UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

A multimodal multiple kernel learning approach to Alzheimer's disease detection

Donini, M; Monteiro, JM; Pontil, M; Shawe-Taylor, J; Mourao-Miranda, J; (2016) A multimodal multiple kernel learning approach to Alzheimer's disease detection. In: Proceedings of the 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP). IEEE: Vietri sul Mare, Italy. Green open access

[thumbnail of Shawe-Taylor_multiple-kernel-learning.pdf]
Preview
Text
Shawe-Taylor_multiple-kernel-learning.pdf - Accepted Version

Download (408kB) | Preview

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.

Type: Proceedings paper
Title: A multimodal multiple kernel learning approach to Alzheimer's disease detection
Event: 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP)
ISBN-13: 9781509007462
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/MLSP.2016.7738881
Publisher version: https://doi.org/10.1109/MLSP.2016.7738881
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: Kernel, Alzheimer's disease, Training, Neuroimaging, Linear programming, Standards, Multiple kernel learning, feature selection
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/1534838
Downloads since deposit
407Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item