Fitbit Devices Can Now Automatically Identify Exercises and Track Workouts


Fitbit has released a software upgrade for its Surge and Charge HR activity trackers that adds functionality allowing the devices to automatically detect when users begin a workout, and even discern what type of exercises were done. Prior to the update, Fitbit users needed to manually tell their devices that they were about to start a workout, after which they were prompted to enter details on the type of exercise they would be doing. This information was subsequently used to trend workout habits and calculate daily caloric burn.

To help reduce manual workout logging, Fitbit has enhanced its activity trackers with software that will detect an increase in activity levels, and then analyze the details of that activity to identify what exercise is being performed. The extent to which Fitbit will identify activities is limited. In a press release, the company reports that its trackers can now automatically identify biking, running, walking, and elliptical use. Beyond this, exercise will be sorted into one of two generic categories: aerobic workouts or sports workouts. By default, Fitbit will not count the activity as a workout until the user spends 30 minutes exercising, but this threshold can be reduced to as low as 10 minutes, or increased all the way to 90 minutes.

While Fitbit’s ability to analyze activity patterns and identify the underlying exercise is limited, great strides have been made in this area in the last few years. Basis offers passive activity tracking that automatically identifies walking, running, and cycling. Jawbone has turned its exercise identification efforts over to machine-learning algorithms, which automatically detect and then compare workout patterns with millions of other Up users to make probability-based guesses as to which exercise they were likely doing. The system presents users with the three most likely options, and then remembers which they chose most often for future reference. Over time, Jawbone says the algorithms become personalized and more accurate. For gym enthusiasts, the only company making meaningful strides in identifying various weight- and machine-based exercises is Atlas Wearables. In 2014, the company raised $680,000 on Indiegogo and is now shipping units that it says can automatically differentiate between 50 common gym exercises, including dumbbell curls, bench press, shoulder press, deadlifts, squats, chin-ups, push-ups, and sit-ups.

Enjoy HIStalk Connect? Sign up for update alerts, or follow us at @HIStalkConnect.

↑ Back to top

Founding Sponsors

Platinum Sponsors