Search

Part 4: Resource, Components and Information Flow; International audience; The major research in the resource management literature focuses primarily on two complementary sub-problems: (1) specification languages for formulating resource requests and (2) constraint problems modelling allocation and scheduling. Both directions assume the knowledge of the underlying platform architecture and the dependencies it induces on the usage of the various resources. In this paper, we bridge this gap by introducing constraint-flow nets (cfNets). A cfNet is defined by a set of resources and dependencies between them, each dependency having an associated constraint schema. The model is inspired by Petri nets, with resources corresponding to places and dependencies—to transitions. Given an architecture of dependent resources, an initial resource request is propagated through the dependencies. The generated constraints are then conjuncted into the global allocation constraint. We study the notion of conflicts in cfNets and prove that for conflict-free cfNets the global allocation constraint can be constructed unambiguously. Furthermore, we provide an SMT-based algorithm for conflict detection and discuss the use of priorities to dynamically resolve conflicts at run-time. Finally, we illustrate the use of cfNets on a case study inspired by the Kalray MPPA architecture.

The decision-making process regarding drug dose, regularly used in everyday medical practice, is critical to patients’ health and recovery. It is a challenging process, especially for a drug with narrow therapeutic ranges, in which a medical doctor decides the quantity (dose amount) and frequency (dose interval) on the basis of a set of available patient features and doctor’s clinical experience (a priori adaptation). Computer support in drug dose administration makes the prescription procedure faster, more accurate, objective, and less expensive, with a tendency to reduce the number of invasive procedures. This paper presents an advanced integrated Drug Administration Decision Support System (DADSS) to help clinicians/patients with the dose computing. Based on a support vector machine (SVM) algorithm, enhanced with the random sample consensus technique, this system is able to predict the drug concentration values and computes the ideal dose amount and dose interval for a new patient. With an extension to combine the SVM method and the explicit analytical model, the advanced integrated DADSS system is able to compute drug concentration-to-time curves for a patient under different conditions. A feedback loop is enabled to update the curve with a new measured concentration value to make it more personalized (a posteriori adaptation).

Poor adherence to medical regimen causes approximately 33% to 69% of medication-related hospitalizations and accounts for $100 billion in annual health care costs. In this paper we address the problem of unintentional non adherence, when patient fails to take a medication due to forgetfulness or carelessness. We present the safe approach to software implementation of a portable reminder device with enabled personalization of medical regimen. The presented prototype is designed for imatinib administration, a drug used to treat Chronic Myeloid Leukemia (CML). However, thanks to the component-based structure of the software, the method can be applied to other cases by replacing implementation of certain components.

This paper proposes a parameterized Support Vector Machine (ParaSVM) approach for modeling the Drug Concentration to Time (DCT) curves. It combines the merits of Support Vector Machine (SVM) algorithm that considers various patient features and an analytical model that approxi- mates the predicted DCT points and enables curve calibrations using occasional real Therapeutic Drug Monitoring (TDM) measurements. The RANSAC algorithm is applied to construct the parameter library for the relevant basis functions. We show an example of using ParaSVM to build DCT curves and then calibrate them by TDM measurements on imatinib case study.

Design correctness and performance are major issues which are usually considered separately, and with different emphasis, by traditional system design flows. In this paper we show that one can meaningfully connect and benefit from the advantages of two design frameworks, with different design goals. We consider BIP for high-level rigorous design and correct-by-construction implementation, and metroII, for low-level platform-based design and performance evaluation.

Nowadays medical software is tightly coupled with medical devices that perform patient state monitoring and lately even some basic treatment procedures. Medical guidelines (GLs) can be seen as specification of a medical system which requires their computer-interpretable representation of medical GLs. Until now most of the medical GLs are often represented in a textual format and therefore often suffer from such structural problems as incompleteness, inconsistencies, ambiguity and redundancy, which makes the translation process to the machine-interpretable language more complicated. Computer-based interpretation of GLs can improve the quality of protocols as well as the quality of medical service. Several GLs formal representation methods have been presented recently. Only some of them enable automatic formal verification by introducing an additional translation path to the existing model checking environments. However, if a verified property fails it is difficult to trace back the result needed to change the model. Moreover, these formalisms provide the notion of time mostly in terms of actions order. In this paper we preset the application of a well-know formal behaviour representation approach of embedded systems design domain to medical GLs interpretation. We use Timed Automata extended with Tasks (TAT) and TIMES toolbox to represent medical GLs as a system behaviour in a computer interpretable form. We discuss the verification issues with the help of the anticancer drug imatinib case study.

