Approximately 41,000 individuals live with upper-limb loss (loss of at least one hand) in the US. Fortunately, prosthetic devices have advanced considerably in the past decades with the development of dexterous, anthropomorphic hands. However, potentially the most promising used control strategy, myoelectric control, lacks a correspondingly high-level of performance and hence the use of dexterous hands remains highly limited. The need for a complete overhaul in upper limb prosthesis control is well highlighted by the abandonment rates of myoelectric devices, which can reach up to 40% in the case of trans-humeral amputees. The area of research that has received the most focus over the past decade has been ?pattern recognition,? which is a signal processing based control method that uses multi-channel surface electromyography as the control input. While pattern recognition provides intuitive operation of multiple prosthetic degrees of freedom, it lacks robustness and requires frequent, often daily calibration. Thus, it has not yet achieved the desired clinical acceptance. Our team proposes clinical translation of a novel highly adaptive upper limb prosthesis control system that incorporates two major advances: 1) machine learning (robust classification by implementing a non-boundary based algorithm), and 2) training by retrospectively incorporating user data from activities of daily living (ADL). The proposed system will enable machine intelligence with user input for prosthesis control. Our work is organized as follows: Phase I: (a) First, we will implement a fundamentally new machine intelligence technique, Extreme Learning Machine with Adaptive Sparse Representation Classification (EASRC), that is more resilient to untrained noisy conditions that users may encounter in the real-world and requires less data than traditional myoelectric signal processing. (b) In parallel, we will implement an adaptive learning algorithm, Nessa, which allows users to relabel misclassified data recorded during use and then update the EASRC classifier to adapt to any major extrinsic or intrinsic changes in the signals. Taken together, EASRC and Nessa comprise the Retrospectively Supervised Classification Updating (RESCU) system. Once, the RESCU implementation is complete, we will optimize the system through a joint effort with Johns Hopkins University, and complete an iterative benchtop RESCU evaluation with a focus group of 3 amputee subjects and their prosthetists. Our milestones for Phase I are as follows: Milestone 1.1: Extreme Learning Machine with Adaptively Sparse Representation (EASRC) algorithm successfully implemented and verified Milestone 1.2: Implementation of Nessa adaptive learning algorithm and smartwatch interface Milestone 1.3: User Needs and Design Inputs locked as a result of Focus Group testing Milestone 1.4: Hold a pre-submission meeting with FDA for feedback on device classification and planned product performance testing Milestone 1.5: Hold a Scientific Steering Group (SSG) meeting Milestone 1.6: Convene a Study Monitoring Committee (SMC) and hold an initial meeting to review clinical plans. Milestone 1.7: Develop Clinical Study Protocol Milestone 1.8: Register the study on www.clinicaltrials.gov.
In this project, we aim to empower the user by bringing them into the control loop of their prosthesis and improve the stability of their control strategy over time. Specifically, we implement to a robust classifier, an adaptive learning algorithm, and a smartwatch interface, which allows the user to teach their device when it misunderstands the commands that the user is sending to control the prosthesis. This will result in improved control without cumbersome or time-consuming effort on the part of the user and, more importantly, we hope that it will give the user a greater sense of empowerment and ownership over their prosthesis.
