Monitoring Infants By Automatic Video Processing

This work has, as its objective, the development of non-invasive and low-cost systems for monitoring and automatic diagnosing specific neonatal diseases by means of the analysis of suitable video signals. We focus on monitoring infants potentially at risk of diseases characterized by the presence or absence of rhythmic movements of one or more body parts. Seizures and respiratory diseases are specifically considered, but the approach is general. Seizures are defined as sudden neurological and behavioural alterations. They are age-dependent phenomena and the most common sign of central nervous system dysfunction. Neonatal seizures have onset within the 28th day of life in newborns at term and within the 44th week of conceptional age in preterm infants. Their main causes are hypoxic-ischaemic encephalopathy, intracranial haemorrhage, and sepsis. Studies indicate an incidence rate of neonatal seizures of 0.2% live births, 1.1% for preterm neonates, and 1.3% for infants weighing less than 2500 g at birth. Neonatal seizures can be classified into four main categories: clonic, tonic, myoclonic, and subtle. Seizures in newborns have to be promptly and accurately recognized in order to establish timely treatments that could avoid an increase of the underlying brain damage. Respiratory diseases related to the occurrence of apnoea episodes may be caused by cerebrovascular events. Among the wide range of causes of apnoea, besides seizures, a relevant one is Congenital Central Hypoventilation Syndrome (CCHS) \cite{Healy}. With a reported prevalence of 1 in 200,000 live births, CCHS, formerly known as Ondine's curse, is a rare life-threatening disorder characterized by a failure of the automatic control of breathing, caused by mutations in a gene classified as PHOX2B. CCHS manifests itself, in the neonatal period, with episodes of cyanosis or apnoea, especially during quiet sleep. The reported mortality rates range from 8% to 38% of newborn with genetically confirmed CCHS. Nowadays, CCHS is considered a disorder of autonomic regulation, with related risk of sudden infant death syndrome (SIDS). Currently, the standard method of diagnosis, for both diseases, is based on polysomnography, a set of sensors such as ElectroEncephaloGram (EEG) sensors, ElectroMyoGraphy (EMG) sensors, ElectroCardioGraphy (ECG) sensors, elastic belt sensors, pulse-oximeter and nasal flow-meters. This monitoring system is very expensive, time-consuming, moderately invasive and requires particularly skilled medical personnel, not always available in a Neonatal Intensive Care Unit (NICU). Therefore, automatic, real-time and non-invasive monitoring equipments able to reliably recognize these diseases would be of significant value in the NICU. A very appealing monitoring tool to automatically detect neonatal seizures or breathing disorders may be based on acquiring, through a network of sensors, e.g., a set of video cameras, the movements of the newborn's body (e.g., limbs, chest) and properly processing the relevant signals. An automatic multi-sensor system could be used to permanently monitor every patient in the NICU or specific patients at home. Furthermore, a wire-free technique may be more user-friendly and highly desirable when used with infants, in particular with newborns. This work has focused on a reliable method to estimate the periodicity in pathological movements based on the use of the Maximum Likelihood (ML) criterion. In particular, average differential luminance signals from multiple Red, Green and Blue (RGB) cameras or depth-sensor devices are extracted and the presence or absence of a significant periodicity is analysed in order to detect possible pathological conditions. The efficacy of this monitoring system has been measured on the basis of video recordings provided by the Department of Neurosciences of the University of Parma. Concerning clonic seizures, a kinematic analysis was performed to establish a relationship between neonatal seizures and human inborn pattern of quadrupedal locomotion. Moreover, we have decided to realize simulators able to replicate the symptomatic movements characteristic of the diseases under consideration. The reasons is, essentially, the opportunity to have, at any time, a 'subject' on which to test the continuously evolving detection algorithms. Finally, we have developed a smartphone App, called 'Smartphone based contactless epilepsy detector' (SmartCED), able to detect neonatal clonic seizures and warn the user about the occurrence in real-time.

