Graham McNeill PhD

Graham McNeill


Publications:
2013
  Breastfeeding and introduction of complementary foods during infancy in relation to the risk of asthma and atopic diseases up to 10 years
Nwaru, BI, Craig, LCA, Allan, K, Prabhu, N, Turner, SW, McNeill, G, Erkkola, M, Seaton, A & Devereux, G 2013, 'Breastfeeding and introduction of complementary foods during infancy in relation to the risk of asthma and atopic diseases up to 10 years' Clinical and Experimental Allergy, vol 43, no. 11, pp. 1263-73. DOI: 10.1111/cea.12180

BACKGROUND: It has been hypothesized that changes in diet during early life may have contributed to the increase in childhood asthma and atopy. The long-term effect of the timing and content of infant feeding on the incidence of asthma and atopic diseases in children is unclear.

OBJECTIVE: To investigate the associations between duration of breastfeeding and the timing of introduction of complementary foods during the first 6 months and parental-reported asthma, wheeze and atopic eczema up to 10 years of age.

METHODS: Infant feeding practices (breastfeeding and introduction of complementary foods) of 1924 singleton children participating in the Study of Eczema and Asthma To Observe the influence of Nutrition (SEATON) birth cohort were prospectively collected up to 6 months with outcomes (wheeze, atopic eczema and asthma) being assessed at 1, 2, 5 and 10 years. Data were analysed using generalized estimating equations and discrete hazards models with adjustment for confounders.

RESULTS: By 6 months, 59% and 35% of mothers had stopped exclusive and total breastfeeding, respectively. Although formula feeding was adversely associated with wheeze in the past 12 months (adjusted OR for no formula feeding: 070, 95% CI 0.50-0.97), and the introduction of biscuits/bread after 5 months of age adversely associated with atopic eczema (adjusted OR 1.34, 95% CI 1.06-1.69), these results lost their statistical significance after adjustment for multiple testing. Stratification of the results by the presence of eczema by 6 months of age and family atopic history did not substantially differ from the results of the whole study population.

CONCLUSION AND CLINICAL RELEVANCE: Our results suggest that the nature of infant feeding during the first 6 months seems not to substantially influence the long-term risk of asthma and atopic diseases in children, nor in children at high risk of atopic disease because of a family history of atopic disease.


