• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

基于多任务学习和权值系数-最近邻的自适应多类型指纹室内定位与定位方法。

Adaptive Multi-Type Fingerprint Indoor Positioning and Localization Method Based on Multi-Task Learning and Weight Coefficients -Nearest Neighbor.

机构信息

School of Computer Science and Technology, Chongqing University of Posts and Telecommunications, Chongqing 400065, China.

出版信息

Sensors (Basel). 2020 Sep 21;20(18):5416. doi: 10.3390/s20185416.

DOI:10.3390/s20185416
PMID:32967320
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC7570491/
Abstract

The complex indoor environment makes the use of received fingerprints unreliable as an indoor positioning and localization method based on fingerprint data. This paper proposes an adaptive multi-type fingerprint indoor positioning and localization method based on multi-task learning (MTL) and Weight Coefficients -Nearest Neighbor (WCKNN), which integrates magnetic field, Wi-Fi and Bluetooth fingerprints for positioning and localization. The MTL fuses the features of different types of fingerprints to search the potential relationship between them. It also exploits the synergy between the tasks, which can boost up positioning and localization performance. Then the WCKNN predicts another position of the fingerprints in a certain class determined by the obtained location. The final position is obtained by fusing the predicted positions using a weighted average method whose weights are the positioning errors provided by positioning error prediction models. Experimental results indicated that the proposed method achieved 98.58% accuracy in classifying locations with a mean positioning error of 1.95 m.

摘要

复杂的室内环境使得基于指纹数据的接收指纹无法可靠地用作室内定位和定位方法。本文提出了一种基于多任务学习（MTL）和权值系数-最近邻（WCKNN）的自适应多类型指纹室内定位和定位方法，该方法融合了磁场、Wi-Fi 和蓝牙指纹进行定位和定位。MTL 融合了不同类型指纹的特征，以搜索它们之间的潜在关系。它还利用了任务之间的协同作用，从而提高了定位和定位性能。然后，WCKNN 根据获得的位置预测指纹在某个类别中的另一个位置。最终位置通过使用加权平均方法融合预测位置来获得，其权重由定位误差预测模型提供的定位误差。实验结果表明，该方法在分类位置时的准确率达到 98.58%，平均定位误差为 1.95m。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/1a9b149a301b/sensors-20-05416-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/370acc82edcf/sensors-20-05416-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/4c1b80c1f3fa/sensors-20-05416-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/faad95a9319f/sensors-20-05416-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/1a107863c6c2/sensors-20-05416-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/739962169de5/sensors-20-05416-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/ddd6eb48d509/sensors-20-05416-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/f778ff89c941/sensors-20-05416-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/c4d48bb8c994/sensors-20-05416-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/9be0f20609fd/sensors-20-05416-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/565c9f2cdb56/sensors-20-05416-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/24e9f8829954/sensors-20-05416-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/300aff9e7e77/sensors-20-05416-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/bff50e258a55/sensors-20-05416-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/6bd4d8c49b61/sensors-20-05416-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/7cd7aa44c199/sensors-20-05416-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/1a9b149a301b/sensors-20-05416-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/370acc82edcf/sensors-20-05416-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/4c1b80c1f3fa/sensors-20-05416-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/faad95a9319f/sensors-20-05416-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/1a107863c6c2/sensors-20-05416-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/739962169de5/sensors-20-05416-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/ddd6eb48d509/sensors-20-05416-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/f778ff89c941/sensors-20-05416-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/c4d48bb8c994/sensors-20-05416-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/9be0f20609fd/sensors-20-05416-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/565c9f2cdb56/sensors-20-05416-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/24e9f8829954/sensors-20-05416-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/300aff9e7e77/sensors-20-05416-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/bff50e258a55/sensors-20-05416-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/6bd4d8c49b61/sensors-20-05416-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/7cd7aa44c199/sensors-20-05416-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/d053/7570491/1a9b149a301b/sensors-20-05416-g016.jpg

