Document Type : Research Paper


Computer Science Dept., University of Technology-Iraq, Alsina’a street, 10066 Baghdad, Iraq.


The human activity recognition (HAR) field has recently become one of the trendiest research topics due to ready-made sensors such as accelerometers and gyroscopes equipped with smartphones and smartwatches as an embedded devices, decreasing the cost and power consumption. As a result, human activity is considered a time series classification problem. Now a day, deep learning approaches such as Convolutional Neural Network (CNN) have been successful when implemented with HAR to learn automatically higher-order features and, at the same time, work as a classifier. Recently, a one-dimensional Convolutional Neural Network (1D CNN) has been suggested and carried out at the best performance levels in numerous applications, such as the classification of personalized biomedical data and time series classification. This paper studies how to leverage a 1D single CNN model to produce an excellent performance on the human activity raw data. This is done by empirically tuning the values of hyperparameters, such as kernel size, filter maps, number of epochs, batch size, and promoting an advanced multi-headed 1D CNN by employing each convolutional layer with a different kernel size to gain an ensemble–like results. The selected hyper parameter's impact is evaluated on a publicly available dataset named UCI HAR collected from smartphone sensors to perform six activities. A significant determinant of better results depends on the hyperparameter that has been chosen. The results demonstrated that tuning the hyperparameter of 1D CNN increased activity recognition accuracy.

Graphical Abstract


  • How to leverage a 1D single CNN model to produce an excellent performance on the human activity raw data.
  • Better results depend on the hyperparameter that has been chosen.
  •   Tuning the hyperparameter of 1D CNN increased the accuracy of activity recognition.


Main Subjects

[1] L. Pei et al., Human behavior cognition using smartphone sensors, Sensors (Switzerland), 13 (2013) 1402–1424, doi: 10.3390/s130201402.
[2] M. Shoaib, S. Bosch, O. D. Incel, H. Scholten, and P. J. M. Havinga, A survey of online activity recognition using mobile phones, Sensors (Switzerland), 15 (2015) 2059–2085, doi: 10.3390/s150102059.
[3] A. Wang, G. Chen, J. Yang, S. Zhao, and C. Y. Chang, A Comparative Study on Human Activity Recognition Using Inertial Sensors in a Smartphone, IEEE Sens. J., 16 (2016) 4566–4578, doi: 10.1109/JSEN.2016.2545708.
[4] J. Wang, Y. Chen, S. Hao, X. Peng, and L. Hu, Deep learning for sensor-based activity recognition: A survey, Pattern Recognit. Lett., 119 (2019) 3–11, doi: 10.1016/j.patrec.2018.02.010.
[5] S. Nazir, S. Patel, and D. Patel, Assessing Hyper Parameter Optimization and Speedup for Convolutional Neural Networks, 10 (2020) 1–17, doi: 10.4018/IJAIML.2020070101.
[6] K. G. Pasi and S. R. Naik, Effect of parameter variations on accuracy of Convolutional Neural Network, Int. Conf. Comput. Anal. Secur. Trends, CAST 2016 (2017) 98–403, doi: 10.1109/CAST.2016.7915002.
[7] C. A. Ronao and S. B. Cho, Human activity recognition with smartphone sensors using deep learning neural networks, Expert Syst. Appl., 2016, doi: 10.1016/j.eswa.2016.04.032.
[8] A. Koutsoukas, K. J. Monaghan, X. Li, and J. Huan, Deep-learning: Investigating deep neural networks hyper-parameters and comparison of performance to shallow methods for modeling bioactivity data, J. Cheminform., 9 (2017) 1–13, doi: 10.1186/s13321-017-0226-y.
[9] S. Nazir, S. Patel, and D. Patel, “Hyper Parameters Selection for Image Classification in Convolutional Neural Networks,” Proc. 2018 IEEE 17th Int. Conf. Cogn. Informatics Cogn. Comput. ICCI*CC 2018 (2018) 401–407, doi: 10.1109/ICCI-CC.2018.8482081.
[10] A. Agrawal and N. Mittal, Using CNN for facial expression recognition: a study of the effects of kernel size and number of filters on accuracy, Vis. Comput., 36 (2020) 405–412, doi: 10.1007/s00371-019-01630-9.
[11] I. Mitiche, A. Nesbitt, S. Conner, P. Boreham, and G. Morison, 1D-CNN based real-time fault detection system for power asset diagnostics, IET Gener. Transm. Distrib., 14 (2020) 5766–5773.
[12] L. Eren, T. Ince, and S. Kiranyaz, A Generic Intelligent Bearing Fault Diagnosis System Using Compact Adaptive 1D CNN Classifier, J. Signal Process. Syst., 91 (2019) 179–189, doi: 10.1007/s11265-018-1378-3.
[13] S. H. Kim, Z. W. Geem, and G. T. Han, Hyperparameter optimization method based on harmony search algorithm to improve performance of 1D CNN human respiration pattern recognition system, Sensors (Switzerland), 20 (2020) 1–20, doi: 10.3390/s20133697.
[14] S. Gafsi, Convolutional Neural Networks : Hyperparameters tuning and numerical results-A case study Project Proposal : Convolutional Neural Networks : A case study CS404 / 505 : Convex Optimization for Data Analysis Gafsi Saddam,” no. May, (2018).
[15] D. Anguita, A. Ghio, L. Oneto, X. Parra, and J. L. Reyes-Ortiz, Human Activity Recognition on Smartphones Using a Multiclass Hardware-Friendly Support Vector Machine BT  - Ambient Assisted Living and Home Care, (2012) 216–223.