A Task-Graph Execution Manager for Reconfigurable Multi-tasking Systems

Reconfigurable hardware can be used to build multi tasking systems that dynamically adapt themselves to the requirements of the running applications. This is especially useful in embedded systems, since the available resources are very limited and the reconfigurable hardware can be reused for different applications. In these systems computations are frequently represented as task graphs that are executed taking into account their internal dependencies and the task schedule. The management of the task graph execution is critical for the system performance. In this regard, we have developed two dif erent versions, a software module and a hardware architecture, of a generic task-graph execution manager for reconfigurable multi-tasking systems. The second version reduces the run-time management overheads by almost two orders of magnitude. Hence it is especially suitable for systems with exigent timing constraints. Both versions include specific support to optimize the reconfiguration process.

Movement-related potentials in Huntington's disease: movement preparation and execution

Movement-related potentials (MRPs) reflect increasing cortical activity related to the preparation and execution of voluntary movement. Execution and preparatory components may be separated by comparing MRPs recorded from actual and imagined movement. Imagined movement initiates preparatory processes, but not motor execution activity. MRPs are maximal over the supplementary motor area (SMA), an area of the cortex involved in the planning and preparation of movement. The SMA receives input from the basal ganglia, which are affected in Huntington's disease (HD), a hyperkinetic movement disorder. In order to further elucidate the effects of the disorder upon the cortical activity relating to movement, MRPs were recorded from ten HD patients, and ten age-matched controls, whilst they performed and imagined performing a sequential button-pressing task. HD patients produced MRPs of significantly reduced size both for performed and imagined movement. The component relating to movement execution was obtained by subtracting the MRP for imagined movement from the MRP for performed movement, and was found to be normal in HD. The movement preparation component was found by subtracting the MRP found for a control condition of watching the visual cues from the MRP for imagined movement. This preparation component in HD was reduced in early slope, peak amplitude, and post-peak slope. This study therefore reported abnormal MRPs in HD. particularly in terms of the components relating to movement preparation, and this finding may further explain the movement deficits reported in the disease.

Gamma-band oscillations in fronto-central areas during performance of a sensorimotor integration task: A qEEG coherence study

This study aimed to elucidate electrophysiological and cortical mechanisms involved in anticipatory actions when 23 healthy right-handed subjects had to catch a free falling object by qEEG gamma-band (30-100 Hz). It is involved in cognitive processes, memory, spatial/temporal and proprioceptive factors. Our hypothesis is that an increase in gamma coherence in frontal areas will be observed during moment preceding ball drop, due to their involvement in attention, planning, selection of movements, preparation and voluntary control of action and in central areas during moment after ball drop, due to their involvement in motor preparation, perception and execution of movement. However, through a paired t-test, we found an increase in gamma coherence for F3-F4 electrode pair during moment preceding ball drop and confirmed our hypothesis for C3-C4 electrode pair. We conclude that gamma plays an important role in reflecting binding of several brain areas in a complex motor task as observed in our results. Moreover, for selection of movements, preparation and voluntary control of action, motor preparation, perception and execution of movement, the integration of somatosensory and visual information is mandatory. (C) 2010 Elsevier Ireland Ltd. All rights reserved.

Impairments of movement kinematics in patients with Huntington's disease: A comparison with and without a concurrent task

This study aimed to quantify the efficiency and smoothness of voluntary movement in Huntington's disease (HD) by the use of a graphics tablet that permits analysis of movement profiles. In particular, we aimed to ascertain whether a concurrent task (digit span) would affect the kinematics of goal-directed movements. Twelve patients with HD and their matched controls performed 12 vertical zig-zag movements, with both left and right hands (with and without the concurrent task), to large or small circular targets over long or short extents. The concurrent task was associated with shorter movement times and reduced right-hand superiority. Patients with HD were overall slower, especially with long strokes, and had similar peak velocities for both small and large targets, so that controls could better accommodate differences in target size. Patients with HD spent more time decelerating, especially with small targets, whereas controls allocated more nearly equal proportions of time to the acceleration and deceleration phases of movement, especially with large targets. Short strokes were generally less force inefficient than were long strokes, especially so for either hand in either group in the absence of the concurrent task, and for the right hand in its presence. With the concurrent task, however, the left hand's behavior changed differentially for the two groups; for patients with HD, it became more force efficient with short strokes and even less efficient with long strokes, whereas for controls, it became more efficient with long strokes. Controls may be able to divert attention away from the inferior left hand, increasing its automaticity, whereas patients with HD, because of disease, may be forced to engage even further online visual control under the demands of a concurrent task. Patients with HD may perhaps become increasingly reliant on terminal visual guidance, which indicates an impairment in constructing and refining an internal representation of the movement necessary for its. effective execution. Basal ganglia dysfunction may impair the ability to use internally generated cues to guide movement.