Multi-valued control problems and mixture density network

We have proposed a novel robust inversion-based neurocontroller that searches for the optimal control law by sampling from the estimated Gaussian distribution of the inverse plant model. However, for problems involving the prediction of continuous variables, a Gaussian model approximation provides only a very limited description of the properties of the inverse model. This is usually the case for problems in which the mapping to be learned is multi-valued or involves hysteritic transfer characteristics. This often arises in the solution of inverse plant models. In order to obtain a complete description of the inverse model, a more general multicomponent distributions must be modeled. In this paper we test whether our proposed sampling approach can be used when considering an arbitrary conditional probability distributions. These arbitrary distributions will be modeled by a mixture density network. Importance sampling provides a structured and principled approach to constrain the complexity of the search space for the ideal control law. The effectiveness of the importance sampling from an arbitrary conditional probability distribution will be demonstrated using a simple single input single output static nonlinear system with hysteretic characteristics in the inverse plant model.

The role of oscillatory brain activity in object processing and figure-ground segmentation in human vision

The perception of an object as a single entity within a visual scene requires that its features are bound together and segregated from the background and/or other objects. Here, we used magnetoencephalography (MEG) to assess the hypothesis that coherent percepts may arise from the synchronized high frequency (gamma) activity between neurons that code features of the same object. We also assessed the role of low frequency (alpha, beta) activity in object processing. The target stimulus (i.e. object) was a small patch of a concentric grating of 3c/°, viewed eccentrically. The background stimulus was either a blank field or a concentric grating of 3c/° periodicity, viewed centrally. With patterned backgrounds, the target stimulus emerged--through rotation about its own centre--as a circular subsection of the background. Data were acquired using a 275-channel whole-head MEG system and analyzed using Synthetic Aperture Magnetometry (SAM), which allows one to generate images of task-related cortical oscillatory power changes within specific frequency bands. Significant oscillatory activity across a broad range of frequencies was evident at the V1/V2 border, and subsequent analyses were based on a virtual electrode at this location. When the target was presented in isolation, we observed that: (i) contralateral stimulation yielded a sustained power increase in gamma activity; and (ii) both contra- and ipsilateral stimulation yielded near identical transient power changes in alpha (and beta) activity. When the target was presented against a patterned background, we observed that: (i) contralateral stimulation yielded an increase in high-gamma (>55 Hz) power together with a decrease in low-gamma (40-55 Hz) power; and (ii) both contra- and ipsilateral stimulation yielded a transient decrease in alpha (and beta) activity, though the reduction tended to be greatest for contralateral stimulation. The opposing power changes across different regions of the gamma spectrum with 'figure/ground' stimulation suggest a possible dual role for gamma rhythms in visual object coding, and provide general support of the binding-by-synchronization hypothesis. As the power changes in alpha and beta activity were largely independent of the spatial location of the target, however, we conclude that their role in object processing may relate principally to changes in visual attention.

Genetics and competing strategies in a threshold model for mail processing

Multi-agent algorithms inspired by the division of labour in social insects are applied to a problem of distributed mail retrieval in which agents must visit mail producing cities and choose between mail types under certain constraints.The efficiency (i.e. the average amount of mail retrieved per time step), and the flexibility (i.e. the capability of the agents to react to changes in the environment) are investigated both in static and dynamic environments. New rules for mail selection and specialisation are introduced and are shown to exhibit improved efficiency and flexibility compared to existing ones. We employ a genetic algorithm which allows the various rules to evolve and compete. Apart from obtaining optimised parameters for the various rules for any environment, we also observe extinction and speciation. From a more theoretical point of view, in order to avoid finite size effects, most results are obtained for large population sizes. However, we do analyse the influence of population size on the performance. Furthermore, we critically analyse the causes of efficiency loss, derive the exact dynamics of the model in the large system limit under certain conditions, derive theoretical upper bounds for the efficiency, and compare these with the experimental results.

A novel method for studying the cortical processing of human swallowing using Synthetic Aperture Magnetometry(SAM)

