Please wait a minute...
浙江大学学报(工学版)  2025, Vol. 59 Issue (9): 1814-1825    DOI: 10.3785/j.issn.1008-973X.2025.09.005
计算机技术     
去中心化的室内定位众包数据质量控制方法
张学军(),邝浚鑫,李成泽,李梅,张斌,加小红
兰州交通大学 电子与信息工程学院,甘肃 兰州 730070
Decentralized indoor positioning crowdsourcing data quality control method
Xuejun ZHANG(),Junxin KUANG,Chengze LI,Mei LI,Bin ZHANG,Xiaohong JIA
School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China
 全文: PDF(1342 KB)   HTML
摘要:

现有基于区块链的众包指纹收集方法在数据质量控制共识、激励机制报酬分配方面缺乏对指纹数据本身分布特征的有效利用,从而影响数据收集质量. 为此提出考虑指纹数据分布特征的去中心化的室内定位众包数据质量控制方法. 根据指纹数据分布特征设计数据质量控制共识算法,通过检索相同标签类内的历史数据估算指纹数据分布的特征参数,当用户提交的指纹数据向量与历史均值向量的带权均方差小于给定阈值时,将用户数据上链,若链上已有该数据则不上链以抵御重放攻击. 为了保护用户身份隐私,将用户数据匿名上传并利用Schnorr协议验证区块所有权. 根据用户提交的指纹分布与链上指纹分布的数据质量误差来确定合适的激励函数. 在UJIIndoorLoc、MALL、WiFi-RSS这3个指纹数据集上的实验表明,与原始数据集相比,通过本研究方法筛选的指纹数据使室内定位模型的训练精度分别提升约10、3、10个百分点,有效提高了指纹数据采集的质量.

关键词: 室内定位接收信号强度(RSS)指纹区块链众包收集数据质量    
Abstract:

Existing blockchain-based crowdsourcing methods for fingerprint data lack effective utilization of fingerprint distribution characteristics in data quality control consensus and incentive mechanism reward distribution, affecting data collection quality. To address this issue, a decentralized indoor positioning crowdsourcing data quality control method considering fingerprint distribution features was proposed. A data quality control consensus algorithm was designed based on fingerprint distribution characteristics. Characteristic parameters were estimated by retrieving historical data within identical label classes. User-submitted fingerprint vectors were chained only when their weighted mean square error with historical mean vectors was below a given threshold. Duplicate data were rejected to resist replay attacks. To protect user identity privacy, data were anonymously uploaded with the block ownership verified using the Schnorr protocol. An appropriate incentive function was determined according to the data quality errors between user-submitted and on-chain fingerprint distributions. Experiments on three fingerprint datasets (UJIIndoorLoc, MALL and WiFi-RSS) demonstrated that compared with the original datasets, fingerprint data filtered by the proposed method improved training accuracy of indoor positioning models by approximately 10, 3 and 10 percentage points respectively, effectively enhancing fingerprint data acquisition quality.

Key words: indoor positioning    received signal strength (RSS) fingerprint    blockchain    crowdsourcing collection    data quality
收稿日期: 2024-07-31 出版日期: 2025-08-25
CLC:  TP 3-05  
基金资助: 国家自然科学基金资助项目(61762058,62366029);甘肃省重点研发计划资助项目(25YFFA089);甘肃省教育厅产业支撑基金资助项目(2022CYZC-38);高校教师创新基金项目(2024A-039).
作者简介: 张学军(1977—),男,教授,博导,从事数据安全与机器学习、物联网安全研究. orcid.org/0009-0000-5726-0661. E-mail:xuejunzhang@mail.lzjtu.cn
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章  
张学军
邝浚鑫
李成泽
李梅
张斌
加小红

引用本文:

张学军,邝浚鑫,李成泽,李梅,张斌,加小红. 去中心化的室内定位众包数据质量控制方法[J]. 浙江大学学报(工学版), 2025, 59(9): 1814-1825.

Xuejun ZHANG,Junxin KUANG,Chengze LI,Mei LI,Bin ZHANG,Xiaohong JIA. Decentralized indoor positioning crowdsourcing data quality control method. Journal of ZheJiang University (Engineering Science), 2025, 59(9): 1814-1825.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2025.09.005        https://www.zjujournals.com/eng/CN/Y2025/V59/I9/1814

