arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1905.10550eess.IVcs.CVcs.LGstat.AP
收藏

三维CNN回归函数的数据融合增强及其流体智能预测

Ensemble of 3D CNN regressors with data fusion for fluid intelligence prediction

Skolkovo Institute of Science and Technology(斯科尔科沃科学技术学院)

Marina Pominova, Anna Kuzina, Ekaterina Kondrateva, Svetlana Sushchinskaya, Maxim Sharaev, Evgeny Burnaev, and Vyacheslav Yarkin

摘要:

在这项工作中,我们的目标是预测儿童的流体智力分数的基础上,结构T1加权磁共振图像从最大的长期研究大脑发育和儿童健康。目标变量回归的数据收集网站,社会人口统计变量和脑容量,从而独立于潜在的信息因素,这是不直接相关的大脑功能。我们研究了特征提取和深度学习方法以及不同的深度CNN架构及其集成。我们提出了一种先进的VoxCNN集成架构,在盲测试中产生MSE(92.838)。

英文摘要:

In this work, we aim at predicting children's fluid intelligence scores based on structural T1-weighted MR images from the largest long-term study of brain development and child health. The target variable was regressed on a data collection site, socio-demographic variables and brain volume, thus being independent to the potentially informative factors, which are not directly related to the brain functioning. We investigate both feature extraction and deep learning approaches as well as different deep CNN architectures and their ensembles. We propose an advanced architecture of VoxCNNs ensemble, which yield MSE (92.838) on blind test.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