User Preference Learning for Multimedia Personalization in Pervasive Computing Environment

Yu, Zhiwen; Zhang, Daqing; Zhou, Xingshe; Li, Changde

doi:10.1007/11552451_32

Cited by 11 publications

(5 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other researchers estimated the user sentiment from feedback and ratings in [81] using such as Naive Bayes Neural Network, and Nearest Neighbour algorithm. Similar works using different data based on this model, such as the investigation on searching result preference [82], [83]. However, individual preference is not stable over time because of the influence of environments, experiences, and education.…”

Section: B: Supervised Learning Based Modelmentioning

confidence: 98%

A Survey of Online Data-Driven Proactive 5G Network Optimisation Using Machine Learning

Guo

Zhang

2020

IEEE Access

View full text Add to dashboard Cite

In the fifth-generation (5G) mobile networks, proactive network optimisation plays an important role in meeting the exponential traffic growth, more stringent service requirements, and to reduce capital and operational expenditure. Proactive network optimisation is widely acknowledged as one of the most promising ways to transform the 5G network based on big data analysis and cloud-fog-edge computing, but there are many challenges. Proactive algorithms will require accurate forecasting of highly contextualised traffic demand and quantifying the uncertainty to drive decision making with performance guarantees. Context in Cyber-Physical-Social Systems (CPSS) is often challenging to uncover, unfolds over time, and even more difficult to quantify and integrate into decision making. The first part of the review focuses on mining and inferring CPSS context from heterogeneous data sources, such as online user-generated-content. It will examine the state-of-the-art methods currently employed to infer location, social behaviour, and traffic demand through a cloud-edge computing framework; combining them to form the input to proactive algorithms. The second part of the review focuses on exploiting and integrating the demand knowledge for a range of proactive optimisation techniques, including the key aspects of load balancing, mobile edge caching, and interference management. In both parts, appropriate state-of-the-art machine learning techniques (including probabilistic uncertainty cascades in proactive optimisation), complexity-performance trade-offs, and demonstrative examples are presented to inspire readers. This survey couples the potential of online big data analytics, cloud-edge computing, statistical machine learning, and proactive network optimisation in a common cross-layer wireless framework. The wider impact of this survey includes better cross-fertilising the academic fields of data analytics, mobile edge computing, AI, CPSS, and wireless communications, as well as informing the industry of the promising potentials in this area.INDEX TERMS Online data, data analytics, proactive network optimisation, 5G.

show abstract

Section: B: Supervised Learning Based Modelmentioning

confidence: 98%

A Survey of Online Data-Driven Proactive 5G Network Optimisation Using Machine Learning

Guo

Zhang

2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The gain estimation is also motivated by the works in context-aware information access and presentation such as [20,18,17,13,3]. The work in [20] provides a mechanism to show information of various types in the large display based on the user's preferences and display templates.…”

Section: Related Workmentioning

confidence: 99%

“…However, it is not clear if and how the user's preference attributes change over time and impact the subsequent information delivery. Authors in [18] present a relevant-feedback based preference learning mechanism, where the high-capability master device learns the user's preference based on the feedback from the low-capability slave devices by observing the user's behaviour. The learned preference is used for multimedia personalization in a pervasive environment.…”

Section: Related Workmentioning

confidence: 99%

Dynamic gain estimation in ambient media services

Hossain

Atrey

Saddik

2008

Proceedings of the 1st ACM International Workshop on Semantic Ambient Media Experiences

View full text Add to dashboard Cite

This paper presents a mechanism for dynamically estimating the gain in ambient media services. Gain estimation is an attempt to measure the extent to which a certain media service is useful for a user in a particular context. Such a measure may provide invaluable support for personalizing a user's ambient environment through the selection of timely, context-aware and interesting media services. The proposed method considers multiple factors including the user's profile, context, media reputation, and the interaction history to dynamically estimate the gain of a service. The gain estimation method has been incorporated in a prototype smart mirror system in a smart environment setting. Experimental results demonstrate the suitability of the proposed method.

show abstract

“…Our current system applies Jena2 generic rule engine (Carroll, Dickinson, & Dollin, 2004) to support forward-chaining reasoning over the OWL represented context • Context learner deduces user preference of multimedia through implicit machine learning techniques. We have designed a user preference learning approach suitable in pervasive computing environment that uses centralized Master-Slave architecture and applies relevance feedback and Naïve Bayes classifier approach (Yu, Zhang, Zhou, & Li, 2005).…”

Section: Context-aware Multimedia Middleware Architecturementioning

confidence: 99%

“…In pervasive computing environments, multiple devices are attached to a user and are used at anytime anywhere. Each of these devices can independently gather user feedback information, but the information may be very fractional Yu, Zhang, Zhou, and Li (2005) propose a user preference learning approach suitable in pervasive computing environment that uses centralized Master-Slave architecture. It applies relevance feedback and Naïve Bayes classifier approach to compiling statistical analysis on user viewing history aggregated by the context aggregator from all kinds of media playing devices (e.g., PC, television, and PDA).…”

mentioning

confidence: 99%

Middleware Support for Context-Aware Ubiquitous Multimedia Services

Zhang

2006

Handbook of Research on Mobile Multimedia

Self Cite

View full text Add to dashboard Cite

In order to facilitate the development and proliferation of multimedia services in ubiquitous environment, a context-aware multimedia middleware is indispensable. This chapter discusses the middleware support issues for context-aware multimedia services. The enabling technologies for the middleware such as representation model, context management, and multimedia processing are described in detail. On top of our previous work, the design and implementation of a context-aware multimedia middleware, called CMM, is presented. The infrastructure integrates both functions of context middleware and multimedia middleware. This chapter also aims to give an overview of underlying technologies so that researchers in ubiquitous multimedia domain can understand the key design issues of such a middleware.

show abstract

User Preference Learning for Multimedia Personalization in Pervasive Computing Environment

Cited by 11 publications

References 2 publications

A Survey of Online Data-Driven Proactive 5G Network Optimisation Using Machine Learning

A Survey of Online Data-Driven Proactive 5G Network Optimisation Using Machine Learning

Dynamic gain estimation in ambient media services

Middleware Support for Context-Aware Ubiquitous Multimedia Services

Contact Info

Product

Resources

About