Algorithms for Synthetic Aperture Radar Imagery XII, 2005
Addressing the challenge of robust ATR, this paper describes the development and demonstration of... more Addressing the challenge of robust ATR, this paper describes the development and demonstration of Machine Learning for Robust ATR. The primary innovation of this work is the development of an automated way of developing heuristic inference rules that can draw on multiple models and multiple feature types to make more robust ATR decisions. The key realization is that this meta learning problem is one of structural learning; that can be conducted independently of parameter learning associated with each model and feature based technique, and more effectively draw on the strengths of all such techniques, and even information from unforeseen techniques. This is accomplished by using robust, genetics-based machine learning for the ill conditioned combinatorial problem of structural rule learning, while using statistical and mathematical techniques for parameter learning. This paper describes a learning classifier system approach (with evolutionary computation for structural learning) for robust ATR and points to a promising solution to the structural learning problem, across multiple feature types (which we will refer to as the meta-learning problem), for ATR with EOCs. This system was tested on MSTAR Public Release SAR data using nominal and extended operation conditions. These results were also compared against two baseline classifiers, a PCA based distance classifier and a MSE classifier. The systems were evaluated for accuracy (via training set classification) and robustness (via testing set classification). In both cases, the LCS based robust ATR system performed very well with accuracy over 99% and robustness over 80%.
Attention deficit/hyperactivity disorder (ADHD) is an early-onset neurobehavioural disorder chara... more Attention deficit/hyperactivity disorder (ADHD) is an early-onset neurobehavioural disorder characterised by symptoms of inattention, impulsivity and/or hyperactivity. Methylphenidate (MPH), an effective first-line treatment for ADHD patients, has been found to enhance prefrontal dependent cognition in patients and in healthy volunteers. The mechanisms by which this drug exerts its behavioural effects remain unclear. [18F]fallypride, a high affinity D2/D3 receptor radiotracer, has to date never been shown to be displaced by oral MPH. We used [18F]fallypride in 16 adult ADHD patients and 16 matched controls to investigate (1) D2/D3 availability in striatal sub-regions and substantia nigra (2) relative increases in endogenous DA levels across these regions following 0.5 mg/kg MPH and (3) relationships between (1) and (2) with performance on a sustained attention task. These parameters were assessed in the context of a carefully designed counterbalanced placebo-controlled dual PET scan study. MPH plasma level dependent effects were accounted for. [18F]fallypride binding potential in regions defined on magnetic resonance images was calculated using a reference tissue model. Using rigorous methodology, this study found that inattention, one of the core features of ADHD, was associated with decreased D2/D3 R availability in left caudate across all subjects, regardless of diagnosis. MPH displaced [18F]fallypride preferentially in the sensori-motor striatum, but also in the associative striatum, ventral striatum and substantia nigra (SN). Cognitive effects of the drug on sustained attention were baseline performance dependent, with only low performers showing improvements (all p<0.05). Drug-induced increases in endogenous DA levels in striatum and substantia nigra following MPH had different modulatory effects on cognition (p<0.01). These data provide support for a continuum model of underlying dopaminergic dysregulations in ADHD and implicate, for the first time, a negative nigro-striatal feedback system in the cognitive modulation of oral MPH.
The Liverpool Telescope: performance and first results. [Proceedings of SPIE 5489, 679 (2004)]. I... more The Liverpool Telescope: performance and first results. [Proceedings of SPIE 5489, 679 (2004)]. Iain A. Steele, Robert J. Smith, Paul C. Rees, Ian P. Baker, SD Bates, Michael F. Bode, Mark K. Bowman, Dave Carter, Jason Etherton ...
