Deep Learning In Wireless Sensor Network
DOI:
https://doi.org/10.29304/jqcm.2021.13.1.755Keywords:
CNN, Deep Learning, Processing, WSNAbstract
In the era of the development of the Internet of Things, how collecting data from sensors located everywhere in society is an important issue, and in wireless sensor networks, distributed processing technology for deep learning using advanced computing and coordination between peripherals has attracted attention. In this study, a new architecture is proposed for the distributed implementation of deep learning in a wireless sensor network where the distributed application divides the middle layer of deep learning into each sensor with the purpose of reducing traffic and reducing the load, in order to improve data processing speed, but this is done by increasing the number of connections and energy consumption, and in order to evaluate the effectiveness of the proposed method, been compared the amount of data communication and accuracy of learning between learning by using Convolutional Neural Network (CNN) normally and the distributed learning, and this was done using the Raspberry Pi open-source hardware platform, the system that is low-cost and highly scalable in terms of sensor devices type and the number of sensor nodes, which makes them well suited to a wide range of applications related to environmental monitoring, the sensors device have been connected to hardware and software design. Some software components, such as operating systems, sensor/hardware drivers, may need development. In the proposed method, the amount of data is large because the result in the middle of the computation processing is sent and it can be predicted that the total computation processing time will be reduced because the computational processing handled by each node will be reduced by section processing. The concentration of energy consumption can also be suppressed because the proposed method achieves decentralization compared to performing all calculations with a single sensor.
Downloads
References
[2] P. Sujeet , Localization Adopting Machine Learning Techniques in Wireless Sensor Networks , INTERNATIONAL JOURNAL OF COMPUTER SCIENCES AND ENGINEERING 6(1):366-374, January (2018).
[3] Fangyuan Lei, Jun Cai, Qingyun Dai, Huimin Zhao, Deep Learning Based Proactive Caching for Effective WSN-Enabled Vision Applications. Complexity 2019: 5498606:1-5498606:12 (2019).
[4] Z. Chaoyun, P. Paul, and H. Hamed, Deep Learning in Mobile and Wireless Networking: A Survey, IEEE COMMUNICATIONS SURVEYS & TUTORIALS,(2019).
[5] Swetha. R , Santhosh Amarnath.V , Anitha Sofia.V.S , Wireless Sensor Network : A Survey, Department of Computer Technology, Sri Krishna Arts and Science College, Coimbatore, Tamil Nadu, India,( IJARCCE ) International Journal of Advanced Research in Computer and Communication Engineering Vol. 7, Issue 11, (pp.114-117), November (2018).
[6] Li Deng and Dong Yu , Deep Learning: Methods and Applications , Foundations and Trends in Signal Processing: Vol. 7: No. 3–4, pp 197-387,(2014).
[7] SAMIRA POUYANFAR, , SAAD SADIQ and YILIN YAN & others ,A Survey on Deep Learning: Algorithms, Techniques, and Applications, ACM Computing Surveys, Vol. 51, No. 5, Article 92. Publication date: September (2018).
[8] Jiuxiang Gua , Zhenhua Wangb, & others , Recent Advances in Convolutional Neural Networks , Nanyang Technological University, Singapore, arXiv:1512.07108v6 [cs.CV] 19 Oct (2017).
[9] Lucas Tindall, Cuong Manh Luong, Plankton Classification Using VGG 16 Network, (2017).
[10] Mart´ın Abadi, Ashish Agarwal, Paul Barham, & others ,TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems, Preliminary White Paper, November 9, (2015)
[11] Jyotsna Bankar , Nitin R Gavai, Convolutional Neural Network based Inception v3 Model for Animal Classification, International Journal of Advanced Research in Computer and Communication Engineering(IJARCCE) ISO 3297:2007 Certified Vol. 7, Issue 5,(PP: 142-146), May (2018).
[12] Sheikh Mohammad Ferdoush, a low-cost wireless sensor network system using Raspberry pi and arduino for environmental monitoring applications , university of north texas, may (2014).