Simultaneous Feature Selection and Heterogeneity Control for SVM Classification: An Application to Mental Workload Assessment

Abstract In this study, an expert system is presented for analyzing the mental workload of interacting with a mobile phone while facing common daily tasks. Psychophysiological signals were collected from various devices, each characterized by a different cost and obtrusiveness. To deal with user-level signal data, a support vector machine-based feature selection approach is proposed. Given the limited person-level information available, our goal was to construct robust models by pooling population-level information across users (as a heterogeneity control). A single optimization problem that combines four objectives is proposed: model, margin maximization, feature selection, and heterogeneity control. The costs of using the devices were estimated, leading to a decision tool that allowed experiment designers to evaluate the marginal benefit of using a given device in terms of performance and its cost.