Sensor systems need to be able to sustain operations for long periods of time (years) and be reliable in harsh and often remote environments, e.g. bridges, deep in forests, along vast border areas [1]. This PhD project will innovate in engineering a ‘smart’ sensor system which is highly reliable in facilitating an intelligent ‘always-on’ sensing capability; it will enable a new generation of smart always-sensing systems.
The project aims to:
(1) demonstrate the autonomous detection and prediction of events e.g. environment/structure anomalies, using leading edge brain-inspired computational algorithms such as astrocyte-neuron networks [2]; and
(2) demonstrate high reliability capabilities of the computational algorithms in FPGA hardware [3].
Therefore, the aim is to develop a highly novel system architecture that is ‘smart’ in processing sensory information, and self-adaptable to errors/faults over long time scales (years). Fundamentally, the research aims to prototype a smart sensor system, which integrates a novel, neural FPGA-based processor with existing sensors.
The core objectives are defined as:
1. Investigate an astrocyte-neuron network (smart algorithm) which performs detection and prediction of environment/structure anomalies.
2. Benchmark the ‘smart’ algorithm performance against traditional approaches [4-6].
3. Use existing hardware blocks [3] to implement the smart algorithm in FPGAs.
4. Develop an FPGA hardware demonstrator of always-on smart sensor system, evaluate it and benchmark hardware reliability.
The successful student will be located at the Intelligent Systems Research Centre on the Magee campus of the Ulster University and undertake research visits to Letterkenny Institute of Technology (Dr. Furey) to explore sensor data analysis using traditional approaches.
Anticipated Outcomes
The anticipated outcome of the project will be a new scalable solution to self-repair in future computing systems. A highly novel self-repairing embedded hardware architecture will be developed with wide impact on the Electronic Systems research community. Also, several published conference and journal papers on the performance of the proposed mechanisms.
Resources
Access to modern Altera FPGAs and a large suite of Agilent logic analyser/oscilloscope instrumentation; existing in-house FPGA-based astrocyte-neurons [3] available; data and tools on astrocyte-neuron network modelling; and access to real-world sensor data from forest fires.
References
[1] Yu L. et al. “Real-Time Forest Fire Detection with Wireless Sensor Networks,” IEEE International Conference on Wireless Communications, Networking and Mobile Computing, pp. 1214–1217, 2015.
[2] Naeem M et al. “On The Role of Astroglial Syncytia in Self-Repairing Spiking Neural Networks”, IEEE Trans. Neural Net. & Learning Systems, 2015.
[3] Liu J et al. "Self-Repairing Mobile Robotic Car using Astrocyte-Neuron Networks", IEEE International Joint Conference on Neural Networks, 2016.
[4] Li X. et al. “Forest Fire Smoke Detection Using Back-Propagation Neural Network Based on MODIS Data”; Remote Sensing, 7(4), pp.4473-98, 2015.
[5] Moavenia B. et al.; "Damage identification study of a seven-story full-scale building slice tested on the UCSD-NEES shake table", Structural Safety, 32(2) issue 5, Sept. 2010, pp. 347-356.
[6] S. Wu et al.; "Using Popular Object Detection Methods for Real Time Forest Fire Detection," International Symposium on Computational Intelligence and Design, pp.280-284, 2018.
Applicants should hold, or expect to obtain, a First or Upper Second Class Honours Degree in a subject relevant to the proposed area of study.
We may also consider applications from those who hold equivalent qualifications, for example, a Lower Second Class Honours Degree plus a Master’s Degree with Distinction.
In exceptional circumstances, the University may consider a portfolio of evidence from applicants who have appropriate professional experience which is equivalent to the learning outcomes of an Honours degree in lieu of academic qualifications.
If the University receives a large number of applicants for the project, the following desirable criteria may be applied to shortlist applicants for interview.
The University offers the following levels of support:
The following scholarship options are available to applicants worldwide:
These scholarships will cover full-time PhD tuition fees for three years (subject to satisfactory academic performance) and will provide a £900 per annum research training support grant (RTSG) to help support the PhD researcher.
Applicants who already hold a doctoral degree or who have been registered on a programme of research leading to the award of a doctoral degree on a full-time basis for more than one year (or part-time equivalent) are NOT eligible to apply for an award.
Please note: you will automatically be entered into the competition for the Full Award, unless you state otherwise in your application.
The scholarship will cover tuition fees at the Home rate and a maintenance allowance of £19,000 (tbc) per annum for three years (subject to satisfactory academic performance).
This scholarship also comes with £900 per annum for three years as a research training support grant (RTSG) allocation to help support the PhD researcher.
Due consideration should be given to financing your studies. Further information on cost of living
Submission deadline
Friday 7 February 2020
12:00AM
Interview Date
23 to 24 March 2020
Preferred student start date
Mid September 2020
Telephone
Contact by phone
Email
Contact by email