Decoding Upper-Limb Motor Imagery from EEG Signals: A Systematic Review of Methods and Applications

Brain-computer interfaces (BCIs) have emerged as a promising technology with significant potential across various domains in recent years, including healthcare, industry, and entertainment. Among the many BCI paradigms, motor imagery (MI) based on electroencephalography (EEG) is one of the most commonly used and has been widely applied in medical settings. However, due to the inherently low signal-to-noise ratio and non-stationary nature of EEG signals, current decoding accuracy remains suboptimal-particularly in the classification of movements involving the same limb, where finer motion distinctions and higher decoding precision are urgently needed. This review summarizes the research on upper-limb MI-EEG classification and applications over the past 5 years and analyzes the relevant data extracted from the literature. The objective is to provide a comprehensive overview of the current state of research on decoding hand motor imagery from MI-EEG signals and to examine the challenges encountered in practical applications. We systematically investigate state-of-the-art methods, compare their performance and underlying assumptions, and discuss emerging trends and open challenges. Furthermore, we explore how these decoding methods can be translated into real-world applications, highlighting their potential as well as their limitations. The aim of this work is to provide valuable insights and guidance for researchers and developers in the field of EEG-based BCIs.