1435 research outputs found
Sort by
A Temporal Visual Distribution of Learning Activities in FLOSS Repositories
No full textProcess mining is a relatively new field that encompasses
powerful data and process analytics techniques for understanding processes
from event data. In addition to these main techniques, it provides
means enabling a pictorial representation of the occurrence of events
over time. By applying such visualizations to event data from Free/Libre
Open Source Software (FLOSS) environments, we get a complete understanding
of how certain activities take place within such environments
over time. Particularly, given the increasing interests in learning
paradigms present in FLOSS communities, we believe that a temporal
visual representation of learning events can yield great benefits. In this
paper, we make use of the dotted chart in process mining to model and
present a representation of learning behaviours over time for FLOSS participant
QoS-aware Deployment of IoT Applications Through the Fog
No full textFog computing aims at extending the Cloud by bringing computational power, storage and communication capabilities to the edge of the network, in support of the IoT. Segmentation, distribution and adaptive deployment of functionalities over the continuum from Things to Cloud are challenging tasks, due to the intrinsic heterogeneity, hierarchical structure and very large scale infrastructure they will have to exploit.
In this paper we propose a simple, yet general, model to support the QoS-aware deployment of multi-component IoT applications over Fog infrastructures. The model describes operational systemic qualities of the available infrastructure (latency and bandwidth), interactions among software components and Things, and business policies. Algorithms to determine eligible deployment plans for an application over a Fog infrastructure are presented. A Java tool, FogTorch, based on the proposed model has been prototyped
Dipyridamole in Heart Failure due to Dilated Cardiomyopathy: A Pilot Study
No full textIntroduction: Dipyridamole (DIP) might be beneficial in heart failure (HF). It has been reported to improve symptoms in observational, small‑scale studies. The PRoFESS study for secondary prevention of stroke observed a reduction in the risk of HF with acetylsalicylic acid (ASA) plus DIP in comparison with clopidogrel. The present pilot study was aimed at assessing the clinical effects of DIP and ASA in dilated cardiomyopathy.
Materials and Methods: Nineteen outpatients with nonischemic HF, New York Heart Association (NYHA) Class II, ejection fraction (EF) <40%, were randomized to ASA 25 mg, or ASA 25 mg plus DIP 200 mg (ASA + DIP), twice daily. They were evaluated at baseline and after 6 months for symptoms, EF, and exercise capacity through 6‑min walk test.
Results: Eleven subjects were in the ASA group and 8 in the ASA + DIP. Dyspnea improved, without differences between the two arms: n = 6/5/0/0 for NYHA I/II/III/IV in ASA, n = 4/3/1/0 in ASA + DIP. EF increased in both groups (ASA: from 34 [28–35%] to 40 [32–46%]; ASA + DIP from 32.5 [25.75–34%] to 36 [31.5–46%]). No change in meters walked or points in the Borg scale was observed. In a similar population, an adequately powered study would need to recruit 38 subjects.
Conclusion: The study, although underpowered, did not show any difference between the two treatment strategies. While this appears in contrast with previous studies, the strict inclusion criteria, the randomized, double‑blind design, and the clinical end‑points give strength to our findings. A properly sized trial would be within the capabilities of a single center
Optimization tools for solving equilibrium problems with nonsmooth data
No full textThe paper deals with the gap function approach for equilibrium problems with locally Lipschitz data. The gap function inherits the locally Lipschitz continuity of the data. Hence, the connections between its generalized directional derivatives, monotonicity conditions on the equilibrium bifunction and descent properties can be analysed. In turn, this analysis leads to devise
two descent methods. Finally, the results of preliminary numerical tests arereported
Modelling the behaviour of management operations in TOSCA
No full textManaging complex applications over heterogeneous clouds is one of the emerging problems in the cloud era. The OASIS Topology and Orchestration Specification for Cloud Applications (TOSCA) aims at solving this problem by providing a language to describe and manage complex cloud applications in a portable and vendor-agnostic way.
TOSCA permits to define an application as an orchestration of components, whose types can specify states, requirements, capabilities and management operations --- but not how they interact with each other.
