Education, Science, Technology, Innovation and Life
Open Access
Sign In

ALOHA Improvement Algorithm for Dynamic Frame Time Slots with Transformer

Download as PDF

DOI: 10.23977/jnca.2024.090102 | Downloads: 2 | Views: 174

Author(s)

Weijie Zhan 1

Affiliation(s)

1 School of Physics and Electronic Science, Hunan University of Science and Technology, Xiangtan, 411201, China

Corresponding Author

Weijie Zhan

ABSTRACT

In recent years, with the widespread application of RFID technology in production and daily life, the demand for tag reading systems has been increasing. When faced with a large number of tags, RFID systems often experience severe collisions within the same reading frame due to tag responses, leading to low reading efficiency. The key to solving this problem lies in the speed and accuracy of the tag number estimation algorithm. Based on the analysis of traditional algorithms, this paper proposes a new tag number estimation algorithm. This algorithm generates tag datasets with specific word lengths based on the principle of the dynamic framed slotted ALOHA (DFSA) algorithm and establishes a model using a Transformer neural network to predict the number of tags. The network establishes a mapping relationship between the reader and the remaining number of tags to estimate the tag count. Compared with traditional algorithms, the innovation of this paper lies in the introduction of the self-attention mechanism, which significantly improves the accuracy of tag number prediction while reducing the time consumption of the reading system. Simulation results show that the proposed algorithm improves system efficiency while maintaining accuracy, offering a new solution for large-scale RFID applications.

KEYWORDS

RFID; Dynamic frame slot; ALOHA algorithm; Transformer

CITE THIS PAPER

Weijie Zhan, ALOHA Improvement Algorithm for Dynamic Frame Time Slots with Transformer. Journal of Network Computing and Applications (2024) Vol. 9: 8-15. DOI: http://dx.doi.org/10.23977/jnca.2024.090102.

REFERENCES

[1] F. Costa, S. Genovesi, M. Borgese, A. Michel, F. A. Dicandia, and G. Manara, "A Review of RFID Sensors, the New Frontier of Internet of Things," Sensors, vol. 21, no. 9, p. 3138, 2021.
[2] Bao Shengwen, Fang Yongjun, Xiao Xiaobing, et al. Research and Application of RFID Technology in Medical Equipment Management System [J]. Electronic Product World, 2022, 29(03): 43-46.
[3] Xiao Chang, Ding Huan, Fu Huiling, et al. Design and Application of Medical Fabric Management Module Based on RFID and Barcode Technology [J]. China Medical Equipment, 2022, 37(06): 119-122.
[4] Fu Hao, Lin Kan, Qin Tong. Research on Intelligent Warehouse Management System in Power Plants Based on RFID Technology [J]. Electric Power Survey and Design, 2022, (05): 72-76.
[5] Li Lingqiao. Application of RFID Technology in the Field of Clothing Warehousing and Logistics [J]. Chemical Fiber & Textile Technology, 2022, 51(09): 58-60.
[6] Liu Feiran, Xu Dong, Tian Yunfeng, et al. Application of RFID Technology in the Informationization of Urban Rail Transit Vehicle Maintenance [J]. Urban Rail Transit Research, 2023, 26(10): 148-152.
[7] He Tao. Application of RFID Technology in Elevator Safety Management System [J]. IC Application, 2022, 39(03): 176-177.
[8] Yan Yijia, Yan Hongtao, Wang Zhibiao, et al. Application of RFID in Safety Warning Management System in High-risk Places [J]. Science & Technology Innovation and Application, 2019, (27): 167-168.
[9] Wang Shuai. Research on the Performance of RFID Anti-collision Algorithms [D]. Nanjing University of Posts and Telecommunications, 2020.
[10] Hu Huangshui, Zhang Guo, Wang Hongzhi, et al. An RFID Anti-collision Algorithm Based on Equal-area Division [J]. Journal of Jilin University (Science Edition), 2020, 58(01): 120-126.
[11] Wang Dongyun, Zhang Weiping, Wang Zhijia. Research on RFID Tag Anti-collision Based on Improved ALOHA Algorithm [J]. Packaging Engineering, 2021, 42(17): 244-248.
[12] Yang Chao, Zhao Yifan, Li Bo, et al. Research on RFID Tag Anti-collision Algorithm Based on Deep Learning [J]. Modern Electronics Technique, 2021, 44(22): 21-25.
[13] Ming Dongyue, Wang Shangpeng, Lei Ming, et al. Improved Dynamic Framed Slotted ALOHA Algorithm Combined with BP Neural Network [J]. Mini-Micro Systems, 2021, 42(09): 1920-1923.
[14] Shayo E I , Abdalla A T , Mwambela A J .Dynamic multi-frame multi-spreading factor scheduling algorithm for LoRaWAN[J].Journal of Electrical Systems and Information Technology, 2023, 10(1).DOI:10.1186/s43067-023-00077-2.
[15] Fan Caiyun, Sun Ruyi, Tong Junyi. Air Quality Index Prediction Based on Spatial Factors and LSTM Neural Network [J]. Practice and Understanding of Mathematics, 2021, 51(15): 194-202.
[16] Xu Lin, Xu Tingting. Population Prediction Method Based on BP Neural Network Model [J]. Information & Computer (Theoretical Edition), 2023, 35(04): 181-183.
[17] Guo Hui, Liu Yunting, Kong Zhenxing, et al. Research on VO2max Prediction Method Based on BP Neural Network [J]. Laboratory Science, 2020, 23(05): 44-48.
[18] Ren Huan, Wang Xuguang. A Survey of Attention Mechanism [J]. Application Research of Computers, 2021, 41(S1): 1-6.
[19] Wen Q S, Zhou T, Zhang C L, et al. Transformers in Time Series: A Survey [C]. IJCAI 2023: 6778-6786.
[20] Liang Hongtao, Liu Shuo, Du Junwei, et al. A Survey on the Application of Deep Learning in Time Series Prediction [J]. Journal of Computer Science and Exploration, 2023, 17(06): 1285-1300.
[21] Zhou Weihui, Jiang Niande, Wan Xinyue, et al. A Hybrid RFID Anti-collision Algorithm Based on ALOHA and Multi-tree [J]. Journal of East China University of Technology (Natural Science Edition), 2021, 44(01): 96-100.
[22] Lü Congying. A Novel RFID Tag Anti-collision Algorithm [J]. Manufacturing Automation, 2013, 35(20): 75-76.

Downloads: 1371
Visits: 128837

Sponsors, Associates, and Links


All published work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright © 2016 - 2031 Clausius Scientific Press Inc. All Rights Reserved.