Reducing False Alarms in Wearable Seizure Detection With EEGformer: A Compact Transformer Model for MCUs.

The long-term, continuous analysis of electroencephalography (EEG) signals on wearable devices to automatically detect seizures in epileptic patients is a high-potential application field for deep neural networks, and specifically for transformers, which are highly suited for end-to-end time series processing without handcrafted feature extraction. In this work, we propose a small-scale transformer detector, the EEGformer, compatible with unobtrusive acquisition setups that use only the temporal channels. EEGformer is the result of a hardware-oriented design exploration, aiming for efficient execution on tiny low-power micro-controller units (MCUs) and low latency and false alarm rate to increase patient and caregiver acceptance.

Elder Barn Owl Nestlings Flexibly Redistribute Parental Food according to Siblings' Need or in Return for Allopreening.

Kin selection and reciprocation of biological services are distinct theories invoked to explain the origin and evolutionary maintenance of altruistic and cooperative behaviors. Although these behaviors are not considered to be mutually exclusive, the cost-benefit balance of behaving altruistically or cooperating reciprocally and the conditions promoting a switch between such different strategies have rarely been tested. Here, we examine the association between allofeeding, allopreening, and vocal solicitations in wild barn owl () broods under different food abundance conditions: natural food provisioning and after an experimental food supplementation.