Search

Processing multiple channels of bioelectrical signals for bionic assistive robot volitional motion control is still a challenging task due to the interference of systematic noise, artifacts, individual bio-variability, and other factors. Emerging machine learning (ML) provides an enabling technology for the development of the next generation of smart devices and assistive systems and edging computing. However, the integration of ML into a robotic control system faces major challenges. This paper presents ML computing to process twelve channels of shoulder and upper limb myoelectrical signals for shoulder motion pattern recognition and real-time upper arm exoskeleton volitional control. Shoulder motion patterns included drinking, opening a door, abducting, and resting. ML algorithms included support vector machine (SVM), artificial neural network (ANN), and Logistic regression (LR). The accuracy of the three ML algorithms was evaluated respectively and compared to determine the optimal ML algorithm. Results showed that overall SVM algorithms yielded better accuracy than the LR and ANN algorithms. The offline accuracy was 96 ± 3.8% for SVM, 96 ± 3.8% for ANN, and 93 ± 6.3% for LR, while the online accuracy was 90 ± 9.1% for SVM, 86 ± 12.0% for ANN, and 85 ± 11.3% for LR respectively. The offline pattern recognition had a higher accuracy than the accuracy of real-time exoskeleton motion control. This study demonstrated that ML computing provides a reliable approach for shoulder motion pattern recognition and real-time exoskeleton volitional motion control.

ABSTRACT Human papillomaviruses (HPVs) consist of two capsid proteins: major capsid protein L1 and minor capsid protein L2. The L2 protein has been shown to be involved in intracellular trafficking events that lead to the deposition of the viral DNA into the nucleus. In this study, we investigate the role of HPV16 L2 residues 43-DQILQ-47 during intracellular trafficking in human keratinocytes. We demonstrate that the highly conserved amino acids aspartic acid, isoleucine, and leucine are involved with the intracellular trafficking of the virus. Amino acid substitution of the isoleucine and leucine residues with alanine residues results in a significant decrease in infectivity of the pseudovirions without any changes to the binding or internalization of the virus. The pseudovirions containing these substitutions exhibit an altered trafficking pattern and do not deposit the viral pseudogenome into the nucleus. Instead, these mutated pseudovirions display a lack of interaction with syntaxin 18, an ER SNARE protein, are unable to progress past the endoplasmic reticulum (ER) and are redirected to the lysosomes. The results of this study help to elucidate the role and potential involvement of the 43-DQILQ-47 sequence during intracellular trafficking, specifically during trafficking beyond the ER. IMPORTANCE High-risk types of human papillomaviruses (HPVs), such as HPV16, are highly associated with cervical, anogenital, and oropharyngeal cancers. The minor capsid protein L2 is essential for the intracellular trafficking of the viral DNA to the nucleus. This study investigates the role of amino acid residues 43-DQILQ-47 of the HPV16 L2 protein in the intracellular trafficking of the virus. Understanding how the virus traffics through the cell is a key factor in the development of additional preventative antiviral therapies. This study illustrates, through modification of the 43-DQILQ-47 sequence in pseudovirions, the importance of the 43-DQILQ-47 sequence in the trafficking of the virus beyond the endoplasmic reticulum.