Probabilistic Visual Learning for Object Representation
IEEE Transactions on Pattern Analysis and Machine Intelligence
Pattern Recognition with Fuzzy Objective Function Algorithms
Pattern Recognition with Fuzzy Objective Function Algorithms
A Middleware Infrastructure for Active Spaces
IEEE Pervasive Computing
Refining Initial Points for K-Means Clustering
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Ubiquitous Home: Real-Life Testbed for Home Context-Aware Service
TRIDENTCOM '05 Proceedings of the First International Conference on Testbeds and Research Infrastructures for the DEvelopment of NeTworks and COMmunities
JADE: A software framework for developing multi-agent applications. Lessons learned
Information and Software Technology
Multi-agent based simulation: where are the agents?
MABS'02 Proceedings of the 3rd international conference on Multi-agent-based simulation II
Discriminant analysis by a neural network with mahalanobis distance
ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part II
UbiREAL: realistic smartspace simulator for systematic testing
UbiComp'06 Proceedings of the 8th international conference on Ubiquitous Computing
| Hi-index | 0.00 |
Energy conservation and CO2 emission reduction have both recently become critical environmental issues. Despite the considerable efforts of governments and technological developments by private enterprise, such as energy saving appliances and solar power systems, CO2 emissions per household are still increasing. Continued effort not only from companies, but also from each household and individuals is necessary. This paper describes a smart home system that is aware of household situations, performs automatic energy conservation when necessary, mines data on individual activities and gives advice and suggestions to individuals. Initially, the system records related objects and domestic human activities and structures and places the recorded data into three data logs: a space log, a device log, and a person log. Secondly, the system recognizes a device- or appliance-related situation and deduces individual activities by applying data mining techniques to the structured data logs. Finally, the system automatically conserves energy according to situation and gives appropriate advice to individuals by making them aware of their activities. A long-term objective of this system is to build a perception-influence relational model with which the system can adopt personalized presentation styles to give personalized advice to different individuals. It is expected that people's behavior under this system will shift imperceptibly towards lifestyles and domestic routines that conserve energy and reduce CO2 emissions.