Japanese IT giant NEC has collaborated with the Singapore public transport provider SMRT Corporation to prevent bus accidents using AI technology. NEC Asia Pacific vice president Mervyn Cheah, speaking at the Tech Leaders Forum on Monday, told the firm had been involved with various projects based on artificial intelligence, and one of them revolved around habits of the bus drivers.

The company will predict whether a bus is likely to cause an accident in the next three months or so by collecting and analyzing data which includes historical records of the bus driver, telematics data of each bus, and onboard data scientists. If the prediction is affirmative, they can preempt that be simply sending the respective driver for training. This will facilitate the prevention of accidents that could possibly prove to be fatal and life threatening.

Mervyn said they have conducted a successful trial with SMRT and further explained that buses could be fitted with cameras for biometric analysis. This is a cost the bus company doesn’t wish to outlay, so even when during the trial two data scientists were employed to study a bus driver’s behavior. He was quoted saying,

Singapore is growing to be 5.7 million now, It’s going to be 7 million in the next decade, so we believe that traffic management will be a big thing. It might be the same in Sydney as well.

The buses are equipped with eco-drive sensors that track and analyze driving behavior, which are further connected with illuminating indicators which light up as and when a disparity occurs such as speeding for a longer time, abrupt lane change, sudden acceleration or deceleration, etc., thereby giving visual cues to drivers to adjust their speeds accordingly.

However, Cheah believes it is not ideal to completely rely on telematics information and hence human observation is also prominent. This can be attributed to the fact as the expert can study how a bus driver balances the controls required to steer the bus against passenger interaction.

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.