Human activity recognition from inertial sensor time-series using batch normalized deep LSTM recurrent networks : WestminsterResearch

Publication dates
Title	Human activity recognition from inertial sensor time-series using batch normalized deep LSTM recurrent networks
Authors	Zebin, T., Sperrin, M., Peek, N. and Casson, A.J.
Type	Conference paper
Abstract	In recent years machine learning methods for human activity recognition have been found very effective. These classify discriminative features generated from raw input sequences acquired from body-worn inertial sensors. However, it involves an explicit feature extraction stage from the raw data, and although human movements are encoded in a sequence of successive samples in time most state-of-the-art machine learning methods do not exploit the temporal correlations between input data samples. In this paper we present a Long-Short Term Memory (LSTM) deep recurrent neural network for the classification of six daily life activities from accelerometer and gyroscope data. Results show that our LSTM can processes featureless raw input signals, and achieves 92 % average accuracy in a multi-class-scenario. Further, we show that this accuracy can be achieved with almost four times fewer training epochs by using a batch normalization approach.
Keywords	Deep Learning, Activity Recognition
Year	2018
Conference	2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
Publisher	IEEE
Published	29 Oct 2018
Journal citation	pp. 4385-4388
ISSN	1558-4615
	1557-170X
ISBN	9781538636466
	9781538636459
	9781538636473
Funder	EPSRC (Engineering and Physical Sciences Research Council)
Digital Object Identifier (DOI)	https://doi.org/10.1109/EMBC.2018.8513115
Web address (URL) of conference proceedings	https://ieeexplore.ieee.org/abstract/document/8513115
Web address (URL)	https://ieeexplore.ieee.org/abstract/document/8513115
File	2018_embc_tahmina_lstm.pdf

Related outputs

Design and implementation of a deep recurrent model for prediction of readmission in urgent care using electronic health records
Zebin, T. and Chaussalet, T.J. 2019. Design and implementation of a deep recurrent model for prediction of readmission in urgent care using electronic health records. 16th IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology. Certosa di Pontignano, Siena - Tuscany, Italy 09 - 11 Jul 2019 IEEE . https://doi.org/10.1109/CIBCB.2019.8791466

A deep learning approach for length of stay prediction in clinical settings from medical records
Zebin, T., Rezvy, S. and Chaussalet, T.J. 2019. A deep learning approach for length of stay prediction in clinical settings from medical records. 16th IEEE International Conference on Computational Intelligence in Bioinformatics and Computational Biology. Certosa di Pontignano, Siena - Tuscany, Italy 09 - 11 Jul 2019 IEEE . https://doi.org/10.1109/CIBCB.2019.8791477

Intrusion Detection and Classification with Autoencoded Deep Neural Network
Rezvy, S, Petridis, M, Lasebae, A and Zebin, T. 2019. Intrusion Detection and Classification with Autoencoded Deep Neural Network. in: Innovative Security Solutions for Information Technology and Communications Springer. pp. 142-156

Inertial Sensor Based Modelling of Human Activity Classes: Feature Extraction and Multi-sensor Data Fusion Using Machine Learning Algorithms
Zebin, T., Scully, PJ and Ozanyan, K B. 2017. Inertial Sensor Based Modelling of Human Activity Classes: Feature Extraction and Multi-sensor Data Fusion Using Machine Learning Algorithms. in: eHealth 360°. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering Springer. pp. 306-314

Human activity recognition with inertial sensors using a deep learning approach
Zebin, T., Scully, P.J. and Ozanyan, K.B. 2016. Human activity recognition with inertial sensors using a deep learning approach. 2016 IEEE SENSORS. Orlando, FL, USA 30 Oct - 03 Nov 2016 IEEE . https://doi.org/10.1109/ICSENS.2016.7808590

Permalink - https://westminsterresearch.westminster.ac.uk/item/q9x24/human-activity-recognition-from-inertial-sensor-time-series-using-batch-normalized-deep-lstm-recurrent-networks

Human activity recognition from inertial sensor time-series using batch normalized deep LSTM recurrent networks

Related outputs

Share this

Usage statistics

Export as