Projects 2016/2017


1) Approximate Networking


Abstract: Decades of experience have shown that there is no single one-size-fits-all solution that can be used to provision Internet globally and that invariably there are tradeoffs in the design of Internet. Despite the best efforts of networking researchers and practitioners, an ideal Internet experience is inaccessible to an overwhelming majority of people the world over, mainly due to the lack of cost efficient ways of provisioning high-performance global Internet. In this paper, we argue that instead of an exclusive focus on a utopian goal of universally accessible “ideal networking” (in which we have high throughput and quality of service as well as low latency and congestion), we should consider providing “approximate networking” through the adoption of context-appropriate tradeoffs. Approximate networking can be used to implement a pragmatic tiered global access to the Internet for all (GAIA) system in which different users the world over have different context-appropriate (but still contextually functional) Internet experience. In addition, approximate networking can be used to simplify network architectures and protocols to be robust to uncertain conditions of scarcity and limits.

References:

  • Qadir, Junaid, et al. "Approximate Networking for Global Access to the Internet for All (GAIA)." arXiv preprint arXiv:1603.07431 (2016) [pdf].
  • Video presentation: https://www.youtube.com/watch?v=4hKvgIi-HZY.

  • Collaborators: University of Cambridge; University of Surrey.

    The project will be ideal for a student who wishes to undertake original research work in the field of networking, and pursue advanced degrees (MS and PhD). By the end of this project, the student can expect to learn basic research skills and familiarity with computer networking research.


    2) Big data for development


    Abstract: With the explosion of social media sites and proliferation of digital computing devices and Internet access, massive amounts of public data is being generated on a daily basis. Efficient techniques/ algorithms to analyze this massive amount of data can provide near real-time information about emerging trends and provide early warning in case of an imminent emergency (such as the outbreak of a viral disease). In addition, careful mining of these data can reveal many useful indicators of socioeconomic and political events, which can help in establishing effective public policies. The emerging ability to use big data techniques for development (BD4D) promises to revolutionalize healthcare, education, and agriculture; facilitate the alleviation of poverty; and help to deal with humanitarian crises and violent conflicts. The focus of this talk will be on reviewing the application of big data analytics for the purpose of human development. Besides all the benefits, the large-scale deployment of BD4D is beset with several challenges due to the massive size, fast-changing and diverse nature of big data. The most pressing concerns relate to efficient data acquisition and sharing, establishing of context (e.g., geolocation and time) and veracity of a dataset, and ensuring appropriate privacy.

    References:

  • Ali, Anwaar, et al. "Big Data For Development: Applications and Techniques."arXiv preprint arXiv:1602.07810 (2016) [pdf].
  • Slides: http://www.slideshare.net/junaidq/big-data-for-development [link].
  • Qadir, Junaid, et al. "Crisis Analytics: Big Data Driven Crisis Response."arXiv preprint arXiv:1602.07813 (2016) [pdf].

  • Collaborators: University of Cambridge; University of Groningen; University of Stirling.

    The project will be ideal for a student who wishes to undertake original research work in the field of networking, and pursue advanced degrees (MS and PhD). By the end of this project, the student can expect to learn basic research skills and familiarity with computer networking research.


    3) Computational social science & Network science


    Abstract: Computational social science refers to the academic sub-disciplines concerned with computational approaches to the social sciences. This means that computers are used to model, simulate, and analyze social phenomena. With the advances in technology such as mobile phones, we can now collect data about human behavior on a scale never before possible and with tremendous granularity and precision. The ability to collect and process "big data" enables researchers to address core questions in the social sciences in new ways and opens up new areas of inquiry.

    Some questions that we can study are:


  • Pakistan-specific twitter/ online social media analytics.
  • We can think of determining the clusters of different population subsets and how they differ (cf.http://www.ramb.ethz.ch/CDstore/www2005-ws/workshop/wf10/AdamicGlanceBlogWWW.pdf).
  • We can identify what kind of views are represented by traditional media (e.g., the twitter account/ web pages of Dawn vs. Jang vs. Express)
  • Can we identify the influential voices in this debate? (cf. http://www.egr.msu.edu/waves/people/usman_files/ICC11_Centrality.pdf).
  • With the tumultuous polarized current state of affairs in Pakistan, I think now would be an excellent time to use online social analytics for getting a macro pulse of the nation on many important affairs (vis-à-vis politics, sports, etc.)

    References:

  • Computational Social Science course at Princeton: [link].
  • Network Science: [link], [link].
  • Book on Network Science by Barabasi available at: [link].

  • Online social network (OSN) analytics:


  • Gilani, Zafar, Liang Wang, Jon Crowcroft, Mario Almeida, and Reza Farahbakhsh. "Stweeler: A Framework for Twitter Bot Analysis." In Proceedings of the 25th International Conference Companion on World Wide Web, pp. 37-38. International World Wide Web Conferences Steering Committee, 2016. [pdf].
  • http://www.ccs.neu.edu/home/amislove/twittermood/.
  • http://wefeel.csiro.au/.
  • http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7042256.

  • Collaborators: University of Cambridge; University of Groningen; University of Stirling.

