Topographic mappings and feed-forward neural networks

This thesis is a study of the generation of topographic mappings - dimension reducing transformations of data that preserve some element of geometric structure - with feed-forward neural networks. As an alternative to established methods, a transformational variant of Sammon's method is proposed, where the projection is effected by a radial basis function neural network. This approach is related to the statistical field of multidimensional scaling, and from that the concept of a 'subjective metric' is defined, which permits the exploitation of additional prior knowledge concerning the data in the mapping process. This then enables the generation of more appropriate feature spaces for the purposes of enhanced visualisation or subsequent classification. A comparison with established methods for feature extraction is given for data taken from the 1992 Research Assessment Exercise for higher educational institutions in the United Kingdom. This is a difficult high-dimensional dataset, and illustrates well the benefit of the new topographic technique. A generalisation of the proposed model is considered for implementation of the classical multidimensional scaling (¸mds}) routine. This is related to Oja's principal subspace neural network, whose learning rule is shown to descend the error surface of the proposed ¸mds model. Some of the technical issues concerning the design and training of topographic neural networks are investigated. It is shown that neural network models can be less sensitive to entrapment in the sub-optimal global minima that badly affect the standard Sammon algorithm, and tend to exhibit good generalisation as a result of implicit weight decay in the training process. It is further argued that for ideal structure retention, the network transformation should be perfectly smooth for all inter-data directions in input space. Finally, there is a critique of optimisation techniques for topographic mappings, and a new training algorithm is proposed. A convergence proof is given, and the method is shown to produce lower-error mappings more rapidly than previous algorithms.

Combining the wavelet transform and forecasting models to predict gas forward prices

This paper presents a forecasting technique for forward energy prices, one day ahead. This technique combines a wavelet transform and forecasting models such as multi- layer perceptron, linear regression or GARCH. These techniques are applied to real data from the UK gas markets to evaluate their performance. The results show that the forecasting accuracy is improved significantly by using the wavelet transform. The methodology can be also applied to forecasting market clearing prices and electricity/gas loads.

Effects of yellow filters on visual acuity, contrast sensitivity and reading under conditions of forward light scatter

Background Yellow filters are sometimes recommended to people with low vision. Our aim was investigate the effects of three commercial yellow filters on visual acuity and contrast sensitivity (with and without glare) and reading (without glare) under conditions of forward light scatter (FLS). Method Fifty-five healthy subjects were assessed with Corning Photochromic Filters (CPFs) 450, 511 and 527 and a filter producing FLS. The effects on log MAR visual acuity, Pelli–Robson contrast sensitivity with and without glare, and reading (measured with MNRead charts) without glare were determined. Results Statistically significant differences were found between the overall effect of glare and between CPFs for visual acuity and contrast sensitivity. A gradual decline in visual acuity, contrast sensitivity and reading with increasing CPF absorption was noted. Conclusion Effects of CPF450, 511, 527 on visual acuity, contrast sensitivity and reading under conditions of FLS were negative but not clinically significant.

Promoting scholarship - the way forward:learning and teaching research in a complex environment – a typology

Scholarship in learning and teaching.

Effect of a commercially available warm compress on eyelid temperature and tear film in healthy eyes

Purpose: To evaluate eyelid temperature change and short-term effects on tear film stability and lipid layer thickness in healthy patients using a commercially available warm compress (MGDRx EyeBag) for ophthalmic use. Methods: Eyelid temperature, noninvasive tear film breakup time (NITBUT), and tear film lipid layer thickness (TFLLT) of 22 healthy subjects were measured at baseline, immediately after, and 10 minutes after application of a heated eyebag for 5 minutes to one eye selected at random. A nonheated eyebag was applied to the contralateral eye as a control. Results: Eyelid temperatures, NITBUT, and TFLLT increased significantly from baseline in test eyes immediately after removal of the heated eyebag compared with those in control eyes (maximum temperature change, 2.3 +/- 1.2[degrees]C vs. 0.3 +/- 0.5[degrees]C, F = 20.533, p < 0.001; NITBUT change, 4.0 +/- 2.3 seconds vs. 0.4 +/- 1.7 seconds, p < 0.001; TFLLT change, 2.0 +/- 0.9 grades vs. 0.1 +/- 0.4 grades, Z = -4.035, p < 0.001). After 10 minutes, measurements remained significantly higher than those in controls (maximum temperature change, 1.0 +/- 0.7[degrees]C vs. 0.1 +/- 0.3[degrees]C, F = 14.247, p < 0.001; NITBUT change, 3.6 +/- 2.1 seconds vs. 0.1 +/- 1.9 seconds, p < 0.001; TFLLT change, 1.5 +/- 0.9 vs. 0.2 +/- 0.5 grades, Z = -3.835, p < 0.001). No adverse events occurred during the study. Conclusions: The MGDRx EyeBag is a simple device for heating the eyelids, resulting in increased NITBUT and TFLLT in subjects without meibomian gland dysfunction that seem to be clinically significant. Future studies are required to determine clinical efficacy and evaluate safety after long-term therapy in meibomian gland dysfunction patients. © 2013 American Academy of Optometry

Feed-forward neural networks and topographic mappings for exploratory data analysis

A recent novel approach to the visualisation and analysis of datasets, and one which is particularly applicable to those of a high dimension, is discussed in the context of real applications. A feed-forward neural network is utilised to effect a topographic, structure-preserving, dimension-reducing transformation of the data, with an additional facility to incorporate different degrees of associated subjective information. The properties of this transformation are illustrated on synthetic and real datasets, including the 1992 UK Research Assessment Exercise for funding in higher education. The method is compared and contrasted to established techniques for feature extraction, and related to topographic mappings, the Sammon projection and the statistical field of multidimensional scaling.

