Back to Search
Start Over
Active learning enabled activity recognition
- Source :
- PerCom
- Publication Year :
- 2016
- Publisher :
- IEEE, 2016.
-
Abstract
- © 2016 IEEE, 2016 IEEE International Conference on Pervasive Computing and Communications (PerCom)<br />Activity recognition in smart environment has been investigated rigorously in recent years. Researchers are enhancing the underlying activity discovery and recognition process by adding various dimensions and functionalities. But one significant barrier still persists which is collecting the ground truth information. Ground truth is very important to initialize a supervised learning of activities. Due to a large variety in number of Activities of Daily Living (ADLs), acknowledging them in a supervised way is a non-trivial research problem. Most of the previous researches have referenced a subset of ADLs and to initialize their model, they acquire a vast amount of informative labeled training data. On the other hand to collect ground truth and differentiate ADLs, human intervention is indispensable. As a result it takes an immense effort and raises privacy concerns to collect a reasonable amount of labeled data. In this paper, we propose to use active learning to alleviate the labeling effort and ground truth data collection in activity recognition pipeline. We investigate and analyze different active learning strategies to scale activity recognition and propose a dynamic k-means clustering based active learning approach. Experimental results on real data traces from a retirement community-(IRB #HP-00064387) help validate the early promise of our approach.
- Subjects :
- Computer Networks and Communications
Computer science
Active learning (machine learning)
02 engineering and technology
Crowdsourcing
Machine learning
computer.software_genre
Data modeling
Activity recognition
Labeling
020204 information systems
0202 electrical engineering, electronic engineering, information engineering
Hardware_ARITHMETICANDLOGICSTRUCTURES
Cluster analysis
Ground truth
business.industry
Smart homes
Supervised learning
Uncertainty
Data models
Adaptation models
Data science
Computer Science Applications
Hardware and Architecture
Wearable sensors
020201 artificial intelligence & image processing
Smart environment
Artificial intelligence
business
computer
Software
Mobile Pervasive & Sensor Computing Lab
Information Systems
Subjects
Details
- Database :
- OpenAIRE
- Journal :
- 2016 IEEE International Conference on Pervasive Computing and Communications (PerCom)
- Accession number :
- edsair.doi.dedup.....2060a794e96b6eb32560f7ba58f2216a