Publications by authors named "Zhao-Jun Ni"
[Identifying Depressive Disorder With Sleep Electroencephalogram Data: A Study Based on Deep Learning].
Sichuan Da Xue Xue Bao Yi Xue Ban
March 2023
Article Synopsis
- The study investigates the use of a deep learning approach that integrates Vision Transformer (ViT) and Transformer to identify depressive disorder from sleep EEG signals.
- The research involves preprocessing EEG data from 28 patients with depression and 37 control participants, converting the signals into images, and analyzing them to extract relevant features for classification.
- Results indicate that the combination of delta, theta, and beta waves from REM sleep leads to high accuracy (92.8%) and precision (93.8%) in detecting depression, with generally lower performance during sleep stage transitions.
Article Synopsis
- Most Japanese apricot cultivars typically exhibit self-incompatibility patterns, but the cultivar 'Zaohong' was found to be self-compatible (SC) through self-pollination tests.
- The SC in 'Zaohong' resulted from a loss of pollen function, specifically identified as having the S-genotype S 2 S 15, with no significant mutations in its S-haplotypes.
- Additionally, researchers discovered a new F-box gene related to SFB genes, suggesting that factors beyond the S-locus, such as PmF-box genes, might contribute to the pollen's loss of function.