Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2023 Feb 13;9(2):e13636.
doi: 10.1016/j.heliyon.2023.e13636. eCollection 2023 Feb.

AUTO-HAR: An adaptive human activity recognition framework using an automated CNN architecture design

Walaa N Ismail  1   2 , Hessah A Alsalamah  3   4 , Mohammad Mehedi Hassan  3 , Ebtesam Mohamed  2
Affiliations
Review

AUTO-HAR: An adaptive human activity recognition framework using an automated CNN architecture design

Walaa N Ismail et al. Heliyon. .

Abstract

Convolutional neural networks (CNNs) have demonstrated exceptional results in the analysis of time- series data when used for Human Activity Recognition (HAR). The manual design of such neural architectures is an error-prone and time-consuming process. The search for optimal CNN architectures is considered a revolution in the design of neural networks. By means of Neural Architecture Search (NAS), network architectures can be designed and optimized automatically. Thus, the optimal CNN architecture representation can be found automatically because of its ability to overcome the limitations of human experience and thinking modes. Evolution algorithms, which are derived from evolutionary mechanisms such as natural selection and genetics, have been widely employed to develop and optimize NAS because they can handle a blackbox optimization process for designing appropriate solution representations and search paradigms without explicit mathematical formulations or gradient information. The Genetic optimization algorithm (GA) is widely used to find optimal or near-optimal solutions for difficult problems. Considering these characteristics, an efficient human activity recognition architecture (AUTO-HAR) is presented in this study. Using the evolutionary GA to select the optimal CNN architecture, the current study proposes a novel encoding schema structure and a novel search space with a much broader range of operations to effectively search for the best architectures for HAR tasks. In addition, the proposed search space provides a reasonable degree of depth because it does not limit the maximum length of the devised task architecture. To test the effectiveness of the proposed framework for HAR tasks, three datasets were utilized: UCI-HAR, Opportunity, and DAPHNET. Based on the results of this study, it has been found that the proposed method can efficiently recognize human activity with an average accuracy of 98.5% (∓1.1), 98.3%, and 99.14% (∓0.8) for UCI-HAR, Opportunity, and DAPHNET, respectively.

Keywords: CNN topology; Convolution neural networks; Deep learning; Evolutionary neural network search; Genetic algorithms; Human activity recognition.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
The Proposed AUTO-HAR Deep Learning Architecture.
Figure 2
Figure 2
Basic CNN Architecture.
Figure 3
Figure 3
AUTO-CNN architecture design and optimization.
Figure 4
Figure 4
Addition of a basic block to a fixed FC part.
Figure 5
Figure 5
Example of encoding CNN architecture with a depth of two.
Algorithm 1
Algorithm 1
An algorithm to search for the optimal the CNN architecture.
Algorithm 2
Algorithm 2
Function: Make POPULATION.
Figure 6
Figure 6
The performance of the proposed model for 25-generations of UCI dataset (a) loss and (b) mean accuracy.
Figure 7
Figure 7
Accuracy for 50 epochs from UCI dataset.
Figure 8
Figure 8
Loss for 50 epochs from UCI dataset.
Figure 9
Figure 9
Confusion matrix for UCI dataset of proposed model.
Figure 10
Figure 10
UCI_HAR 10-Fold False Discovery Rate.
Figure 11
Figure 11
UCI_HAR Specificity.
Figure 12
Figure 12
Confusion matrix for Opportunity dataset of proposed model.
Figure 13
Figure 13
Accuracy of AUTO-CNN on Daphnet dataset.
Figure 14
Figure 14
Confusion matrix for Daphnet dataset of proposed model.
Figure 15
Figure 15
Daphnet 10-Fold False Discovery Rate.
Figure 16
Figure 16
Daphnet Specificity.
Figure 17
Figure 17
The best architecture for UCI dataset.
Figure 18
Figure 18
The best architecture for Daphnet dataset.
See this image and copyright information in PMC

References

    1. Zhang S., Li Y., Zhang S., Shahabi F., Xia S., Deng Y., Alshurafa N. Deep learning in human activity recognition with wearable sensors: a review on advances. Sensors. 2022;22(4):1476. - PMC - PubMed
    1. Ismail W.N., Hassan M.M., Alsalamah H.A. Context-enriched regular human behavioral pattern detection from body sensors data. IEEE Access. 2019;7:33834–33850.
    1. Gao G., Li Z., Huan Z., Chen Y., Liang J., Zhou B., Dong C. Human behavior recognition model based on feature and classifier selection. Sensors. 2021;21(23):7791. - PMC - PubMed
    1. Subramanian R.R., Vasudevan V. A deep genetic algorithm for human activity recognition leveraging fog computing frameworks. J. Vis. Commun. Image Represent. 2021;77
    1. Quaid M.A.K., Jalal A. Wearable sensors based human behavioral pattern recognition using statistical features and reweighted genetic algorithm. Multimed. Tools Appl. 2020;79(9):6061–6083.

LinkOut - more resources