algorithm for predicting focal epileptic seizures by monitoring R–R interval (RRI) data in real time. The developed algorithm adopts a self-attentive autoencoder (SA-AE), which is a neural network for time-series data. The results of applying the developed seizure prediction algorithm to clinical data demonstrated that it functioned well in most patients; however, false positives (FPs) occurred in specific participants. In a future work, we will investigate the causes of FPs and optimize the developing seizure prediction algorithm to further improve performance using newly added clinical data.

     

New type latch for hard disk drive

A new type latch for hard disk drive is proposed. It can retract and protect a read/write head, without additional installation of a few cams and a magnet such as in a conventional hard disk drive. The new latch mechanism comprises two elements. One is a ramp with groove for parking a suspension tab and the other is a balanced-type suspension previously proposed to achieve required shock resistance for mobile use. The new latch mechanism is driven by the Lorentz force of VCM coil generated in the vertical and horizontal directions.