Sub-striatal regions of interest (ROIs) are widely used in PET studies to investigate the role of... more Sub-striatal regions of interest (ROIs) are widely used in PET studies to investigate the role of dopamine in the modulation of neural networks implicated in emotion, cognition and motor function. One common approach is that of Mawlawi et al. (2001) and Martinez et al. (2003), where each striatum is divided into five sub-regions. This study focuses on the use of two spatial normalization-based alternatives to manual sub-striatal ROI delineation per subject: manual ROI delineation on a template brain and the production of probabilistic ROIs from a set of subject-specific manually delineated ROIs. Two spatial normalization algorithms were compared: SPM5 unified segmentation and ART. The ability of these methods to quantify sub-striatal regional non-displaceable binding potential (BP(ND)) and BP(ND) % change (following methylphenidate) was tested on 32 subjects (16 controls and 16 ADHD patients) scanned with the dopamine D(2)/D(3) ligand [(18)F]fallypride. Probabilistic ROIs produced by ART provided the best results, with similarity index values against subject-specific manual ROIs of 0.75-0.89 (mean 0.84) compared to 0.70-0.85 (mean 0.79) for template ROIs. Correlations (r) for BP(ND) and BP(ND) % change between subject-specific manual ROIs and these probabilistic ROIs of 0.90-0.98 (mean 0.95) and 0.98-1.00 (mean 0.99) respectively were superior overall to those obtained with template ROIs, although only marginally so for BP(ND) % change. The significance of relationships between BP(ND) measures and both behavioural tasks and methylphenidate plasma levels was preserved with ART combined with both probabilistic and template ROIs. SPM5 virtually matched the performance of ART for BP(ND) % change estimation but was inferior for BP(ND) estimation in caudate sub-regions. ART spatial normalization combined with probabilistic ROIs and to a lesser extent template ROIs provides an efficient and accurate alternative to time-consuming manual sub-striatal ROI delineation per subject, especially when the parameter of interest is BP(ND) % change.
Observatory Operations: Strategies, Processes, and Systems III, 2010
The Liverpool Telescope has undergone a major revision of operations model, improving the facilit... more The Liverpool Telescope has undergone a major revision of operations model, improving the facility&amp;#39;s flexibility and rapid response to targets of opportunity. We switched from a &amp;quot;full service&amp;quot; model where observers submitted requests to the Support Astronomer for checking and uploading into the scheduler database to a direct access model where observers personally load sequences directly into the database at
Algorithms for Synthetic Aperture Radar Imagery XII, 2005
Addressing the challenge of robust ATR, this paper describes the development and demonstration of... more Addressing the challenge of robust ATR, this paper describes the development and demonstration of Machine Learning for Robust ATR. The primary innovation of this work is the development of an automated way of developing heuristic inference rules that can draw on multiple models and multiple feature types to make more robust ATR decisions. The key realization is that this meta learning problem is one of structural learning; that can be conducted independently of parameter learning associated with each model and feature based technique, and more effectively draw on the strengths of all such techniques, and even information from unforeseen techniques. This is accomplished by using robust, genetics-based machine learning for the ill conditioned combinatorial problem of structural rule learning, while using statistical and mathematical techniques for parameter learning. This paper describes a learning classifier system approach (with evolutionary computation for structural learning) for robust ATR and points to a promising solution to the structural learning problem, across multiple feature types (which we will refer to as the meta-learning problem), for ATR with EOCs. This system was tested on MSTAR Public Release SAR data using nominal and extended operation conditions. These results were also compared against two baseline classifiers, a PCA based distance classifier and a MSE classifier. The systems were evaluated for accuracy (via training set classification) and robustness (via testing set classification). In both cases, the LCS based robust ATR system performed very well with accuracy over 99% and robustness over 80%.
