EPSRC logo

Details of Grant 

EPSRC Reference: EP/Y030133/1
Title: Edgy Organism
Principal Investigator: Trefzer, Dr M A
Other Investigators:
Gatsis, Dr K Gheorghiu, Dr E Perera, Dr C
Rhodes, Dr O
Researcher Co-Investigators:
Project Partners:
Department: Electronics
Organisation: University of York
Scheme: Standard Research - NR1
Starts: 01 July 2024 Ends: 31 December 2026 Value (£): 1,409,507
EPSRC Research Topic Classifications:
Software Engineering
EPSRC Industrial Sector Classifications:
No relevance to Underpinning Sectors
Related Grants:
Panel History:  
Summary on Grant Application Form
The Edgy Organism project aims to develop electronic surveillance systems capable of detecting and alerting anomalous behavior or identifying individuals who pose a threat in crowded public spaces. The challenge lies in creating systems that are minimally intrusive, operate with limited supervision and power, and can adapt in remote or unknown locations for extended periods. The project proposes integrating spiking neural network (SNN) technology into low-power neuromorphic hardware to achieve these goals.

SNN hardware, such as Intel Loihi and True North, has reached a stage of maturity where scalable building blocks of synapses and neurons are available. These devices can process data using sophisticated bio-inspired models. The goal of Edgy Organism is to combine and push the boundaries of these technologies to create a system that can detect, classify, and potentially predict anomalous patterns of life (PoL) by drawing analogies with the nervous system of biological organisms.

The project will demonstrate the capabilities of the Edgy Organism system through two real-world scenarios: Stand-off, which involves observing and processing patterns of life from a satellite, and Leave-behind, which entails covert surveillance in close proximity. The concept of Edgy Organism is based on leveraging the unique information processing capabilities of the human brain to make fast decisions with minimal computing power. This concept, known as neuromorphic engineering, combines neuroscience and neural network research to create adaptable systems that can operate effectively in dynamic environments while meeting low size, weight, and power requirements.

Despite the availability of low SWaP-capable neuromorphic devices like Intel Loihi, the field is still in its early stages and lacks scalability and adaptability for task-driven applications. The Edgy Organism project aims to fill this gap by developing a design methodology, neural network architecture, and low SWaP neuromorphic hardware implementation for autonomous monitoring and decision-making in uncertain environments.

The project will draw inspiration from the brain's processing and representation of data, targeting the Intel Loihi device for its efficiency in running complex SNNs. Principles from the visual cortex and the hippocampal-entorhinal grid-cell system will be used to create efficient neural encodings of PoL and build a high-dimensional cognitive map capable of representing and detecting anomalies. The efficiency, resilience, and security of these neural encodings will be evaluated in the Stand-off and Leave-behind scenarios.

Overall, the Edgy Organism project aims to revolutionize surveillance systems by leveraging spiking neural network technology and neuromorphic hardware to create autonomous, low-power, and efficient monitoring systems capable of detecting and reacting to anomalous behavior in various real-world scenarios.
Key Findings
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Potential use in non-academic contexts
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Impacts
Description This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Summary
Date Materialised
Sectors submitted by the Researcher
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Project URL:  
Further Information:  
Organisation Website: http://www.york.ac.uk