On the limited memory BFGS method for large scale optimization
Mathematical Programming: Series A and B
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Smart Environments: Technology, Protocols and Applications (Wiley Series on Parallel and Distributed Computing)
Layered representations for learning and inferring office activity from multiple sensory channels
Computer Vision and Image Understanding - Special issue on event detection in video
Shallow parsing with conditional random fields
NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
Fine-Grained Activity Recognition by Aggregating Abstract Object Usage
ISWC '05 Proceedings of the Ninth IEEE International Symposium on Wearable Computers
Pattern Recognition and Machine Learning (Information Science and Statistics)
Pattern Recognition and Machine Learning (Information Science and Statistics)
Assistive intelligent environments for automatic health monitoring
Assistive intelligent environments for automatic health monitoring
Designing Smart Homes: The Role of Artificial Intelligence (Lecture Notes in Computer Science)
Designing Smart Homes: The Role of Artificial Intelligence (Lecture Notes in Computer Science)
Coupled Hidden Semi Markov Models for Activity Recognition
WMVC '07 Proceedings of the IEEE Workshop on Motion and Video Computing
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
Conditional random fields for activity recognition
Conditional random fields for activity recognition
Efficient duration and hierarchical modeling for human activity recognition
Artificial Intelligence
A long-term evaluation of sensing modalities for activity recognition
UbiComp '07 Proceedings of the 9th international conference on Ubiquitous computing
The design of a portable kit of wireless sensors for naturalistic data collection
PERVASIVE'06 Proceedings of the 4th international conference on Pervasive Computing
Simultaneous tracking and activity recognition (STAR) using many anonymous, binary sensors
PERVASIVE'05 Proceedings of the Third international conference on Pervasive Computing
Fitting distal limb segments for accurate skeletonization in human action recognition
Journal of Ambient Intelligence and Smart Environments
Automatic extraction of advice-revealing sentences foradvice mining from online forums
Proceedings of the seventh international conference on Knowledge capture
Detection of daily living activities using a two-stage Markov model
Journal of Ambient Intelligence and Smart Environments - Intelligent agents in Ambient Intelligence and smart environments
Journal of Ambient Intelligence and Smart Environments
Inferring ECA-based rules for ambient intelligence using evolutionary feature extraction
Journal of Ambient Intelligence and Smart Environments
Hi-index | 0.00 |
Accurately recognizing human activities from sensor data recorded in a smart home setting is a challenging task. Typically, probabilistic models such as the hidden Markov model (HMM) or conditional random fields (CRF) are used to map the observed sensor data onto the hidden activity states. A weakness of these models, however, is that the type of distribution used to model state durations is fixed. Hidden semi-Markov models (HSMM) and semi-Markov conditional random fields (SMCRF) model duration explicitly, allowing state durations to be modelled accurately. In this paper we compare the recognition performance of these models on multiple fully annotated real world datasets consisting of several weeks of data. In our experiments the HSMM consistently outperforms the HMM, showing that accurate duration modelling can result in a significant increase in recognition performance. SMCRFs only slightly outperform CRFs, showing that CRFs are more robust in dealing with violations of the modelling assumptions. The datasets used in our experiments are made available to the community to allow further experimentation.