Background: Recurrence is an important cornerstone in breast cancer behaviour, intrinsically related to mortality. In spite of its relevance, it is rarely recorded in the majority of breast cancer datasets, which makes research in its prediction more difficult. Objectives: To evaluate the performance of machine learning techniques applied to the prediction of breast cancer recurrence. Material and Methods: Revision of pub- lished works that used machine learning techniques in local and open source databases between 1997 and 2014. Results: The revision showed that it is difficult to obtain a representative dataset for breast cancer recurrence and there is no consensus on the best set of predictors for this disease. High accuracy results are often achieved, yet compromising sensitivity. The missing data and class imbalance problems are rarely addressed and most often the chosen performance metrics are inappropriate for the context. Discussion and Conclusions: Although different techniques have been used, prediction of breast cancer recurrence is still an open problem. The combination of different machine learning techniques, along with the definition of standard predictors for breast cancer recurrence seem to be the main future directions to obtain better results.
Attestation is a mechanism used by a trusted entity to validate the software integrity of an untrusted platform. Over the last years, several attestation techniques have been proposed. While they all use variants of a challenge-response protocol, they make different assumptions about what an attacker can and cannot do. Thus, they propose intrinsically divergent validation approaches. We survey in this paper the different approaches to attestation focussing in particular on those aimed at Wireless Sensor Networks. We discuss the motivations, challenges, assumptions, and attacks of each approach. We then organise them in a taxonomy and discuss the state of the art, carefully analysing the advantages and disadvantages of each proposal. We also point towards the open research problems and give directions on how to address them.
The connected car -a vehicle capable of accessing to the Internet, of communicating with smart devices as well as other cars and road infrastructures, and of collecting real-time data from multiple sources- is likely to play a fundamental role in the foreseeable Internet Of Things. In a context ruled by very strong competitive forces, a significant amount of car manufacturers and software and hardware developers have already embraced the challenge of providing innovative solutions for new generation vehicles. Today's cars are asked to relieve drivers from the most stressful operations needed for driving, providing them with interesting and updated entertainment functions. In the meantime, they have to comply to the increasingly stringent standards about safety and reliability. The aim of this paper is to provide an overview of the possibilities offered by connected functionalities on cars and the associated technological issues and problems, as well as to enumerate the currently available hardware and software solutions and their main features.
Security isolation is a foundation of computing systems that enables resilience to different forms of attacks. This article seeks to understand security isolation by systematizing its many characteristics. We provide a hierarchical classification structure for grouping isolation techniques. At the top level, we consider two principle aspects: mechanism and policy. Each aspect is broken down into salient dimensions that describe key properties. We apply our classification to more than 80 papers that cover a breadth of security isolation techniques and evaluate trade-offs. Finally, we motivate the creation of smart security isolation and highlight the open issues that will enable it.
Cloud computing enables users to provision resources on demand and execute applications in a way that meets their requirements by choosing virtual resources that fit their application resource needs. Then, it becomes the task of cloud resource providers to accommodate these virtual resources onto physical resources. This problem is a fundamental challenge in Cloud Computing as resource providers need to map virtual resources onto physical resources in a way that takes into account the providers' optimization objectives. This paper surveys the relevant body of literature that deals with this mapping problem and how it can be addressed in different scenarios and through different objectives and optimization techniques. The evaluation aspects of different solutions are also considered. The paper aims at both identifying and classifying research done in the area adopting a categorization that can enhance understanding of the problem.
Interconnection networks are of paramount importance for any high-performance parallel computer. The main issues are the topology, routing and flow-control algorithms, while physical constraints determine the realistic properties of the network. We present some theoretical background related to often used network topologies. The interconnection networks of the best-performing petascale parallel computers from the past and present Top500 lists are analyzed. The lessons learned from this analysis led us to the conclusion that novel solutions in computer networks are needed to improved performance of future exascale parallel computers.