Towards a wearable low-cost ultrasound device for classification of muscle activity and muscle fatigue

Being able to reliably predict muscle contractions is important for athletes and rehabilitation patients alike. Numerous techniques and surrogates exist for this task. However, they are in general not well suited for everyday use and not able to extract information of muscles located in deeper body layers. To address this shortcoming, we present an approach to classify muscle contractions with raw ultrasound radio-frequency data (A-Scans) collected with a wearable system. It consists of a single element ultrasound transducer connected to custom-built acquisition hardware and an Android app to receive, store and analyze the data. We rely on data from the lower legs of healthy volunteers performing squats as sample exercises and use machine learning methods, ranging from sequence similarity measurement techniques to artificial neural networks, to classify the radio-frequency data. Results of our preliminary experimental setup prove its feasibility to classify muscle contractions based on ultrasound measurements.