Visual perception and deep learning in smart homes and the Internet of Things

Authors

  • Jiamiao Li

DOI:

https://doi.org/10.54097/bcvmxs60

Keywords:

Smart Home, Internet of Things, Visual Perception, Deep Learning.

Abstract

 In recent years, IOT (Internet of Things) has been widely used in the field of smart homes. IOT technology is an important stage in the development process of the "digital information age", with a history of more than ten years of development. It is widely used in the communication industry, especially in the field of smart homes. The basic principle of DL is to establish a multi-layer neural learning network, which learns a large amount of data to obtain better features and improve the accuracy of classification and recognition. This article conducts research on the visual perception of smart homes based on DL (Deep Learning) and IOT. Utilizing an intelligent gateway to achieve the mutual conversion of the underlying ZigBee protocol and in ternet protocol, the cloud service platform is interacted with by the Netty middleware and gateway. The entire system is centered around the Internet cloud platform, connecting the underlying IOT devices and the mobile network platform of the application layer to achieve the construction of a smart home system. The device then collects the user's EEG signals in real-time and hands them over to a trained specific network for classification. Finally, based on the classification results, the serial device sends signals to the smart home terminal to achieve the final practical operation actions, such as turning on the lights and fans.

Downloads

Download data is not yet available.

References

Yaldi I R H, Gunawan T S, Kartiwi M. Smart Home System using Internet of Things [J]. International Journal of Electrical & Computer Engineering, 2021, 10 (8): 29 - 36.

Na L I, Yulu Z. Design of Smart Home System Based on ZigBee [J]. Journal of Beijing Polytechnic College, 2020, 25 (9): 19 - 24.

Shen J, Wang C, Li T, et al. Secure data uploading scheme for a smart home system [J]. Information ences, 2021, 18 (10): 186 - 197.

Gazzawe F, Lock R. Smart Home [J]. Advances in Intelligent Systems and Computing, 2018, 17 (4): 10 - 17.

Wei Z, Yihuai W, Computer S O, et al. Smart Home System Based on Raspberry Pi 3 [J]. Microcontrollers & Embedded Systems, 2018, 36 (10): 26 - 34.

Rahmati A, Fernandes E, Eykholt K, et al. Tyche: Risk-Based Permissions for Smart Home Platforms[J]. Internet Technology Letters, 2022, 18 (5): 48 - 55.

Sicari S, Rizzardi A, Miorandi D, et al. Securing the smart home: A real case study [J]. Internet Technology Letters, 2018: e22. DOI: 10.1002/itl2.22.

Saleem T J, Chishti A. Deep Learning for Internet of Things Data Analytics [J]. Procedia Computer Science, 2019, 163 (22): 381 - 390.

Ma W. Analysis of anomaly detection method for Internet of things based on deep learning [J]. Transactions on Emerging Telecommunications Technologies, 2020, 12 (2): 7 - 13.

Liang S D. Smart and Fast Data Processing for Deep Learning in Internet of Things: Less is More [J]. Institute of Electrical and Electronics Engineers (IEEE), 2019, 12 (4): 10 - 19.

Downloads

Published

13-03-2024