Attention deficit/hyperactivity disorder (ADHD) is an early-onset neurobehavioural disorder chara... more Attention deficit/hyperactivity disorder (ADHD) is an early-onset neurobehavioural disorder characterised by symptoms of inattention, impulsivity and/or hyperactivity. Methylphenidate (MPH), an effective first-line treatment for ADHD patients, has been found to enhance prefrontal dependent cognition in patients and in healthy volunteers. The mechanisms by which this drug exerts its behavioural effects remain unclear. [18F]fallypride, a high affinity D2/D3 receptor radiotracer, has to date never been shown to be displaced by oral MPH. We used [18F]fallypride in 16 adult ADHD patients and 16 matched controls to investigate (1) D2/D3 availability in striatal sub-regions and substantia nigra (2) relative increases in endogenous DA levels across these regions following 0.5 mg/kg MPH and (3) relationships between (1) and (2) with performance on a sustained attention task. These parameters were assessed in the context of a carefully designed counterbalanced placebo-controlled dual PET scan study. MPH plasma level dependent effects were accounted for. [18F]fallypride binding potential in regions defined on magnetic resonance images was calculated using a reference tissue model. Using rigorous methodology, this study found that inattention, one of the core features of ADHD, was associated with decreased D2/D3 R availability in left caudate across all subjects, regardless of diagnosis. MPH displaced [18F]fallypride preferentially in the sensori-motor striatum, but also in the associative striatum, ventral striatum and substantia nigra (SN). Cognitive effects of the drug on sustained attention were baseline performance dependent, with only low performers showing improvements (all p<0.05). Drug-induced increases in endogenous DA levels in striatum and substantia nigra following MPH had different modulatory effects on cognition (p<0.01). These data provide support for a continuum model of underlying dopaminergic dysregulations in ADHD and implicate, for the first time, a negative nigro-striatal feedback system in the cognitive modulation of oral MPH.
The Liverpool Telescope: performance and first results. [Proceedings of SPIE 5489, 679 (2004)]. I... more The Liverpool Telescope: performance and first results. [Proceedings of SPIE 5489, 679 (2004)]. Iain A. Steele, Robert J. Smith, Paul C. Rees, Ian P. Baker, SD Bates, Michael F. Bode, Mark K. Bowman, Dave Carter, Jason Etherton ...
Sub-striatal regions of interest (ROIs) are widely used in PET studies to investigate the role of... more Sub-striatal regions of interest (ROIs) are widely used in PET studies to investigate the role of dopamine in the modulation of neural networks implicated in emotion, cognition and motor function. One common approach is that of Mawlawi et al. (2001) and Martinez et al. (2003), where each striatum is divided into five sub-regions. This study focuses on the use of two spatial normalization-based alternatives to manual sub-striatal ROI delineation per subject: manual ROI delineation on a template brain and the production of probabilistic ROIs from a set of subject-specific manually delineated ROIs. Two spatial normalization algorithms were compared: SPM5 unified segmentation and ART. The ability of these methods to quantify sub-striatal regional non-displaceable binding potential (BP(ND)) and BP(ND) % change (following methylphenidate) was tested on 32 subjects (16 controls and 16 ADHD patients) scanned with the dopamine D(2)/D(3) ligand [(18)F]fallypride. Probabilistic ROIs produced by ART provided the best results, with similarity index values against subject-specific manual ROIs of 0.75-0.89 (mean 0.84) compared to 0.70-0.85 (mean 0.79) for template ROIs. Correlations (r) for BP(ND) and BP(ND) % change between subject-specific manual ROIs and these probabilistic ROIs of 0.90-0.98 (mean 0.95) and 0.98-1.00 (mean 0.99) respectively were superior overall to those obtained with template ROIs, although only marginally so for BP(ND) % change. The significance of relationships between BP(ND) measures and both behavioural tasks and methylphenidate plasma levels was preserved with ART combined with both probabilistic and template ROIs. SPM5 virtually matched the performance of ART for BP(ND) % change estimation but was inferior for BP(ND) estimation in caudate sub-regions. ART spatial normalization combined with probabilistic ROIs and to a lesser extent template ROIs provides an efficient and accurate alternative to time-consuming manual sub-striatal ROI delineation per subject, especially when the parameter of interest is BP(ND) % change.
Observatory Operations: Strategies, Processes, and Systems III, 2010
The Liverpool Telescope has undergone a major revision of operations model, improving the facilit... more The Liverpool Telescope has undergone a major revision of operations model, improving the facility&amp;#39;s flexibility and rapid response to targets of opportunity. We switched from a &amp;quot;full service&amp;quot; model where observers submitted requests to the Support Astronomer for checking and uploading into the scheduler database to a direct access model where observers personally load sequences directly into the database at
Uploads
Papers by Robert Smith