ClusterNN: a hybrid classification approach to mobile activity recognition.
Bashir, Sulaimon; Doolan, Daniel; Petrovski, Andrei
Liming Luke Chen
Mobile activity recognition from sensor data is based on supervised learning algorithms. Many algorithms have been proposed for this task. One of such algorithms is the K-nearest neighbour (KNN) algorithm. However, since KNN is an instance based algorithm its use in mobile activity recognition has been limited to offline evaluation on collected data. This is because for KNN to work well all the training instances must be kept in memory for similarity measurement with the test instance. This is however prohibitive for mobile environment. Therefore, we propose an unsupervised learning step that reduces the training set to a proportional size of the original dataset. The novel approach applies clustering to the dataset to obtain a set of micro clusters from which cluster characteristics are extracted for similarity measurement with new unseen data. These reduced representative sets can be used for classifying new instances using the nearest neighbour algorithm step on the mobile phone. Experimental evaluation of our proposed approach using real mobile activity recognition dataset shows improved result over the basic KNN algorithm.
BASHIR, S., DOOLAN, D. and PETROVSKI, A. 2015. ClusterNN: a hybrid classification approach to mobile activity recognition. In Chen, L.L., Steinbauer, M., Khalil, I. and Anderst-Kotsis, G. (eds.) Proceedings of the 13th International advances in mobile computing and multimedia conference (MoMM 2015), 11-13 December 2015, Brussels, Belguim. New York: ACM [online], pages 263-267. Available from: https://doi.org/10.1145/2837126.2837140
|Conference Name||13th International advances in mobile computing and multimedia conference (MoMM 2015)|
|Conference Location||Brussels, Belgium|
|Start Date||Dec 11, 2015|
|End Date||Dec 13, 2015|
|Acceptance Date||Nov 1, 2015|
|Online Publication Date||Dec 11, 2015|
|Publication Date||Dec 31, 2015|
|Deposit Date||Dec 19, 2016|
|Publicly Available Date||Dec 19, 2016|
|Publisher||ACM Association for Computing Machinery|
|Keywords||Activity recognition; KNN; Smartphones; ClusterNN|
BASHIR 2016 ClusterNN
Publisher Licence URL
You might also like
Change detection for activity recognition.
A framework for unsupervised change detection in activity recognition.
Designing a context-aware cyber physical system for smart conditional monitoring of platform equipment.
AI-based intrusion detection systems for in-vehicle networks: a survey.