NITL : what the transport and logistics industry needs going forward

The transport industry - particularly in road transport - is under serious competitive pressure. Rising costs - evident but not limited to fuel and insurance - combined with a market place that has become more demanding in relation to price and service, has resulted in a situation where companies have had to seriously reassess the nature of their competitive advantage. The competitive strategies of companies in the sector are being reviewed in light of the effective commoditisation of transport as a direct result of the traditional strong emphasis on cost and price reductions.

Effect of a commercially available warm compress on eyelid temperature and tear film in healthy eyes

PURPOSE: To evaluate eyelid temperature change and short-term effects on tear film stability and lipid layer thickness in healthy patients using a commercially available warm compress (MGDRx EyeBag) for ophthalmic use. METHODS: Eyelid temperature, noninvasive tear film breakup time (NITBUT), and tear film lipid layer thickness (TFLLT) of 22 healthy subjects were measured at baseline, immediately after, and 10 minutes after application of a heated eyebag for 5 minutes to one eye selected at random. A nonheated eyebag was applied to the contralateral eye as a control. RESULTS: Eyelid temperatures, NITBUT, and TFLLT increased significantly from baseline in test eyes immediately after removal of the heated eyebag compared with those in control eyes (maximum temperature change, 2.3 ± 1.2 °C vs. 0.3 ± 0.5 °C, F = 20.533, p <0.001; NITBUT change, 4.0 ± 2.3 seconds vs. 0.4 ± 1.7 seconds, p <0.001; TFLLT change, 2.0 ± 0.9 grades vs. 0.1 ± 0.4 grades, Z = -4.035, p <0.001). After 10 minutes, measurements remained significantly higher than those in controls (maximum temperature change, 1.0 ± 0.7 °C vs. 0.1 ± 0.3 °C, F = 14.247, p <0.001; NITBUT change, 3.6 ± 2.1 seconds vs. 0.1 ± 1.9 seconds, p <0.001; TFLLT change, 1.5 ± 0.9 vs. 0.2 ± 0.5 grades, Z = -3.835, p <0.001). No adverse events occurred during the study. CONCLUSIONS: The MGDRx EyeBag is a simple device for heating the eyelids, resulting in increased NITBUT and TFLLT in subjects without meibomian gland dysfunction that seem to be clinically significant. Future studies are required to determine clinical efficacy and evaluate safety after long-term therapy in meibomian gland dysfunction patients. Copyright © 2014 American Academy of Optometry.

Putting children forward for epilepsy surgery:a qualitative study of UK parents' and health professionals' decision-making experiences

Background Against a backdrop of recommendations for increasing access to and uptake of early surgical intervention for children with medically intractable epilepsy, it is important to understand how parents and professionals decide to put children forward for epilepsy surgery and what their decisional support needs are. Aim The aim of this study was to explore how parents and health professionals make decisions regarding putting children forward for pediatric epilepsy surgery. Methods Individual interviews were conducted with nine parents of children who had undergone pediatric epilepsy surgery at a specialist children's hospital and ten healthcare professionals who made up the children's epilepsy surgery service multidisciplinary healthcare team (MDT). Three MDT meetings were also observed. Data were analyzed thematically. Findings Four themes were generated from analysis of interviews with parents: presentation of surgery as a treatment option, decision-making, looking back, and interventions. Three themes were generated from analysis of interviews/observations with health professionals: triangulating information, team working, and patient and family perspectives. Discussion Parents wanted more information and support in deciding to put their child forward for epilepsy surgery. They attempted to balance the potential benefits of surgery against any risks of harm. For health professionals, a multidisciplinary approach was seen as crucial to the decision-making process. Advocating for the family was perceived to be the responsibility of nonmedical professionals. Conclusion Decision-making can be supported by incorporating families into discussions regarding epilepsy surgery as a potential treatment option earlier in the process and by providing families with additional information and access to other parents with similar experiences.

Performance improvement of broadband distributed Raman amplifier using bidirectional pumping with first and dual order forward pumps

In this paper, a new bidirectional pumping scheme with dual order forward pumps is proposed. Performance is compared numerically with conventional bidirectional and backward only pumping schemes for a 70 nm bandwidth, 61.5 km distributed Raman amplifier. We demonstrate that it is possible to design a flat gain spectrum with improved noise figure and OSNR, as well as a low gain ripple (<1 dB).