Combining meta and ensemble learning to classify EEG for seizure detection.

Despite two decades of extensive research into electroencephalogram (EEG)-based automated seizure detection analysis, the persistent imbalance between seizure and non-seizure categories remains a significant challenge. This study integrated meta-sampling with an ensemble classifier to address the issue of imbalanced classification existing in seizure detection. In this framework, a meta-sampler was employed to autonomously acquire undersampling strategies from EEG data.

Efficient EEG Feature Learning Model Combining Random Convolutional Kernel with Wavelet Scattering for Seizure Detection.

Automatic seizure detection has significant value in epilepsy diagnosis and treatment. Although a variety of deep learning models have been proposed to automatically learn electroencephalography (EEG) features for seizure detection, the generalization performance and computational burden of such deep models remain the bottleneck of practical application. In this study, a novel lightweight model based on random convolutional kernel transform (ROCKET) is developed for EEG feature learning for seizure detection.

Study on the Nodal Composite Bearing Performance of Nontruncated PHC Pipe Pile and Bearing Platform.

In this paper, low circumferential reciprocating load foot-scale tests were performed on two nontruncated PHC B 600 130 tubular piles with bearing nodes to characterize the damage process and morphology of the specimens and to investigate the load-carrying performance of the members. The test results reveal that under the action of tensile-bending-shear loading, the bearing concrete in the node area buckles and is damaged, the anchored reinforcement in the node area yields, the constraint is weakened, an articulation point is formed, and the node rotational capacity increases. When the embedment depth increases from 200 mm to 300 mm, the ultimate bearing capacities of the positive and negative nodes increase by 31.

Synthesis of EU-1/ZSM-48 Co-Crystalline Zeolites from High-Silica EU-1 Seeds: Tailoring Phase Proportions and Promoting Long Crystalline-Phase Stability.

A facile, specific, seed-assisted strategy for the synthesis of EU-1/ZSM-48 co-crystalline zeolites in the presence of hexamethonium ions (HM ) has been developed. EU-1/ZSM-48 co-crystalline zeolites with various phase proportions, with EU-1 in the range of 25 wt %-86 wt %, were obtained by adding high-silica EU-1 seeds (SiO /Al O ratio of 300) and adjusting the synthesis parameters. Not only can the phase proportions of EU-1/ZSM-48 co-crystalline zeolites be controlled, but also the stability period for co-crystallization of the two phases can be extended through varying the amount of EU-1 seeds and the HM template.