AI tool can recommend workouts based on fitness tracker data
Team Udayavani, Apr 23, 2019, 1:51 PM IST
Los Angeles: Scientists have developed an artificial intelligence tool that can make recommendations for workouts based on data from your fitness trackers.
The tool, called FitRec, was trained on a dataset of more than 250,000 workout records for more than 1,000 runners, according to scientists from the University of California San Diego in the US.
This allowed computer scientists to build a model that analysed past performance to predict speed and heart rate given specific future workout times and routes.
FitRec also is capable of identifying important features that affect workout performance, such as whether a route has hills and the user’s level of fitness.
The tool can recommend alternate routes for runners who want to achieve a specific target heart rate. It also is capable of making short-term predictions, such as telling runners when to slow down to avoid exceeding their desired maximum heart rate.
The team was able to develop the tool partially because they were among the first to collect and model a massive fitness dataset for academic research.
However, developing FitRec was no easy feat as the fitness dataset has a huge number of workout records, but only a small number of data points per individual.
“Personalisation is crucial in models of fitness data because individuals vary widely in many areas, including heart rate and ability to adapt to different exercises,” said Julian McAuley, a professor at UC San Diego.
“The main challenge in building this type of model is that the dynamics of heart rates as people exercise are incredibly complex, requiring sophisticated techniques to model,” researchers said.
To build an effective model, computer scientists needed a tool that uses all of the data to learn but at the same time can learn personalised dynamics from a small number of data points per user.
Enter a deep learning architecture called long short-term memory networks (or LSTM), which the researchers adapted to capture the individual dynamic behaviours of each user in the dataset.
Researchers fed the networks a subset of a public dataset from endomondo.com, an app and website that function as a workout diary. After cleaning up the data, researchers wound up with more than 100,000 workout records to train the networks.
They validated FitRec’s predictions by comparing them with existing workout records that were not part of the training dataset.
In the future, FitRec could be trained to include other data, such as the way users’ fitness levels evolve over time, to make its predictions. The tool could also be applied to more complex recommendation routes, for example safety-aware routes.
However, in order for the tool to be used in commercial fitness apps, researchers would need to have access to more detailed fitness tracking data and deal with various data quality issues.
Udayavani is now on Telegram. Click here to join our channel and stay updated with the latest news.
Top News
Related Articles More
Dogs understand more than they let on, create mental images of known words: Study
ISRO achieves major milestone in RLV Landing Experiment
More risk of malware infection while accessing pirated websites: Study
Piracy sites in India pose greater risk of malware, surpassing adult sites, gambling ads: Study
Online wellness content: 3 ways to tell evidence-based health information from pseudoscience
MUST WATCH
Latest Additions
Priyanka Gandhi questions govt under Cong’s media campaign for LS polls
Delhi under constitutional crisis, Kejriwal should quit if he has scant regard for people: BJP
Fare of shared cabs on Pune, Nashik and Shirdi routes from Mumbai hiked
Cong’s D K Suresh, only incumbent MP from Karnataka, files nomination from Bangalore Rural
Sena (UBT) firm on contesting from Sangli, nobody should do anything that will help BJP: Raut