Abstract | ||
---|---|---|
A key aspect of ubiquitous computing is using sensor networks to effectively and unobtrusively infer human activities in their environment. A typical top-down approach is to first label and decompose activities as sequences of actions with certain probabilities, and then use these predefined activity models for recognition and prediction. This approach, however, does not capture the internal goals of different actions, and it only deals with those explicitly defined activity models. In this article, inspired by traditional activity theory and qualitative process theory, we present a goal-directed human activity computing model. A formal activity ontology is proposed so as to capture the internal semantic relations between different atomic activities such as actions and processes. A number of representative inference rules are then introduced to predict the future activities based on the activity ontology. The proposed formal activity computing model is simulated and demonstrated with Maude, a formal specification and programming language. |
Year | DOI | Venue |
---|---|---|
2011 | 10.3233/AIS-2011-0103 | JAISE |
Keywords | Field | DocType |
decompose activity,activity ontology,activity model,traditional activity theory,formal activity ontology,predefined activity model,proposed formal activity computing,goal-directed human activity computing,future activity,different atomic activity | Specification language,Mobile computing,Ontology,Formal language,Computer science,Formal specification,Human–computer interaction,Ubiquitous computing,Formal methods,Rule of inference | Journal |
Volume | Issue | ISSN |
3 | 2 | 1876-1364 |
Citations | PageRank | References |
1 | 0.34 | 12 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jianwen Xiang | 1 | 113 | 23.36 |
Jing Tian | 2 | 7 | 3.43 |
Akira Mori | 3 | 1 | 0.34 |