    The project will be ideal for a student who wishes to undertake original research work in the field of networking, and pursue advanced degrees (MS and PhD). By the end of this project, the student can expect to learn basic research skills and familiarity with computer networking research.


    4) Applied machine learning in networking


    4a) ML and AI in Networks


    The use of applied machine learning algorithms to improve the practice of computer networking through the design of better performing algorithms and protocols.

    For ideas around this topic, see the CFP of IEEE ICNP Workshop on Machine Learning in Computer Networks http://networkml.github.io/.

    References:

  • Ahad, Nauman, Junaid Qadir, and Nasir Ahsan. "Neural networks in wireless networks: Techniques, applications and guidelines." Journal of Network and Computer Applications 68 (2016): 1-27 [pdf].
  • Arif, Moiz, Adnan K. Kiani, and Junaid Qadir. "Machine learning based optimized live virtual machine migration over WAN links." Telecommunication Systems (2016): 1-13 [pdf].
  • Qadir, Junaid. "Artificial intelligence based cognitive routing for cognitive radio networks." Artificial Intelligence Review 45.1 (2016): 25-96 [pdf].

  • Collaborators: Sunway University, Malaysia.


    4b) Network Scientiometrics


    The use of data mining/ machine learning to learn about the field of computer networks research (scientiometrics applied to the field of networking).

    References:

    Chiu, Dah Ming, and Tom ZJ Fu. "Publish or Perish in the Internet Age: a study of publication statistics in computer networking research." ACM SIGCOMM Computer Communication Review 40.1 (2010): 34-43 [pdf].


    The project will be ideal for a student who wishes to undertake original research work in the field of networking, and pursue advanced degrees (MS and PhD). By the end of this project, the student can expect to learn basic research skills and familiarity with computer networking research.


    5) Mobile health


    Compared to its neighbors, Pakistan’s health performance is below par in the majority of health indicators---with Pakistan’s health profile being characterized by high infant and child mortality, and a large burden of communicable and non-communicable diseases. The Pakistani health system is burdened by a large number of patients that suffer from chronic diseases (the prevalence of diabetes is reported at 10 percent, and one in three adults over 45 years suffers from high blood pressure). Despite having a vast integrated public health system, which is administratively managed at the district level, the Pakistani healthcare service is largely dysfunctional and a large segment of the population (especially those in rural areas) has to suffer inferior-quality health service. This dismal performance can be attributed to many factors including the lack of government support (in terms of government funds for health), political instability, lack of qualified staff (particularly in rural/remote areas), and other socio-cultural factors. As a result, the Pakistani healthcare system underperforms due to the the system being inefficient, understaffed, overwhelmed with patients, siloed, and data-poor.

    Although not a silver bullet, we are convinced that the use of technology can significantly improve the healthcare service available to the Pakistani population. In particular, we are interested in using a mobile technology augmented healthcare (mHealth) system (which has been defined by the World Health organization as the support of medical and public health practice through mobile devices—such as mobile phones, patient monitoring devices, personal digital assistants and other wireless devices). Our optimism around mHealth is based on the wide uptake and increasingly sophisticated capabilities of modern phones and smartphones. We believe that combining mobile phone technology with other advances in information and communication technology (ICT)—in fields such as artificial intelligence, machine-learning, computing systems and networks—can revolutionize the health sector in developing countries (such as Pakistan). An mHealth system has the potential to transform the current healthcare system into a system that is more optimized, personalized, and integrated. MHealth can also be instrumental in steering medicine away from its current overbearing engagement with treating diseases towards an ecosystem that emphasizes wellness and prevention.

    Collaborators: Engineering for Health program at University of Surrey; University of Stirling; University of Cambridge.


    6) Global Access to the Internet for All (GAIA) using wireless technology


    We live in a world in which there is a great disparity between the lives of the rich and the poor. Information and communi- cation technology (ICT) offers promise in bridging this digital divide through its focus on connecting human capacity with computing and informational content. It is well known that Internet access has the capability of fostering development and growth by enabling access to information, education, and opportunities. Unfortunately, the availability of Internet in worldwide terms is limited, with an estimated 4 billion people— an estimated 60% of the human population—lacking Internet access. The people in rural areas are particularly hard hit since socio-economic factors preclude the provisioning of Internet and mobile telephony in these sparsely populated low- income areas.


    There is a growing interest in using novel wireless solutions—such as TV white space (TVWS), satellites, drones, free space optics—to unfetter rural areas from the encumber- ing constraints of infrastructure (traditionally associated with broadband Internet provisioning). The aim of this feature topic (FT) is to highlight the research being done on leveraging “wireless technologies for development” (W4D), and thereby increase the quality of life for a larger segment of human societies by providing them opportunities to connect resources and capacity, especially by provisioning affordable universal Internet access. This FT is especially timely since it coincides with the recent push by various companies (such as Facebook/ Internet.org) and organizations (such as the Global Access to the Internet for All (GAIA) research group at the Internet Research Task Force (IRTF)) for the vision of global access to the Internet for all.

    Collaborators: Network for Development Lab (N4D), University of Cambridge.