Visible to the public Biblio

Filters: Author is Li, Dong  [Clear All Filters]
Conference Paper
Li, Dong, Jiao, Yiwen, Ge, Pengcheng, Sun, Kuanfei, Gao, Zefu, Mao, Feilong.  2021.  Classification Coding and Image Recognition Based on Pulse Neural Network. 2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID). :260–265.
Based on the third generation neural network spiking neural network, this paper optimizes and improves a classification and coding method, and proposes an image recognition method. Firstly, the read image is converted into a spike sequence, and then the spike sequence is encoded in groups and sent to the neurons in the spike neural network. After learning and training for many times, the quantization standard code is obtained. In this process, the spike sequence transformation matrix and dynamic weight matrix are obtained, and the unclassified data are output through the same matrix for image recognition and classification. Simulation results show that the above methods can get correct coding and preliminary recognition classification, and the spiking neural network can be applied.
Liu, Donglan, Liu, Xin, Zhang, Hao, Yu, Hao, Wang, Wenting, Ma, Lei, Chen, Jianfei, Li, Dong.  2019.  Research on End-to-End Security Authentication Protocol of NB-IoT for Smart Grid Based on Physical Unclonable Function. 2019 IEEE 11th International Conference on Communication Software and Networks (ICCSN). :239–244.
As a national strategic hot spot, the Internet of Things (IoT) has shown its vigor and vitality. With the development of IoT, its application in power grid is more and more extensive. As an advanced technology for information sensing and transmission, IoT has been applied extensively in power generation, transmission, transformation, distribution, utilization and other processes, and will develop with broad prospect in smart grid. Narrow Band Internet of Things (NB-IoT) is of broad application prospects in production management, life-cycle asset management and smart power utilization of smart grid. Its characteristics and security demands of application domain present a challenge for the security of electric power business. However, current protocols either need dual authentication and key agreements, or have poor compatibility with current network architecture. In order to improve the high security of power network data transmission, an end-to-end security authentication protocol of NB-IoT for smart grid based on physical unclonable function and state secret algorithm SM3 is proposed in this paper. A self-controllable NB-IoT application layer security architecture was designed by introducing the domestic cryptographic algorithm, extending the existing key derivation structure of LTE, and combining the physical unclonable function to ensure the generation of encryption keys between NB-IoT terminals and power grid business platforms. The protocol of this paper realizes secure data transmission and bidirectional identity authentication between IoT devices and terminals. It is of low communication costs, lightweight and flexible key update. In addition, the protocol also supports terminal authentication during key agreement, which furtherly enhances the security of business systems in smart grid.