CLUSTERING AND NEAREST NEIGHBOUR BASED CLASSIFICATION APPROACH FOR MOBILE ACTIVITY RECOGNITION
Keywords:
Activity Recognition, KNN, Smartphones, ClusteringAbstract
We present a hybridized algorithm based on clustering and nearest neighbour classier for mobile activity recognition. The algorithm transforms a training dataset into a more compact and reduced representative set that lessens the computational cost on mobile devices. This is achieved by applying clustering on the original dataset with the concept of percentage data retention to direct the operation. After clustering, we extract three reduced and transformed representation of the original dataset to serve as the reference data for nearest neighbour classication. 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 that uses all the training dataset.
Downloads
References
Muhammad Shoaib, Stephan Bosch, Ozlem Durmaz Incel, Hans Scholten, and Paul JM
Havinga. A survey of online activity recognition using mobile phones. Sensors,
(1):2059{2085, 2015.
Gary M Weiss and Je rey W Lockhart. The impact of personalization on smartphone-
based activity recognition. In AAAI Workshop on Activity Context Representation: Tech-
niques and Languages, 2012.
Sulaimon A Bashir, Daniel C Doolan, and Andrei Petrovski. The impact of feature vector
length on activity recognition accuracy on mobile phone. Lecture Notes in Engineering
and Computer Science: Proceedings of The World Congress on Engineering 2015, 1-3
July, 2015, London, U.K., 1:332{337, 2015.
Sulaimon A Bashir, Daniel C Doolan, and Andrei Petrovski. The e ect of window length
on accuracy of smartphone-based activity recognition. IAENG International Journal of
Computer Science, 23(1), 2016.
Sian Lun Lau and K. David. Movement recognition using the accelerometer in smart-
phones. In Future Network and Mobile Summit, 2010, pages 1{9, June 2010.
Zoltan Prekopcsak, Sugarka Soha, Tamas Henk, and Csaba Gaspar-Papanek. Activity
recognition for personal time management. Springer, 2009.
Nitin Bhatia et al. Survey of nearest neighbor techniques. arXiv preprint
arXiv:1007.0085, 2010.
T Hastie, R Tibshirani, and J Friedman. The Elements of Statistical Learning Data
Mining, Inference, and Prediction. Springer Verlag, New York, 2nd edition edition,
M Narasimha Murty and V Susheela Devi. Pattern recognition: An algorithmic approach.
Springer Science & Business Media, 2011.
Stephen J Preece, John Yannis Goulermas, Laurence PJ Kenney, and David Howard.
A comparison of feature extraction methods for the classi cation of dynamic activities
from accelerometer data. IEEE Transactions on Biomedical Engineering, 56(3):871{879,
Mark Hall, Eibe Frank, Geo rey Holmes, Bernhard Pfahringer, Peter Reutemann, and
Ian H. Witten. The weka data mining software: an update. ACM SIGKDD explorations
newsletter, 11(1):10{18, 2009.
Media Anugerah Ayu, Siti Aisyah Ismail, Ahmad Faridi Abdul Matin, and Teddy Man-
toro. A comparison study of classi er algorithms for mobile-phone's accelerometer based
activity recognition. Procedia Engineering, 41:224{229, 2012.
Mustafa Kose, Ozlem Durmaz Incel, and Cem Ersoy. Online human activity recognition
on smart phones. In Workshop on Mobile Sensing: From Smartphones and Wearables to
Big Data, pages 11{15, 2012.
Zahraa Said Abdallah, Mohamed Medhat Gaber, Bala Srinivasan, and Shonali Krish-
naswamy. Cbars: Cluster based classi cation for activity recognition systems. In Ad-
vanced Machine Learning Technologies and Applications, pages 82{91. Springer, 2012.
Sulaimon A. Bashir, Daniel C Doolan, and Andrei Petrovski. Clusternn: A hybrid clas-
si cation approach to mobile activity recognition. In Liming Chen, Matthias Steinbauer,
Ismail Khalil, and Gabriele Kotsis, editors, Proceedings of the 13th International Con-
ference on Advances in Mobile Computing & Multimedia (MoMM2015), pages 263{267,
Jennifer R Kwapisz, Gary M Weiss, and Samuel A Moore. Activity recognition using
cell phone accelerometers. ACM SigKDD Explorations Newsletter, 12(2):74{82, 2011.
Davide Anguita, Alessandro Ghio, Luca Oneto, Xavier Parra, and Jorge Luis Reyes-
Ortiz. A public domain dataset for human activity recognition using smartphones. In
th European Symposium on Arti cial Neural Networks, Computational Intelligence and
Machine Learning, ESANN 2013, 2013.
