Search

Adaptation in embedded processing is key in order to address efficiency. The concept of extensible embedded processors works well if a few a-priori known hot spots exist. However, they are far less efficient if many and possible at-design-time-unknown hot spots need to be dealt with. Our RISPP approach advances the extensible processor concept by providing flexibility through runtime adaptation by what we call "instruction rotation". It allows sharing resources in a highly flexible scheme of compatible components (called atoms and molecules). As a result, we achieve high speed-ups at moderate additional hardware. Furthermore, we can dynamically tradeoff between area and speed-up through runtime adaptation. We present the main components of our platform and discuss by means of an H.264 video codec.

The new McDonald diagnostic criteria for multiple sclerosis (MS) incorporate detailed criteria for the interpretation and classification of magnetic resonance imaging (MRI) findings, but, in contrast, provide no instructions for the interpretation of clinical findings. Because MS according to the McDonald criteria is one of the primary endpoints in a large trial enrolling patients after the first manifestation suggestive for a demyelinating disease (BENEFIT study), it was decided to organize a centralized eligibility assessment for this trial. During this eligibility assessment it was observed that there were marked inconsistencies in the decisions of participating neurologists with respect to the classification of clinical symptoms as being caused by one or more lesions provoking discussions in about one in every five patients. This paper describes these inconsistencies and their sources, and recommends a systematic approach that attempts to reduce the variability in interpreting clinical findings.

Realistic visualisation becomes more and more important in medicine. Whenever a patient individual 3D-model was generated the aim is to visualise the model as realistic as possible. We use 3D-models in our diagnostic and therapeutic tools for intraoperative visualisation of e.g. CT-scans. Most medical tools uses surface-rendering or volume-rendering for virtual visualisation. The coloration of a visualised model is normally done by using a convenient colour for each surface resp. volume. Our approach for 3D-models generated from motion in image series (e.g. videoendoscopes) is to add textures to the 3D-model. The main problem is, to handle the huge amount of videoimage-data (20Mb/sec.) and render the model in realtime.

Muscle forces stabilize the spine and have a great influence on spinal loads. But little is known about their magnitude. In a former in vitro experiment, a good agreement with intradiscal pressure and fixator loads measured in vivo could be achieved for standing and extension of the lumbar spine. However, for flexion the agreement between in vitro and in vivo measurements was insufficient. In order to improve the determination of trunk muscle forces, a three-dimensional nonlinear finite element model of the lumbar spine with an internal fixation device was created and the same loads were applied as in a previous in vitro experiment. An extensive adaptation process of the model was performed for flexion and extension angles up to 20 degrees and -15 degrees, respectively. With this validated computer model intra-abdominal pressure, preload in the fixators, and a combination of hip- and lumbar flexion angle were varied until a good agreement between analytical and in vivo results was reached for both, intradiscal pressure and bending moments in the fixators. Finally, the fixators were removed and the muscle forces for the intact lumbar spine calculated. A good agreement with the in vivo results could only be achieved at a combination of hip- and lumbar flexion. For the intact spine, forces of 170, 100 and 600 N are predicted in the m. erector spinae for standing, 5 degrees extension and 30 degrees flexion, respectively. The force in the m. rectus abdominus for these body positions is less than 25 N. For more than 10 degrees extension the m. erector spinae is unloaded. The finite element method together with in vivo data allows the estimation of trunk muscle forces for different upper body positions in the sagittal plane. In our patients, flexion of the upper body was most likely a combination of hip- and lumbar spine bending.

In our article [1], we did not declare some potential competing interests for Prof. Dr. med. Ludwig Kappos

Adaptive computing refers to the capability of a computing system to adapt one or more of its properties (e.g. performance) during runtime. There are diverse reasons of why it is advantageous for a computing system to adapt during runtime and there are various enabling techniques and paradigms that allow a computing system to perform such an adaptation. In the following, we limit our explanations of adaptive computing systems to the newest advances in embedded computing systems. Often, reconfigurable computing is referred to as adaptive computing. Actually, it corresponds to one of the key paradigms that along with application-specific instruction set processors enable adaptive computing. We will shortly discuss state-of-the-art in both areas.

Background Immobilisation, blood loss, sleep deficiency, and (concomitant) medications during perioperative periods might lead to acute exacerbation of symptoms in patients with the restless legs syndrome (RLS). Continuous transdermal delivery of the dopamine agonist rotigotine provides stable plasma levels over 24 h and may provide RLS patients with a feasible treatment option for perioperative situations. To assess the feasibility of use of rotigotine transdermal patch for the perioperative management of moderate to severe RLS, long-term data of an open-label extension of a rotigotine dose-finding study were retrospectively reviewed. Methods The data of all 295 patients who had entered the 5-year study were screened independently by two reviewers for the occurrence of surgical interventions during the study period. The following data were included in this post-hoc analysis: patient age, sex, surgical intervention and outcome, duration of hospital stay, rotigotine maintenance dose at the time of surgery, rotigotine dose adjustment, and continuation/discontinuation of rotigotine treatment. All parameters were analysed descriptively. No pre-specified efficacy assessments (e.g. IRLS scores) were available for the perioperative period. Results During the study period, 61 surgical interventions were reported for 52 patients (median age, 63 years; 67% female); the majority of patients (85%) had one surgical intervention. The mean rotigotine maintenance dose at time of surgery was 3.1 ± 1.1 mg/24 h. For most interventions (95%), rotigotine dosing regimens were maintained during the perioperative period. Administration was temporarily suspended in one patient and permanently discontinued in another two. The majority (96%) of the patients undergoing surgery remained in the study following the perioperative period and 30 of these patients (61%) completed the 5-year study. Conclusions Although the data were obtained from a study which was not designed to assess rotigotine use in the perioperative setting, this post-hoc analysis suggests that treatment with rotigotine transdermal patch can be maintained during the perioperative period in the majority of patients and may allow for uninterrupted alleviation of RLS symptoms. Trial Registration The 5-year rotigotine extension study is registered with ClinicalTrials.gov, identifier NCT00498186.

