Researchers say wireless access points could double as analysis tools that detect radio-frequency interference and automatically adjust to preserve the quality of Wi-Fi connections.

Such upgraded devices could eliminate the need for separate, costly spectrum analysers that discover interfering devices but do nothing to counter interference, say researchers at the University of Wisconsin.

The software, called Airshark, can identify Bluetooth and ZigBee devices, cordless phones, wireless video cameras and Xboxes with accuracy in the range of 91.23% and 100%, depending on signal strength.

Airshark taps into the application programming interface of wireless cards used on access points to gather data about radio frequencies in the surrounding environment. The software has been trained to recognise signatures of various devices, and can pick them out from the ambient radio noise with more than 90% accuracy even if signals from multiple such devices are present.

False positives were 0.39% for environments with four or more interfering devices and using various signal strengths. The researchers found the rate was 0.068% for signals stronger than -80dBm. "We also found its performance to be comparable to a commercial signal analyser," according to their research paper 'Airshark: Detecting Non-WiFi RF Devices using Commodity WiFi Hardware.'

The researchers say that with Airshark embedded in access points, the software could kick off interference-mitigation mechanisms. For example, if a connection between an access point and a client machine suffers from interference from an analog cordless phone, Airshark would detect it. With this information, the access point could invoke channel-width adaptation and broadcast on a narrower channel that doesn't overlap with the phone, researchers say.

An AP-client link experiences short-term interference from an analogue cordless phone in a narrowband (less than 1MHz). The AP detects the analogue phone and its characteristics, and hence decides to use channel width adaptation functions to operate on a narrower, non-overlapping 10MHz channel instead of the usual 20MHz channel.

In a Wi-Fi environment employing multiple access points Airshark could physically locate interfering devices by collaborating among the access points to triangulate on its signal, the researchers say.