In this work, we utilize T1-weighted MR images and StackNet to predict fluid intelligence in adolescents. Our framework includes feature extraction, feature normalization, feature denoising, feature selection, training a StackNet, and predicting fluid intelligence. The extracted feature is the distribution of different brain tissues in different brain parcellation regions. The proposed StackNet consists of three layers and 11 models. Each layer uses the predictions from all previous layers including the input layer. The proposed StackNet is tested on a public benchmark Adolescent Brain Cognitive Development Neurocognitive Prediction Challenge 2019 and achieves a mean absolute error of 82.42 on the combined training and validation set with 10-fold cross-validation.

Ever wondered how Kaggle masters combine hundreds of different machine learning models to win modelling competitions? Ever wondered how to become ranked #1 on Kaggle? StackNet has helped me do that! StackNet is an open-source, scalable and automated meta-modelling framework that combines various supervised models to improve performance. Written in Java, this library automates many of the laborious aspects of building stacking models, so that you can focus on the important parts and move higher up the Kaggle leaderbo ards.