Skip to main content

Research Repository

Advanced Search

All Outputs (113)

A faster learning neural network classifier using selective backpropagation (1997)
Presentation / Conference Contribution
Craven, M. P. A faster learning neural network classifier using selective backpropagation. Presented at Fourth IEEE International Conference on Electronics, Circuits and Systems

The problem of saturation in neural network classification problems is discussed. The listprop algorithm is presented which reduces saturation and dramatically increases the rate of convergence.

The technique uses selective application of the bac... Read More about A faster learning neural network classifier using selective backpropagation.

Shape recognition using a novel fractal technique (1996)
Presentation / Conference Contribution
Neil, G., Curtis, K. M., & Craven, M. (1996, October). Shape recognition using a novel fractal technique. Presented at Third IEEE International Conference on Electronics, Circuits, and Systems, Rhodes, Greece

Fractal transformations are an exciting new scale invariant shape recognition technique developed by the authors. They have been successfully used for spatially invariant shape recognition using a cumbersome rotational invariance algorithm. Within th... Read More about Shape recognition using a novel fractal technique.

Consideration of multiplexing in neural network hardware (1994)
Journal Article
Craven, M., Curtis, K., & Hayes-Gill, B. (1994). Consideration of multiplexing in neural network hardware. IEE Proceedings Circuits Devices and Systems, 141(3), 237-240. https://doi.org/10.1049/ip-cds%3A19941103

This paper presents the results of research into a scheme for overcoming the communications 'bottleneck' within hardware neural networks, utilising frequency division multiplexing of amplitude modulated neural signals. The introduction explains the p... Read More about Consideration of multiplexing in neural network hardware.

Two quadrant analogue squarer circuit based on MOS square-law characteristic (1991)
Journal Article
Craven, M., & Hayes-Gill, B. (1991). Two quadrant analogue squarer circuit based on MOS square-law characteristic. Electronics Letters, 27(25), 2307–2308. https://doi.org/10.1049/el%3A19911429

A novel analogue CMOS circuit is presented which performs the arithmetical squaring of a voltage, using the square-law characteristic of the MOS transistor in saturation. The core circuit is constructed from four identical building blocks, which are... Read More about Two quadrant analogue squarer circuit based on MOS square-law characteristic.

Frequency division multiplexing in analogue neural network (1991)
Journal Article
Hayes-Gill, B., & Craven, M. (1991). Frequency division multiplexing in analogue neural network. Electronics Letters, 27(11), 918-920. https://doi.org/10.1049/el%3A19910575

Frequency division multiplexing has been studied as a means of communication between neural layers in an analogue multilayered perceptron neural network architecture, trained using the back-propagation learning algorithm. Simulation results on networ... Read More about Frequency division multiplexing in analogue neural network.

From SnappyApp to Screens in the Wild: gamifying an Attention Hyperactivity Deficit Disorder continuous performance test for public engagement and awareness
Book Chapter
Craven, M. P., Young, Z., Simons, L., Schnädelbach, H., & Gillott, A. From SnappyApp to Screens in the Wild: gamifying an Attention Hyperactivity Deficit Disorder continuous performance test for public engagement and awareness. In 2014 International Conference on Interactive Technologies and Games, ITAG 2014: 16-17 October 2014, Nottingham, Nottinghamshire, United Kingdom. IEEE. https://doi.org/10.1109/iTAG.2014.12

Attention Deficit Hyperactivity Disorder (ADHD) is a neurodevelopmental condition that is characterised by three core behaviours: inattention, hyperactivity and impulsivity. It is typically thought that around 3-5% of school aged children have ADHD,... Read More about From SnappyApp to Screens in the Wild: gamifying an Attention Hyperactivity Deficit Disorder continuous performance test for public engagement and awareness.

Factors influencing wider acceptance of Computer Assisted Orthopaedic Surgery (CAOS) technologies for Total Joint Arthroplasty
Report
Craven, M. P., Davey, S. M., & Martin, J. L. Factors influencing wider acceptance of Computer Assisted Orthopaedic Surgery (CAOS) technologies for Total Joint Arthroplasty

Computer-assisted orthopaedic surgery (CAOS) promises to improve outcomes of joint arthroplasty through better alignment and orientation of implants, but take up has so far been modest. Following an overview of CAOS technologies covering image-guided... Read More about Factors influencing wider acceptance of Computer Assisted Orthopaedic Surgery (CAOS) technologies for Total Joint Arthroplasty.

How does the healthcare industry involve users in medical device development? Pointers for UbiHealth
Presentation / Conference Contribution
Craven, M. P., & Martin, J. L. How does the healthcare industry involve users in medical device development? Pointers for UbiHealth. Presented at UbiHealth 2004: 3rd International Workshop on Ubiquitous Computing for Pervasive Healthcare Applications

This paper introduces the Multidisciplinary Assessment of Technology Centre for Healthcare (MATCH) and outlines the problem of integrating a user-centred approach for development of medical devices together with the information and communication tech... Read More about How does the healthcare industry involve users in medical device development? Pointers for UbiHealth.

A hybrid neural network/rule-based technique for on-line gesture and hand-written character recognition
Presentation / Conference Contribution
Craven, M. P., Curtis, K. M., Hayes-Gill, B. H., & Thursfield, C. A hybrid neural network/rule-based technique for on-line gesture and hand-written character recognition. Presented at Proceedings of the Fourth IEEE International Conference on Electronics, Circuits and Systems

A technique is presented which combines rule-based and neural network pattern recognition methods in an integrated system in order to perform learning and recognition of hand-written characters and gestures in realtime.

The GesRec system is introd... Read More about A hybrid neural network/rule-based technique for on-line gesture and hand-written character recognition.

Multiple channel crosstalk removal using limited connectivity neural networks
Presentation / Conference Contribution
Craven, M. P., Curtis, K. M., & Hayes-Gill, B. R. Multiple channel crosstalk removal using limited connectivity neural networks. Presented at 3rd IEEE International Conference on Electronics, Circuits, and Systems (ICECS 96)

Limited connectivity neural network architectures are investigated for the removal of crosstalk in systems using mutually overlapping sub-channels for the communication of multiple signals, either analogue or digital. The crosstalk error is modelled... Read More about Multiple channel crosstalk removal using limited connectivity neural networks.