ABSTRACT
Artificial intelligence internet of things (AIoT) is a technology that came into being under the development of artificial intelligence (AI) and Internet of things (IOT) where deep learning is vigorously promoted and used. Compared with the traditional concept of the Internet of things, the main difference of AIoT technology is that it applies interconnected devices which are embedded with the capacity of neural network model reasoning to the perception layer, this reduce reliance on edge servers (especially for neural network model training or reasoning). Thus, the edge devices of the system will get a more intelligent execution power. For the IOT system structures that have been built at present, most of the interconnection devices in the sensing layer, such as data acquisition nodes or execution nodes, are designed with the low and medium performance microcontroller unit as the processing core. After using the technology such like lightweight neural network and global average pooling, we succeed in deploying the convolutional neural network model to the low and medium performance microcontroller. Thus, the original node can get the reasoning result of neural network model in offline state and use it as a decision element for the operation of the system whit a simple modification of the program.
- Y. Pang, M. Sun, X. Jiang and X. Li, "Convolution in Convolution for Network in Network," in IEEE Transactions on Neural Networks and Learning Systems, vol. 29, no. 5, pp. 1587-1597, May 2018, doi: 10.1109/TNNLS.2017.2676130.Google ScholarCross Ref
- Forrest N. Iandola, Song Han, Matthew W. Moskewicz, Khalid Ashraf, William J. Dally, Kurt Keutzer, SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and < 0.5MB model size, arXiv:1602.07360v4.Google Scholar
- Zhu Xuechen, Chen Sanlin, Cai Gang, Huang Zhihong. Convolutional Neural Network Model Compression Method for Reducing Parameter Scale [J]. Computer and Modernization, 2021(09):83-89.Google Scholar
- Jia Heming, Lang Chunbo, Jiang Zichao. Plant Leaf Disease Identification Method Based on Lightweight Convolutional Neural Network [J], Computer Application. 2021,41(06):1812-1819.Google Scholar
- Item Xinjian, Song Xiaomin, Zheng Yongping, Wang Haibo, Fang Zhengyang. Research on MobileNet-YOLO-based Embedded Face Detection [J], Journal of China Agricultural Machinery. 2022,43(04):124-130.Google Scholar
- T.-Y. Hsiao, Y. -C. Chang and C. -T. Chiu, "Filter-based Deep-Compression with Global Average Pooling for Convolutional Networks," 2018 IEEE International Workshop on Signal Processing Systems (SiPS), 2018, pp. 247-251, doi: 10.1109/SiPS.2018.8598453.Google ScholarCross Ref
Index Terms
- A research of convolutional neural network model deployment in low- to medium-performance microcontrollers
Recommendations
Convolutional Neural Network Single-Point Control Model
ICNSER2019: Proceedings of the International Conference on Industrial Control Network and System Engineering ResearchThe artificial intelligence as-a-service represented by the convolutional neural network faces many security problems, such as the adversary bypassing the cloud access control to obtain the control of the convolutional neural network model. In view of ...
Research on improved wavelet convolutional wavelet neural networks
AbstractConvolutional neural network (CNN) is recognized as state of the art of deep learning algorithm, which has a good ability on the image classification and recognition. The problems of CNN are as follows: the precision, accuracy and efficiency of ...
A hybrid deep learning model by combining convolutional neural network and recurrent neural network to detect forest fire
AbstractForest fire poses a serious threat to wildlife, environment, and all mankind. This threat has prompted the development of various intelligent and computer vision based systems to detect forest fire. This article proposes a novel hybrid deep ...
Comments