A motor imagery based brain-computer interface system via swarm-optimized fuzzy integral and its application

摘要: A brain-computer interface (BCI) system provides a convenient means of communication between the human brain and computer, which is applied not only to healthy people but also for that suffer from motor neuron diseases (MNDs). Motor imagery (MI) one well-known basis designing Electroencephalography (EEG)-based real-life BCI systems. However, EEG signals are often contaminated with severe noise various uncertainties, imprecise incomplete information streams. Therefore, this study proposes spectrum ensemble based on swam-optimized fuzzy integral integrating decisions sub-band classifiers established by common spatial pattern (SBCSP) method. Firstly, SBCSP effectively extracts features signals, thereby multiple linear discriminant analysis (MLDA) employed during MI classification task. Subsequently, particle swarm optimization (PSO) used regulate subject-specific parameters assigning optimal confidence levels in fusion stage proposed system. Moreover, systems usually tend have complex architectures, be bulky size, require time-consuming processing. To overcome drawback, wireless wearable measurement investigated study. Finally, our experimental result, found produce significant improvement terms receiver operating characteristic (ROC) curve. Furthermore, we demonstrate robotic arm can reliably controlled using This paper presents novel insights regarding possibility MI-based applications.