FIDO technology and roadmap

Home > FIDO AI > Technology

Our technology

FIDO is a constantly evolving advanced water leak detection AI technology which predicts leak probability and leak size to more than 92% accuracy. Jump to technical roadmap.

The FIDO algorithm

At the heart of our technology lies FIDO AI, our patented hybrid deep-learning multi-tiered algorithm.

The algorithm analyses the vibrational frequencies and wave functions of any audio and kinetic file in a multitude of discreet and distinct ways. It filters out extraneous data and is unaffected by background noise or pipe material.

Files from any client asset such as sensors, third party apps or FIDO’s own smartphone app are automatically uploaded to the FIDO platform for analysis.

Client data is accessed via secure data exchange and not held by FIDO Tech.

Our technology is an implementation of scientist Neil Edward’s work on differential analysis and machine learning.

Deep learning based on verified truths

FIDO instantly compares new files against more than 2 million verified leak and non-leak samples in its library. It is the largest library of leakage data in the world, and growing.

First, it decides if the file it’s analysing is a leak, then it calculates its likely size relative to a baseline.

Fully hardware agnostic, FIDO can work with data from any 3rd party sensor and can incorporate other available utility company data points such as flow, pressure and leak resolution information.

Once verified, data gathered further adds to its deep learning knowledge and improves accuracy.

FIDO is compliant with industry data sharing protocols because it processes and learns remotely.

Constantly evolving to meet new challenges

As FIDO acquires more and more real fix data, the machine-learning algorithm is improving and re-applying old data to look for other data patterns. Replace with “complex and multi faceted data associations and relationships”

Leak-sizing is an example of this. As FIDO gathers and verifies relevant vibrational signatures with flow data, the accuracy and precision of the leak size results will improve to the point that absolute leak volume/hour prediction will be possible for each leak sound.

We’re also developing the application of specific waveform analysis to narrow leak location to a single defined point between sensor locations.

Technical roadmap

Quarterly software updates go through extensive offline concept testing and development before being made available to clients during beta testing as a release candidate on the platform.

At release candidate stage, FIDO uses real data to rapidly learn and improve the accuracy of new functions before they go live.

The architecture diagram below shows how all the software and hardware components in the FIDO solution interact with each other and customer platforms.

All current major FIDO releases and release candidates

Items are listed oldest to newest.

  • FIDO AI
    • Status: LIVE
    • Description: Deep-learning algorithm with leak probability of more than 92% accuracy
  • Leak-sizing
    • Status: LIVE
    • Description: FIDO AI software update to allow leaks to be ranked by volumetric size, includes identification of pipe material
  • FIDO Bug
    • Status: LIVE
    • Description: Our next generation mobile multi-use sensor device with digital microphone and half-AA batteries for longer operational life
  • FIDO Sweep
    • Status: LIVE
    • Description: FIDO AI software update to allow mobile end-to-end leak detection process for non-sensor areas
  • FIDO Leak Central
    • Status: Release candidate
    • Description: Due for go-live in July 2021. FIDO AI software update to allow next generation performance metrics and leakage trend-spotting