Learn More
BACKGROUND Electroencephalography (EEG) based sleep staging is commonly used in clinical routine. Feature extraction and representation plays a crucial role in EEG-based automatic classification of sleep stages. Sparse representation (SR) is a state-of-the-art unsupervised feature learning method suitable for EEG feature representation. NEW METHOD(More)
An ideal magnetic rail should provide a homogeneous magnetic field along the longitudinal direction to guarantee the reliable friction-free operation of high temperature superconducting (HTS) maglev vehicles. But in reality, magnetic field inhomogeneity may occur due to lots of reasons; the joint gap is the most direct one. Joint gaps inevitably exist(More)
This paper proposes a fast learning method for fuzzy measure determination named fuzzy extreme learning machine (FELM). Moreover, we apply it to a special application domain, which is known as unit combination strategy evaluation in real time strategy (RTS) game. The contribution of this paper includes three aspects. First, we describe feature interaction(More)