I-centric communications: personalization, ambient awareness, and adaptability for future mobile services

Arbanowski, Stefan; Ballon, Pieter; David, Klaus; Droegehorn, Olaf; Eertink, Henk; Kellerer, Wolfgang; Kranenburg, H. van; Raatikainen, Kimmo; Popescu-Zeletin, Radu

doi:10.1109/mcom.2004.1336722

Cited by 81 publications

(35 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We report now the results obtained by testing our proposed architecture in a variety of settings 3 . In this experiment, we compared the distraction ratio as well as the hit ratio obtained by our approach with the respective ratios obtained by utilizing an Unguided Recommendation System.…”

Section: E Service Notification Based On a Publish/subcribe Paradigmmentioning

confidence: 99%

An intelligent architecture for service provisioning in pervasive environments

Yazidi

Reichert

Granmo

et al. 2011

2011 International Symposium on Innovations in Intelligent Systems and Applications

View full text Add to dashboard Cite

Abstract-The vision of pervasive environments is being realized more than ever with the proliferation of services and computing resources located in our surrounding environments. Identifying those services that deserve the attention of the user is becoming an increasingly-challenging task. In this paper, we present an adaptive multi-criteria decision making mechanism for recommending relevant services to the mobile user. In this context, "Relevance" is determined based on a user-centric approach that combines both the reputation of the service, the user's current context, the user's profile, as well as a record of the history of recommendations. Our decision making mechanism is adaptive in the sense that it is able to cope with users' contexts that are changing and drifts in the users' interests, while it simultaneously can track the reputations of services, and suppress repetitive notifications based on the history of the recommendations. The paper also includes some brief but comprehensive results concerning the task of tracking service reputations by analyzing and comprehending Word-of-Mouth communications, as well as by suppressing repetitive notifications. We believe that our architecture presents a significant contribution towards realizing intelligent and personalized service provisioning in pervasive environments.

show abstract

Section: E Service Notification Based On a Publish/subcribe Paradigmmentioning

confidence: 99%

An intelligent architecture for service provisioning in pervasive environments

Yazidi

Reichert

Granmo

et al. 2011

2011 International Symposium on Innovations in Intelligent Systems and Applications

View full text Add to dashboard Cite

show abstract

“…The reports serve as an input to the OMA-Based-Partitioning, given formally in Algorithm 1 taken from [30,32]. 3 Decisions about whether the service is reliable or not are the output of the overall procedure. The decision is based on intelligently combining the feedback of deceptive and fair users.…”

Section: Service Reputation Managermentioning

confidence: 99%

“…If we can discern that an event is repeating (even though this repetition is non-periodic), we should attempt to suppress it. To be more specific, 3 In the algorithm, W D l (t) denotes: {Last D records prior to instant t relative to service S l }. The details of the procedures Reward_Agreeing_Nodes, Penalize_Agreeing_Nodes, Penalize_Disagreeing_Nodes and Reward_Disagreeing_Nodes are found in [30,32].…”

Section: Notification Novelty Checkermentioning

confidence: 99%

A New Tool for the Modeling of AI and Machine Learning Applications: Random Walk-Jump Processes

Yazidi

Granmo

Oommen

2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The vision of pervasive environments is being realized more than ever with the proliferation of services and computing resources located in our surrounding environments. Identifying those services that deserve the attention of the user is becoming an increasingly-challenging task. In this paper, we present an adaptive multi-criteria decision making mechanism for recommending relevant services to the mobile user. In this context, "Relevance" is determined based on a user-centric approach that combines both the reputation of the service, the user's current context, the user's profile, as well as a record of the history of recommendations. Our decision making mechanism is adaptive in the sense that it is able to cope with users' contexts that are changing and drifts in the users' interests, while it simultaneously can track the reputations of services, and suppress repetitive notifications based on the history of the recommendations. The paper also includes some brief but comprehensive results concerning the task of tracking service reputations by analyzing and comprehending Word-of-Mouth communications, as well as by suppressing repetitive notifications. We believe that our architecture presents a significant contribution towards realizing intelligent and personalized service provisioning in pervasive environments.

show abstract

“…information on the geographical coordinates and the velocity of the user. According to [6], position awareness is very important for future mobile applications and services. In our approach, we assume that position information can be suitably acquired by the user/terminal using one of the techniques currently available in communications networks (for example, satellite navigation systems like GPS, even augmented exploiting terrestrial infrastructure like 3G or WLAN [24], [5]).…”

Section: The Proposed Situationandlocation-aware Systemmentioning

confidence: 99%

“…This kind of registration is the most suitable way for getting first knowledge of the user profile that, afterwards, is continuously updated. Hence, our approach has the advantages of both collaborative and content-based user modelling techniques: this hybrid approach, which will be better clarified in the following, is the best to our aims [6], [8], [9], [10], [11], [12]. 1) A user U j connects to the network by means of a specific device D i.…”

Section: A the High-level Behaviourmentioning

confidence: 99%

"Scenario"-adaptivity for e-service management in heterogeneous networks

Molinaro

Pudano²,

Ursino³

2006

African Journal of ICT

View full text Add to dashboard Cite

Abstract-A "Situation&Location" aware system has the main task of handling the set of distributed information and resources available within heterogeneous networks to provide a user with seamless and optimized network access to the desired service from any location. Situation&Location and its whole set of variables can be a powerful means to trade-off among user requirements, application constraints, and underlying network conditions. We propose a Multi Agent System able to capture the concept of Situation&Location and perform the task highlighted above. We follow a general-purpose approach with the aim of guaranteeing the highest versatility is possible. The main strength of our proposed system is its "adaptability" that can be achieved without the use of either new terminals or novel technologies. The only requirement is the introduction of a middleware functionality into already existing terminals and into some network servers.

show abstract

I-centric communications: personalization, ambient awareness, and adaptability for future mobile services

Cited by 81 publications

References 6 publications

An intelligent architecture for service provisioning in pervasive environments

An intelligent architecture for service provisioning in pervasive environments

A New Tool for the Modeling of AI and Machine Learning Applications: Random Walk-Jump Processes

"Scenario"-adaptivity for e-service management in heterogeneous networks

Contact Info

Product

Resources

About