RFID Indoor positioning based on Semi-supervised Actor-Critic Co-training

doi:10.19682/j.cnki.1005-8885.2020.0030

中国邮电高校学报(英文) ›› 2020, Vol. 27 ›› Issue (5): 69-81.doi: 10.19682/j.cnki.1005-8885.2020.0030

所属专题：人工智能专题

RFID Indoor positioning based on Semi-supervised Actor-Critic Co-training

李丽; 郑嘉利; 全艺璇; 林子涵; 李映超; 黄天星

1. 广西大学
2. 广西多媒体通信与网络技术重点实验室
3. 广西民族大学

收稿日期:2020-01-22 修回日期:2020-08-14 出版日期:2020-10-22 发布日期:2020-10-23
通讯作者: 郑嘉利 E-mail:zji@gxu.edu.cn
基金资助:
国家自然科学基金

RFID Indoor positioning based on Semi-supervised Actor-Critic Co-training

Li Li, Zheng Jiali, Quan Yixuan, Lin Zihan, Li Yingchao, Huang Tianxing

Guangxi University Guangxi University for Nationalities

Received:2020-01-22 Revised:2020-08-14 Online:2020-10-22 Published:2020-10-23
Supported by:
the National Natural Science Foundation of China and the Natural Science Foundation of Guangxi Province, China

摘要/Abstract

摘要： For large-scale radio frequency identification ( RFID) indoor positioning system, the positioning scale is relatively large, with less labeled data and more unlabeled data, and it is easily affected by multipath and white noise. An RFID positioning algorithm based on semi-supervised actor-critic co-training (SACC) was proposed to solve this problem. In this research, the positioning is regarded as Markov decision-making process. Firstly, the actor-critic was combined with random actions and selects the unlabeled best received signal arrival intensity (RSSI) data by co-training of the semi-supervised. Secondly, the actor and the critic were updated by employing Kronecker-factored approximation calculate (K-FAC) natural gradient. Finally, the target position was obtained by co-locating with labeled RSSI data and the selected unlabeled RSSI data. The proposed method reduced the cost of indoor positioning significantly by decreasing the number of labeled data. Meanwhile, with the increase of the positioning targets, the actor could quickly select unlabeled RSSI data and updates the location model. Experiment shows that, compared with other RFID indoor positioning algorithms, such as twin delayed deep deterministic policy gradient (TD3), deep deterministic policy gradient (DDPG), and actor-critic using Kronecker-factored trust region ( ACKTR), the proposed method decreased the average positioning error respectively by 50.226%, 41.916%, and 25.004%. Meanwhile, the positioning stability was improved by 23.430%, 28.518%, and 38.631%.

关键词: RFID, RSSI, semi-supervised actor-critic, Kronecker-Factored, co-training

Abstract: For large-scale radio frequency identification ( RFID) indoor positioning system, the positioning scale is relatively large, with less labeled data and more unlabeled data, and it is easily affected by multipath and white noise. An RFID positioning algorithm based on semi-supervised actor-critic co-training (SACC) was proposed to solve this problem. In this research, the positioning is regarded as Markov decision-making process. Firstly, the actor-critic was combined with random actions and selects the unlabeled best received signal arrival intensity (RSSI) data by co-training of the semi-supervised. Secondly, the actor and the critic were updated by employing Kronecker-factored approximation calculate (K-FAC) natural gradient. Finally, the target position was obtained by co-locating with labeled RSSI data and the selected unlabeled RSSI data. The proposed method reduced the cost of indoor positioning significantly by decreasing the number of labeled data. Meanwhile, with the increase of the positioning targets, the actor could quickly select unlabeled RSSI data and updates the location model. Experiment shows that, compared with other RFID indoor positioning algorithms, such as twin delayed deep deterministic policy gradient (TD3), deep deterministic policy gradient (DDPG), and actor-critic using Kronecker-factored trust region ( ACKTR), the proposed method decreased the average positioning error respectively by 50.226%, 41.916%, and 25.004%. Meanwhile, the positioning stability was improved by 23.430%, 28.518%, and 38.631%.

Key words: RFID, RSSI, semi-supervised actor-critic, Kronecker-Factored, co-training

中图分类号:

TP301.6

Li Li, Zheng Jiali, Quan Yixuan, Lin Zihan, Li Yingchao, Huang Tianxing. RFID Indoor positioning based on Semi-supervised Actor-Critic Co-training[J]. The Journal of China Universities of Posts and Telecommunications, 2020, 27(5): 69-81.

