Search

Your search keyword '"Lyons, T. J."' showing total 379 results
Start Over Author "Lyons, T. J."
379 results on '"Lyons, T. J."'

1. Using path signatures to predict a diagnosis of Alzheimer's disease

Author

Moore, P. J., Gallacher, J., and Lyons, T. J.

Subjects
Quantitative Biology - Quantitative Methods, Statistics - Applications, 62J12, 92D30
Abstract

The path signature is a means of feature generation that can encode nonlinear interactions in the data as well as the usual linear features. It can distinguish the ordering of time-sequenced changes: for example whether or not the hippocampus shrinks fast, then slowly or the converse. It provides interpretable features and its output is a fixed length vector irrespective of the number of input points so it can encode longitudinal data of varying length and with missing data points. In this paper we demonstrate the path signature in providing features to distinguish a set of people with Alzheimer's disease from a matched set of healthy individuals. The data used are volume measurements of the whole brain, ventricles and hippocampus from the Alzheimer's Disease Neuroimaging Initiative (ADNI). The path signature method is shown to be a useful tool for the processing of sequential data which is becoming increasingly available as monitoring technologies are applied., Comment: 5 pages, 3 figures. arXiv admin note: text overlap with arXiv:1808.03273

Published
2018
Full Text
View/download PDF

2. Application of the Signature Method to Pattern Recognition in the CEQUEL Clinical Trial

Author

Kormilitzin, A. B., Saunders, K. E. A., Harrison, P. J., Geddes, J. R., and Lyons, T. J.

Subjects
Statistics - Applications, Statistics - Machine Learning
Abstract

The classification procedure of streaming data usually requires various ad hoc methods or particular heuristic models. We explore a novel non-parametric and systematic approach to analysis of heterogeneous sequential data. We demonstrate an application of this method to classification of the delays in responding to the prompts, from subjects with bipolar disorder collected during a clinical trial, using both synthetic and real examples. We show how this method can provide a natural and systematic way to extract characteristic features from sequential data., Comment: 16 pages, 7 figures

Published
2016

34. The simulation of surface heat fluxes in a land surface-atmosphere model

Author

Huang, Xinmei and Lyons, T. J.

Subjects
Energy transfer -- Models, Water vapor, Atmospheric -- Research, Evapotranspiration -- Research, Soil temperature -- Research, Earth sciences
Abstract

A modified version of the soil-canopy-boundary layer model developed at Oregon State University may be used to recreate energy interactions between land and atmosphere. This model calculates the flow of water vapor to the atmosphere separately from soil and vegetation cover. Flow of heat from bare soil surface is correctly estimated by this model. The evapotranspiration level in dense vegetation cover is overestimated and the model does not take into account horizontal variations in soil, water transfer and variations in soil temperature.

Published
1995

38. Irish endocrine society: Proceedings of the Irish Endocrine Society, 14th annual meeting, Cork Regional Hospital, Cork, November 3rd’4th, 1989

Author

Walsh, C. H., Murphy, A. L., Cunningham, S., McKenna, T. J., Byrne, B., Igoe, D., Cunningham, S. K., Culliton, M., Igoe, D., Costigan, C., McKnight, J. A., McCance, D. R., Roberts, G., Sheridan, B., Atkinson, A. B., Lanigan, O., O’Leary, P., Moran, T., Smyth, P. P. A., Hadden, D. R., Atkinson, A. B., Kennedy, L., Foley-Nolan, D., Foley-Nolan, A., Temperley, D., Devlin, J., Bell, P. M., Neely, R. D. G., Rooney, D. P., Sheridan, B., Trimble, E. R., Rooney, D. P., Edgar, J. D. M., Sheridan, B., Doherty, R., Atkinsion, A. B., Bell, P. M., O’Hare, J. A., Rand, L., Krolewski, A., McKenna, C., McKieman, J., Whitehead, H. M., Buchanan, K., Fillmore, Davina, Ardill, Joy, Johnston, C., Robinson, Wendy, Hadden, D. R., Silvestri, G., Dunn, J. A., Dwyer, D. G., Baynes, J. W., Lyons, T. J., Owens, D., Stinson, J., Collins, P., Johnson, A., Tomkin, G., Smyth, P. P. A., Smith, D. F., O’Carroll, D., Murray, M., O’Higgins, N. J., Hetherton, A. M., McKenna, T. J., Counihan, T. B., Poole, D. B. R., O’Donovan, D. K., Grimes, H., and O’Donnell, J.

Published
1990
Full Text
View/download PDF

46. Using path signatures to predict a diagnosis of Alzheimer’s disease.

Author

Moore, P. J., Lyons, T. J., Gallacher, J., and null, null

Subjects
*ALZHEIMER'S disease, *HIPPOCAMPUS (Brain), *MILD cognitive impairment, *FEATURE selection, *DIAGNOSIS
Abstract

The path signature is a means of feature generation that can encode nonlinear interactions in data in addition to the usual linear terms. It provides interpretable features and its output is a fixed length vector irrespective of the number of input points or their sample times. In this paper we use the path signature to provide features for identifying people whose diagnosis subsequently converts to Alzheimer’s disease. In two separate classification tasks we distinguish converters from 1) healthy individuals, and 2) individuals with mild cognitive impairment. The data used are time-ordered measurements of the whole brain, ventricles and hippocampus from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). We find two nonlinear interactions which are predictive in both cases. The first interaction is change of hippocampal volume with time, and the second is a change of hippocampal volume relative to the volume of the whole brain. While hippocampal and brain volume changes are well known in Alzheimer’s disease, we demonstrate the power of the path signature in their identification and analysis without manual feature selection. Sequential data is becoming increasingly available as monitoring technology is applied, and the path signature method is shown to be a useful tool in the processing of this data. [ABSTRACT FROM AUTHOR]

Published
2019
Full Text
View/download PDF

47. Random forest prediction of Alzheimer’s disease using pairwise selection from time series data.

Author

Moore, P. J., Lyons, T. J., Gallacher, J., and null, null

Subjects
*ALZHEIMER'S disease, *BASAL ganglia diseases, *PRESENILE dementia, *SENILE dementia, *GENETICS of Alzheimer's disease
Abstract

Time-dependent data collected in studies of Alzheimer’s disease usually has missing and irregularly sampled data points. For this reason time series methods which assume regular sampling cannot be applied directly to the data without a pre-processing step. In this paper we use a random forest to learn the relationship between pairs of data points at different time separations. The input vector is a summary of the time series history and it includes both demographic and non-time varying variables such as genetic data. To test the method we use data from the TADPOLE grand challenge, an initiative which aims to predict the evolution of subjects at risk of Alzheimer’s disease using demographic, physical and cognitive input data. The task is to predict diagnosis, ADAS-13 score and normalised ventricles volume. While the competition proceeds, forecasting methods may be compared using a leaderboard dataset selected from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and with standard metrics for measuring accuracy. For diagnosis, we find an mAUC of 0.82, and a classification accuracy of 0.73 compared with a benchmark SVM predictor which gives mAUC = 0.62 and BCA = 0.52. The results show that the method is effective and comparable with other methods. [ABSTRACT FROM AUTHOR]

Published
2019
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results