Skip to main content

Advertisement

SpringerLink
Log in

Efficiency investigation of artificial neural networks in human activity recognition

  • Original Research
  • Published:
Journal of Ambient Intelligence and Humanized Computing Aims and scope Submit manuscript

Abstract

Nowadays, human activity recognition (HAR) is an important component of many ambient intelligent solutions where accelerometer and gyroscope signals give the information about the physical activity of an observed person. It has gained increasing attention by the availability of commercial wearable devices such as smartphones, smartwatches, etc. Previous studies have shown that HAR can be seen as a general machine learning problem with a particular data pre-processing stage. In the last decade, several researchers measured high recognition rates on public data sets with numerous “shallow” machine learning techniques. In some cases artificial neural networks (ANNs) produced better performance than other shallow techniques while in other cases it was less effective. After the appearance of deep learning, a significant part of HAR researches turned toward more complex solutions such as convolutional neural networks (CNNs) and they claimed that CNNs can substitute the feature extraction stage in shallow techniques and can outperform them. Therefore in the current state of the art, the efficiency of ANNs against CNNs and other machine learning techniques is unclear. The aim of this study is to investigate the performance of more ANN structures with different hyper-parameters and inputs on two public databases. The result will show that the two key factors in ANN design are the data-preprocessing and the hyper-parameter setup because the accuracy difference between a well and a badly parameterized ANN is huge. A well-tuned ANN with extracted features can outperform other machine learning methods in the HAR problem including CNN classifiers.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

Notes

  1. https://people.eecs.berkeley.edu/~yang/software/WAR/.

  2. http://archive.ics.uci.edu/ml/datasets/Human+Activity+Recognition+Using+Smartphones.

References

  • Anguita, D, Ghio A, Oneto L, Parra X, Reyes-Ortiz L (2013) A public domain dataset for human activity recognition using smartphones. In: Proceedings of 21th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, pp 437–442

  • Ayachi FS, Nguyen HP, Pelletier CL, Goubault E, Boissy P, Duval C (2016) Wavelet-based algorithm for auto detection of daily living activities of older adults captured by multiple inertial measurement units (IMUs). Physiol Meas 37:442–461

    Article  Google Scholar 

  • Bayat A, Pomplun M, Tran DA (2014) A study on human activity recognition using accelerometer data from smartphones. Procedia Comput Sci 34:450–457

    Article  Google Scholar 

  • Bergstra J, Bengio Y (2012) Random search for hyper-parameter optimization. J Mach Learn Res 12:281–305

    MathSciNet  MATH  Google Scholar 

  • Bhattacharya S, Lane ND (2016) From smart to deep: robust activity recognition on smartwatches using deep learning. In: Proceedings of the 2016 IEEE international conference on pervasive computing and communication workshops, Sydney, pp 1–6

  • Botta A, Donato W, Persico V, Pecape A (2015) Integration of cloud computing and internet of things: a survey. Future Gener Comp Syst 56:684–700

    Article  Google Scholar 

  • Chen Y, Xue Y (2015) Deep learning approach to human activity recognition based on single accelerometer. In: Proceedings of the 2015 IEEE international conference on systems, man, and cybernetics, Hong Kong, pp 1488–1492

  • Chernbumroong S, Cang S, Atkins A, Yu H (2013) Elderly activities recognition and classification for applications in assisted living. Expert Syst Appl 40:1662–1674

    Article  Google Scholar 

  • Ciresan DC, Meier U, Gambardella LM, Schmidhuber J (2010) Big deep simple neural nets excel on hand-written digit recognition. Neural Comput 22:1–14

    Article  MathSciNet  Google Scholar 

  • Collobert R, Weston J, Bottou L, Karlen M, Kavukcuoglu K, Kuksa P (2011) Natural language processing (almost) from scratch. J Mach Learn Res 12:2493–2537

    MATH  Google Scholar 

  • De Maio C, Fenza G, Loia V, Orciuoli F (2017a) Distributed online temporal Fuzzy concept analysis for stream processing in smart cities. J Parallel Distr Com. doi:10.1016/j.jpdc.2017.02.002

    Google Scholar 

  • De Maio C, Fenza G, Loia V, Orciuoli F (2017b) Making sense of cloud-sensor data streams via Fuzzy cognitive maps and temporal Fuzzy concept analysis. Neurocomputing. doi:10.1016/j.neucom.2016.06.090

    Google Scholar 

  • Duarte F, Lourenco A, Abrantes A (2014) Classification of physical activities using a smart phone: evaluation study using multiple users. Procedia Technol 17:239–247

    Article  Google Scholar 

  • Gao L, Bourke AK, Nelson J (2014) Evaluation of accelerometer based multi-sensor versus single sensor activity recognition systems. Med Eng Phys 36:779–785

    Article  Google Scholar 

  • Gjoreski H, Bizjak J, Gjoreski M, Gams M (2016) Comparing deep a classical machine learning methods for human activity recognition using wrist accelerometer. In: Proceedings of the 25th international joint conference on artificial intelligence, New York, pp 1–7

  • Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of 13th international conference on artificial intelligence and statistics, Sardinia, pp 249–256

  • Godfrey A, Conway R, Meagher D, Olaighin G (2008) Direct measurement of human movement by accelerometry. Med Eng Phys 30:1364–1386

    Article  Google Scholar 

  • Gou Q, Liu B, Chen CW (2016) A two-layer and multi-strategy framework for human activity recognition using smartphone. In: Proceedings of the IEEE international conference on communications, Kuala Lumpur, pp 120–126

  • Hagan MT, Demuth HB, Beale MH, Jesus OD (2014) Neural network design (2th ed.). eBook. http://hagan/okstate.edu/NNDesign.pdf. Accessed 10 Jan 2017

  • Hammerla NY, Halloran S, Plots T (2016) Deep, convolutional, and recurrent models for human activity recognition using wearables. In: Proceedings of 25th international joint conference on artificial intelligence, New York, pp 1533–1540

  • Jatoba CL, Grobmann U, Kunze U, Ottenbacher J, Stork W (2008) Context-aware mobile health monitoring: evaluation of different pattern recognition methods for classification of physical activity. In: Proceedings of the 30th annual international IEEE EMBS conference, Vancouver, pp 5250–5253

  • Jiang W, Yin Z (2015) Human activity recognition using wearable sensors by deep convolutional neural networks. In: Proceedings of the 23th ACM international conference on multimedia, Brisbane, pp 1307–1310

  • Karantonis DM, Narayanan MR, Mathie M, Lovell NH, Celler BG (2006) Implementation of real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring. IEEE Trans Inf Technol B 10:156–167

    Article  Google Scholar 

  • Kastner M, Strickert M, Villmann T (2013) A sparse kernelized matrix learning vector quantization model for human activity recognition. In: European symposium of artificial neural networks, computational intelligence and machine learning, Bruges, pp 449–454

  • Khan AM, Lee YK, Lee SY, Kim TS (2010) A triaxial accelerometer-based physical-activity recognition via augmented-signal features and a hierarchical recognizer. IEEE Trans Inf Technol B 14:1166–1172

    Article  Google Scholar 

  • Kilinc O, Dalzell A, Uluturk I, Uysal I (2015) Inertial based recognition of daily activities with ANNs and spectrotemporal features. In: Proceedings of the IEEE 14th international conference on machine learning and applications, Miami, pp 733–738

  • Krizevsky A, Sutskerev I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: Neural information processing systems, Nevada, pp 1–9

  • Lara OD, Labrador MA (2013) A survey on human activity recognition using wearable sensors. IEEE Commun Surv Tutor 15:1192–1209

    Article  Google Scholar 

  • Liu H, Motoda H, Setiono R, Zhao Z (2010) Feature selection: an ever evolving frontier in data mining. In: Proceedings of the 4th workshop on feature selection in data mining, Hyderabad, pp 4–13

  • Maurer U, Smailagic A, Siewiorek DP, Deisher M (2006) Activity recognition and monitoring using multiple sensors on different body positions. In: Proceedings of the international workshop on wearable and implementable body sensor networks, Cambridge, pp 112–116

  • Nielsen MA (2015) Neural networks and deep learning. Determination Press. http://neuralnetworksanddeeplearning.com/. Accessed 12 Apr 2017

  • Oniga S, Suto J (2014) Human activity recognition using neural networks. In Proceedings of the 15th International Carpathian Control Conference, Velke Karlovice, pp 759–762

  • Oniga S, Suto J (2015) Optimal recognition method of human activities using artificial neural networks. Meas Sci Rev 15:323–327

    Article  Google Scholar 

  • Oniga S, Suto J (2016) Activity recognition in adaptive assistive systems using artificial neural networks. Elektronika ir Elektrotechnika 22:68–72

    Article  Google Scholar 

  • Ordonez FJ, Roggen D (2016) Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition. Sensors 16:115–130

    Article  Google Scholar 

  • Orha I, Oniga S (2015) Wearable sensor network for activity recognition using inertial sensors. Carpath J Electron Comput Eng 8:3–6

    Google Scholar 

  • Paillard-Borg S, Wang HX, Winblad B, Fratiglioni L (2009) Pattern of participation in leisure activities among older people in relation to their health conditions and contextual factors: a survey in Swedish urban area. Ageing Soc 29:803–821

    Article  Google Scholar 

  • Parades BR, Aung H, Berthouze NB (2013) One-vs-one classifier ensemble with majority voting for activity recognition. In: European symposium of artificial neural networks, computational intelligence and machine learning, Bruges, pp 443–448

  • Pinardi S, Bisiani R (2010) Movement recognition with intelligent multisensory analysis, a lexical approach. In: Proceedings of 6th international conference on intelligent environment, Kuala Lumpur, pp 170–177

  • Polikar R (1999) The story of wavelets. Phys Mod Top Mech Electr Eng 1:192–197

    MATH  Google Scholar 

  • Ponce H, Villasenor MLM, Pechuan LM (2016) A novel wearable sensor-based human activity recognition approach using artificial hydrocarbon networks. Sensors 16:1–28

