Decoding cognitive subtasks of complex problem solving using fMRI signals

Brain decoding aims to predict cognitive states of the brain during a mental process. In order to analyze the active brain regions and decode cognitive subtasks of complex problem solving, we use the data collected from subjects scanned while playing Tower of London (TOL) game. TOL is a problem solving task consisting of two major subtasks, namely, planning and execution. We propose a pipeline of 3 steps for a subtask decoding in this problem solving experiment. The first step of the pipeline is voxel selection and regrouping the selected voxels to their related AAL brain region so that we can obtain informative voxels and resolve curse of dimensionality of the data. Second step is temporal interpolation of the time series to increase the number of brain slice. Then, pseudo-random noise addition is applied to these time series for the purpose of generalization of learning methods. It is observed that this step increases the representation power of the fMRI data for TOL experiment. Lastly, we employ k-means clustering and linear support vector machines (SVM) to observe the effects of above-mentioned steps. We observe that there is gradual increases of the decoding performances on both supervised and unsupervised methods after each of the steps.