The technology is thought to have particular promise for the rapidly growing wearable healthcare market – where energy consumption and security of data are both major issues.
Current gait recognition systems work by gathering motion and velocity information from accelerometers worn by the user. However, the relatively high power consumption of accelerometer sampling has made it challenging to adopt gait recognition for wearables.
What’s more, whilst kinetic energy harvesting systems have long been seen as an attractive alternative to batteries for some applications they typically only generate tens to hundreds of microwatts of electricity, which is nowhere near enough to power accelerometer sampling.
The proposed solution, developed by CSIRO’S data innovation research division Data61 dispenses with sensors altogether, and instead monitors the output voltages of a Kinetic Energy Harvester. According to a paper on the project, the output from this device, which uses the piezoelectric effect to translate a user’s motion into electrical energy, corresponds to the unique walking pattern of an individual. The resulting system is claimed to reduce energy consumption by almost 80 per cent.
To test how secure KEH gait authentication is, the researchers conducted a trial on 20 users. Data was collected from each user using two different settings from various environments. Users walked in several environments including indoor on carpet and outdoor on grass and asphalt terrains to capture natural gait changes over time and surfaces.
The trial showed that KEH-Gait can achieve an authentication accuracy of 95 per cent and reduce energy consumption by 78 per cent, compared to conventional accelerometer-based authentication techniques.
The KEH-Gait system was also tested against 'attackers' who attempted to imitate an individual's motions. The analysis found only 13 out of 100 imposter trials were wrongfully accepted by the system as genuine trials.
Group leader of the Networks Research Group at Data61 Prof Dali Kafaar said there were benefits to the KEH-Gait approach compared to passwords, pins, signatures and fingerprints.
"Firstly, it is convenient because as we walk around each day our gait can be sampled continuously and verified without us having to manually adjust anything," Prof Kafaar said.
"Secondly, it's more secure than passwords because the way we walk is difficult to mimic. Since the KEH-gait keeps authenticating the user continuously, it collects a significant amount of information about our movements, making it difficult to imitate or hack unlike guessing passwords or pin codes."
Commenting on the overall project Data61 researcher Sara Khalifa said: "By applying both techniques we have developed a way to achieve two goals at once - powering devices and the ability to verify a person's identity using a wearable device by capturing the energy generated from the way they walk."
As well as KEH-Gait sampling, Data61 is exploring other authentication techniques such as unique breathing patterns and distinctive behavioural biometrics from the way users innately interact with their devices.