Data Mining Practical Machine Learning Tools and Techniques

Machine Learning (ML) has been enjoying an unprecedented surge in applications that solve problems and enable automation in diverse domains. Primarily, this is due to the explosion in the availability of data, significant improvements in ML techniques, and advancement in computing capabilities. Undoubtedly, ML has been applied to various mundane and complex problems arising in network operation and management. There are various surveys on ML for specific areas in networking or for specific network technologies. This survey is original, since it jointly presents the application of diverse ML techniques in various key areas of networking across different network technologies. In this way, readers will benefit from a comprehensive discussion on the different learning paradigms and ML techniques applied to fundamental problems in networking, including traffic prediction, routing and classification, congestion control, resource and fault management, QoS and QoE management, and network security. Furthermore, this survey delineates the limitations, give insights, research challenges and future opportunities to advance ML in networking. Therefore, this is a timely contribution of the implications of ML for networking, that is pushing the barriers of autonomic network operation and management.

/pdf/a-comprehensive-survey-on-machine-learning-for-networking-3t5h3kbpe8.pdf

A comprehensive survey on machine learning for networking: evolution, applications and research opportunities

http://gac.des.udc.es/~gltaboada/papers/taboada_scp11preprint.pdf

Java in the High Performance Computing arena: Research, practice and experience

Crowdsourcing is currently attracting much attention from organisations for its competitive advantages over traditional work structures regarding how to utilise skills and labour and especially to harvest expertise and innovation. Prior research suggests that the decision to crowdsource cannot simply be based on perceived advantages; rather multiple factors should be considered. However, a structured account and integration of the most important decision factors is still lacking. This research fills the gap by providing a systematic literature review of the decision to crowdsource. Our results identify nine factors and sixteen sub-factors influencing this decision. These factors are structured into a decision framework concerning task, people, management, and environmental factors. Based on this framework, we give several recommendations for managers making the crowdsourcing decision.

Factors influencing the decision to crowdsource: A systematic literature review

Compressive sensing based data quality improvement for crowd-sensing applications

Today, smart phone's malwares are deceptive enough to spoof itself as a legal mobile application. The front-end service of Trojans is attractive enough to deceive mobile users. Mobile users download similar malwares without knowing their illegitimate background threat. Unlike other vendors, Android is an open-source mobile operating system, and hence, it lacks a dedicated team to analyze the application code and decide its trustworthiness. We propose an augmented framework for Android that monitors the dynamic behavior of application during its execution. Our proposed architecture called Security Enhanced Android Framework (seaf) validates the behavior of an application through its permissions exercising patterns. Based on the exercised permissions' combination, the mobile user is intimated about the dangerous behavior of an application. We have implemented the proposed framework within Android software stack and ported it to device. Our initial investigation shows that our solution is practical enough to be used in the consumer market.

/pdf/an-android-runtime-security-policy-enforcement-framework-wy1k4sovri.pdf

An Android runtime security policy enforcement framework

With the transition to multicore processors almost complete, the parallel processing community is seeking efficient ways to port legacy message passing applications on shared memory and multicore processors. MPJ Express is our reference implementation of Message Passing Interface (MPI)-like bindings for the Java language. Starting with the current release, the MPJ Express software can be configured in two modes: the multicore and the cluster mode. In the multicore mode, parallel Java applications execute on shared memory or multicore processors. In the cluster mode, Java applications parallelized using MPJ Express can be executed on distributed memory platforms like compute clusters and clouds. The multicore device has been implemented using Java threads in order to satisfy two main design goals of portability and performance. We also discuss the challenges of integrating the multicore device in the MPJ Express software. This turned out to be a challenging task because the parallel application executes in a single JVM in the multicore mode. On the contrary in the cluster mode, the parallel user application executes in multiple JVMs. Due to these inherent architectural differences between the two modes, the MPJ Express runtime is modified to ensure correct semantics of the parallel program. Towards the end, we compare performance of MPJ Express (multicore mode) with other C and Java message passing libraries---including mpiJava, MPJ/Ibis, MPICH2, MPJ Express (cluster mode)---on shared memory and multicore processors. We found out that MPJ Express performs signicantly better in the multicore mode than in the cluster mode. Not only this but the MPJ Express software also performs better in comparison to other Java messaging libraries including mpiJava and MPJ/Ibis when used in the multicore mode on shared memory or multicore processors. We also demonstrate effectiveness of the MPJ Express multicore device in Gadget-2, which is a massively parallel astrophysics N-body siimulation code.