图 1  区块头和区块体结构
图 2  去中心化的室内定位RSS指纹数据质量控制框架
图 3  指纹数据分布误差
输出形式参数个数
Conv2d_1(Conv2D)(None,1,53,32)192
Conv2d_2(Conv2D)(None,1,53,32)10304
max_pooling2d_1(MaxPooling2D)(None,1,24,64)0
dropout_1 (Dropout)(None,1,13,64)0
flatten_1 (Flatten)(None,832)0
dense_1 (Dense)(None,128)106624
dropout_2 (Dropout)(None,128)0
dense_2 (Dense)(None,10)1290
表 1  CNN定位模型的网络参数
数据集平均耗时/ms
PoWFQ-
winlen10
PoWFQ-
winlen15
PoWFQ-
winlen20
UJIIndoorLoc21.633333.398734.3033
WiFi-RSS20.990019.162828.4033
MALL18.530018.396721.7110
表 2  不同窗口大小下的平均共识耗时
滑动窗口大小数据集$ {a_{\rm{train}}} $$ {l_{\rm{train}}} $$ {a_{\rm{val}}} $$ {l_{\rm{val}}} $
PoWFQ-winlen10UJIIndoorLoc0.89190.34880.65632.1507
WiFi-RSS0.79180.65560.50582.0796
MALL0.90930.26170.89270.3614
PoWFQ-winlen15UJIIndoorLoc0.96640.07260.60003.1297
WiFi-RSS0.63971.09720.24054.3345
MALL0.72160.75920.69760.8146
PoWFQ-winlen20UJIIndoorLoc0.87400.40000.63332.1305
WiFi-RSS0.74310.77470.44323.5678
MALL0.70040.80390.71740.7660
表 3  不同窗口大小的PoWFQ对模型性能的影响
数据集PoWFQ-
winlen10
PoWFQ-
winlen15
PoWFQ-
winlen20
UJIIndoorLoc0.1363110.001960?0.145020
MALL0.1967420.0129950.013133
WiFi-RSS0.149871?0.099422?0.075516
表 4  不同窗口大小PoWFQ筛选数据集后轮廓系数的变化
数据集UJIIndoorLocMALLWiFi-RSS
原始数据19937700018750
PoWFQ-winlen101638448005072
PoWFQ-winlen151183746534917
PoWFQ-winlen201971648746118
表 5  不同窗口大小PoWFQ筛选不同数据集后的条数变化
数据集ts/ms
PoWPoSDpoSPoDPoWFQ
UJIIndoorLoc1964.60009.72339.366713.616721.6333
MALL427.54008.60338.866710.053318.5300
WiFi-RSS345.02678.84338.990010.003320.9900
表 6  不同共识算法上传300条记录的平均耗时
共识算法数据隐私双花攻击数据质量
Pod×
Pow××
Pos×××
Dpos×××
PoWFQ
表 7  不同共识算法功能对比
图 4  3个数据集上的模型训练和测试精度对比
共识算法数据集$ {a_{{{\mathrm{train}}}}} $$ {l_{{{\mathrm{train}}}}} $$ {a_{{{\mathrm{val}}}}} $$ {l_{{{\mathrm{val}}}}} $
PoWUJIIndoorLoc0.77100.74720.44483.7624
WiFi-RSS0.70560.98210.68871.1992
MALL0.87200.34580.90930.3323
PoSUJIIndoorLoc0.80050.66610.67001.4324
WiFi-RSS0.69990.99770.69621.2308
MALL0.88320.32640.90360.3490
DPoSUJIIndoorLoc0.79570.67990.64121.6682
WiFi-RSS0.67791.07180.65441.3273
MALL0.87160.37040.89570.3506
PoDUJIIndoorLoc0.84320.58760.35265.6292
WiFi-RSS0.30862.81000.07824.4087
MALL0.89000.34250.29623.2239
PoWFQUJIIndoorLoc0.89190.34880.65632.1507
WiFi-RSS0.79180.65560.50582.0796
MALL0.90930.26170.89270.3614
表 8  PoW、PoS、DpoS、PoD与PoWFQ对模型性能的影响
数据集原始数据PoWFQ筛选后PoD筛选后
UJIIndoorLoc0.1279070.1363110.019306
MALL0.1907220.1967420.036098
WiFi-RSS0.1434820.1498710.210153
表 9  不同数据集筛选前后的轮廓系数
图 5  UJIIndoorLoc数据集中用户的报酬因子
21 KHATRI I, KUMAR D, GUPTA A A noise robust kernel fuzzy clustering based on picture fuzzy sets and KL divergence measure for MRI image segmentation[J]. Applied Intelligence, 2023, 53 (13): 16487- 16518
doi: 10.1007/s10489-022-04315-4
22 WANG H, LIAO Y, LI Y, et al BDR-net: bhattacharyya distance-based distribution metric modeling for rotating object detection in remote sensing[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 72: 5002612
23 张学军, 何福存, 盖继扬, 等 边缘计算下指纹室内定位差分私有联邦学习模型[J]. 计算机研究与发展, 2022, 59 (12): 2667- 2688
ZHANG Xuejun, HE Fucun, GAI Jiyang, et al A differentially private federated learning model for fingerprinting indoor localization in edge computing[J]. Journal of Computer Research and Development, 2022, 59 (12): 2667- 2688