In [1][2], we already discussed a simple extension of TOSCA that permits describing the behaviour of a component's management operations and their relations with its states, requirements, and capabilities. The objective of this short report is to show how to enrich the TOSCA modelling language to provide such extension
QoS Routing with worst-case delay constraints: models, algorithms and performance analysis
No full textIn a network where weighted fair-queueing schedulers are used at each link, worst-case end-to-end delays can be inferred from per-link rate reservations. Therefore, it is also possible to compute resource-constrained paths that meet target delay constraints, and optimize some key performance metrics (e.g., minimize the overall reserved rate, maximize the remaining capacity at bottleneck links, etc.). Despite the large amount of literature on QoS routing appeared since the mid '90s, few papers so far have discussed solving such path computation problem at optimality in general settings. In this paper, we formulate and solve the optimal path computation and resource allocation problem assuming different types of weighted fair-queueing schedulers in the network. We show that, depending on the scheduling algorithm, routing a new flow may or may not affect the performance of existing flows; hence, explicit admission control constraints may be required to ensure that existing flows still meet their deadline afterwards. Yet, for the relevant schedulers proposed in the literature the problem can be formulated as a Mixed-Integer Second-Order Cone problem (MI-SOCP), and can be solved at optimality in split-second times even in fairly large networks
Delay-constrained Routing Problems: Accurate Scheduling Models and Admission Control
No full textIt has been recently shown that the problem of routing a new packet flow in a computer network subject to a constraint on the worst-case end-to-end delay of its packets can be formulated as a Mixed-Integer Second-Order Cone Program (MI-SOCP), and solved with general-purpose tools on instances of realistic size in time compatible with real-time use. However, that result was obtained for only one of the classes of schedulers in use in today's networks, namely Strictly Rate-Proportional ones. Furthermore, that result relies on assuming that each link is "fully loaded", so that the reserved rate of the flow coincides with its guaranteed rate. These assumptions entail both simple latency expressions, and the fact that flows are isolated from each other as far as their end-to-end delay is concerned; that is, admitting a new flow does not increase the end-to-end delay of the existing ones. However, other classes of scheduling algorithms commonly found in current networks both yield more complex latency formulae and do not enforce strict flow independence. Furthermore, the delay actually depends on the guaranteed rate of the flow, which can be significantly larger than the reserved rate if the network is less loaded. In this paper we extend the result to other classes of schedulers and to a more accurate representation of the latency, showing that, despite the increase in complexity, the problem is still efficiently solvable, even when admission control needs to be factored in, for realistic instances, provided that the right modeling choices are made
Predicting the QoS of service orchestrations
No full textThe ability to a priori predict the QoS of a service orchestration is of pivotal importance both for the design of service compositions and for the definition of their SLAs. In this paper we present an algorithm to probabilistically predict the QoS of WS-BPEL service orchestrations. Our algorithm employs Monte Carlo simulations and it improves previous approaches by coping with complex dependency structures, unbound loops, fault handling, and unresponded service invocations. A proof-of-concept implementation of the algorithm in F# is described
TOSCA-MART: A Method for Adapting and Reusing Cloud Applications
No full textTo fully appreciate cloud computing powers, design and development of cloud applications should be eased and supported. The OASIS TOSCA standard enables developers to design and develop cloud applications by specifying their topologies as orchestrations of typed nodes and relationships.However, building such application topologies often results in reinventing the wheel multiple times when similar solutions are manually created for different applications by different developers having the same requirements. Thus, the reusability of existing TOSCA solutions is crucial to ease and support design and development processes. In this paper, we tackle this issue. We introduce TOSCA-MART, a method that enables deriving valid implementations for custom components from a repository of complete and validated cloud applications. The method enables developers to specify individual components in their application topologies, and illustrates how to match, adapt, and reuse existing (fragments of) applications to implement these components while fulfilling all their compliance requirements. We also characterize and validate TOSCA-MART by means of a prototypical implementation based on an open source toolchain and a case study