Amazon.com Recommendations: Item-to-Item Collaborative Filtering
IEEE Internet Computing
The Aware Home: A Living Laboratory for Ubiquitous Computing Research
CoBuild '99 Proceedings of the Second International Workshop on Cooperative Buildings, Integrating Information, Organization, and Architecture
Text categorization by boosting automatically extracted concepts
Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval
Boosting support vector machines for text classification through parameter-free threshold relaxation
CIKM '03 Proceedings of the twelfth international conference on Information and knowledge management
Segmenting motion capture data into distinct behaviors
GI '04 Proceedings of the 2004 Graphics Interface Conference
Fine-Grained Activity Recognition by Aggregating Abstract Object Usage
ISWC '05 Proceedings of the Ninth IEEE International Symposium on Wearable Computers
Common sense based joint training of human activity recognizers
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Behavior detection based on touched objects with dynamic threshold determination model
EuroSSC'07 Proceedings of the 2nd European conference on Smart sensing and context
Detection of user mode shift in home
UCS'07 Proceedings of the 4th international conference on Ubiquitous computing systems
| Hi-index | 0.00 |
We are developing a system which assists users by collaboration between the users and environment. Our collaboration system provides services according to user behavior proactively in homes when environment detects high-level user behavior such as "leaving the home". To realize such a collaboration system, this paper proposes a method for detecting high-level user behavior. The proposed method dynamically sets values suitable for individual behavioral pattern of each user to thresholds used for detection. A conventional method determines threshold values common to all users. However, the common values are not always suitable for all users. Our method determines threshold values suitable for a user by utilizing data of other users whose characteristics are similar to the user, with collaborative filtering.