A Self-Learning and Adaptive Control Scheme for Phantom Prosthesis Control Using Combined Neuromuscular and Brain-Wave Bio-Signals

Abstract

The control scheme in a myoelectric prosthesis includes a pattern recognition section whose task is to decode an input signal, produce a respective actuation signal and drive the motors in the prosthesis limb towards the completion of the user’s intended gesture motion. The pattern recognition architecture works with a classifier which is typically trained and calibrated offline with a supervised learning framework. This method involves the training of classifiers which form part of the pattern recognition scheme, but also induces additional and often undesired lead time in the prosthesis design phase. In this study, a three-phase identification framework is formulated to design a control architecture capable of self-learning patterns from bio-signal inputs from electromyography (neuromuscular) and electroencephalography (brain wave) biosensors, for a transhumeral amputee case study. The results show that the designed self-learning framework can help reduce lead time in prosthesis control interface customisation, and can also be extended as an adaptive control scheme to minimise the performance degradation of the prosthesis controller.

Multiscale depth of anaesthesia prediction for surgery using frontal cortex electroencephalography

“…With a potential view towards a generalised DoA prediction method such as BIS, the DWS is proposed to be the best fit due to its concise standard deviation prediction band alongside low computational complexity metrics. Given the nature of the proposed patient-specific approach, it is anticipated that a real-time model 'System Identification' process is to be conducted at the start alongside an anaesthetist, where the computational model builds a patient-specific model, like the proposed approach done by Nsugbe et al [35].…”

“…Given the nature of the proposed patient‐specific approach, it is anticipated that a real‐time model ‘System Identification’ process is to be conducted at the start alongside an anaesthetist, where the computational model builds a patient‐specific model, like the proposed approach done by Nsugbe et al. [35].…”

Predictive Glucose Monitoring for People with Diabetes Using Wearable Sensors

“…Further work would now involve the inclusion of further features from the Fitbit wearable device in order to observe if it is possible to enhance the prediction accuracy of the designed model. In addition to this, a feature selection exercise can also be conducted to assess and evaluate the impactful drivers which are key predictors for the glucose prediction, in addition to alternate ML methods such as regressions and unsupervised learning [20,21].…”

A Pilot on the Use of Unsupervised Learning and Probabilistic Modelling Towards Cancer Extent Prediction

“…The prediction machine comprised of a combination of an unsupervised learning method to cluster and label the data, followed by supervised learning of the partitioned data (Khanam et al, 2015;Singh et al, 2016). The unsupervised learning method involved the use of probabilistic Gaussian mixture models (GMM) and fuzziness (fuzzy c-means) based learners which not only separate the data into distinct clusters, but also produce uncertainty/fuzziness metrics which were translated into stages of cervical cancer to create subclasses for supervised learning, and were capable of working in an automated fashion (Nsugbe, 2022;Nsugbe et al, 2020).…”

“…-K-means: this is an iterative clustering method where data is partitioned into k clusters, based on the Euclidean distance metric (Likas et al, 2003;Nsugbe et al, 2020). The algorithm is centered on the Expectation-Maximization (E-M) where the E step involves the assignment of clusters using the objective function assuming a random initialization…”