Drug delivery is one of the most common clinical routines in hospitals, and is critical to patients’ health and recovery. It includes a decision making process in which a medical doctor decides the amount (dose) and frequency (dose interval) on the basis of a set of available patients’ feature data and the doctor’s clinical experience (a priori adaptation). This process can be computerized in order to make the prescription procedure in a fast, objective, inexpensive, non-invasive and accurate way. This paper proposes a Drug Administration Decision Support System (DADSS) to help clinicians/patients with the initial dose computing. The system is based on a Support Vector Machine (SVM) algorithm for estimation of the potential drug concentration in the blood of a patient, from which a best combination of dose and dose interval is selected at the level of a DSS. The addition of the RANdom SAmple Consensus (RANSAC) technique enhances the prediction accu- racy by selecting inliers for SVM modeling. Experiments are performed for the drug imatinib case study which shows more than 40% improvement in the prediction accuracy compared with previous works. An important extension to the patient features’ data is also proposed in this paper.

Computer-based interpretation of medical guide- lines (GLs) has drawn lots of attention in the past three decades. It is essential to use a formalism for GLs representation that would enable the validation of GLs structural properties, be able to map medical actions into the time scale and support the automatic formal verification of GLs without additional translation paths. In this paper we preset a novel approach based on Timed Automata extended with Tasks (TAT) for the medical protocol formal representation using the TIMES toolbox. We discuss the verification issues with the help of the Imatinib case study.

This paper advocates a rigorously formal and compositional style for obtaining key performance and/or interface metrics of systems with real-time constraints. We propose a hierarchical approach that couples the independent and different by nature frameworks of Modular Performance Analysis with Real-time Calculus (MPARTC) and Parametric Feasibility Analysis (PFA). Recent work on Real-time Calculus (RTC) has established an embedding of state-based component models into RTC-driven performance analysis for dealing with more expressive component models. However, with the obtained analysis infrastructure it is possible to analyze components only for a fixed set of parameters, e. g., fixed CPU speeds, fixed buffer sizes etc., such that a big space of parameters remains unstudied. In this paper, we overcome this limitation by integrating the method of parametric feasibility analysis in an RTC-based modeling environment. Using the PFA tool-flow, we are able to find regions for component parameters that maintain feasibility and worst-case properties. As a result, the proposed analysis infrastructure produces a broader range of valid design candidates, and allows the designer to reason about the system robustness.

The implementation of service-rich, highly interconnected applications and the increasing demand for performance, requires the development of highly optimized and flexible computing platforms. However, the tight real-time requirements of such systems, together with constraints on cost and physical size of the devices, results in increased design complexity and system heterogeneity. This creates a large design space. In this paper, we propose a structured approach based on system level specification languages that supports the rapid exploration and performance evaluation of computing platforms, including their middleware components, through simulation of abstract models. Accuracy is achieved through an off-line rapid architecture profiling procedure. We focus on a process network model, which is more suitable to the description of concurrent functions and data-dominated applications than a traditional sequential programming model. We describe the structure of our simulation framework, and use it to evaluate the performance of the lower layers of the UMTS protocol when mapped on software defined radio oriented architectures.

The safe and, at the same time, efficient deployment of parallelisable applications on many-core platforms is a challenging task. Theoretical Models of Computation (MoC) require the realistic estimation of task Worst-Case Execution Time (WCET) to provide safe latency guarantees. Due to interferences on shared resources, task WCET estimations are often exceedingly pessimistic. In reality, though, rarely do all the tasks execute with their WCET, thus introducing an efficiency gap, which is of consequence in realizing safety-critical and mixed-criticality systems. In this paper, we outline the additional research efforts required to i) derive a safe deployment from a MoC reducing that efficiency gap and ii) adapt at runtime to further improve performance and still preserve safety. We also outline the impact of the level of data-parallelisation onto this efficiency gap and present experimental evidence of the performance improvements from accurate WCET estimation, level of data-parallelisation and runtime adaptation.

The optimal deployment of data streaming applications onto multi-/many-core platforms providing real-time guarantees requires to solve the application partitioning/placement, buffer allocation, task mapping and scheduling optimisation problem using the tasks Worst-Case Execution Time (WCET). In turn, task WCET varies due to interferences that tasks experience when accessing shared resources, which vary depending on the solutions of the optimisation problem. To break this cyclic dependency we propose a detailed interference-based method that first over-approximates WCET based on the solution for application partitioning/placement and then tightens it by pruning out the interferences from tasks not overlapping in memory access and time. We prove that the derived bounds are safe. We have found that interferences on average amount to 10 % of WCET, and were able to improve the latency-guarantee up to 34 %.

The technologies for continuous measurement of the anaesthetic agents circulating in body fluids are not mature yet, though some preliminary prototypes exist already. We present a control algorithm that based on the real measurement of propofol plasma concentration may adjust the delivery rate. This opens a possibility for a safer anesthesia when the technologies for online measurement of drug concentration will be mature enough to be combined with our model.