-
[show abstract]
[hide abstract]
ABSTRACT: Discovering semantic knowledge is significant for understanding and interpreting how people interact in a meeting discussion. In this paper, we propose a mining method to extract frequent patterns of human interaction based on the captured content of face-to-face meetings. Human interactions, such as proposing an idea, giving comments, and expressing a positive opinion, indicate user intention toward a topic or role in a discussion. Human interaction flow in a discussion session is represented as a tree. Tree-based interaction mining algorithms are designed to analyze the structures of the trees and to extract interaction flow patterns. The experimental results show that we can successfully extract several interesting patterns that are useful for the interpretation of human behavior in meeting discussions, such as determining frequent interactions, typical interaction flows, and relationships between different types of interactions.
IEEE Transactions on Knowledge and Data Engineering 05/2012; · 1.66 Impact Factor
-
IEEE Trans. Knowl. Data Eng. 01/2012; 24:759-768.
-
[show abstract]
[hide abstract]
ABSTRACT: Social and community intelligence research aims to reveal individual and group behaviors, social interactions, and community dynamics by mining the digital traces that people leave while interacting with Web applications, static infrastructure, and mobile and wearable devices.
Computer 08/2011; · 1.47 Impact Factor
-
[show abstract]
[hide abstract]
ABSTRACT: There are many devices embedded in a smart home environment. It is a challenge to operate these devices due to the heterogeneity and the mobility of them. In this paper, we propose a context-aware resource management framework, which aims to (1) discover available resources and update the states of those devices according to the changes of contexts; (2) allocate suitable resources to meet the needs of user tasks. Context-awareness facilitates decision making in the process of resource allocation by considering device states and user contexts including user situations, user tasks, device capabilities, and so on. A prototype system is implemented based on the context-aware resource management framework. The prototype system shows that the framework proposed is feasible.
Ubiquitous Information Technologies and Applications (CUTE), 2010 Proceedings of the 5th International Conference on; 01/2011
-
Personal and Ubiquitous Computing. 01/2011; 15:253-269.
-
Personal and Ubiquitous Computing. 01/2011; 15:219-220.
-
IEEE Computer. 01/2011; 44:21-28.
-
IEEE Systems Journal. 01/2011; 5:506-517.
-
UbiComp 2011: Ubiquitous Computing, 13th International Conference, UbiComp 2011, Beijing, China, September 17-21, 2011, Proceedings; 01/2011
-
Ubiquitous Intelligence and Computing - 8th International Conference, UIC 2011, Banff, Canada, September 2-4, 2011. Proceedings; 01/2011
-
[show abstract]
[hide abstract]
ABSTRACT: Ubiquitous search of the physical world has recently received significant attention. In this paper, we investigate situation
analysis based user intention recognition, which can be useful to retrieve information that may perfectly satisfy a user’s
needs. We first introduce a hierarchical user intention model based on CRFs (Conditional Random Fields). With the model, a
BP (Belief Propagation) based inference method is proposed to recognize user search intention based on situation analysis.
A variety of sensing mechanisms are adopted to collect context information of the physical world for robust and reliable situation
analysis. We developed a prototype in a real home setting and experiments were performed to examine the effectiveness of the
proposed approach.
KeywordsSituation analysis-search intention-CRFs-ubiquitous search
05/2010: pages 35-51;
-
[show abstract]
[hide abstract]
ABSTRACT: Human interaction is one of the most important characteristics of group social dynamics in meetings. In this paper, we propose an approach for capture, recognition, and visualization of human interactions. Unlike physical interactions (e.g., turn-taking and addressing), the human interactions considered here are incorporated with semantics, i.e., user intention or attitude toward a topic. We adopt a collaborative approach for capturing interactions by employing multiple sensors, such as video cameras, microphones, and motion sensors. A multimodal method is proposed for interaction recognition based on a variety of contexts, including head gestures, attention from others, speech tone, speaking time, interaction occasion (spontaneous or reactive), and information about the previous interaction. A support vector machines (SVM) classifier is used to classify human interaction based on these features. A graphical user interface called MMBrowser is presented for interaction visualization. Experimental results have shown the effectiveness of our approach.
Pervasive Computing and Communications (PerCom), 2010 IEEE International Conference on; 05/2010
-
[show abstract]
[hide abstract]
ABSTRACT: We conduct a study to determine when best to provide reminders by recognizing the interruption relations that occur in human behaviors. A model based on Petri Net to describe the execution of multiple activities is proposed. This approach aids the automatic analysis of activity interruption and supports adaptive prompting. We describe our experience in building a medication system that provides context-aware reminders for elder adults to take their medication. Experimental results show that our system can improve users' medication adherence in an efficient and flexible way.
Pervasive Computing and Communications Workshops (PERCOM Workshops), 2010 8th IEEE International Conference on; 05/2010
-
Personal and Ubiquitous Computing. 01/2010; 14:695-702.
-
Cybernetics and Systems. 01/2010; 41:105-122.
-
J. UCS. 01/2010; 16:1291-1310.
-
Multimedia Syst. 01/2010; 16:231-241.
-
ACM Comput. Surv. 01/2010; 42.
-
Multimedia Tools Appl. 01/2010; 47:71-86.
-
Eigth Annual IEEE International Conference on Pervasive Computing and Communications, PerCom 2010, March 29 - April 2, 2010, Mannheim, Germany; 01/2010
