Abstract
Brain-Computer Interfaces (BCIs) are systems allowing people to interact with the environment bypassing the natural neuromuscular and hormonal outputs of the peripheral nervous system (PNS). These interfaces record a user’s brain activity and translate it into control commands for external devices, thus providing the PNS with additional artificial outputs. In this framework, the BCIs based on the P300 Event-Related Potentials (ERP), which represent the electrical responses recorded from the brain after specific events or stimuli, have proven to be particularly successful and robust. The presence or the absence of a P300 evoked potential within the EEG features is determined through a classification algorithm. Linear classifiers such as stepwise linear discriminant analysis and support vector machine (SVM) are the most used discriminant algorithms for ERPs’ classification. Due to the low signal-to-noise ratio of the EEG signals, multiple stimulation sequences (a.k.a. iterations) are carried out and then averaged before the signals being classified. However, while augmenting the number of iterations improves the Signal-to-Noise Ratio, it also slows down the process. In the early studies, the number of iterations was fixed (no stopping environment), but recently several early stopping strategies have been proposed in the literature to dynamically interrupt the stimulation sequence when a certain criterion is met in order to enhance the communication rate. In this work, we explore how to improve the classification performances in P300 based BCIs by combining optimization and machine learning. First, we propose a new decision function that aims at improving classification performances in terms of accuracy and Information Transfer Rate both in a no stopping and early stopping environment. Then, we propose a new SVM training problem that aims to facilitate the target-detection process. Our approach proves to be effective on several publicly available datasets.
Highlights
A Brain-Computer Interface (BCI) is a system that records a user’s brain activity and allows him to interact with the environment by exploiting both signal processing and machineExtended author information available on the last page of the articleAnnals of Operations Research learning algorithms
In order to better understand the contribution of the new training problem, we look at the single-subject results, dividing the participants into two classes: Class 1 subjects where the standard support vector machine (SVM) problem is better than the new M-SVM; Class 2 subjects where the standard SVM problem is worse than the new M-SVM
BCIs are proposed for a wide range of applications, such as those for communicating (Sellers et al 2006), for entertainment (Bianchi 2020), environmental or neuroprostheses control (Muller-Putz and Pfurtscheller 2008), rehabilitation (Bockbrader et al 2018), and supporting diagnoses (Lugo et al 2016), to name a few
Summary
A Brain-Computer Interface (BCI) is a system that records a user’s brain activity and allows him to interact with the environment by exploiting both signal processing and machine. EEG represents one of the most used methods since they are non invasive and inexpensive; for this reason they have been used for a wide variety of tasks (Chaovalitwongse et al 2006; Khojandi et al 2019) In this framework, BCIs based on event-related potentials (ERPs) have proven to be successful and robust (Schreuder et al 2013). Since each iteration takes about 3 seconds to be completed, this strategy increases the time needed to detect brain signals affecting down the communication rate To overcome this drawback, different early stopping (ES) or Dynamic Stopping methods have been introduced, where after a calibration phase, a suitable termination criterion is established to be tested online when the number of iteration is sufficient to ensure a reliable classification. We explore how to improve the classification performance by combining optimization and machine learning both in the classical setting with a fixed number of repetitions and in the early stopping setting
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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
