LeRec: a NN/HMM hybrid for on-line handwriting recognition
Neural Computation
Connectionist Speech Recognition: A Hybrid Approach
Connectionist Speech Recognition: A Hybrid Approach
Hybrid HMM-NN Architectures for Connected Digit Recognition
IJCNN '00 Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 5 - Volume 5
Wireless Sensor Networks for Health Monitoring
MOBIQUITOUS '05 Proceedings of the The Second Annual International Conference on Mobile and Ubiquitous Systems: Networking and Services
Fine-Grained Activity Recognition by Aggregating Abstract Object Usage
ISWC '05 Proceedings of the Ninth IEEE International Symposium on Wearable Computers
The class imbalance problem: A systematic study
Intelligent Data Analysis
Conditional random fields for activity recognition
Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems
Accurate activity recognition in a home setting
UbiComp '08 Proceedings of the 10th international conference on Ubiquitous computing
Review: The use of pervasive sensing for behaviour profiling - a survey
Pervasive and Mobile Computing
Wireless sensor networks for personal health monitoring: Issues and an implementation
Computer Communications
An activity monitoring system for elderly care using generative and discriminative models
Personal and Ubiquitous Computing
Simultaneous tracking and activity recognition (STAR) using many anonymous, binary sensors
PERVASIVE'05 Proceedings of the Third international conference on Pervasive Computing
Machine Recognition of Human Activities: A Survey
IEEE Transactions on Circuits and Systems for Video Technology
| Hi-index | 0.00 |
Activities of daily living are good indicators of the health status of elderly, and activity recognition in a smart environment is a well-known problem that has been previously addressed by several studies. This paper presents a hybrid model based on ANN (Artificial Neural Network) and HMM (Hidden Markov Modeling) techniques in order to tackle the task of activity recognition in a home setting. The output scores of the ANN, after processing, are used as observation probabilities in the model. We evaluate our approach comparing it with classical probabilistic models using three datasets obtained from real data streams. Finally, we show how our approach achieves significative better recognition performance, at a confidence interval of 95%, in several features spaces, proving the hybrid approach to be better suited for the addressed domain.