A robust intelligence regression model for monitoring Parkinson's disease based on speech signals

Ahmed M. Anter, Ali Wagdy Mohamed, Min Zhang, Zhiguo Zhang

Abstract: Highlights•A robust model based on BALO and adaptive ELM is proposed and integrated with IoT framework for PD monitoring and diagnosis.•BALO is used for feature selection, while DEELM is guided by DE for optimal hyper-parameters to predict PD-UPDRS scores.•BALO-DEELM is assessed for a real-world PD problem using various performance criteria and outcomes relative to prior study.•Different comparisons are carried out with different meta-heuristics and ML prediction methods.•BALO-DEELM is more robust and can achieve high prediction accuracies with less computational time and high convergence speed.