Abstract
The use of machine learning techniques in Internet of Things (IoT) applications is increasing by the diversity of the IoT scenario. In addition, machine learning libraries contribute to this growth by promoting stable and easy-to-manipulate implementations, reducing the need to develop complex algorithms and bringing researchers’ attention to other end-application activities. However, library diversity can make it difficult to choose from, since factors such as computational resource use are critical in an IoT scenario where such elements are limited. This work analyzes the performance, energy consumption and resource usage of two of the major machine learning libraries on the market, through standardized applications. It was found that the Pytorch 1.1.0 can be used with lower consumption.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Angra, S., Ahuja, S.: Machine learning and its applications: a review. In: International Conference on Big Data Analytics and Computational Intelligence (ICBDAC), pp. 57–60, March 2017
Zantalis, F., Koulouras, G., Karabetsos, S., Kandris, D.: A review of machine learning and IoT in smart transportation. Future Internet 11(4), 94 (2019)
Niranjan, A., Mishra, G.: Etas - efficient traffic signal assistance system using deep learning. In: ICCCNT, pp. 1–5, July 2018
Jan, T., Sajeev, A.S.M.: Boosted probabilistic neural network for IoT data classification. In: DASC/PiCom/DataCom/CyberSciTech, pp. 408–411, August 2018
Ta-Shma, P., Akbar, A., Gerson-Golan, G., Hadash, G., Carrez, F., Moessner, K.: An ingestion and analytics architecture for IoT applied to smart city use cases. IEEE Internet Things J. 5(2), 765–774 (2018)
Chollet, F., et al.: Keras (2015). https://keras.io
Abadi, M., et al.: TensorFlow: large-scale machine learning on heterogeneous systems 2015, software available from tensorflow.org (2015). https://www.tensorflow.org/
Paszke, A., et al.: Automatic differentiation in PyTorch. In: NIPS Autodiff Workshop (2017)
Chen, T., et al.: MXNet: a flexible and efficient machine learning library for heterogeneous distributed systems. In: Neural Information Processing Systems,Workshop on Machine Learning Systems (2016). http://arxiv.org/abs/1512.01274
Kononenko, I.: Machine learning for medical diagnosis: history, state of the art and perspective. Artif. Intell. Med. 23(1), 89–109 (2001)
McCulloch, W.S., Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys. 5(4), 115–133 (1943)
Werbos, P.: Generalization of backpropagation with application to are current gas market model. Neural Netw. 1, 339–356 (1988)
Zhang, J., et al.: Automated detection and localization of myocardial infarction with staked sparse autoencoder and treebagger. IEEE Access 7, 70 634–70 642 (2019)
Hentschel, K., Jacob, D., Singer, J., Chalmers, M.: Supersensors: Raspberry Pi devices for smart campus infrastructure, pp. 58–62, August 2016
Gerhardt, T.E., Silveira, D.T.: Métodos de pesquisa. EditoraUFRGS (2009)
Valletta, J.J., Torney, C., Kings, M., Thornton, A., Madden, J.: Applications of machine learning in animal behaviour studies. Anim. Behav. 124, 203 – 220 (2017). http://www.sciencedirect.com/science/article/pii/S0003347216303360
Wang, G.: Machine learning for inferring animal behavior from location and movement data. Ecol. Inform. 49, pp. 69–76 (2019). http://www.sciencedirect.com/science/article/pii/S1574954118302036
Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning (2011)
Salih, F., Omer, S.A.M.: Raspberry pi as a video server. In: International Conference on Computer, Control, Electrical, and Electronics Engineering (ICCCEEE), August 2018
Sandeep, V., et al.: Globally accessible machine automation using raspberry Pi based on internet of things. In: ICACCI, pp.1144–1147, August 2015
Fundation, R.P.: Raspberry Pi 3 model b (2016). https://www.raspberrypi.org/products/raspberry-pi-3-model-b
Sandeep, V., et al.: Globally accessible machine automation using raspberry Pi based on internet of things. In: ICACCI, pp. 1144–1147, August 2015
Xiao, H., Rasul, K., Vollgraf, R.: Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms. arXiv:1708.07747, August 2017
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. In: Proceedings of the IEEE, vol. 86(11), pp. 2278–2324, November 1998
Harrison, D., Rubinfeld, D.L.: Hedonic housing prices and the demand for clean air. J. Environ. Econ. Manage. 5, 81–102 (1978). http://www.sciencedirect.com/science/article/pii/0095069678900062
Menezes, A.H., Kelvin, R.D.O., Oliveira, L.P., Oliveira, P.J.D.S.: IoT Environment to Train Service Dogs, S3C (2017). https://doi.org/10.1109/S3C.2017.8501386
Acknowledgments
The authors would like to thank the Federal Institute of Paraíba (IFPB)/Campus João Pessoa for financially supporting the presentation of this research and, especially thank you, to the IFPB Interconnect Notice - No. 01/2020.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Oliveira, L.P. et al. (2021). Deep Learning Library Performance Analysis on Raspberry (IoT Device). In: Barolli, L., Woungang, I., Enokido, T. (eds) Advanced Information Networking and Applications. AINA 2021. Lecture Notes in Networks and Systems, vol 225. Springer, Cham. https://doi.org/10.1007/978-3-030-75100-5_33
Download citation
DOI: https://doi.org/10.1007/978-3-030-75100-5_33
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-75099-2
Online ISBN: 978-3-030-75100-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)