Alexandros Psychas

An integrated information lifecycle management framework for exploiting social network data to identify dynamic large crowd concentration events in smart cities applications

Abstract With the current availability of an extreme diversity of data sources and services, emerging from the Internet of Things and Cloud domains, the challenge is shifted towards identifying intelligent, abstracted and adaptive ways of correlating and combining the various levels of information. The purpose of this work is to demonstrate such a combination, on one hand at the service level, through integrating smart cities platforms for user level data, and on the other hand at Complex Event Processing, Storage and Analytics capabilities together with Twitter data. The final goal is to identify events of interest to the user such as Large Crowd Concentration (LCC) in a given area, in order to enrich application level information with related event identification that can enable more sophisticated actions on behalf of that user. The identification is based on observation of Twitter activity peaks compared to historical data on a dynamic time and location of interest. The approach is validated through a two-month experiment in the city of Madrid, identifying LCCs in sporting events around two sports venues and analyzing various approaches with relation to the needed thresholds definition.

Dynamic Social and Media Content Syndication for Second Screen

Todays generation of Internet devices has changed how users are interacting with media, from passive and unidirectional users to proactive and interactive. Users can use these devices to comment or rate a TV show and search for related information regarding characters, facts or personalities. This phenomenon is known as second screen. This paper describes SAM, an EU-funded research project that focuses on developing an advanced digital media delivery platform based on second screen interaction and content syndication within a social media context, providing open and standardised ways of characterising, discovering and syndicating digital assets. This work provides an overview of the project and its main objectives, focusing on the NLP challenges to be faced and the technologies developed so far.

SAM: Dynamic and Social Content Delivery for Second Screen Interaction

Social media services offer a wide range of opportunities for businesses and developers to exploit the vast amount of information and user-generated content produced via social media. In addition, the notion of TV second screen usage -- the interleaved usage of TV and smart devices such as smartphones -- appears ever more prominent, with viewers continuously seeking further information and deeper engagement while watching movies, TV shows or event coverage. In this work-in-progress contribution, we present SAM, an innovative platform that combines social media, content syndication and targets second screen usage to enhance media content provisioning and advance the user experience. SAM incorporates modern technologies and novel features in the areas of content management, dynamic social media, social mining, semantic annotation and multi-device representation to facilitate an advanced business environment for broadcasters, content and metadata providers and editors to better exploit their assets and increase revenues.

A Toolkit Based Architecture for Optimizing Cloud Management, Performance Evaluation and Provider Selection Processes

Cloud environments are criticized for their volatility in performance aspects, making it extremely difficult for time- critical applications owners to perform the decisive step for migration and owners of SaaS to present performance vs cost tradeoffs to their customers when acting as IaaS customers. The aim of this work is to present an architectural approach based on which a)IaaS providers may enhance the stability and performance effectiveness of their infrastructures, through overhead modelling, runtime analysis and optimal groupings of concurrently running services, b) IaaS adopters to understand the application computational nature, investigate abstracted QoS metrics for providers ranking, minimize procurement time and selection processes, automate deployment/orchestration and monitor the maintenance of their SLA c) 3rd parties to act as independent validators of IaaS QoS features, through a constant monitoring and benchmarking process for performance and SLA evaluation.

Efficient Context Management and Personalized User Recommendations in a Smart Social TV Environment

With the emergence of Smart TV and related interconnected devices, second screen solutions have rapidly appeared to provide more content for end-users and enrich their TV experience. Given the various data and sources involved - videos, actors, social media and online databases- the aforementioned market poses great challenges concerning user context management and sophisticated recommendations that can be addressed to the end-users. This paper presents an innovative Context Management model and a related first and second screen recommendation service, based on a user-item graph analysis as well as collaborative filtering techniques in the context of a Dynamic Social & Media Content Syndication (SAM) platform. The model evaluation provided is based on datasets collected online, presenting a comparative analysis concerning efficiency and effectiveness of the current approach, and illustrating its added value.

Second Screen User Profiling and Multi-level Smart Recommendations in the Context of Social TVs

In the context of Social TV, the increasing popularity of first and second screen users, interacting and posting content online, illustrates new business opportunities and related technical challenges, in order to enrich user experience on such environments. SAM (Socializing Around Media) project uses Social Media-connected infrastructure to deal with the aforementioned challenges, providing intelligent user context management models and mechanisms capturing social patterns, to apply collaborative filtering techniques and personalized recommendations towards this direction. This paper presents the Context Management mechanism of SAM, running in a Social TV environment to provide smart recommendations for first and second screen content. Work presented is evaluated using real movie rating dataset found online, to validate the SAM’s approach in terms of effectiveness as well as efficiency.

Opportunistic Collaborative Service Networks: The Facilitator for Efficient Data and Services Exchange

The dynamic rapidly changing and technology-rich digital environment and the market economic constraints shift service provisioning from a pre- and strictly-defined to an on-demand and ad-hoc orientation, where applications depend on dynamic, scarce, distributed resources, which operate at different temporal and spatial scales, have different (potentially conflicting) objectives and are governed under different domains of control. The framework described in this paper aims at enabling the exploitation of all available highly heterogeneous resources (i.e. clouds, communicating objects, sensors and smart devices) by providing a service-based environment that allows for harvesting, dynamically creating and managing these diverse, discrete and distributed resources. Swarms refer to opportunistic service networks, which as new constructs can rapidly emerge in relation either to users and applications requirements or to events and information of great potential for the wider community, coordinated by an open and distributed runtime model.