Maxxyt: An Autonomous Wearable Device for Real-Time Tracking of a Wide Range of Exercises

Strength training exercises are an important part of fitness training. Although several fitness devices exist to track and analyze cardio-training activities like walking and running, devices to track repetitive movements during strength training exercises are few and they have technical limitations. We introduce Maxxyt - an autonomous wearable device that can count repetitive movements during strength training in real-time. Maxxyt functions without any prior exercise-specific training and can self-adapt to any generic exercise involving repetitive movements. It has been designed with the motive of optimizing the experience of a typical user training in a gym. It uses an Arduino-compatible microcontroller, with primary memory of 4 KB. Maxxyt provides hap tic and visual feedback to the user within 2 seconds from starting an exercise. The proposed method to count repetitions involves three phases: i) pre-processing, ii) peak-detection using adaptive techniques, and iii) aggregation of results from various axes. We present results on test data collected in a gym consisting of 1171 repetitions from 100 sets of 10 distinct exercises. The repetition count accuracy of the device is 2 repetitions 98% of the time. These results suggest a new paradigm of responsive, wearable strength training fitness devices.