Stable Feature Selection from Brain sMRI

Authors: Bo Xin, Lingjing Hu, Yizhou Wang, Wen Gao

AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments show that the proposed nonnegative model performs much better in exploring the intrinsic structure of data via selecting stable features compared with other state-of-the-arts.
Researcher Affiliation Academia National Engineering Laboratory for Video Technology, Key Laboratory of Machine Perception, School of EECS, Peking University, Beijing, 100871, China Yanjing Medical College, Capital Medical University, Beijing, 101300, China
Pseudocode No The paper describes algorithms and mathematical formulations but does not include structured pseudocode or an algorithm block.
Open Source Code No No explicit statement or link providing access to the open-source code for the described methodology was found.
Open Datasets Yes The data are obtained from the Alzheimer s Disease Neuroimaging Initiative (ADNI) database2. We split all the baseline data into 1.5T and 3.0T MRI scans datasets (named 15T and 30T). 2http://adni.loni.ucla.edu
Dataset Splits Yes 10-fold cross-validation (CV) evaluation is applied and the classification accuracy for all tasks are summarized in Tab. 2.
Hardware Specification Yes All experiments are carried out on an Intel(R) Core(TM) i7-3770 CPU at 3.40GHz.
Software Dependencies Yes Although off-the-shelf convex solvers such as CVX (Grant and Boyd 2013) can be applied to solve the optimization, it hardly scales to high-dimensional problems in feasible time.
Experiment Setup No For each model, we used grid-search to find the optimal parameters respectively. No specific hyperparameters, ranges for grid search, or resulting optimal parameters are provided for reproducibility.