Abstract

Many neuroscience studies have been devoted to understand brain neural responses correlating to cognition using functional magnetic resonance imaging (fMRI). In contrast to univariate analysis to identify response patterns, it is shown that multi-voxel pattern analysis (MVPA) of fMRI data becomes a relatively effective approach using machine learning techniques in the recent literature. MVPA can be considered as a multi-objective pattern classification problem with the aim to optimize response patterns, in which informative voxels interacting with each other are selected, achieving high classification accuracy associated with cognitive stimulus conditions. To solve the problem, we propose a feature interaction detection framework, integrating hierarchical heterogeneous particle swarm optimization and support vector machines, for voxel selection in MVPA. In the proposed approach, we first select the most informative voxels and then identify a response pattern based on the connectivity of the selected voxels. The effectiveness of the proposed approach was examined for the Haxby’s dataset of object-level representations. The computational results demonstrated higher classification accuracy by the extracted response patterns, compared to state-of-the-art feature selection algorithms, such as forward selection and backward selection.

Highlights

  • Functional magnetic resonance imaging is one of the publicly used neuroimaging techniques to capture brain neural activity in small volumetric units in the brain by measuring the change of blood-oxygen-level dependent (BOLD) signals over time

  • For subject 5, the classification results produced by Hierarchical heterogeneous particle swarm optimization (HHPSO)–support vector machine (SVM) and particle swarm optimization (PSO)–SVM were not as good as the results produced by without feature selection (WFS) or sequential backward feature selection (SBS)

  • We addressed and solved the challenging, high-dimensional voxel selection problem in multivoxel pattern analysis (MVPA) in neuroscience by combining HHPSO and SVM

Read more

Summary

Introduction

Functional magnetic resonance imaging (fMRI) is one of the publicly used neuroimaging techniques to capture brain neural activity in small volumetric units (called voxels) in the brain by measuring the change of blood-oxygen-level dependent (BOLD) signals over time. Speaking, it has advanced the understanding of brain functional activity by fMRI in various cognitive and behavioral neuroscience applications, such as Alzheimer’s disease [1], aging [2], autism [3], depression [4], schizophrenia [5], and attentiondeficit hyperactivity disorder [6]. It leads to two-fold objectives: (1) it aims to select a minimum number of voxels included in classification models and (2) the classification accuracy needs to be maximized

Objectives
Results
Conclusion
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call