Melbourne, Nov 25 (ANI): Finding it hard to count the number of sets and reps you did while lifting weights? Then kiss your problem good bye, for a new technique helps you to recognise what type of exercise you are doing and how many repetitions have you completed.

The revolutionary technique, designed by Keng-hao Chang, a graduate student of computer science at the University of California, Berkeley and team, uses sensor-embedded gloves and a waistband designed to help make the findings.

In the initial tests of the system, the sensors were 85-95 percent accurate in recognising the exercise being performed. And out of 100 repetitions, the system miscounted by fewer than five.

"People can use this to share their progress with others. They can share their secret and how they do their exercise," News in Science quoted Chang, as saying.

Dr Jamie Ward, a researcher of human activity recognition at the UK's Lancaster University said that the application is very interesting.

"The application itself is very interesting," Ward said.

The system is tied with an online community of exercisers and could lead to a new kind of digital personal trainer that gives real-time tips or warnings on form and posture.

It would also connect people with others to help achieve their goals.

Workout gloves are fixed with wireless sensors called accelerometers, which track motion in three directions: side to side, up and down, and front and back.

The data collected is sent via a wireless connection to a computer, where custom software analyses the information to distinguish a bicep curl from a tricep curl.

Also, another accelerometer on the belt tracks motions in three axes to distinguish whether the exerciser is standing or lying on a bench. This information is helpful because the motion of some exercises - for example a bench press, which works the chest, and the movement of an overhead dumbbell press, which works the shoulders - are quite similar.

However, Ward said that there are number so challenges in front of the system.

"I believe you could make a product out of it. [But] there are a number challenges to overcome first,” Ward said.

For example, the sensors need battery power.

"It would be nice if the devices could be powered just from the movements themselves," Ward said.

"Wristwatches can do that but they use a very small amount of power, and accelerometers use more power,” he added.

There is also the issue of privacy.

"If the environment is smart so that the objects are monitoring you, it obviously raises some privacy issues," said Ward. (ANI)