Story image

Fujitsu develops automatic labelling technology to accelerate AI

13 May 2019

Fujitsu Laboratories and Kumamoto University have announced the development of technology to easily create the training data necessary to apply AI to time-series data, such as those from accelerometers and gyroscopic sensors.

Time-series data obtained from sensors do not include anything other than ever-changing numerical data. Therefore, in order to create training data for use in machine learning, it was necessary to manually attach finely detailed labels to the data in accordance to its changing values, indicating what was done and when at each point where the numerical values changed. For this reason, huge numbers of man-hours were required, and the use of AI with time-series data had seen limited progress.

Fujitsu Laboratories and Kumamoto University have supposedly enabled the automatic creation of highly accurate training data with appropriate labels for each action, just by manually attaching a single label to each longer time period, even if they include multiple actions, indicating the major action in that time period according to human judgement.

Because this significantly reduces the number of man-hours required, this technology will accelerate the use of AI with time-series data. The new development is expected to enable easier installation of services such as fall detection, operational functionality checks, and abnormality detection for machines, in smartphones and various other devices.

Development Background

In recent years, with the evolution of technology such as the Internet of Things (IoT), it has become possible to obtain a large amount of time-series data from a variety of sensors. For example, by developing functionality in which AI can determine the meaning of the motions of people and objects from the characteristics captured by accelerometers, it is expected that advanced functionality for monitoring people and machines can be incorporated into smartphones and various equipment. In order to apply AI to this sort of time-series data, it is necessary to create training data to train AI.

Effects

Fujitsu Laboratories and Kumamoto University conducted a trial where they attached labels to time-series data from accelerometers while performing mock work processes in a factory such as polishing. As a result, they confirmed that this technology was able to correctly label 92% of time periods.

They judged that this was equivalent to the highly accurate results obtained when using data that was manually labelled in detail as training data. With this technology, one can easily create training data for AI use from time-series data, and further development is expected for the functionality that uses AI to determine activities captured by sensors.

In addition, because this technology makes determinations based on just the numerical characteristics of time-series data, and does not rely on the type of sensor, it could also be applied to time-series data obtained from devices such as temperature sensors and pulse wave sensors.

What the future of fibre looks like in NZ
The Commerce Commission has released its emerging views paper on the rules, requirements and processes which will underpin the new regulatory regime for New Zealand’s fibre networks.
Gen Z confidence in the economy is on the decline
Businesses need to work hard to improve their reputations.
Why NZ businesses have less than two years to adopt digital before disruption hits
Research found that digital disruption is already impacting two-thirds of New Zealand organisations.
Dell EMC launches interactive AI Experience Zones
The AI Experience Zones are designed to educate visitors about how to start, identify, and implement an AI project.
What NZ can learn from the Baltimore cyberattack
“Businesses must control physical access to their computers and secure their networks."
Infratil seeks clearance to acquire up to 50% stake in Vodafone NZ
The commission will give clearance to a proposed merger if they are satisfied that the merger is unlikely to have the effect of substantially lessening competition in a market.
Hands-on review: MiniTool Power Data Recovery Software
I came across a wee gem of advice when researching the world of data recovery. As soon as you get that sinking feeling and realise you’ve lost a file, stop using your computer.
Deepfakes the 'next wave of concern' - but can law really stomp it out?
Enforcing the existing law will be difficult enough, and it is not clear that any new law would be able to do better. Overseas attempts to draft law for deepfakes have been seriously criticised.