The effects of bromazepam over the temporo-parietal areas during the performance of a visuomotor task: A qEEG study

This study investigated the effects of bromazepam on qEEG when 14 healthy subjects were asked to perform a visuomotor task (i.e., motor vehicle driving task). The subjects were exposed to two experimental conditions: the placebo (PL) and 6 mg of bromazepam (Br 6 mg), following a randomized, double-blind design on different days. Specifically, we observe absolute power extracted from qEEG data for theta band. We expected to see a decrease in absolute theta power in the temporal and parietal areas due to the influence of bromazepam for the experimental group when compared with the placebo group. We found a main effect for the condition factor for electrodes T3, T4, P3 and P4. We also observed a main effect for the period factor for electrodes P3 and P4. We observed that the ingestion of 6 mg of bromazepam induces different patterns in theta power at the temporal and parietal sites. We concluded that 6 mg of bromazepam was an important factor in the fluctuation of the activities in the temporal and parietal areas. We then hypothesize about the specific role of this drug during the execution of a visuomotor task and within the sensorimotor integration process. (C) 2011 Elsevier Ireland Ltd. All rights reserved.

Integration of Cortical Areas during Performance of a Catching Ball Task

The study aimed to elucidate electrophysiological and cortical mechanisms involved in anticipatory actions when healthy subjects had to catch balls in free drop. Specific alpha absolute power changes were measured in quantitative electroencephalography (qEEG). Our hypothesis is that during the preparation of motoraction (i.e.. 2 s before the ball drops) integration occurs among the left medial frontal, left primary somatomotor and left posterior parietal cortices, showing a differentiated activity involving expectation, planning and preparedness. We contend that in right-handers, the left hemisphere takes on a dominant role for the regulation of motor behavior. The sample was composed of 23 healthy right handed subjects (13 men and 10 women), with ages varying between 25 and 40 years old (32.5 +/- 7.5), absence of mental and physical illness. The experiment consisted of a task of catching balls with the right hard in free drop. The three-way ANOVA analysis demonstrated all interaction between moment and position in left-medial frontal cortex (F3 electrode), somatomotor cortex (C3 electrode) and posterior parietal cortex (P3 electrode: p < 0.05). Summarizing, the experimental task enabled the observation of integration among frontal, central and parietal regions. This integration appears to be more predominant in expectation, planning and motor preparation.

Integration of cortical areas during performance of a catching ball task

The study aimed to elucidate electrophysiological and cortical mechanisms involved in anticipatory actions when healthy subjects had to catch balls in free drop; specifically through quantitative electroencephalography (qEEG) alpha absolute power changes. Our hypothesis is that during the preparation of motor action (i.e., 2 s before ball`s drop) occurred integration among left medial frontal, left primary somatomotor and left posterior parietal cortices, showing a differentiated activity involving expectation, planning and preparedness. This hypothesis supports a lateralization of motor function. Although we contend that in right-handers the left hemisphere takes on a dominant role for the regulation of motor behavior. The sample was composed of 23 healthy subjects (13 male and 10 female), right handed, with ages varying between 25 and 40 years old (32.5 +/- 7.5), absence of mental and physical illness, right handed, and do not make use of any psychoactive or psychotropic substance at the time of the study. The experiment consisted of a task of catching balls in free drop. The three-way ANOVA analysis demonstrated an interaction between moment and position in left medial frontal cortex (F3 electrode), somatomotor cortex (C3 electrode) and posterior parietal cortex (P3 electrode: p < 0.001). Summarizing, through experimental task employed, it was possible to observe integration among frontal, central and parietal regions. This integration appears to be more predominant in expectation, planning and motor preparation. In this way, it established an absolute predominance of this mechanism under the left hemisphere. (C) 2008 Elsevier Ireland Ltd. All rights reserved.

