Papers by Georgios Exarchakos
Abstract Quality of Experience (QoE) is a metric that quantifies the quality experienced while us... more Abstract Quality of Experience (QoE) is a metric that quantifies the quality experienced while using a service. This is a subjective metric that is crucial for determining the level of satisfaction with the quality of services, such as multimedia streaming or games. Because of its subjective character, QoE is estimated accurately by executing complex and cumbersome subjective studies, or not as accurately by using objective signal distortion metrics.
Mechanisms for Parallel Data Transport
Abstract Evolving paradigms of parallel transport mechanisms are necessary to satisfy the ever in... more Abstract Evolving paradigms of parallel transport mechanisms are necessary to satisfy the ever increasing need of high performing communication systems. Parallel transport mechanisms can be described as a technique to send several data simultaneously using several parallel channels. The authors' survey captures the entire building blocks in designing next generation parallel transport mechanisms by firstly analyzing the basic structure of a transport mechanism using a point to point scenario.
On the Way to the Pervasive Web
Web applications bring about extraordinary breakthroughs regarding our digital ecosystem. Pretty ... more Web applications bring about extraordinary breakthroughs regarding our digital ecosystem. Pretty much anything with a chip and a radio interface can connect to the Web. However, many advocate a complete overhaul of the Internet as the only means to sustain innovation and productivity. Nobody knows what the next-generation of the Internet will look like; though important clues are visible as years of research have already generated phenomenal ideas.
A Peek at the Future Internet
The Internet “connectivity machine” is the generative engine of our modern digital society. It ha... more The Internet “connectivity machine” is the generative engine of our modern digital society. It has been the launching pad of the Web (now the Web 2.0), truly the largest and most versatile information system ever built. While the Web phenomenon relentlessly continues, scientists worldwide are now living the dream of yet a more generative next-generation network.
Discovering Virtual Resources
Virtual resources are considerably more numerous than the physical devices which host them. There... more Virtual resources are considerably more numerous than the physical devices which host them. There are many more files than servers; more videos than people. Thus, the task of discovering relevant resources is certainly a daunting one. The search engines help to retrieve data from servers. Yet, discovering resources stored in a virtual environment requires “deep” searching techniques which must be able to explore not only the multitude of web servers, but also the ordinary computers and terminals.
Six Problems for the Service Provider
The Internet is far from being perfect, and thus we are bound to see many remarkable changes in t... more The Internet is far from being perfect, and thus we are bound to see many remarkable changes in the near future. In examining what the Net can and cannot do today, what are the top six reasons to upgrade it? The Net is not sufficiently ubiquitous, reactive, proactive, information-driven, distribution-efficient and searchable. This chapter introduces these widely recognized issues, paving the way for the solutions presented in Chap. 4 and thereafter.
Cooperative stalking of transient nomadic resources on overlay networks
Abstract Highly dynamic overlay networks have a native ability to adapt their topology through re... more Abstract Highly dynamic overlay networks have a native ability to adapt their topology through rewiring to resource location and migration. However, this characteristic is not fully exploited in distributed resource discovery algorithms of nomadic resources. Recent and emergent computing paradigms (eg agile, nomadic, cloud, peer-to-peer computing) increasingly assume highly intermittent and nomadic resources shared over large-scale overlays.
Firewalks: Discovery Mechanism for Non-replicable Reusable Resources
Abstract Converged networks are viewed as a multi-access platform on which fixed and mobile commu... more Abstract Converged networks are viewed as a multi-access platform on which fixed and mobile communications can be easily merged into a unified system thus enabling the deployment of rich and personalized services. In this paper, we provide the outcomes of our research into the challenges introduced by terminal mobility in converged networks.
Abstract In IPTV streaming, issues of entire frame losses limit the use of state-of-the-art video... more Abstract In IPTV streaming, issues of entire frame losses limit the use of state-of-the-art video quality analyses techniques. We present an experimental evaluation of degradation in video quality when streaming different types of video in an IPTV scenario. The PacketStorm network emulator is used to emulate real IPTV networks as detailed in the ITU-T G. 1050 recommendation.
Abstract Peer-to-Peer networks are dynamic computational environments that can experience massive... more Abstract Peer-to-Peer networks are dynamic computational environments that can experience massive and sudden increases of their workloads. Typical P2P networks cannot cope with significant workload increases due to the limited processing power of their member nodes. In this paper we propose the G-ROME system which aims to interconnect multiple independent DHT-based P2P networks for the purposes of transferring capacity from underutilized to overloaded networks.
ABSTRACT Optimizing the Quality of Experience and avoiding under or over provisioning in video de... more ABSTRACT Optimizing the Quality of Experience and avoiding under or over provisioning in video delivery services requires understanding of how different resources affect the perceived quality. The utility of resources, such as bit-rate, is directly calculated by proportioning the improvement in quality over the increase in costs. However, perception of quality in video is subjective and, hence, difficult and costly to directly estimate with the commonly used rating methods.