    Article  Google Scholar 

  • Preece JS, Goulermas JY, Kenney LPJ, Howard D (2009) A comparison of feature extraction methods for classification of dynamic activities from accelerometer data. IEEE T Bio-Med Eng 56:871–879

    Article  Google Scholar 

  • Reiss A, Hendeby G, Sticker D (2013) A competitive approach for human activity recognition on smartphones. In: European symposium of artificial neural networks, computational intelligence and machine learning, Bruges, pp 455–460

  • Ronao CA, Cho SB (2016) Human activity recognition with smartphone sensors using deep learning neural networks. Expert Syst Appl 59:235–244

    Article  Google Scholar 

  • Saeys Y, Inza I, Larranaga P (2007) A review of feature selection techniques in bioinformatics. Bioinformatics 23:2507–2517

    Article  Google Scholar 

  • Saez Y, Baldominos A, Isasi P (2016) A comparison study of classifier algorithms for cross-person physical activity recognition. Sensors 17:66–92

    Article  Google Scholar 

  • Sebestyen G, Tirea A, Albert R (2012) Monitoring human activity through portable devices. Carpath J Electron Comput Eng 5:101–106

    Google Scholar 

  • Sheng M, Jiang J, Su B, Tang Q, Yahya AA, Wang G (2016) Short-time activity recognition with wearable sensors using convolutional neural networks. In: Proceedings of the 15th ACM SIGGRAPH conference on virtual-reality continuum and its applications in industry, Zhuhai, pp 413–416

  • Shoaib M, Bosch S, Incel OD, Scholten H, Havinga PJM (2015) A survey of online activity recognition using mobile phones. Sensors 15:2059–2085

    Article  Google Scholar 

  • Simard PY, Steinkraus D, Platt JC (2003) Best practice for convolutional neural networks applied to visual document analysis. In Proceedings of the 7th International Conference on Document Analysis and Recognition, Washington, pp 958–962

  • Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: Proceedings of 5th international conference on learning representations, San Diego, pp 1–14

  • Su B, Tang Q, Wang G, Sheng M (2016) The recognition of human daily actins with wearable motion sensor systems. Lect Notes Comput Sci Trans Edutainment XII(9292):68–77

    Article  Google Scholar 

  • Suto J, Oniga S, Buchman A (2015) Real time human activity monitoring. Annales Mathematicae et Informaticae 44:187–196

    MATH  Google Scholar 

  • Suto J, Oniga S, Pop-Sitar P (2016) Comparison of wrapper and filter feature selection algorithms on human activity recognition. In: Proceedings of the 6′th international conference on computers communications and control, Oradea, Baile Felix, pp 124–129

  • Suto J, Oniga S, Pop-Sitar P (2017) Feature analysis to human activity recognition. Int J Comp Commun 12:116–130

    Article  Google Scholar 

  • Wang J, Chen R, Sun X, She MFH, Wu Y (2011) Recognizing human daily activities from accelerometer signal. Procedia Eng 15:1780–1786

    Article  Google Scholar 

  • Yang JY, Wang JS, Chen YP (2008) Using acceleration measurements for activity recognition: an effective learning algorithm for constructing neural classifiers. Pattern Recogn Lett 29:2213–2220

    Article  Google Scholar 

  • Yang AY, Jafari R, Sastry SS, Bajcsy R (2009) Distributed recognition of human actions using wearable motion sensor networks. J Ambient Intell Smart Environ 1:103–115

    Google Scholar 

  • Yang JB, Nguyen MN, San PP, Li XL, Krishnaswamy S (2015) Deep convolutional neural networks on multichannel time series for human activity recognition. In: Proceedings of the 24th international joint conference on artificial intelligence, Buenos Aires, pp 3995–4001

  • Zheng M, Nguyen LT, Yu B, Mengshoel OJ, Zhu J, Wu P, Zhang J (2014) Convolutional neural networks for human activity recognition using mobile sensors. In: Proceedings of the 6th international conference on mobile computing, applications and Services, Austin, pp 197–205

Download references

Acknowledgements

The publication was supported through the new Hungarian National Excellence Program of the Ministry of Human Capacities. The project identifier is ÚNKP-16-3.

Author information

Authors and Affiliations

  1. Department of Informatics Systems and Networks, Faculty of Informatics, University of Debrecen, Kassai Road, 26, 4028, Debrecen, Hungary

    Jozsef Suto & Stefan Oniga

  2. Department of Electronic and Computer Engineering, Technical University of Cluj-Napoca, North University Centre of Baia Mare, Str. Dr. Victor Babes, 62A, 43008, Baia Mare, Romania

    Stefan Oniga

Authors
  1. Jozsef Suto
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Stefan Oniga
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jozsef Suto.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Suto, J., Oniga, S. Efficiency investigation of artificial neural networks in human activity recognition. J Ambient Intell Human Comput 9, 1049–1060 (2018). https://doi.org/10.1007/s12652-017-0513-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12652-017-0513-5

Keywords

Search

Navigation