General Information
Organisations: Deanery of Molecular, Genetic and Population Health Sciences.
Authors: Nwaru, B I, Craig, L C A, Allan, K, Prabhu, N, Turner, S W, McNeill, G, Erkkola, M, Seaton, A & Devereux, G.
Keywords: (Age Factors, Asthma, Breast Feeding, Child, Child, Preschool, Dermatitis, Atopic, Female, Follow-Up Studies, Humans, Hypersensitivity, Immediate, Infant, Infant Nutritional Physiological Phenomena, Male, Respiratory Sounds, Risk Factors. )
Number of pages: 11
Pages: 1263-73
Publication Date: Nov 2013
Publication Information
Category: Article
Journal: Clinical and Experimental Allergy
Volume: 43
Issue number: 11
ISSN: 0954-7894
Original Language: English
DOIs: 10.1111/cea.12180
2007
  Linear and nonlinear generative probabilistic class models for shape contours
McNeill, G & Vijayakumar, S 2007, Linear and nonlinear generative probabilistic class models for shape contours. in Proceedings of the 24th international conference on Machine learning. ACM, pp. 617-624. DOI: 10.1145/1273496.1273574
We introduce a robust probabilistic approach to modeling shape contours based on a low-dimensional, nonlinear latent variable model. In contrast to existing techniques that use objective functions in data space without explicit noise models, we are able to extract complex shape variation from noisy data. Most approaches to learning shape models slide observed data points around fixed contours and hence, require a correctly labeled 'reference shape' to prevent degenerate solutions. In our method, unobserved curves are reparameterized to explain the fixed data points, so this problem does not arise. The proposed algorithms are suitable for use with arbitrary basis functions and are applicable to both open and closed shapes; their effectiveness is demonstrated through illustrative examples, quantitative assessment on benchmark data sets and a visualization task.
General Information
Organisations: Institute of Perception, Action and Behaviour .
Authors: McNeill, Graham & Vijayakumar, S..
Number of pages: 8
Pages: 617-624
Publication Date: 2007
Publication Information
Category: Conference contribution
Original Language: English
DOIs: 10.1145/1273496.1273574
2006
  Hierarchical procrustes matching for shape retrieval
McNeill, G & Vijayakumar, S 2006, Hierarchical procrustes matching for shape retrieval. in Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on. vol. 1, pp. 885-894. DOI: 10.1109/CVPR.2006.133
We introduce Hierarchical Procrustes Matching (HPM), a segment-based shape matching algorithm which avoids problems associated with purely global or local methods and performs well on benchmark shape retrieval tests. The simplicity of the shape representation leads to a powerful matching algorithm which incorporates intuitive ideas about the perceptual nature of shape while being computationally efficient. This includes the ability to match similar parts even when they occur at different scales or positions. While comparison of multiscale shape representations is typically based on specific features, HPM avoids the need to extract such features. The hierarchical structure of the algorithm captures the appealing notion that matching should proceed in a global to local direction.
General Information
Organisations: Institute of Perception, Action and Behaviour .
Authors: McNeill, Graham & Vijayakumar, S..
Number of pages: 10
Pages: 885-894
Publication Date: 2006
Publication Information
Category: Conference contribution
Original Language: English
DOIs: 10.1109/CVPR.2006.133
  Part-based probabilistic point matching
McNeill, G & Vijayakumar, S 2006, Part-based probabilistic point matching. in Pattern Recognition, 2006. ICPR 2006. 18th International Conference on. vol. 2, IEEE, pp. 382-386. DOI: 10.1109/ICPR.2006.916
We present a probabilistic technique for matching partbased shapes. Shapes are represented by unlabeled point sets, so discontinuous boundaries and non-boundary points do not pose a problem. Occlusions and significant dissimilarities between shapes are explained by a 'background model' and hence, their impact on the overall match is limited. Using a part-based model, we can successfully match shapes which differ as a result of independent part transformations a form of variation common amongst real objects of the same class. A greedy algorithm that learns the parts sequentially can be used to estimate the number of parts and the initial parameters for the main algorithm.
General Information
Organisations: Institute of Perception, Action and Behaviour .
Authors: McNeill, Graham & Vijayakumar, S..
Number of pages: 5
Pages: 382-386
Publication Date: 2006
Publication Information
Category: Conference contribution
Original Language: English
DOIs: 10.1109/ICPR.2006.916
  A probabilistic approach to robust shape matching
McNeill, G & Vijayakumar, S 2006, A probabilistic approach to robust shape matching. in Image Processing, 2006 IEEE International Conference on. pp. 937-940. DOI: 10.1109/ICIP.2006.312629
We present a probabilistic approach to shape matching that is invariant to rotation, translation and scaling. Shapes can be represented by unlabeled point sets, so discontinuous boundaries and non-boundary points do not pose a problem. Occlusion, significant dissimilarities between shapes and image clutter are explained by a background model, and hence, their impact on the overall match is limited. The ability to operate on incomplete shape representations and ignore part of the input means that, unlike many matching algorithms, our technique performs well on real images. We derive a continuous version of the model which can be used when the 'query shape' is more accurately described by a set of line segments-e.g. a boundary polygon or line drawing. The effectiveness of the algorithms is demonstrated using the benchmark MPEG-7 data set and real images
General Information
Organisations: Institute of Perception, Action and Behaviour .
Authors: McNeill, Graham & Vijayakumar, S..
Number of pages: 4
Pages: 937-940
Publication Date: 2006
Publication Information
Category: Conference contribution
Original Language: English
DOIs: 10.1109/ICIP.2006.312629
  Part-based probabilistic point matching using equivalence constraints
McNeill, G & Vijayakumar, S 2006, Part-based probabilistic point matching using equivalence constraints. in Proc. Advances in Neural Information Processing Systems (NIPS '06), Vancouver, Canada.
Correspondence algorithms typically struggle with shapes that display part-based
variation. We present a probabilistic approach that matches shapes using independent part transformations, where the parts themselves are learnt during matching. Ideas from semi-supervised learning are used to bias the algorithm towards finding ‘perceptually valid’ part structures. Shapes are represented by unlabeled point sets of arbitrary size and a background component is used to handle occlusion, local dissimilarity and clutter. Thus, unlike many shape matching techniques, our approach can be applied to shapes extracted from real images. Model parameters are estimated using an EM algorithm that alternates between finding a soft correspondence and computing the optimal part transformations using Procrustes analysis.
General Information
Organisations: Institute of Perception, Action and Behaviour .
Authors: McNeill, Graham & Vijayakumar, S..
Publication Date: 2006
Publication Information
Category: Conference contribution
Original Language: English
2005
  2D shape classification and retrieval
McNeill, G & Vijayakumar, S 2005, 2D shape classification and retrieval. in Proc. 19th. International Joint Conference on Artificial Intelligence (IJCAI '05), Edinburgh, UK.
We present a novel correspondence-based technique for efficient shape classification and retrieval. Shape boundaries are described by a set of (ad hoc) equally spaced points – avoiding the need to extract “landmark points”. By formulating the correspondence problem in terms of a simple generative model, we are able to efficiently compute matches that incorporate scale, translation, rotation and reflection invariance. A hierarchical scheme with likelihood cut-off provides additional speed-up. In contrast to many shape descriptors, the concept of a mean (prototype) shape follows naturally in this setting. This enables model based classification, greatly reducing the cost of the testing phase. Equal spacing of points can be defined in terms of either perimeter distance or radial angle. It is shown that combining the two leads to improved classification/retrieval performance.
General Information
Organisations: Institute of Perception, Action and Behaviour .
Authors: McNeill, Graham & Vijayakumar, S..
Number of pages: 6
Publication Date: 2005
Publication Information
Category: Conference contribution
Original Language: English

Projects:
Incorporating prior knowledge for inference (PhD)

Personal Website