相似文献

1
Adaptive Multi-Type Fingerprint Indoor Positioning and Localization Method Based on Multi-Task Learning and Weight Coefficients -Nearest Neighbor.基于多任务学习和权值系数-最近邻的自适应多类型指纹室内定位与定位方法。
Sensors (Basel). 2020 Sep 21;20(18):5416. doi: 10.3390/s20185416.
2
Fusing Bluetooth Beacon Data with Wi-Fi Radiomaps for Improved Indoor Localization.融合蓝牙信标数据与Wi-Fi无线电地图以改进室内定位
Sensors (Basel). 2017 Apr 10;17(4):812. doi: 10.3390/s17040812.
3
LightGBM Indoor Positioning Method Based on Merged Wi-Fi and Image Fingerprints.基于融合Wi-Fi和图像指纹的LightGBM室内定位方法
Sensors (Basel). 2021 May 25;21(11):3662. doi: 10.3390/s21113662.
4
Adaptive Residual Weighted -Nearest Neighbor Fingerprint Positioning Algorithm Based on Visible Light Communication.基于可见光通信的自适应残差加权最近邻指纹定位算法。
Sensors (Basel). 2020 Aug 8;20(16):4432. doi: 10.3390/s20164432.
5
An Adaptive Bluetooth/Wi-Fi Fingerprint Positioning Method based on Gaussian Process Regression and Relative Distance.一种基于高斯过程回归和相对距离的自适应蓝牙/ Wi-Fi指纹定位方法
Sensors (Basel). 2019 Jun 21;19(12):2784. doi: 10.3390/s19122784.
6
Unsupervised Indoor Localization Based on Smartphone Sensors, iBeacon and Wi-Fi.基于智能手机传感器、iBeacon和Wi-Fi的无监督室内定位
Sensors (Basel). 2018 Apr 28;18(5):1378. doi: 10.3390/s18051378.
7
An Improved Bluetooth Indoor Positioning Method Using Dynamic Fingerprint Window.基于动态指纹窗的蓝牙室内定位改进方法
Sensors (Basel). 2020 Dec 18;20(24):7269. doi: 10.3390/s20247269.
8
An Indoor Fingerprint Positioning Algorithm Based on WKNN and Improved XGBoost.基于 WKNN 和改进 XGBoost 的室内指纹定位算法。
Sensors (Basel). 2023 Apr 13;23(8):3952. doi: 10.3390/s23083952.
9
Fast Signals of Opportunity Fingerprint Database Maintenance with Autonomous Unmanned Ground Vehicle for Indoor Positioning.利用自主式无人地面车辆进行快速信号机会指纹数据库维护，实现室内定位。
Sensors (Basel). 2018 Oct 12;18(10):3419. doi: 10.3390/s18103419.
10
A Crowd-Sourcing Indoor Localization Algorithm via Optical Camera on a Smartphone Assisted by Wi-Fi Fingerprint RSSI.一种基于Wi-Fi指纹RSSI辅助的智能手机光学摄像头众包室内定位算法。
Sensors (Basel). 2016 Mar 19;16(3):410. doi: 10.3390/s16030410.

引用本文的文献

1
EnRank: An Ensemble Method to Detect Pulmonary Hypertension Biomarkers Based on Feature Selection and Machine Learning Models.EnRank：一种基于特征选择和机器学习模型检测肺动脉高压生物标志物的集成方法。
Front Genet. 2021 Apr 27;12:636429. doi: 10.3389/fgene.2021.636429. eCollection 2021.
2
SICD: Novel Single-Access-Point Indoor Localization Based on CSI-MIMO with Dimensionality Reduction.SICD：基于降维 CSI-MIMO 的新型单接入点室内定位
Sensors (Basel). 2021 Feb 13;21(4):1325. doi: 10.3390/s21041325.
3
Transfer Learning for Wireless Fingerprinting Localization Based on Optimal Transport.

本文引用的文献

1
An Adaptive Bluetooth/Wi-Fi Fingerprint Positioning Method based on Gaussian Process Regression and Relative Distance.一种基于高斯过程回归和相对距离的自适应蓝牙/ Wi-Fi指纹定位方法
Sensors (Basel). 2019 Jun 21;19(12):2784. doi: 10.3390/s19122784.
2
Use of Magnetic Field for Mitigating Gyroscope Errors for Indoor Pedestrian Positioning.磁场在减轻室内行人定位陀螺仪误差中的应用。
Sensors (Basel). 2018 Aug 7;18(8):2592. doi: 10.3390/s18082592.
3
A Bluetooth Low Energy Indoor Positioning System with Channel Diversity, Weighted Trilateration and Kalman Filtering.
基于最优传输的无线指纹定位迁移学习
Sensors (Basel). 2020 Dec 7;20(23):6994. doi: 10.3390/s20236994.
一种具有信道分集、加权三边测量和卡尔曼滤波的低功耗蓝牙室内定位系统。
Sensors (Basel). 2017 Dec 16;17(12):2927. doi: 10.3390/s17122927.
4
Reducing the dimensionality of data with neural networks.使用神经网络降低数据维度。
Science. 2006 Jul 28;313(5786):504-7. doi: 10.1126/science.1127647.