The EMIA PROJECT Epi-terrestrial Multi-modals Input Assimilation
Extreme weather is an escalating urban issue while hundreds to thousands of screens showing traffic congestion with streams of pedestrians sprawling across. Can a smart city system flexibly react to every unique population and deal with impending urban flash floods?
The missing keys are:
- knowing what happens on every road between the screens
- how to make all these data relevant to human urban activity, habitat and climate change,
- synchronize the data as intrinsically as hundreds of thousands of traffic coordinators coordinating in unison on every road, under rain sunshine or even flooding
The EMIA project EMIA is designed to do that. It is an extension from an AI forecasting urban flooding residing within a revolutionary superconstruct (AIMU). AIMU assimilates digital twin and makes it legible to AI, while staying geo-topologically accurate and relevant.
Unlike conventional machine learning algorithms in traffic CCTV, EMIA proposes a refocus of implementing road safety standards by extracting human centric parameters from existing traffic CCTV, as well as extending the reach of information by incorporating and analyzing video footage transmitted from enrolled dashcams among frequent road users. The source of the footage will be anonymized, and any unsuitable footage will be automatically deleted prior to transmission. In addition, EMIA proposes Ai conversion of existing LIDAR points cloud data of Singapore and Virtual Singapore into a High-Definition structure that can be interactive with humans and Ai within the AIMU. This new approach enables faster conversion and easier automatic assimilation and computation of change in urban infrastructure, coastal erosion, traffic diversion and evacuation in a flooding disaster especially in cities susceptible to climate change. Finally, EMIA will mesh the traffic Big Data in the AIMU superconstruct for synchronization and data interaction so that this new form of city Ai will be useful for semi-supervised computation for optimized traffic. These efforts contribute to 6 of 17 United Nation Sustainable Development Goals.
Interactive Coventry – UK
Interactive Coventry Ltd provides solutions for reducing the complexity and cognitive burden on accessing and processing large volumes of data, through the development of embedded hardware and software data analytics applications. The company specializes in smart city applications, machine learning and computer vision algorithms.
Citymatrix Pte Ltd – Singapore
Citymatrix Pte Ltd, Singapore is a newly established entity in Singapore with its technical and administrative staffs from Pentalight Technology Sdn Bhd (PLT) and Metrobinaya Sdn Bhd (METRO), Malaysia. CM is tasked to conduct research & development on AIMU and FLUD by recruiting local Singaporean talents with higher academic caliber, as well as offering sales and consultation for potential clients.
The project is supported by:
PLT- Pentalight Technology Sdn Bhd – Malaysia
PLT is a certified energy service provider and one of highest-grade construction contractor and has been the leader in advanced city scale energy management. PLT has developed AIMU.
METRO – Metrobinaya Sdn Bhd – Malaysia
Metro collaborated with IC in FLUD (Mar 18 – Mar 20). FLUD has started its commercial construction In Seberang Perai covering 1000 acres of residential, commercial to medium industrial area.
Dr Faiyaz Doctor is Research Director of IC and an Assistant Professor at the University of Essex.
Dr Tomasz Maniak is a lead data scientist with a demonstrated history of working in computer software, big data analytics, machine learning and automotive industry.
Dr Charalampos Karyotis is an experienced researcher with hands on experience of proposing and implementing intelligent solutions in real-world problems.
Raymond Tang is Citymatrix CEO and will oversee all deployment and installation activities for EMIA in Singapore.
EMIA is a state-of-the-art weather aware smart city platform which relies on the following features in order to deliver its benefits:
- State of the art machine learning and data analytics
- Intelligent traffic optimization
- Advanced computer vision
- Robust hardware equipment and network design
- Friendly user-machine interfaces
- Large scale digitization
EMIA incorporates a number of innovations including:
1) State of the art machine learning and data analytics: EMIA utilizes state of the art computational intelligence techniques that are able to exploit data of high velocity in realtime. These techniques are able to deal with the inherent uncertainties and noise infected data obtained from the sensors.This technology is used for flood forecasting and computer vision purposes for IC and will form the computational backbone of EMIA’s AI modules. IC has patented this technology which is based on a novel biologically inspired universal generative modelling approach called Hierarchical Spatial-Temporal State Machine (Patent No: PCT/GB2017/051019). This technique is capable of modelling complex multi-dimensional data sources to find correlations between different inputs (spatial), and how those different inputs vary in time (temporal). This technique has been used successfully in challenging application areas, providing state of the art results (e.g. driver assist systems, trafffic management, and other smart city projects), and its deployment in this project is a very promising and offers a low risk approach to address the data analytics requirements of the project.
2) Intelligent traffic optimization: IC has developed high-tech solutions to deal with traffic congestion management and optimization. Our applications are capable of modelling and managing the traffic flows to reduce carbon footprint and promote sustainability.
3) Advanced computer vision: This technology enables our solution to efficiently monitor drainage capacity and water flow.
4) Robust hardware equipment and network design that supports real time machine learning tasks and data broadcasting. This equipment provides real-time forecasting tailored to the morphological and geographical features of the area of deployment.
5) Friendly user-machine interfaces. EMIA shall include both a VR environment for its operators as well as a visualization dashboard with advanced data analytics capabilities to explore historical data and statistics.
6) Large scale digitization. A Digital twin is as good as the accuracy and the gamut (resolution) of the construct. EMIA collects environmental and urban activity data including vegetation, facilities and topology. Additionally, we introduce the concept that these structures have to be interactive to AI and not just humans. Everything in our physical world and most of digital assets are transparent or non-existence to AI. As such, AI cannot provide any extra dimension and computational relation to data points. The system is as simple as achieving the fact that what we see, can now be seen by the AI. The human factor has to immersively link and be represented cybernetically to stroll and work within this functional digital twin. The super-construct is remote working ready and its functions are enhanced with higher bandwidth 4G, 5G or 6G etc. It is built to be compact and resilient in a natural disaster whereby the city landscape may has changed, and the swarm of automation can have a copy of this digital twin within their computational and navigational modelling.
Project Kick Off Meeting
The EMIA – Epi-terrestrial Multi-modal Input Assimilation Project is accepted for funding from Innovate UK and Singapore Enterprise and will commence on the 1st of November 2022. The project is expected to last 30 months and deliver a state-of-the-art weather aware smart city management platform.