Multi-Scale Temporal-Spatial Feature-Based Hybrid Deep Neural Network for Remaining Useful Life Prediction of Aero-Engine.

Remaining useful life (RUL) prediction is crucial for simplifying maintenance procedures and extending the lifespan of aero-engines. Therefore, research on RUL prediction methods for aero-engines is increasingly gaining attention. In particular, some existing deep neural networks based on multiscale features extraction have achieved certain results in RUL predictions for aero-engines.

Recognition memory deficits detected through eye-tracking in well-controlled children with self-limited epilepsy with centrotemporal spikes.

Objective: Children with self-limited epilepsy characterized by centrotemporal spikes (SeLECTS) exhibit cognitive deficits in memory during the active phase, but there is currently a lack of studies and techniques to assess their memory development after well-controlled seizures. In this study, we employed eye-tracking techniques to investigate visual memory and its association with clinical factors and global intellectual ability, aiming to identify potential risk factors by examining encoding and recognition processes.

Methods: A total of 26 recruited patients diagnosed with SeLECTS who had been seizure-free for at least 2 years, along with 24 control subjects, underwent Wechsler cognitive assessment and an eye-movement-based memory task while video-electroencephalographic (EEG) data were recorded.