Finding an upper bound on the increase in execution time due to contention on the memory bus in COTS-based multicore systems

Contention on the memory bus in COTS based multicore systems is becoming a major determining factor of the execution time of a task. Analyzing this extra execution time is non-trivial because (i) bus arbitration protocols in such systems are often undocumented and (ii) the times when the memory bus is requested to be used are not explicitly controlled by the operating system scheduler; they are instead a result of cache misses. We present a method for finding an upper bound on the extra execution time of a task due to contention on the memory bus in COTS based multicore systems. This method makes no assumptions on the bus arbitration protocol (other than assuming that it is work-conserving).

Autonomic Activities in the Execution of Scientific Workflows: Evaluation of the AWARD Framework

Workflows have been successfully applied to express the decomposition of complex scientific applications. However the existing tools still lack adequate support to important aspects namely, decoupling the enactment engine from tasks specification, decentralizing the control of workflow activities allowing their tasks to run in distributed infrastructures, and supporting dynamic workflow reconfigurations. We present the AWARD (Autonomic Workflow Activities Reconfigurable and Dynamic) model of computation, based on Process Networks, where the workflow activities (AWA) are autonomic processes with independent control that can run in parallel on distributed infrastructures. Each AWA executes a task developed as a Java class with a generic interface allowing end-users to code their applications without low-level details. The data-driven coordination of AWA interactions is based on a shared tuple space that also enables dynamic workflow reconfiguration. For evaluation we describe experimental results of AWARD workflow executions in several application scenarios, mapped to the Amazon (Elastic Computing EC2) Cloud.

A Multi-DAG Model for Real-Time Parallel Applications with Conditional Execution

The 30th ACM/SIGAPP Symposium On Applied Computing (SAC 2015). 13 to 17, Apr, 2015, Embedded Systems. Salamanca, Spain.

The Management of the Allergic Child at School: EAACI/GA2LEN Task Force on the Allergic Child at School

Allergy affects at least one-quarter of European schoolchildren, it reduces quality of life and may impair school performance; there is a risk of severe reactions and, in rare cases, death. Allergy is a multi-system disorder, and children often have several co-existing diseases, i.e. allergic rhinitis, asthma, eczema and food allergy. Severe food allergy reactions may occur for the first time at school, and overall 20% of food allergy reactions occur in schools. Up to two-thirds of schools have at least one child at risk of anaphylaxis but many are poorly prepared. A cooperative partnership between doctors, community and school nurses, school staff, parents and the child is necessary to ensure allergic children are protected. Schools and doctors should adopt a comprehensive approach to allergy training, ensuring that all staff can prevent, recognize and initiate treatment of allergic reactions.

A distributed platform for the volunteer execution of workflows on a local area network

Thesis submitted in fulfilment of the requirements for the Degree of Master of Science in Computer Science

Ontology-based representation and generation of workflows for micro-task human-machine computation

Doctoral Program in Computer Science

Dynamic changes in brain functional connectivity during concurrent dual-task performance.

This study investigated the spatial, spectral, temporal and functional proprieties of functional brain connections involved in the concurrent execution of unrelated visual perception and working memory tasks. Electroencephalography data was analysed using a novel data-driven approach assessing source coherence at the whole-brain level. Three connections in the beta-band (18-24 Hz) and one in the gamma-band (30-40 Hz) were modulated by dual-task performance. Beta-coherence increased within two dorsofrontal-occipital connections in dual-task conditions compared to the single-task condition, with the highest coherence seen during low working memory load trials. In contrast, beta-coherence in a prefrontal-occipital functional connection and gamma-coherence in an inferior frontal-occipitoparietal connection was not affected by the addition of the second task and only showed elevated coherence under high working memory load. Analysis of coherence as a function of time suggested that the dorsofrontal-occipital beta-connections were relevant to working memory maintenance, while the prefrontal-occipital beta-connection and the inferior frontal-occipitoparietal gamma-connection were involved in top-down control of concurrent visual processing. The fact that increased coherence in the gamma-connection, from low to high working memory load, was negatively correlated with faster reaction time on the perception task supports this interpretation. Together, these results demonstrate that dual-task demands trigger non-linear changes in functional interactions between frontal-executive and occipitoparietal-perceptual cortices.