Challenge
This project was a partnership between Internet of Things and network communications experts Technocomm Consulting Ltd and Kingston University (KU) London.
It sought to enhance air quality monitoring by developing and deploying cost-effective electrochemical air sensors integrated with advanced AI technology. This combination would deliver precise, real-time air quality readings at any location.
The objective of the project was to model the changes that occur in electrochemical sensors over time and under various environmental conditions, explicitly analysing response times, measurement drift, accuracy, and sensitivity and design a machine learning continuous compensation algorithm.
Outcome
Multiple sensors were placed alongside precision reference stations to collect data and environmental telemetry. This data was fed into advanced AI models to design predictive algorithms that adjust sensor readings in real time, ensuring ongoing accuracy throughout the sensors’ lifespan. The developed models were also applied retrospectively to enhance the accuracy of historical data.
The project team held weekly progress meetings, where the academic team and industry partner presented findings and discussed contingencies and future scopes of the projects. Technocomm credited the settings with keeping the team “focused and objective” and enabling them to “exemplify how true teamwork leads to success”.
The partnership achieved its scientific objectives through data collection, feature selection, model training, model evaluation and fine-tuning, and a model-based study on sensor behaviour. KU facilitated a meeting between Kingston Council and Technocomm, leading to the implementation of air-quality monitoring devices in two of the council’s major streets, providing valuable data for future research and demonstrating how the EnviroSense devices could be deployed at scale. Additional units have been deployed and started collecting data in Kuala Lumpur, Malaysia, in collaboration with a local university.
Ultimately, by improving Technocomm’s mobile sensing technology, the project provided rich, relevant, and accurate air quality data at street level in real time. This data has the potential to inform policy decisions and enable emergency measures at local levels, thereby directly contributing to public health protection.
Impact
The successful completion of this project laid a strong foundation for advancing the adoption of air-quality monitoring networks at local, national, and international levels.
The future of this partnership has the potential to generate intellectual property that contributes to societal well-being and economic value by revolutionising air-quality monitoring and traffic management.
It has opened avenues to apply for additional funding, such as the Innovate UK Smart Grant and the London Government’s Local Council grant. This Innovate UK – Accelerated Knowledge Transfer (AKT) pilot project established a foundation for scaling and enhancing air-quality monitoring technology.
Additional funding would enable broader adoption by improving accuracy, affordability and accessibility, expanding networks to diverse regions, advancing data analytics with machine learning, and integrating real-time traffic management for actionable insights.
It would also improve the machine learning algorithms, and the accuracy and lifetime of the sensors used, as well as enable better visualisation of the live data with analytical tools.
What they say
“This AKT project has been a fantastic opportunity to transfer our academic knowledge to a company addressing a real-world, significant, and timely challenge. Additionally, our collaboration with Technocomm has provided valuable insights into the specific needs of the industry, which will directly enhance our students' learning experience.”
“Our innovative AI-powered sensors transform air-quality monitoring, making it more accurate and accessible than ever. This collaboration not only addressed a critical public health challenge but also set the stage for future advancements and impactful partnerships.”
"EnviroSense AI is still learning and improving, benefiting from the upgradable machine learning algorithms as more data is collected in real-time from multiple sources.”