Research & Innovation

Training for a Marathon? An AI-Powered Playlist May Help Improve Performance

Researchers at Stevens Institute of Technology are using smart-shoe inserts paired with a music interface to help runners train more efficiently

(Hoboken, N.J. – Nov. 4, 2021) - With the New York City marathon taking place this weekend, competitive and recreational runners may feel inspired to start their own training regimen, but according to researchers at Stevens Institute of Technology, picking the perfect playlist may make or break their efforts.  Assistant professor of mechanical engineering, Damiano Zanotto, is currently studying how music tempo can help put runners on the right track when it comes to endurance or high intensity interval training.   

It all starts with the SportSole, an AI-powered shoe insert developed by Zanotto’s team.  SportSole is a footwear-based device that can accurately assess a runner’s gait in terms of stride length, foot-ground clearance, foot trajectory, cadence, symmetry ratios, and running speed.  Zanotto is now adding music to the mix to see how tempo and beat can help a runner stay on a proper training course. 

Using the SportSole in combination with real-time audio modulation software, Zanotto and his team have developed a lightweight wearable system that plays a song and slightly adjusts the playback parameters to help the runner to stay on the beat.  First, the runner selects his/her favorite genre from a database, through a user interface. Then, the software automatically provides the runner with a subset of songs within that genre that match their natural cadence, from which he/she can select the song to be played during training.

If the runner unknowingly speeds up or slows down, the system will automatically adjust the song to trigger the runner to get back on the intended pace, thus maximizing training efforts and effectiveness.  Examples of sound modulation being investigated by Zanotto’s team include changing the song playback speed proportionally to the velocity error or adding white noise (similar to the noise in an old-school FM radio) that is proportional to the velocity error.

Zanotto says the goal is to improve the accuracy of existing wearable technologies (e.g., sport watches) to estimate running performances. Additionally, Zanotto’s system eliminates a runner’s need to look down at a smartwatch to gauge whether they are hitting their stride. Currently, the wearable system includes the smart insoles (SportSole), a running belt containing a small battery and a microcontroller, and wireless earbuds. Eventually, the hope is to create a phone app that will replace the belt module, making the system more user-friendly. 

About Stevens Institute of Technology
Stevens Institute of Technology is a premier, private research university situated in Hoboken, New Jersey. Since our founding in 1870, technological innovation has been the hallmark of Stevens’ education and research. Within the university’s three schools and one college, 8,000 undergraduate and graduate students collaborate closely with faculty in an interdisciplinary, student-centric, entrepreneurial environment. Academic and research programs spanning business, computing, engineering, the arts and other disciplines actively advance the frontiers of science and leverage technology to confront our most pressing global challenges. The university continues to be consistently ranked among the nation’s leaders in career services, post-graduation salaries of alumni, and return on tuition investment.

Stevens media contacts:

Thania Benios
Director of Public Relations
[email protected]

Robin Deehan
Media Relations Manager
[email protected]