doi: 10.7544/issn1000-1239.20210270
24 ZHANG X, HE F, CHEN Q, et al A differentially private indoor localization scheme with fusion of WiFi and bluetooth fingerprints in edge computing[J]. Neural Computing and Applications, 2022, 34 (6): 4111- 4132
doi: 10.1007/s00521-021-06815-9
25 TORRES-SOSPEDRA J, MONTOLIU R, MARTÍNEZ-USÓ A, et al. UJIIndoorLoc: a new multi-building and multi-floor database for WLAN fingerprint-based indoor localization problems [C]// Proceedings of the International Conference on Indoor Positioning and Indoor Navigation. Busan: IEEE, 2014: 261–270.
26 JIANG X, CHEN Y, LIU J, et al FSELM: fusion semi-supervised extreme learning machine for indoor localization with Wi-Fi and Bluetooth fingerprints[J]. Soft Computing, 2018, 22 (11): 3621- 3635
doi: 10.1007/s00500-018-3171-4
27 NABATI M, ALI GHORASHI S A real-time fingerprint-based indoor positioning using deep learning and preceding states[J]. Expert Systems with Applications, 2023, 213: 118889
doi: 10.1016/j.eswa.2022.118889
1 SINHA R S, HWANG S H Comparison of CNN applications for RSSI-based fingerprint indoor localization[J]. Electronics, 2019, 8 (9): 989
doi: 10.3390/electronics8090989
2 FENG X, NGUYEN K A, LUO Z A survey of deep learning approaches for WiFi-based indoor positioning[J]. Journal of Information and Telecommunication, 2022, 6 (2): 163- 216
doi: 10.1080/24751839.2021.1975425
3 HASSEN W F, MEZGHANI J. CNN based approach for indoor positioning services using RSSI fingerprinting technique [C]// Proceedings of the International Wireless Communications and Mobile Computing. Dubrovnik: IEEE, 2022: 778–783.
4 SINGH A, KUMAR G, SAHA R, et al A survey and taxonomy of consensus protocols for blockchains[J]. Journal of Systems Architecture, 2022, 127: 102503
doi: 10.1016/j.sysarc.2022.102503
5 KARA M, LAOUID A, ALSHAIKH M, et al A compute and wait in PoW (CW-PoW) consensus algorithm for preserving energy consumption[J]. Applied Sciences, 2021, 11 (15): 6750
doi: 10.3390/app11156750
6 TRIVEDI A, MISTRY H, SHAH Y, et al. Enhanced schema for proof of stake mechanism based on stake size and random validator selection [C]// Proceedings of the International Conference on Advanced Computing Technologies and Applications. Mumbai: IEEE, 2023: 1–6.
7 KIM J, OH S, KIM Y, et al. Improving voting of block producers for delegated proof-of-stake with quadratic delegate [C]// Proceedings of the International Conference on Platform Technology and Service. Busan: IEEE, 2023: 13–17.
8 HUANG J, KONG L, CHENG L, et al BlockSense: towards trustworthy mobile crowdsensing via proof-of-data blockchain[J]. IEEE Transactions on Mobile Computing, 2024, 23 (2): 1016- 1033
9 LI M, WENG J, YANG A, et al CrowdBC: a blockchain-based decentralized framework for crowdsourcing[J]. IEEE Transactions on Parallel and Distributed Systems, 2019, 30 (6): 1251- 1266
doi: 10.1109/TPDS.2018.2881735
10 WU H, DÜDDER B, WANG L, et al Blockchain-based reliable and privacy-aware crowdsourcing with truth and fairness assurance[J]. IEEE Internet of Things Journal, 2022, 9 (5): 3586- 3598
doi: 10.1109/JIOT.2021.3097950
