**5. Conclusions**

In developing intelligent multifunctional prostheses where symmetrical limb motion intent elicitation protocol was adopted, this study systematically investigated the characteristics of a range of features across varying windowing parameters when applied for movement intent decoding in the context of pattern recognition system,. The interrelation and impact of different windowing parameters on the performances of the feature sets were extensively explored with respect to accuracy, computation complexity, robustness to additive random noise and number of electrode channels. From the experimental results, we found that a combination of features mostly achieved high classification performance with correspondingly higher computation time compared with their individual counterparts (single features) that had lower computation time and high classification error. Interestingly, this phenomenon explains the trade-off that exist between accuracy and controller delay in the practical use of upper limb prosthesis in real-life applications. Furthermore, we discovered that the combinations of features are more robust to noise, compared to single features, and with lesser channels they can still achieved relative good classification performance across varying windowing parameters regardless of the subject category. Particularly, NTDFS, TD-PSD, and TD5AR6 features exhibited consistent stability, robustness, and accuracy across all the windowing parameters for both, able-bodied and amputee subjects compared to the other features. Findings from this study would provide researchers and engineers with a framework for proper selection of appropriate feature set, windowing parameters, and signal conditioning, required to develop a computationally efficient PR-based control strategy for intelligently smart prostheses and other PR based systems aimed at providing smart health care services.

**Author Contributions:** Conceptualization, M.G.A., and O.W.S., investigation, M.G.A., and O.W.S., methodology, M.G.A. and O.W.S.; software, M.G.A.; validation, M.G.A.; subjects recruitment, L.W.; data collection, O.W.S., Y.G., and Y.J. data analysis, M.G.A., and O.W.S.; data interpretation, M.G.A., and O.W.S.; writing—original draft preparation, M.G.A.; writing—review and editing, O.W.S., S.C., P.F., A.K.S., and G.L.; supervision, G.L.; funding acquisition, G.L. All authors have read and agreed to the published version of the manuscript.

**Funding:** The research work was supported in part by the National Natural Science Foundation of China under Grants (#U1613222, #81850410557, #U1913601, #8201101443, #5061773364), CAS President's International Fellowship Initiative Grant (#2019PB0036), Shenzhen Science and Technology Program (#SGLH20180625142402055), the Shenzhen Governmental Basic Research Grant (#JCYJ20160331185848286), the International Collaboration Program, Natural Science Foundation of Guangdong Province (2019A050510029), the Natural Science Foundation of Guangdong Province (2018A030313065), the Science, Technology and Innovation Commission of Shenzhen Municipality Fund (JCYJ20170818163445670), and the Shenzhen Institute of Artificial Intelligence and Robotics for Society.

**Acknowledgments:** Mojisola G. Asogbon Samuel sincerely appreciate the support of the Chinese Government Scholarship (CSC) in the pursuit of a Ph.D. degree at the University of Chinese Academy of Sciences, Beijing, China.

**Conflicts of Interest:** The authors declare no conflict of interest.
