Mobile Users' Context Awareness Model Using A Novelty Contextual-Soundscape Information

2017 ◽  
Author(s):  
Ho Sung Lim ◽  
Jun Lee ◽  
Yong-Jin Kwon
Keyword(s):  
Context Awareness ◽  
Mobile Users

Call U Back

2011 ◽  
Vol 2 (2) ◽  
pp. 1-13
Author(s):  
Xining Li ◽  
Jiazao Lin
Keyword(s):  
Knowledge Sharing ◽  
Context Awareness ◽  
Intelligent Agents ◽  
Business Processes ◽  
Research Area ◽  
Mobile Users ◽  
Great Success ◽  
Context Aware ◽  
Logical Inference ◽  
Business Applications

Mobile commerce (M-commerce) is an attractive research area due to its relative novelty, rapid growth, and great potential in business applications. Over the last decade, various M-commerce applications have been geared to target mobile users and achieved great success. However, most M-commerce applications are developed by different retailers for special purposes and thus lack fully automated business processes to integrate various existing services. This paper presents a novel infrastructure, Call U Back (CUB), for M-commerce applications. The proposed scheme integrates concepts of agent and context-aware workflow to implement automated trading tasks and compose services dynamically. The context awareness is based on ontology and logic models which derive from a set of descriptive contextual attributes for knowledge sharing and logical inference. Based upon the context-aware workflow analysis, the system will generate automated intelligent agents to conduct commerce transactions on behalf of mobile users. The middleware layer of the CUB server has been implemented. An experimental prototype of the system is under development and testing.

Call U Back

2013 ◽  
pp. 61-73
Author(s):  
Xining Li ◽  
Jiazao Lin
Keyword(s):  
Knowledge Sharing ◽  
Context Awareness ◽  
Intelligent Agents ◽  
Business Processes ◽  
Research Area ◽  
Mobile Users ◽  
Great Success ◽  
Context Aware ◽  
Logical Inference ◽  
Business Applications

Mobile commerce (M-commerce) is an attractive research area due to its relative novelty, rapid growth, and great potential in business applications. Over the last decade, various M-commerce applications have been geared to target mobile users and achieved great success. However, most M-commerce applications are developed by different retailers for special purposes and thus lack fully automated business processes to integrate various existing services. This paper presents a novel infrastructure, Call U Back (CUB), for M-commerce applications. The proposed scheme integrates concepts of agent and context-aware workflow to implement automated trading tasks and compose services dynamically. The context awareness is based on ontology and logic models which derive from a set of descriptive contextual attributes for knowledge sharing and logical inference. Based upon the context-aware workflow analysis, the system will generate automated intelligent agents to conduct commerce transactions on behalf of mobile users. The middleware layer of the CUB server has been implemented. An experimental prototype of the system is under development and testing.

scholarly journals An Infrastructure to Enable Lightweight Context-Awareness for Mobile Users

Sensors ◽  
2013 ◽  
Vol 13 (8) ◽  
pp. 9635-9652 ◽  
Author(s):  
Pablo Curiel ◽  
Ana Lago
Keyword(s):  
Context Awareness ◽  
Mobile Users

Context Awareness on Mobile Devices

2015 ◽  
Vol 743 ◽  
pp. 742-747 ◽  
Author(s):  
Z.A. Pan ◽  
J.X. Zhu
Keyword(s):  
Real Time ◽  
Mobile Devices ◽  
Context Awareness ◽  
Mobile Users ◽  
Context Aware ◽  
Context Aware Computing ◽  
Bayes Net ◽  
Real Time Classification

Context aware computing is important for applications to provide smarter and safer<br />service to mobile users, especially when users’ context changing rapidly or regularly. In this paper,<br />we propose a context aware model for mobile devices based on audio and location. The information<br />can easily obtained from sensors, e.g., microphones and GPS. Thus, exploiting the MFCC features<br />and the location, a Bayes Net is trained and built and will be used for context classifying in the<br />real-time classification. The results of experiments implemented on Android 4.0 platform<br />demonstrate promising performance, which indicates that the model is able to support real<br />applications.

Sign in / Sign up

Export Citation Format

Share Document