11 CAI C, ZHENG Y, DU Y, et al Towards private, robust, and verifiable crowdsensing systems via public blockchains[J]. IEEE Transactions on Dependable and Secure Computing, 2021, 18 (4): 1893- 1907
12 SHEN X, XU C, ZHU L, et al Blockchain-based lightweight and privacy-preserving quality assurance framework in crowdsensing systems[J]. IEEE Internet of Things Journal, 2024, 11 (1): 974- 986
doi: 10.1109/JIOT.2023.3288349
13 LU Y, TANG Q, WANG G. ZebraLancer: private and anonymous crowdsourcing system atop open blockchain [C]// Proceedings of the IEEE 38th International Conference on Distributed Computing Systems. Vienna: IEEE, 2018: 853–865.
14 ZOU S, XI J, XU G, et al CrowdHB: a decentralized location privacy-preserving crowdsensing system based on a hybrid blockchain network[J]. IEEE Internet of Things Journal, 2022, 9 (16): 14803- 14817
doi: 10.1109/JIOT.2021.3084937
15 ZHAO W, PENG Y, XIE F, et al. Nominative signature scheme based on schnorr signature [C]// Proceedings of the IEEE International Conference on Computer Science and Automation Engineering. Zhangjiajie: IEEE, 2012: 724–728.
16 LEE H, LEE J Convolutional model with a time series feature based on RSSI analysis with the Markov transition field for enhancement of location recognition[J]. Sensors, 2023, 23 (7): 3453
doi: 10.3390/s23073453
17 TIAN X, ZHANG W, YANG Y, et al Toward a quality-aware online pricing mechanism for crowdsensed wireless fingerprints[J]. IEEE Transactions on Vehicular Technology, 2018, 67 (7): 5953- 5964
doi: 10.1109/TVT.2018.2805383
18 PITU F, GAITAN N C. Survey of security, performance, and profitability of monero: a browser-based cryptocurrency [C]// Proceedings of the 3rd International Conference on Electrical, Computer, Communications and Mechatronics Engineering. Tenerife: IEEE, 2023: 1–5.
19 XU T, CAI Y. Exploring historical location data for anonymity preservation in location-based services [C]// Proceedings of the 27th Conference on Computer Communications. Phoenix: IEEE, 2008: 547–555.
[1] 黄荣,杨文琴,宋志刚. 基于区块链的可信分布式工业数据治理方案[J]. 浙江大学学报(工学版), 2025, 59(2): 269-277.
[2] 邵子豪,霍如,王志浩,倪东,谢人超. 基于区块链的移动群智感知数据处理研究综述[J]. 浙江大学学报(工学版), 2024, 58(6): 1091-1106.
[3] 申自浩,刘梦珂,王辉,刘沛骞,刘琨. 基于区块链的用户自定义位置共享方案[J]. 浙江大学学报(工学版), 2024, 58(4): 655-663.
[4] 赵越,赵赫,谭海波,余斌,俞望年,马志宇. 基于小世界理论的区块链Kademlia网络改进方法[J]. 浙江大学学报(工学版), 2024, 58(1): 1-9.
[5] 崔璨,杨小虎,邱炜伟,黄方蕾. 基于GPU的区块链交易验签加速技术[J]. 浙江大学学报(工学版), 2023, 57(8): 1505-1515.
[6] 王传华,张权,王慧敏,徐欣,麻瓯勃. 区块链架构下具有隐私保护的车联网信誉模型[J]. 浙江大学学报(工学版), 2023, 57(4): 760-772.
[7] 杨晋生,王浩,高镇,郭朝晖. 基于双RSA累加器的无状态交易验证方案[J]. 浙江大学学报(工学版), 2023, 57(1): 178-189.
[8] 刘雪娇,宋庆武,夏莹杰. 基于区块链的车联网矩阵计算安全卸载方案[J]. 浙江大学学报(工学版), 2023, 57(1): 144-154.
[9] 刘雪娇,王慧敏,夏莹杰,赵思苇. 具有隐私保护的车联网空间众包任务分配方法[J]. 浙江大学学报(工学版), 2022, 56(7): 1267-1275.
[10] 王思鹏,杜昌平,宋广华,郑耀. 基于改进MSCKF的无人机室内定位方法[J]. 浙江大学学报(工学版), 2022, 56(4): 711-717.
[11] 何苗,柏粉花,于卓,沈韬. 区块链中可公开验证密钥共享技术[J]. 浙江大学学报(工学版), 2022, 56(2): 306-312.
[12] 董思含,信俊昌,郝琨,姚钟铭,陈金义. 多区块链环境下的连接查询优化算法[J]. 浙江大学学报(工学版), 2022, 56(2): 313-321.
[13] 孙亮,李晓风,赵赫,余斌,周桐,李皙茹. 基于NFT的实物上链资产化方法[J]. 浙江大学学报(工学版), 2022, 56(10): 1900-1911.
[14] 梁秀波,吴俊涵,赵昱,尹可挺. 区块链数据安全管理和隐私保护技术研究综述[J]. 浙江大学学报(工学版), 2022, 56(1): 1-15.
[15] 刘雪娇,殷一丹,陈蔚,夏莹杰,许佳丽,韩立东. 基于区块链的车联网数据安全共享方案[J]. 浙江大学学报(工学版), 2021, 55(5): 957-965.