Paper accepted by IEEE CCNC 2016

September 13, 2015September 18, 2015 ~ drmmu ~ Leave a comment

A full paper entitled “QoE-aware Inter-stream Synchronization in Open N-Screens Cloud” has been accepted by the the QoE and Human-Centered Communications and Application track of IEEE Consumer Communications & Networking Conference (CCNC), Las Vegas, January 9-12, 2016. The conference is held in conjunction with the International Consumer Electronics Show (CES).

I am also a PC member of the Cloud Services and Networking track of the same conference.

Paper abstract:

The growing popularity and increasing performance of mobile devices is transforming the way in which media can be consumed, from single device playback to orchestrated multi-stream experiences across multiple devices. One of the biggest challenges in realizing such immersive media experience is the dynamic management of synchronicity between associated media streams. This is further complicated by the faceted aspects of user perception and heterogeneity of user devices and networks. This paper introduces a QoE-aware open inter-stream media synchronization framework (IMSync). IMSync employs efficient monitoring and control mechanisms, as well as a bespoke QoE impact model derived from subjective user experiments. The impact model balances the accumulative impact of re-synchronization processes and the degree of non-synchronicity to ensure the QoE. Experimental results verify the run-time performance of the framework as a foundation for immersive media experience in open N-Screens cloud.

Network resilience with anomaly detection in the cloud

August 27, 2015 ~ drmmu ~ Leave a comment

Since July 2015, I’ve been involved in Lancaster University’s activities in the EC FP7 SECCRIT (SEcure Cloud computing for CRitical infrastructure IT) project, a multidisciplinary research project with the mission to analyse and evaluate cloud computing technologies with respect to security risks in sensitive environments, and to develop methodologies, technologies, and best practices for creating a secure, trustworthy, and high assurance cloud computing environment for critical infrastructure IT.

We specifically look into network resilience with anomaly detection in the cloud, using the well-known D2R2+DR (Defence, Detect, Remediate, Recover, Diagnose and Refine) principle. The first phase of D2R2 begins with defence, making the network as resistant as possible to challenges. Inevitably however, a network will be threatened and it must be able to detect this automatically. It will then remediate any damage to minimize the overall impact, and finally will recover as it repairs itself and transitions back to normal operation. The second longer-term phase DR consists of diagnosing any design flaws that permitted the defences to be penetrated, followed by a refinement of network behaviour to increase its future resilience. From this strategy, we derive a set of design principles leading to resilient networks.

IEEE Multimedia special issue on Social Multimedia and Storytelling (July–September 2015)

August 24, 2015August 24, 2015 ~ drmmu ~ Leave a comment

Quick link to my paper: http://www.computer.org/csdl/mags/mu/2015/03/mmu2015030054-abs.html

Social Multimedia and Storytelling

July–September 2015

From the Editor

This special issue touches on many significant aspects of multimedia retrieval, including content analysis and understanding, content- and context-based indexing, search and retrieval, HCI technologies, and image and video summarization and visualization. It converges on the nexus of social multimedia and storytelling around real-world experiences, events, and places. Aside from the challenging research problems in this emerging area, its topics are linked to a host of important commercial and creative applications in sectors such as media, entertainment, arts and culture, sports, and music. READ ARTICLE »

A collaboration with TU-Berlin sees an accepted paper on context-aware user behaviour modelling at RecsysTV (Recsys 2015)

August 4, 2015August 4, 2015 ~ drmmu ~ Leave a comment

With over 2,000 registered users, Lancaster’s Vision IPTV system is a purpose-built research platform that allows experimentation of new media and web technologies. In a collaboration between Lancaster and TU-Berlin’s Distributed Artificial Intelligence Laboratory (DAI-Labor), Jing Yuan and her colleagues at DAI-Labor investigated a novel approach in analysing a large corpus of TV programme and user interaction data extracted from Vision’s statistics database. We use a LDA-based topic model, with a tailored extension to capture 2-dimensional contextual information, to infer latent user preference and user interaction distributions. In the next step, we’ll generalise the model and integrate it in Vision’s production environment for user evaluation.

Context-aware LDA: Balancing Relevance and Diversity in TV Content Recommenders
Yuan, J., Sivrikaya, F., Hopfgartner. F., Lommatzsch, A., and Mu, M., to appear in 2nd Workshop on Recommendation Systems for Television and Online Video in conjuction with the 9th ACM Conference on Recommender Systems (ACM Recsys). 09/2015

Won the best paper award at IWQoS

June 19, 2015August 4, 2015 ~ drmmu ~ Leave a comment

It was a great fun visiting Portland, Oregon, the city of roses (and beers!), and getting to know a great research community on QoS. Winning the best paper award was certainly one of the highlights of the trip. If you are ever around Portland, don’t forget to visit Washington Park. I particularly enjoyed the hiking on those great forest trails (over 1000 species of trees), the International Rose Test garden, and the Japanese Garden. For the beers, don’t forget to try the DEAD GUY ALE.

I am working on a JSAC and a TOMM submission.

Aside ~ May 21, 2015August 4, 2015 ~ drmmu ~ Leave a comment

Setting up OpenFlow testbed for user-level resource allocation experiments using a number of HP 3800 switches. We use VLAN to bridge OpenStack VMs to physical ports (hence the little connections). After that, its all controlled by software.