https://researchportal.port.ac.uk/portal/files/101654/shafiEtAl2010.pdf

Multicore-enabling the MPJ express messaging library

The generalized use of the Internet and social network platforms has changed the way human beings establish relations, collaborate and share resources. In this context, crowdsourcing (or crowd computing) is becoming a common solution to provide answers to complex problems by automatically coordinating the potential of machines and human beings working together. Several challenges still separate crowdsourcing from its generalized acceptance by industry. For instance, the quality delivered by the workers in the crowd is crucial and depends on different aspects such as their skills, experience, commitment, etc. Trusting the individuals in a social network and their capacity to carry out the different tasks assigned to them becomes essential in speeding up the adoption of this new technology in industrial environments. Capacity to deliver on time, cost or confidentiality are just some other possible obstacles to be removed. In this paper, we discuss some of these issues, provide solutions to improve the quality in systems based on the use of crowdsourcing and present a real industrial problem where we use the crowd to leverage the work capacity of geographically distributed human beings.

Crowdsourcing for Industrial Problems

The need to increase performance while conserving energy lead to the emergence of multi-core processors. These processors provide a feasible option to improve performance of software applications by increasing the number of cores, instead of relying on increased clock speed of a single core. The uptake of multi-core processors by hardware vendors present variety of challenges to the software community. In this context, it is important that messaging libraries based on the Message Passing Interface (MPI) standard support efficient inter-core communication. Typically processing cores of today's commercial multi-core processors share the main memory. As a result, it is vital to develop devices to exploit this. MPJ Express is our implementation of the MPI-like Java bindings. The software has mainly supported communication with two devices; the first is based on Java New I/O (NIO) and the second is based on Myrinet. In this paper, we present two shared memory implementations meant for providing efficient communication of multi-core and SMP clusters. The first implementation is pure Java and uses Java threads to exploit multiple cores. Each Java thread represents anMPI level OS process and communication between these threads is achieved using shared data structures. The second implementation is based on the System V (SysV) IPC API. Our goal is to achieve better communication performance than already existing devices based on Transmission Control Protocol (TCP) and Myrinet on SMP and multi-core platforms. Another design goal is that existing parallel applications must not be modified for this purpose, thus relieving application developers from extra efforts of porting their applications to such modern clusters. We have benchmarked our implementations and report that threads-based device performs the best on an Intel quad-core Xeon cluster.

Towards efficient shared memory communications in MPJ express

The exponential growth in adoption of mobile phones and the widespread availability of wireless networks has caused a paradigm shift in the way we access the Internet. It has not only eased access to the Internet, but also increased users’ appetite for responsive services. New protocols to speed up Internet applications have naturally emerged. The QUIC transport protocol is one prominent case. Initially developed by Google as an experiment, the protocol has already made phenomenal strides, thanks to its support in Google’s servers and Chrome browser. Since QUIC is still a relatively new protocol, there is a lack of sufficient understanding about its behavior in real network scenarios, particularly in the case of wireless networks. In this paper we present a comprehensive study on the performance of QUIC in Wireless Mesh Networks (WMN). We perform a measurement campaign on a production WMN to compare the performance of QUIC against TCP when retrieving files from the Internet. Our results show that while QUIC outperforms TCP in wired networks, it exhibits significantly lower performance than TCP in the WMN. We investigate the reasons for this behavior and identify the root causes of the performance issues. We find that some design choices of QUIC may penalize the protocol in WiFi, e.g., uncovering sub-optimal interactions of QUIC with MAC layer features, such as frame aggregation. Finally, we implement and evaluate our solution and demonstrate up to 28% increase in throughput of QUIC.

/pdf/on-the-performance-of-quic-over-wireless-mesh-networks-27itf009fx.pdf

Jawad Manzoor

Papers

An Android runtime security policy enforcement framework

Multicore-enabling the MPJ express messaging library

Crowdsourcing for Industrial Problems

Towards efficient shared memory communications in MPJ express

On the Performance of QUIC over Wireless Mesh Networks