Breadcrumb Links
Local news
Published June 22, 2024 • Last updated 52 minutes ago • 3 minute read
To save this article, register for free here, or sign in if you have an account.
Merivale High School students Matthew Zou and Rohan Bahl have developed an AI-based computer program that takes into account past accident data to work out the safest route to school. Photo: Tony Caldwell/Postmedia
Article Contents
Two Merrivale High School students have designed a computer program that uses artificial intelligence to plan the safest travel routes for pedestrians and drivers based on Ottawa's historical accident data.
Rohan Bahl and Matthew Zou, both 16, have spent hundreds of hours developing the Traffic Helper app, which began as an end-of-year project for their 12th-grade computer science class and has grown into something much bigger.
Ad 2
This advertisement has not loaded yet, but article continues below.
This content is available to subscribers only
Subscribe now to read the latest news from your city and across Canada.
Exclusive articles from Elizabeth Payne, David Pugliese, Andrew Duffy, Bruce Deachman and more. Plus, our weekly newsletter, Ottawa, Out of Office, features food reviews and event listings. Get unlimited online access to the Ottawa Citizen and 15 news sites with one account. The Ottawa Citizen ePaper is a digital version of our print edition that you can view, share and comment on on any device. Daily puzzles, including the New York Times crossword. Support local journalism.
Subscribe to unlock more articles
Subscribe now to read the latest news from your city and across Canada.
Exclusive articles from Elizabeth Payne, David Pugliese, Andrew Duffy, Bruce Deachman and more. Plus, our weekly newsletter, Ottawa, Out of Office, features food reviews and event listings. Get unlimited online access to the Ottawa Citizen and 15 news sites with one account. The Ottawa Citizen ePaper is a digital version of our print edition that you can view, share and comment on on any device. Daily puzzles, including the New York Times crossword. Support local journalism.
Register/Sign in to view more articles
To continue reading, please create an account or sign in.
Access articles from across Canada with one account. Share your thoughts in the comments and join the conversation. Enjoy additional articles every month. Receive email updates from your favourite authors.
Sign in or create an account
or
Article Contents
“We wanted to take it to the next level,” said Bahr, who is in Year 11 with Zhou in the International Baccalaureate program at Merivale High School. “It took an incredible amount of time to create this.”
Bahr said the idea for the app was born in the aftermath of a nearby pedestrian accident: In October, a Merrivale student was seriously injured when he was struck by a van while crossing the intersection of Merrivale Road and Viewmount Drive.
“I was driven by a passion to prevent this from ever happening again,” Bahr said. “I wanted to create an application that would allow people to plan their own routes, taking into account not just time and distance, but safety as well. It would answer the question: 'How can I take the safest route?'”
Bahl and Zhou, friends since the early days of the IB program, decided to create a computer program that combined open-source data and artificial intelligence to optimize safe travel.
The project began with designing an algorithm to calculate the most efficient route based on time and distance, which the students then modified based on data from Open Ottawa, which provides a large dataset listing road accidents by location.
Ad 3
This advertisement has not loaded yet, but article continues below.
Article Contents
Students utilized machine learning models such as the OpenAI framework, Python TensorFlow, and Meta's PyTorch.
The open source map of Ottawa was powered by the JavaScript library Leaflet, and also used OSMnx, a Python tool that allowed them to model Ottawa's street network, as well as coding tools such as HTML, CSS, and JavaScript.
Zhou said the most challenging part of the project was ensuring the many elements worked seamlessly together.
“This took quite a while because there wasn't much information about the APIs (application programming interfaces) that link Python and JavaScript,” Zhou says, “but we eventually figured it out.”
The resulting app, Traffic Helper, allows users to customize their travel experience by setting separate values ​​for safety, time and distance, allowing users to prioritize safety wherever they need it.
“There's no other transportation application that optimizes for safety,” Bahr said. “Every other tool, like Google or Apple Maps, looks at the quickest route or the shortest distance.”
Ad 4
This advertisement has not loaded yet, but article continues below.
Article Contents
He said the app could also be used by urban planners to predict, for example, how adding traffic lights to a particular intersection would affect safety and traffic flow.
The app is publicly available on GitHub and is open source, and while the students don't plan to commercialize it, they hope others will help develop it so it can be used by people all over the world.
“This app is like the core, and we want other people to jump in and contribute and build on top of it so it can help more people,” Bahr said.
The app is currently limited to Ottawa, but Bahr said it could be expanded to other cities once more advanced computing power becomes available.
Bahr and Zhou, who plan careers in computer science or engineering, said they next want to develop online personal assistants tailored to the needs of elderly and disabled people.
Andrew Duffy is a National Newspaper Award-winning reporter and long-form feature writer based in Ottawa. To support his work, including subscriber-only content, sign up here: ottawacitizen.com/subscribe
Editor's recommendation
Bankrupt Chelsea Hillier ordered to pay damages in Twitter defamation lawsuit
One injured in overnight shooting
Article Contents
Share this article on social networks