Abstract Resource availability in pervasive environments is restricted by many either mobility-an... more Abstract Resource availability in pervasive environments is restricted by many either mobility-and/or security-related factors. Multi-agent systems deployed in such environments would have to rely on a potentially low number of hosts allowing and supporting the arrival and execution of foreign code. To address this issue, this paper proposes to decouple interaction of executing programs and services from the actual software mobility pattern used to realize this interaction.
Abstract With the widespread adoption of mobile Internet, the process of streaming video has beco... more Abstract With the widespread adoption of mobile Internet, the process of streaming video has become varied and complex. A diversity of factors affect the way we perceive quality in video streaming (also known as' quality of experience', or QoE), involving far more than the individual video and network characteristics. Quality is affected by the overall delivery context, terminal specifications but also human factors. It is thus very hard to control the streaming system as a whole, targeting QoE rather than the tuning of individual factors.
Abstract Estimating perceived quality of video is typically done by gauging the user's response o... more Abstract Estimating perceived quality of video is typically done by gauging the user's response on an absolute scale of ratings (excellent, good, fair, poor and bad). However, the internal representation of these adjectives to the stimuli varies significantly in different people. Even though the goal is to make an absolute estimate of the perceived quality, these questions reveal merely relative tendencies due the incorporated bias and variability in the responses.
Department of Computing University of …, Jan 1, 2007
Proceedings of the 9th …, Jan 1, 2011
Skype nodes generate a substantial part of real-time bi-directional video traffic nowadays. Emplo... more Skype nodes generate a substantial part of real-time bi-directional video traffic nowadays. Employing a range of adaptive mechanisms, the application configures video streaming to meet the requirements of the communication and constraints of the underlying network. While other related works focus on passive network monitoring of Skype data flows, this paper studies Skype as a point-to-point streaming engine of video, beyond standard video calling. The emphasis is on the objective video quality as perceived by viewers. We built a testbed to generate network perturbations and stream certain videos between Skype nodes. We examine how network impairments affect objective metrics (i.e. PSNR and SSIM index) of the video and Skype's ability to reconstruct the original sample. The results suggest that Skype is weak at delivering good quality for high motion videos and that it is slow at recovering after a long period of high packet loss.
… Journal On Advances …, Jan 1, 2011
User centric management of multimedia services necessitates understanding of how different system... more User centric management of multimedia services necessitates understanding of how different system parameters affect the perceived quality of the service. Today's multimedia delivery systems are highly complex and diverse and span over multiple domains commonly in control of different entities. Furthermore, the end user devices are highly variable in capabilities and characteristics, which directly affect the perceived quality. In addition to these factors the perceived quality in multimedia is subjective by nature, which leads to complexities in accurate estimation with objective methods and costs with subjective estimation. To deal with the necessities of estimation of Quality of Experience (QoE) we have implemented a software module that aggregates information from probes and subjective quality feedback to develop QoE prediction models. These models are then used as part of the QoE management module to estimate the QoE of multimedia delivery streams in real-time. Additionally, the module calculates and suggests QoE remedies (improvements) for multimedia streams that underperform. The remedies are in the form of a single or multiple target parameter values that need to be reached in order for the stream to reach the desired QoE. The functionalities of this module enable an implementation of a user-centric management loop for multimedia services.
Peer-to-Peer Networking and …, Jan 1, 2011
As a plethora of various distributed applications emerge, new computing platforms are necessary t... more As a plethora of various distributed applications emerge, new computing platforms are necessary to support their extra and sometimes evolving requirements. This research derives its motive from deficiencies of real networked applications deployed on platforms unable to fully support their characteristics and proposes a network architecture to address that issue. Hoverlay is a system that enables logical movement of nodes from one network to another aiming to relieve requesting nodes, which experience high workload. Node migration and dynamic server overlay differentiate Hoverlay from Condor-based architectures, which exhibit more static links between managers and nodes. In this paper, we present a number of important extensions to the basic Hoverlay architecture, which collectively enhance the degree of control owners have over their nodes and the overall level of cooperation among servers. Furthermore, we carried out extensive simulations, which proved that Hoverlay outperforms Condor and Flock of Condors in both success rate and average successful query path length at a negligible increase in messages.
Intelligent Networking and …, Jan 1, 2010
Efficient management of multimedia services necessitates the understanding of how the quality of ... more Efficient management of multimedia services necessitates the understanding of how the quality of these services is perceived by the users. Estimation of the perceived quality or Quality of Experience (QoE) of the service is a challenging process due to the subjective nature of QoE. This process usually incorporates complex subjective studies that need to recreate the viewing conditions of the service in a controlled environment. In this paper we present Machine Learning techniques for modeling the dependencies of different network and application layer quality of service parameters to the QoE of network services using subjective quality feedback. These accurate QoE prediction models allow us to further develop a geometrical method for calculating the possible remedies per network stream for reaching the desired level of QoE. Finally we present a set of possible network techniques that can deliver the desired improvement to the multimedia streams.
Uploads
Papers by Georgios Exarchakos