Abstract | ||
---|---|---|
In neuroimaging-based diagnostic problems, the combination of different sources of information as MR images and clinical data is a challenging task. Their simple combination usually does not provides an improvement if compared with using the best source alone. In this paper, we deal with the well known Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset tackling the AD versus Control task. We use a recently proposed multiple kernel learning approach, called EasyMKL, to combine a huge amount of basic kernels in synergy with a feature selection methodology, pursuing an optimal and sparse solution to facilitate interpretability. Our new approach, called EasyMKLFS, outperforms baselines (e.g. SVM) and state-of-the-art methods as recursive feature elimination and SimpleMKL. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1109/MLSP.2016.7738881 | 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP) |
Keywords | Field | DocType |
Multiple kernel learning,feature selection,neuroimaging,Alzheimer's disease | Kernel (linear algebra),Interpretability,Pattern recognition,Feature selection,Computer science,Multiple kernel learning,Support vector machine,Artificial intelligence,Linear programming,Neuroimaging,Machine learning,Recursion | Conference |
ISSN | ISBN | Citations |
2161-0363 | 978-1-5090-0747-9 | 0 |
PageRank | References | Authors |
0.34 | 13 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Michele Donini | 1 | 80 | 14.67 |
João P. Monteiro | 2 | 50 | 7.04 |
Massimiliano Pontil | 3 | 5820 | 472.96 |
John Shawe-Taylor | 4 | 11879 | 1518.73 |
Janaina Mour ão-Miranda | 5 | 714 | 42.19 |