Mobile Netw Appl DOI 10.1007/s11036-008-0092-y Gain-based Selection of Ambient Media Services in Pervasive Environments M. Anwar Hossain · Pradeep K. Atrey · Abdulmotaleb El Saddik © Springer Science + Business Media, LLC 2008 Abstract Providing ambient media services in the per- vasive environments is a challenging issue. This is due to the fact that users have different satisfaction level in using different media services in varying contexts. We address this issue by proposing a gain-based media service selection mechanism. Gain refers to the extent a media service is satisfying to a user in a particular context. In our proposed mechanism, the gain is dy- namically computed by adopting a user-centered ap- proach that includes user’s context, profile, interaction history, and the reputation of a service. The dynam- ically computed gain is used in conjunction with the cost of using a service (e.g. media subscription and energy consumption cost) to derive our service selec- tion mechanism. We adopt a combination of greedy and dynamic programming based solution to obtain a set of services that would maximize the user’s overall gain in the ambient environment by minimizing the cost constraint. Experimental results demonstrate the potential of this approach. Keywords gain · service selection · ambient media service · context · pervasive environments M. A. Hossain (B ) · A. El Saddik Multimedia Communications Research Laboratory, University of Ottawa, Ottawa, ON, Canada e-mail: anwar@mcrlab.uottawa.ca A. El Saddik e-mail: abed@mcrlab.uottawa.ca P. K. Atrey Applied Computer Science, The University of Winnipeg, Winnipeg, MB, Canada e-mail: p.atrey@uwinnipeg.ca 1 Introduction A pervasive computing environment, like the one that Ambient Intelligence [11] promotes, is a technologi- cally augmented multi-sensor environment capable of capturing the context and activities of the users in order to respond to their needs. One main objective of such an environment is to provide ambient media services to users based on their needs in different context. How- ever, which of the services should be provided to the user given the current context remains a challenging issue. The rich availability of media services in the per- vasive environments and the heterogeneous nature of these services make the selection of right services even more complex. The different types of services that can be provided to the user are audio services (e.g. song, news), visual services (e.g. RSS feeds, news, weather feeds), audio/visual services (e.g. movie, music video, sports news) and so forth. Some of these services might have specific display requirements in perceiving them (e.g., viewing a movie on a computer screen), while others might not have any such constraints (e.g. playing a background music). Therefore, a service selection mechanism is expected to consider all these variability in order to select relevant services for the user. The user’s need for the different types of services in the environment is different in changing context. For example, when a user is driving, it would be intuitive to provide audio services than that of visual or au- dio/visual services in order not to distract the driver. Therefore, user’s satisfaction (we refer as gain) to audio services would be greater than other services in that context. However, when a user is at home and sitting