Post-Stroke Gait Classification Based on Feature Space Transformation and Data Labeling

Despite scientific and clinical advances, stroke is still considered one of the main causes disability, including gait disorders. The search for more effective methods re-education in post-stroke patients most important issues contemporary neurorehabilitation. In this paper, we propose a transformation feature space definition class labels problem to efficiently study related phenomena assess faster. Clustering used define two (improvement recurrence) data labeling process. proposed approach was tested on real-world dataset consisting 50 (male female, aged 49–82 years) after ischemic who participated rehabilitation program. Gait described using speed, cadence, stride length their normalized values. Ten treatment sessions (10 therapy days) were conducted over weeks working days). same specialist took measurements, hence inter-rater reliability can be neglected. Machine learning methods, support vector machine quadratic discriminant analysis classify three cases with different labels. novel approach, characterized by its speed execution accuracy classification, may helpful screening, better targeting, monitoring. minimizes testing supports work physicians, physiotherapists, diagnosticians.