参考文献 19

1.	Caulfield B. Estimating the environmental benefits of ride-sharing: A case study of Dublin. Transportation Research Part D: Transport and Environment, 2009, 14(7): 527-531.
2.	Li Z R, Hong Y L, Zhang Z J. An empirical analysis of on-demand ride sharing and traffic congestion. Proceedings of the 50th Hawaii International Conference on Information Systems (ICIS’16), 2016, Dec 11-14, Dublin, Ireland. 2016: 4-13.
3.	Rai H B, Verlinde S, Merckx J, et al. Crowd logistics: An opportunity for more sustainable urban freight transport? European Transport Research Review, 2017, 9(3): 39.
4.	Liu Y R. Study on model of crowdsourcing express and its development tendency. Storage Transportation and Preservation of Commodities, 2016 (4): 32-33 (in Chinese).
5.	Chen X M, Miao F, Pappas G J, et al. Hierarchical data-driven vehicle dispatch and ride-sharing. Proceedings of the IEEE 56th Annual Conference on Decision and Control (CDC’17), 2017, Dec 12-15, Melbourne, Australia. Piscataway, NJ, USA: IEEE, 2017: 4458-4463.
6.	Arslan A M, Agatz N, Kroon L, et al. Crowdsourced delivery—A dynamic pickup and delivery problem with ad hoc drivers. Transportation Science, 2019, 53(1): 222-235.
7.	Chen M J, Shen W R, Tang P Z, et al. Optimal vehicle dispatching for ride-sharing platforms via dynamic pricing. Proceedings of the 2018 Companion Proceedings of the the Web Conference (WWW’18), 2018, Apr 23-27, Lyon France. Geneva, Switzerland: International World Wide Web Conferences Steering Committee, 2018: 51-52.
8.	Li J B, Xu L P, Mei Q H, et.al. Order and vehicle matching optimization problem based on urban distribution platform. Industrial Engineering and Management, 2019, 24(6): 8-15 (in Chinese).
9.	Xu Z, Li Z X, Guan Q W, et al. Large-scale order dispatch in on-demand ride-hailing platforms: A learning and planning approach. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’18), 2018, Aug 19-23, London UK. New York, NY, USA: ACM, 2018: 905-913.
10	Al-Abbasi A O, Ghosh A, Aggarwal V. Deeppool: Distributed model-free algorithm for ride-sharing using deep reinforcement learning. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(12): 4714-4727.
11	Zheng L B, Chen L, Ye J P. Order dispatch in price-aware ridesharing. Proceedings of the VLDB Endowment, 2018, 11(8): 853-865.
12	Kafle N, Zou B, Lin J. Design and modeling of a crowdsource-enabled system for urban parcel relay and delivery. Transportation Research Part B: Methodological, 2017, 99: 62-82.
13	Ma T Y, Rasulkhani S, Chow J Y J, et al. A dynamic ridesharing dispatch and idle vehicle repositioning strategy with integrated transit transfers. Transportation Research Part E: Logistics and Transportation Review, 2019, 128: 417-442.
14	Wang F X, Zhu Y F, Wang F, et al. Ridesharing as a service: Exploring crowdsourced connected vehicle information for intelligent package delivery. Proceedings of the IEEE/ACM 26th International Symposium on Quality of Service (IWQoS’18), 2018, Jun 4-6, Banff, Canada. Piscataway, NJ, USA: IEEE, 2018: 10p.
15	Hong H T, Li X, He D Q, et al. Crowdsourcing incentives for multi-hop urban package delivery network. IEEE Access, 2019, 7: 26268-26277.
16	Di Febbraro A, Giglio D, Sacco N. On exploiting ride-sharing and crowd-shipping schemes within the physical internet framework. Proceedings of the 21st International Conference on Intelligent Transportation Systems (ITSC’18), 2018, Nov 4-7, Maui, HI, USA. Piscataway, NJ, USA: IEEE, 2018: 1493-1500.
17	Cui Q M, Gu Y, Ni W, et al. Preserving reliability to heterogeneous ultra-dense distributed networks in unlicensed spectrum. IEEE Communications Magazine, 2018, 56(6): 72-78.
18	Kuhn H W. The Hungarian method for the assignment problem. Naval Research Logistics, 1955, 2(1): 83-98.
19	Munkres J. Algorithms for the assignment and transportation problems. Journal of the Society for Industrial and Applied Mathematics, 1957, 5(1): 32-38.

[1]	Zhang Jiangbo, Zheng Jiali, Quan Yixuan, Lin Zihan, Xie Xiaode. Improved sparrow search algorithm for RFID network planning[J]. 中国邮电高校学报(英文版), 2023, 30(1): 93-102.
[2]	谢孝德郑嘉利林子涵何思怡冯敏瑜. Random mating mayfly algorithm for RFID network planning[J]. 中国邮电高校学报(英文版), 2022, 29(5): 40-50.
[3]	林子涵郑嘉利谢孝德冯敏瑜何思怡. RFID network planning based on improved brain storm optimization algorithm[J]. 中国邮电高校学报(英文版), 2022, 29(5): 30-39.
[4]	Lv Lihui, Wang Hong, Ma Zhi, Duan Qianheng, Fei Yangyang, Meng Xiangdong. Methods for solving equations with errors based on the HHL algorithm[J]. 中国邮电高校学报(英文版), 2022, 29(4): 9-20.
[5]	Quan Yixuan, Zheng Jiali, Xie Xiaode, Lin Zihan, Luo Wencong. Hybrid gray wolf optimization-cuckoo search algorithm for RFID network planning [J]. 中国邮电高校学报(英文版), 2021, 28(6): 91-102.
[6]	Lü Chaohui, Pan Jiaying. Extraction technique of region of interest from stereoscopic video[J]. 中国邮电高校学报(英文版), 2017, 24(5): 68-76.
[7]	Ren Xingyi, Song Meina, E Haihong, Song Junde. Social media mining and visualization for point-of-interest recommendation[J]. 中国邮电高校学报(英文版), 2017, 24(1): 67-76.
[8]	张小红胡应梦. RFID mutual-authentication protocol with synchronous updated-keys based on Hash function[J]. Acta Metallurgica Sinica(English letters), 2015, 22(6): 27-35.

RFID Indoor positioning based on Semi-supervised Actor-Critic Co-training

RFID Indoor positioning based on Semi-supervised Actor-Critic Co-training

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献 19

相关文章 8

编辑推荐

Metrics

本文评价