Query Processing Algorithms for Time, Place, Purpose and Personal Profile Sensitive Mobile Recommendation

Pinyapong, Sineenard; Kato, Toshikazu

doi:10.1109/cw.2004.51

Cited by 6 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Do, Gatica-Perez [11] mine user pattern using mobile phone app usage, including mobile Web usage on mobile phone.Zheng V W, Cao B, Zheng Y, et [12] mined useful knowledge from many users' GPS trajectories based on their partial location and activity annotations to provide targeted collaborative location and activity recommendations for each user.Huang K, Zhang C, Ma X, et [13] use a variety of contextual information, such as last used App, time, location, and the user profile, to predict the user's App whether will be open. Pinyapong S, Kato T. [14] proposed the relationship between 3 factors which are time, place and purpose. In consequence, they have summarized the basic rules to analyze essential data and algorithms to query processing.…”

Section: Related Workmentioning

confidence: 99%

Mobile Phone Recommendation Based on Phone Interest

Yuan

Chung

et al. 2014

Web Information Systems Engineering – WISE 2014

View full text Add to dashboard Cite

As cellular users change mobile phone frequently, mobile phone recommendation system is of great importance for mobile operator to achieve business benefit. There are essential challenges for researchers to design such system. Among them, a critical one is how to obtain and model user's interest of mobile phone. So far, recommendation approaches based on phone's hardware features or personalized web behavior could not achieve satisfactory results. In this paper, we propose phone interest for mobile phone recommendation. Phone interest is a latent level concept which is extracted from a group of users' web log data, who have the same mobile phone. We propose a novel probabilistic model named "Phone Interest Model" only based on mobile web log data. All the log data are from cellular operators server, not from mobile phone's application. The model proves its effectiveness on large scale of station cellular data from real cellular operator. In experiments, we validated the model against 1.3 billion of mobile Web logs for 4 million distinct users in Beijing metropolitan areas, and show that the model achieves a good performance in the phone recommendation, also outperforms the baseline methods and offers significantly high fidelity.

show abstract

Section: Related Workmentioning

confidence: 99%

Mobile Phone Recommendation Based on Phone Interest

Yuan

Chung

et al. 2014

Web Information Systems Engineering – WISE 2014

View full text Add to dashboard Cite

show abstract

“…Today, most of the frameworks are built for static contextaware applications. Most advanced frameworks are: [11] concentrating on personal profiles, [6] dealing with the integration of multiple device sensors, [4] focusing on sensor fusion based on bayesian network, [7] presenting an useful toolkit to quickly develop pervasive applications centered on context modeling, [12] considering the context-history of the user, [13] using RDF/OWL representation to abstract the process of context data, [5] and [9] relying on an agentbased framework for context and also dealing with RDF knowledge representation.…”

Section: Introductionmentioning

confidence: 99%

Context-aware applications using personal sensors

Subercaze¹,

Maret²,

Dang³

et al. 2007

Proceedings of the Second International Conference on Body Area Networks BodyNets

View full text Add to dashboard Cite

Context-aware applications require the development of convenient frameworks. Effective mobility requires that mobile applications can integrate new sensors or new types of information. This is not possible within traditional applications, because a redesign phase is necessary. We describe in this article an agent-based framework supporting sensors' data fusion and context-aware information exchanges. An ontology-based representation of data is used. Exchanges inbetween components are carried out within so-called virtual knowledge communities. An application has been designed within this framework ('Wake me up', taking place in the metro). It makes use of wearable sensor, transmitters and cell phones. The wearable sensor is used to determine the user state. Transmitters provide geographical information, and cell phones are used as personal assistants.

show abstract