An Affordable Inkjet-Printed Foot Sole Sensor and Machine Learning for Telehealth Devices

Reduction of cardiovascular disease risk is highly correlated with regularity of exercise, which is not easily observed outside of medical settings, particularly for the elderly. Foot sole monitoring technology is now a saturated market due to its demand for applications in physical therapy, sports, hazardous work, etc. However, the best technology available comes with drawbacks like high prices, bulkiness, discomfort, and low power efficiencies. This work seeks to resolve many of these shortfalls with an inkjet printed foot sole inlay costing ${\$}$1.85 per sensor, is flexible, runs on nanowatts of power, and can easily be fabricated to personally fit the user's foot. A suite of machine learning algorithms are compared to classify 4 foot movements: sitting, standing, walking, and jogging. Algorithm performance results of the sensor samples show the support vector machine kernel reaching 83.5% rate of detecting the correct foot movement and classifies ten times per second. Future work includes embedding the trained algorithm onto a microprocessor, placing it into a shoe sole, and performing trials to collect real-world user data such that the technology matures and benefits significantly to those who need a telehealth device for movement monitoring.