Full Record

New Search | Similar Records

Title Design and Implementation of an Artificial Intelligence-Driven Gait Phase Recognition System for Orthotic Knee Control
Publication Date
Date Accessioned
University/Publisher University of Ottawa
Abstract Microprocessor-controlled stance-control knee-ankle-foot orthoses (M-SCKAFO) can have multiple sensors at all lower-limb segments. This causes M-SCKAFO to be bulky and expensive, with complex control systems. Stance-control systems with sensors local to the knee-joint component would provide a modular orthosis component for easier orthotist-customization and personalization for users with knee-extensor weakness. A gait phase recognition model (GPR) is essential for a fast, accurate, and generalizable real-time orthosis-control. This thesis designed, developed, and evaluated a machine learning-based GPR model for intelligent M-SCKAFO control. The model used gait signals that mimicked thigh inertial sensor and knee angle. Machine learning was implemented to identify gait phases across multiple surface conditions and walking speeds. Thigh-segment angular velocity, thigh-segment acceleration, and knee angle were calculated from 30 able-bodied participants for level and up, down, right-cross, and left-cross slopes at 0.8, 0.6, 0.4 m/s, and self-paced speeds (1.33 m/s, SD = 0.04 m/s). A logistic model tree (LMT) was built with a set of 20 signal features extracted from 0.1s sliding windows. The GPR model determined the walking state and was fed through a “transition sequence verification and correction” (TSVC) algorithm to deal with continuous states. The GPR model was evaluated on a different data set from 12 able-bodied individuals that completed the same walking protocol (validation set). Gait phases were classified successfully regardless of surface-level, walking speed, and individual walking variability. The LMT had a tree size of 1643 nodes with 822 leaf nodes. The GPR model produced overall classification accuracy of 98.4% and increased to 98.7% when TSVC was applied. Results also demonstrated evidence of strong model-generalizability with GPR accuracy of 90.6% and increased to 98.6% when TSVC was applied, on the validation set. This research demonstrated that local sensor signals from thigh and knee, integrated with machine intelligence algorithms, provided viable GPR suitable for real-time orthosis-control. The logistic decision tree model and feature selection approach were computationally efficient for real-time GPR and gave reliable, robust, and generalizable results across multiple surfaces, walking speeds, and individual walking variability. GPR also benefitted from transition sequence verification and correction algorithms, providing enhanced gait phase classification performance.
Subjects/Keywords Artificial Intelligence; Machine Learning; Gait; Stance Control; Knee ankle Foot Orthosis; Orthosis; Control System; Inertial Measurement Unit; Gait Phase Recognition; Microprocessor; Sensors; Feature Selection
Language en
Country of Publication ca
Record ID handle:10393/37730
Repository ottawa
Date Retrieved
Date Indexed 2018-05-29
Issued Date 2018-05-23 00:00:00

Sample Search Hits | Sample Images | Cited Works

…achieve gait phase recognition and stance-control. Rule-based and intelligent algorithms use multiple sensors to determine when the knee requires stability (stance) or free motion (swing) and are often more reliable for walking on…

…gait, the concept of gait phase recognition (GPR), and reviews ubiquitous lower-limb orthosis solutions for knee extensor weakness. The motivation, equipment, and methods used to control stance-control knee-ankle-foot orthoses are explored, as…

…x5B;13]. Stance phase is when the foot remains in contact with the ground, accounting for approximately 60% of a full stride. Stance sub-phases are initial contact (IC), loading response (LR), mid-stance (MS), and…

…terminal stance (TS) [14]. Swing phase is the period after stance phase when the foot leaves the ground and swings through to the following ground contact. Swing sub-phases are pre-swing, initial swing, mid-swing, and terminal swing…

…during a stride. Phase Stance Swing Task Events Weight Acceptance Initial contact Loading response Single Limb Support Swing Limb Advancement Cycle (%) 0-2% 2-12% Mid-stance 12-31% Terminal stance 31-50% Pre-swing 50-62% Initial…

…of antagonist muscles (flexors, extensors) is required to stabilize and support an individual’s weight during stance phase. For stair climbing, someone with severe knee extensor weakness cannot perform step over step locomotion. Compensatory…

…relatively simple control systems that do not require external power, a low profile, low weight, and the ability to fit under trousers. Unfortunately, mechanically controlled SCKAFO can have inconsistent stance/swing phase recognition leading to unreliable…

…During mid-stance phase the artificial extensors initiated knee extension and the flexors began to deplete their air-reserves to gradually reduce the flexion moment about the knee [19], [21]. In the second mode, the system did not…