Skip to main content
Most big cities struggle with traffic, especially during peak hours and congestions on roads in London is at an increasingly large number. On average, London copes with major congestions of approximately 30 million journeys daily, making it hard for cars to exit the city during peak hours. Predicting congestions is very important for traffic management, and real-time data are collected using sensors to control speed, times (arrival and departures), orientation, passenger count, fuel consumption. These sensors operate 24/7 with a 5-minute interval update of data collected and have become an essential part of the ecosystem in terms of reliability and availability in providing daily commuting information.
Using traditional methods to acquire, store, and integrate data from these sensors will not provide transport systems with scalable, adaptable, sustainable, extendable, and highly available network infrastructure. This research proposes an intelligent architecture system to manipulate and capture information using state-of-the-art machine learning and deep learning techniques. The study also aims to build a predictive data analysis model to support strategic decisions to help companies and transport managers optimise real-time transport information such as scheduling road works, passengers' time, and stops usage in a smart city like London.
As a software engineer accustomed to programming and developing applications; PR or self-promotion, unfortunately, is not my key strength especially this part where I am required to write about myself which as it happens is probably the most challenging. My background is mainly in Software Development. I became passionately engaged and interested in Software Development for over six years now and recently developed an interested in Artificial intelligence.