Background/Aims: Positron emission tomography has been applied to study cortical activation during human swallowing, but employs radio-isotopes precluding repeated experiments and has to be performed supine, making the task of swallowing difficult. Here we now describe Synthetic Aperture Magnetometry (SAM) as a novel method of localising and imaging the brain's neuronal activity from magnetoencephalographic (MEG) signals to study the cortical processing of human volitional swallowing in the more physiological prone position. Methods: In 3 healthy male volunteers (age 28–36), 151-channel whole cortex MEG (Omega-151, CTF Systems Inc.) was recorded whilst seated during the conditions of repeated volitional wet swallowing (5mls boluses at 0.2Hz) or rest. SAM analysis was then performed using varying spatial filters (5–60Hz) before co-registration with individual MRI brain images. Activation areas were then identified using standard sterotactic space neuro-anatomical maps. In one subject repeat studies were performed to confirm the initial study findings. Results: In all subjects, cortical activation maps for swallowing could be generated using SAM, the strongest activations being seen with 10–20Hz filter settings. The main cortical activations associated with swallowing were in: sensorimotor cortex (BA 3,4), insular cortex and lateral premotor cortex (BA 6,8). Of relevance, each cortical region displayed consistent inter-hemispheric asymmetry, to one or other hemisphere, this being different for each region and for each subject. Intra-subject comparisons of activation localisation and asymmetry showed impressive reproducibility. Conclusion: SAM analysis using MEG is an accurate, repeatable, and reproducible method for studying the brain processing of human swallowing in a more physiological manner and provides novel opportunities for future studies of the brain-gut axis in health and disease.

Coarse threat images reveal theta oscillations in the amygdala: a magnetoencephalography study

Neurocognitive models propose a specialized neural system for processing threat-related information, in which the amygdala plays a key role in the analysis of threat cues. fMRI research indicates that the amygdala is sensitive to coarse visual threat relevant information—for example, low spatial frequency (LSF) fearful faces. However, fMRI cannot determine the temporal or spectral characteristics of neural responses. Consequently, we used magnetoencephalography to explore spatiotemporal patterns of activity in the amygdala and cortical regions with blurry (LSF) and normal angry, fearful, and neutral faces. Results demonstrated differences in amygdala activity between LSF threat-related and LSF neutral faces (50-250 msec after face onset). These differences were evident in the theta range (4-8 Hz) and were accompanied by power changes within visual and frontal regions. Our results support the view that the amygdala is involved in the early processing of coarse threat related information and that theta is important in integrating activity within emotion-processing networks.

Human sensitivity to phase perturbations in natural images:A statistical framework

Fourier-phase information is important in determining the appearance of natural scenes, but the structure of natural-image phase spectra is highly complex and difficult to relate directly to human perceptual processes. This problem is addressed by extending previous investigations of human visual sensitivity to the randomisation and quantisation of Fourier phase in natural images. The salience of the image changes induced by these physical processes is shown to depend critically on the nature of the original phase spectrum of each image, and the processes of randomisation and quantisation are shown to be perceptually equivalent provided that they shift image phase components by the same average amount. These results are explained by assuming that the visual system is sensitive to those phase-domain image changes which also alter certain global higher-order image statistics. This assumption may be used to place constraints on the likely nature of cortical processing: mechanisms which correlate the outputs of a bank of relative-phase-sensitive units are found to be consistent with the patterns of sensitivity reported here.

Quantification of the relationship between, magnetoencephalographic (MEG) and blood oxygenation dependent (BOLD) images of brain function

Magnetoencephalography (MEG) is the measurement of the magnetic fields generated outside the head by the brain’s electrical activity. The technique offers the promise of high temporal and spatial resolution. There is however an ambiguity in the inversion process of estimating what goes on inside the head from what is measured outside. Other techniques, such as functional Magnetic Resonance Imaging (fMRI) have no such inversion problems yet suffer from poorer temporal resolution. In this study we examined metrics of mutual information and linear correlation between volumetric images from the two modalities. Measures of mutual information reveal a significant, non-linear, relationship between MEG and fMRI datasets across a number of frequency bands.

Applications of fractals to image data compression

Digital image processing is exploited in many diverse applications but the size of digital images places excessive demands on current storage and transmission technology. Image data compression is required to permit further use of digital image processing. Conventional image compression techniques based on statistical analysis have reached a saturation level so it is necessary to explore more radical methods. This thesis is concerned with novel methods, based on the use of fractals, for achieving significant compression of image data within reasonable processing time without introducing excessive distortion. Images are modelled as fractal data and this model is exploited directly by compression schemes. The validity of this is demonstrated by showing that the fractal complexity measure of fractal dimension is an excellent predictor of image compressibility. A method of fractal waveform coding is developed which has low computational demands and performs better than conventional waveform coding methods such as PCM and DPCM. Fractal techniques based on the use of space-filling curves are developed as a mechanism for hierarchical application of conventional techniques. Two particular applications are highlighted: the re-ordering of data during image scanning and the mapping of multi-dimensional data to one dimension. It is shown that there are many possible space-filling curves which may be used to scan images and that selection of an optimum curve leads to significantly improved data compression. The multi-dimensional mapping property of space-filling curves is used to speed up substantially the lookup process in vector quantisation. Iterated function systems are compared with vector quantisers and the computational complexity or iterated function system encoding is also reduced by using the efficient matching algcnithms identified for vector quantisers.