With the proliferation of portable and mobile IoT devices and their increasing processing capability, we witness that the edge of network is moving to the IoT gateways and smart devices. To avoid Big Data issues (e.g. high latency of cloud based IoT), the processing of the captured data is starting from the IoT edge node. However, the available processing capabilities and energy resources are still limited and do not allow to fully process the data on-board. It calls for offloading some portions of computation to the gateway or servers. Due to the limited bandwidth of the IoT gateways, choosing the offloading levels of connected devices and allocating bandwidth to them is a challenging problem. This paper proposes a technique for managing computation offloading in a local IoT network under bandwidth constraints. The existing bandwidth allocation and computation offloading management techniques underutilize the gateway’s resources (e.g. bandwidth) due to the fragmentation issue. This issue stems from the discrete coarse-grained choices (i.e. offloading levels) on the IoT end nodes. Our proposed technique addresses this issue, and utilizes the available resources of the gateway effectively. The experimental results show on average 1 hour (up to 1.5 hour) improvement in battery life of edge devices. The utilization of gateway’s bandwidth increased by 40%&nbsp

Reconfigurable processors provide a means to flexible and energy-aware computing. In this paper, we present a new scheme for runtime energy minimization (REMiS) as part of a dynamically recon-figurable processor that is exposed to run-time varying constraints like performance and footprint (i.e. amount of reconfigurable fabric). The scheme chooses an energy-minimizing set of so-called Special Instructions (considering leakage, dynamic, and reconfiguration energy) and then 'power-gates' a temporarily unused subset of the Special Instruction set. We provide a comprehensive evaluation for different technologies (ranging from 65 nm to 150 nm) and thereby show that our scheme is technology independent, i.e. it is beneficial for various technologies alike. By means of an H.264 video encoder we demonstrate that for certain performance constraints our scheme (applied to our in-house reconfigurable processor) achieves an allover energy saving of up to 40.8% (avg. 24.8%) compared to a performance-maximizing scheme. We also demonstrate that our scheme is equally beneficial to various other state-of-the-art reconfigurable processor architectures like Molen [9] where it achieves energy savings of up to 48.7% (avg. 28.93%) at 65 nm. We have employed an H.264 encoder within this paper as an application in order to demonstrate the strengths of our scheme, since the H.264's complexity and run-time unpredictability present a challenging scenario for state-of-the-art architectures. Categories and Subject Descriptors C.3 [Special-Purpose and Application-Based Systems]: Realtime and embedded systems General Terms: Design, Management

Background Achieving optimal symptom control with minimal side effects is a major goal in clinical practice. Dual-agent dopamine receptor agonist (DA) therapy in Parkinson’s disease (PD) may represent a promising approach to treatment, as the combination of different pharmacokinetic/pharmacological profiles may result in a lesser need for high dosages and, accordingly, may be well tolerated. The objective of the current study was to investigate safety and efficacy of rotigotine transdermal system as add-on to oral DA in patients with advanced PD inadequately controlled with levodopa and low-dose oral DA. Methods PD0015 was an open-label, multinational study in patients with advanced-PD and sleep disturbance or early-morning motor impairment. Patients were titrated to optimal dose rotigotine (≤8 mg/24 h) over 1–4 weeks and maintained for 4–7 weeks (8-week treatment). Dosage of levodopa and oral DA (pramipexole ≤1.5 mg/day, ropinirole ≤6.0 mg/day) was stable. Primary variable was Clinical Global Impressions (CGI) item 4: side effects, assessing safety. Other variables included adverse events (AEs), Patient Global Impressions of Change (PGIC), Unified Parkinson’s Disease Rating Scale (UPDRS) II and III, Parkinson’s Disease Sleep Scale (PDSS-2), Pittsburgh Sleep Quality Index (PSQI), and “off” time. Results Of 90 patients who received rotigotine, 79 (88%) completed the study; 5 (6%) withdrew due to AEs. Most (83/89; 93%) had a CGI-4 score

A novel policy for allocating reconfigurable fabric resources in multi-core processors is presented. We deploy a Minority-Game to maximize the efficient use of the reconfigurable fabric while meeting performance constraints of individual tasks running on the cores. As we will show, the Minority Game ensures a fair allocation of resources, e.g., no single core will monopolize the reconfigurable fabric. Rather, all cores receive a “fair” share of the fabric, i.e., their tasks would miss their performance constraints by approximately the same margin, thus ensuring an overall graceful degradation. The policy is implemented on a Virtex-4 FPGA and evaluated for diverse applications ranging from security to multimedia domains. Our results show that the Minority-Game policy achieves on average 2× higher application performance and a 5× improved efficiency of resource utilization compared to state-of-the-art.

International audience; We present a static analysis framework for real-time task systems running on multi-core processors. Our method analyzes tasks in isolation at the binary level and generates worst-case timing and memory access profiles. These profiles can then be combined to perform an interference analysis at the task system level, as part of a multi-core Worst-Case Response Time (WCRT) analysis. In this paper we introduce a formal description of the models and algorithmic building blocks composing our framework. We also discuss how the memory access profiles generated by our method could be used to feed existing state-of-the-art WCRT frameworks. To the best of our knowledge, it is the first time that a method is documented on how to produce sound, safe and precise inputs for interference analysis methods.