Footwear-Based Wearable Sensors for Physical Activity Monitoring

摘要: Monitoring of posture allocations and activities is important for such applications as physical activity management, energy expenditure estimation, stroke rehabilitation others. At present, accurate devices rely on multiple sensors distributed the body thus may be too obtrusive everyday use. This chapter presents an overview a novel wearable footwear sensor (SmartShoe), which capable very recognition most common postures while being minimally intrusive to subject. SmartShoe relies capturing information from patterns heel acceleration plantar pressure differentiate weight-bearing non-weight-bearing (such example, sitting standing, walking/jogging cycling). Validation results obtained in several studies demonstrate applicability widely varying populations healthy individuals post-stroke, achieving high (95%-98%) average accuracy classification, (root-mean-square error 0.69 METs) prediction, reliable (error 2.6- 18.6%) identification temporal gait parameters. High minimal intrusiveness should enable its use wide range research clinical applications.