The design of a real-time nowcasting system for localised weather

National meteorological offices are largely concerned with synoptic-scale forecasting where weather predictions are produced for a whole country for 24 hours ahead. In practice, many local organisations (such as emergency services, construction industries, forestry, farming, and sports) require only local short-term, bespoke, weather predictions and warnings. This thesis shows that the less-demanding requirements do not require exceptional computing power and can be met by a modern, desk-top system which monitors site-specific ground conditions (such as temperature, pressure, wind speed and direction, etc) augmented with above ground information from satellite images to produce `nowcasts'. The emphasis in this thesis has been towards the design of such a real-time system for nowcasting. Local site-specific conditions are monitored using a custom-built, stand alone, Motorola 6809 based sub-system. Above ground information is received from the METEOSAT 4 geo-stationary satellite using a sub-system based on a commercially available equipment. The information is ephemeral and must be captured in real-time. The real-time nowcasting system for localised weather handles the data as a transparent task using the limited capabilities of the PC system. Ground data produces a time series of measurements at a specific location which represents the past-to-present atmospheric conditions of the particular site from which much information can be extracted. The novel approach adopted in this thesis is one of constructing stochastic models based on the AutoRegressive Integrated Moving Average (ARIMA) technique. The satellite images contain features (such as cloud formations) which evolve dynamically and may be subject to movement, growth, distortion, bifurcation, superposition, or elimination between images. The process of extracting a weather feature, following its motion and predicting its future evolution involves algorithms for normalisation, partitioning, filtering, image enhancement, and correlation of multi-dimensional signals in different domains. To limit the processing requirements, the analysis in this thesis concentrates on an `area of interest'. By this rationale, only a small fraction of the total image needs to be processed, leading to a major saving in time. The thesis also proposes an extention to an existing manual cloud classification technique for its implementation in automatically classifying a cloud feature over the `area of interest' for nowcasting using the multi-dimensional signals.

Mach Bands: multi-scale spatial filtering and co-operative coding of edges and bars

Perception of Mach bands may be explained by spatial filtering ('lateral inhibition') that can be approximated by 2nd derivative computation, and several alternative models have been proposed. To distinguish between them, we used a novel set of ‘generalised Gaussian’ images, in which the sharp ramp-plateau junction of the Mach ramp was replaced by smoother transitions. The images ranged from a slightly blurred Mach ramp to a Gaussian edge and beyond, and also included a sine-wave edge. The probability of seeing Mach Bands increased with the (relative) sharpness of the junction, but was largely independent of absolute spatial scale. These data did not fit the predictions of MIRAGE, nor 2nd derivative computation at a single fine scale. In experiment 2, observers used a cursor to mark features on the same set of images. Data on perceived position of Mach bands did not support the local energy model. Perceived width of Mach bands was poorly explained by a single-scale edge detection model, despite its previous success with Mach edges (Wallis & Georgeson, 2009, Vision Research, 49, 1886-1893). A more successful model used separate (odd and even) scale-space filtering for edges and bars, local peak detection to find candidate features, and the MAX operator to compare odd- and even-filter response maps (Georgeson, VSS 2006, Journal of Vision 6(6), 191a). Mach bands are seen when there is a local peak in the even-filter (bar) response map, AND that peak value exceeds corresponding responses in the odd-filter (edge) maps.

Does normal processing provide evidence of specialised semantic subsystems?

Category-specific disorders are frequently explained by suggesting that living and non-living things are processed in separate subsystems (e.g. Caramazza & Shelton, 1998). If subsystems exist, there should be benefits for normal processing, beyond the influence of structural similarity. However, no previous study has separated the relative influences of similarity and semantic category. We created novel examples of living and non-living things so category and similarity could be manipulated independently. Pre-tests ensured that our images evoked appropriate semantic information and were matched for familiarity. Participants were trained to associate names with the images and then performed a name-verification task under two levels of time pressure. We found no significant advantage for living things alongside strong effects of similarity. Our results suggest that similarity rather than category is the key determinant of speed and accuracy in normal semantic processing. We discuss the implications of this finding for neuropsychological studies. © 2005 Psychology Press Ltd.

