Gait Pattern and Gait Quality Assessment for Individuals with Lower-Limb Disabilities using Machine Learning and Inertial Sensor Data
Bibliographic record
Abstract
Effective rehabilitation and gait monitoring are essential for helping individuals with gait disabilities to improve movement and quality of life. Despite advancements in wearable gait analysis technology, clinical practice still relies heavily on observational methods, and practical adoption of these technologies remains limited. This thesis investigates machine learning approaches for inertial sensor data, to develop clinically relevant gait analysis methods and address barriers to adoption of gait analysis technology. This research was comprised of four objectives. Objectives 1-3 explored machine learning models to assess relative changes in an individual’s gait patterns by directly analyzing accelerometer and gyroscope signals from inertial sensors. Objective 1 demonstrated that raw time-series data from a single gyroscope could be used to detect meaningful changes following a single physiotherapist-led training session. Results showed high classification accuracy for individuals with significant changes in clinically identified gait parameters. Objectives 2 and 3 investigated unsupervised approaches to assess multiple levels of change in gait patterns using gyroscope and accelerometer signals, addressing gaps in current classification and supervised learning approaches. Objective 2 explored using a hidden Markov model-based similarity measure (HMM-SM) to assess change in able-bodied gait patterns, achieving good consistency and validity using inertial sensors on the upper legs and lower legs. Objective 3 extended this approach to lower-limb prosthetic users, demonstrating that wearable sensor signals could be robustly used for monitoring changes in gait patterns. Objective 4 expanded the research to investigate using inertial sensor signals to assess absolute gait quality, evaluated using lower-limb prosthetic users. Various algorithms were benchmarked, including the previously developed HMM-SM, dynamic time warping (DTW) and movement deviation profile (MDP). The results from this study showed strong correlations between inertial sensor measures and the Gait Profile Score, a validated measure of gait quality. This indicates that inertial sensor data could be used to assess overall gait quality. Wearable sensors offer the potential to transform rehabilitation practice. This work explored a unique approach to monitoring gait patterns that can facilitate the design of gait analysis systems that are both highly wearable (i.e., requiring few sensors) and adaptable to different gait disabilities.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".