Abstract
With the rapid development of intelligent devices, motion recognition methods are broadly used in many different occasions. Most of them are based on several traditional machine learning models or their variants, such as Dynamic Time Warping, Hidden Markov Model or Support Vector Machine. Some of them could achieve a relatively high classification accuracy but with a time-consuming training process. Some other models are just the opposite. In this paper, we propose a novel designed deep Convolutional Neural Network (DBCNN) model using “Data-Bands” as input to solve the motion sequence recognition task with a higher accuracy in less training time. Contrast experiments were conducted between DBCNN and several baseline methods and the results demonstrated that our model could outperform these state-of-art models.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Amma C, Gehrig D, Schultz T (2010) Airwriting recognition using wearable motion sensors. In: Proceedings of the 1st augmented human international conference. ACM
Schlömer T et al (2008) Gesture recognition with a Wii controller. In: Proceedings of the 2nd international conference on Tangible and embedded interaction. ACM
Timo P (2005) Accelerometer based gesture recognition using continuous HMMs. Springer, Berlin, pp 639–646 (Pattern Recognit Image Anal)
Kallio S, Juha K, Jani M (2003) Online gesture recognition system for mobile interaction. In: IEEE International conference on systems, man and cybernetics
Liu J et al (2009) uWave: accelerometer-based personalized gesture recognition and its applications. Pervasive Mobile Comput 5:657–675
Wu J et al (2009) Gesture recognition with a 3-d accelerometer. Ubiquitous intelligence and computing. Springer, Berlin, pp 25–38
Wang J-S, Chuang F-C (2012) An accelerometer-based digital pen with a trajectory recognition algorithm for handwritten digit and gesture recognition. IEEE Trans Ind Electron 2998–3007
Chen M, AlRegib G, Juang B-H (2012) A new 6d motion gesture database and the benchmark results of feature-based statistical recognition. In: IEEE international conference on emerging signal processing applications
LeCun Y et al (1998) Gradient-based learning applied to document recognition. Proc IEEE 2278–2324
Cho S-J et al (2006) Two-stage recognition of raw acceleration signals for 3-D gesture-understanding cell phones. In: Tenth international workshop on frontiers in handwriting recognition
Bishop CM (1995) Neural networks for pattern recognition
Bengio Y (2009) Learning deep architectures for AI. In: Machine learning foundations trends, pp 1–127
Hinton GE (2007) Learning multiple layers of representation. Trends Cognit Sci 428–434
Hinton G, Osindero S, Teh Y-W (2006) A fast learning algorithm for deep belief nets. Neural Comput 1527–1554
Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 504–507
Hinton GE (2012) A practical guide to training restricted boltzmann machines. In: Montavon G, Orr GB, Müller K-R (eds) Neural networks: tricks of the trade, vol 7700, 2nd edn. LNCS. Springer, Heidelberg, pp 599–619
Bergstra J et al (2011) Theano: Deep learning on gpus with python. In: BigLearning workshop, NIPS
Bengio Y et al (2007) Greedy layer-wise training of deep networks. In: Advances in neural information processing systems
Chang C-C, Lin C-J (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Zhang, R., Li, C. (2015). Motion Sequence Recognition with Multi-sensors Using Deep Convolutional Neural Network. In: Abraham, A., Jiang, X., Snášel, V., Pan, JS. (eds) Intelligent Data Analysis and Applications. Advances in Intelligent Systems and Computing, vol 370. Springer, Cham. https://doi.org/10.1007/978-3-319-21206-7_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-21206-7_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-21205-0
Online ISBN: 978-3-319-21206-7
eBook Packages: EngineeringEngineering (R0)