Response normalization and blur adaptation:data and multi-scale model

Adapting to blurred or sharpened images alters perceived blur of a focused image (M. A. Webster, M. A. Georgeson, & S. M. Webster, 2002). We asked whether blur adaptation results in (a) renormalization of perceived focus or (b) a repulsion aftereffect. Images were checkerboards or 2-D Gaussian noise, whose amplitude spectra had (log-log) slopes from -2 (strongly blurred) to 0 (strongly sharpened). Observers adjusted the spectral slope of a comparison image to match different test slopes after adaptation to blurred or sharpened images. Results did not show repulsion effects but were consistent with some renormalization. Test blur levels at and near a blurred or sharpened adaptation level were matched by more focused slopes (closer to 1/f) but with little or no change in appearance after adaptation to focused (1/f) images. A model of contrast adaptation and blur coding by multiple-scale spatial filters predicts these blur aftereffects and those of Webster et al. (2002). A key proposal is that observers are pre-adapted to natural spectra, and blurred or sharpened spectra induce changes in the state of adaptation. The model illustrates how norms might be encoded and recalibrated in the visual system even when they are represented only implicitly by the distribution of responses across multiple channels.

Experimental optimization of triangular pulse generation in normal dispersion fiber for all optical processing applications

We experimentally investigate a multi-parameter optimization of conditions for generation of triangular pulses in normal dispersion fiber. We find that triangular pulses suitable for all optical processing applications can be generated for a wide range of input pulse chirps but that triangular pulse quality and stability is improved with increased input pulse chirp.

The chemical modification of polymer blends by reactive processing

The primary objective of this research was to examine the concepts of the chemical modification of polymer blends by reactive processing using interlinking agents (multi-functional, activated vinyl compounds; trimethylolpropane triacrylates {TRIS} and divinylbenzene {DVD}) to target in-situ interpolymer formation between immiscible polymers in PS/EPDM blends via peroxide-initiated free radical reactions during melt mixing. From a comprehensive survey of previous studies of compatibility enhancement in polystyrene blends, it was recognised that reactive processing offers opportunities for technological success that have not yet been fully realised; learning from this study is expected to assist in the development and application of this potential. In an experimental-scale operation for the simultaneous melt blending and reactive processing of both polymers, involving manual injection of precise reactive agent/free radical initiator mixtures directly into molten polymer within an internal mixer, torque changes were distinct, quantifiable and rationalised by ongoing physical and chemical effects. EPDM content of PS/EPDM blends was the prime determinant of torque increases on addition of TRIS, itself liable to self-polymerisation at high additions, with little indication of PS reaction in initial reactively processed blends with TRIS, though blend compatibility, from visual assessment of morphology by SEM, was nevertheless improved. Suitable operating windows were defined for the optimisation of reactive blending, for use once routes to encourage PS reaction could be identified. The effectiveness of PS modification by reactive processing with interlinking agents was increased by the selection of process conditions to target specific reaction routes, assessed by spectroscopy (FT-IR and NMR) and thermal analysis (DSC) coupled dichloromethane extraction and fractionation of PS. Initiator concentration was crucial in balancing desired PS modification and interlinking agent self-polymerisation, most particularly with TRIS. Pre-addition of initiator to PS was beneficial in the enhancement of TRIS binding to PS and minimisation of modifier polymerisation; believed to arise from direct formation of polystyryl radicals for addition to active unsaturation in TRIS. DVB was found to be a "compatible" modifier for PS, but its efficacy was not quantified. Application of routes for PS reaction in PS/EPDM blends was successful for in-situ formation of interpolymer (shown by sequential solvent extraction combined with FT-IR and DSC analysis); the predominant outcome depending on the degree of reaction of each component, with optimum "between-phase" interpolymer formed under conditions selected for equalisation of differing component reactivities and avoidance of competitive processes. This was achieved for combined addition of TRIS+DVB at optimum initiator concentrations with initiator pre-addition to PS. Improvements in blend compatibility (by tensiles, SEM and thermal analysis) were shown in all cases with significant interpolymer formation, though physical benefits were not; morphology and other reactive effects were also important factors. Interpolymer from specific "between-phase" reaction of blend components and interlinking agent was vital for the realisation of positive performance on compatibilisation by the chemical modification of polymer blends by reactive processing.