WiFi RTT RSS dataset for indoor positioning

This is the first batch of WiFi RSS RTT datasets with LOS conditions we published. Please see https://doi.org/10.5281/zenodo.11558792 for the second batch. We provide publicly available datasets of three different indoor scenarios: building floor, office and apartment. The datasets contain both WiFi RSS and RTT signal measures with groud truth coordinates label and LOS condition label. 1.Building Floor This is a detailed WiFi RTT and RSS dataset of a whole floor of a university building, of moare than 92 x 15 square metres. We divided the area of interest was divided into discrete grids and labelled them with correct ground truth coordinates and the LoS APs from the grid. The dataset contains WiFi RTT and RSS signal measures recorded in 642 reference points for 3 days and is well separated so that training points and testing points will not overlap. 2. Office Office scenario is of more than 4.5 x 5.5 square metres. 3 APs are set to cover the whole space. At least two LOS AP could be seen at any reference point (RP). 3.Apartment Apartment scenario is of more than 7.7 x 9.4 square metres.Four APs were leveraged to generate WiFi signal measures for this testbed. Note that AP 1 in the apartment dataset was positioned so that it could had an NLOS path to most of the testbed. Collection methodology The APs utilised were Google WiFi Router AC-1304, the smartphone used to collect the data was Google Pixel 3 with Android 9. The ground truth coordinates were collected using fixed tile size on the floor and manual post-it note markers. Only RTT-enabled APs were included in the dataset. The features of the datasets The features of the building floor dataset are as follows: Testbed area: 92 × 15 m2 Grid size: 0.6 × 0.6 m2 Number of AP: 13 Number of reference points: 642 Samples per reference point: 120 Number of all data samples: 77040 Number of training samples: 57960 Number of testing samples: 19080 Signal measure: WiFi RTT, WiFi RSS Collection time interval: 3 days The features of the office dataset are as follows: Testbed area: 4.5 × 5.5 m2 Grid size: 0.455 × 0.455 m2 Number of AP: 3 Reference points: 37 Samples per reference point: 120 Data samples: 4,440 Training samples: 3,240 Testing samples: 1,200 Signal measure: WiFi RTT, WiFi RSS Other information: LOS condition of every AP Collection time: 1 day Notes: A LOS scenario The features of the apartment dataset are as follows: Testbed area: 7.7 × 9.4 m2 Grid size: 0.48 × 0.48 m2 Number of AP: 4 Reference points: 110 Samples per reference point: 120 Data samples: 13,200 Training samples: 9,720 Testing samples: 3,480 Signal measure: WiFi RTT, WiFi RSS Other information: LOS condition of every AP Collection time: 1 day Notes: Contains an AP with NLOS paths for most of the RPs Dataset explanation The columns of the dataset are as follows: Column 'X': the X coordinates of the sample. Column 'Y': the Y coordinates of the sample. Column 'AP1 RTT(mm)', 'AP2 RTT(mm)', ..., 'AP13 RTT(mm)': the RTT measure from corresponding AP at a reference point. Column 'AP1 RSS(dBm)', 'AP2 RSS(dBm)', ..., 'AP13 RSS(dBm)': the RSS measure from corresponding AP at a reference point. Column 'LOS APs': indicating which AP has a LOS to this reference point. Please note: The RSS value -200 dBm indicates that the AP is too far away from the current reference point and no signals could be heard from it. The RTT value 100,000 mm indicates that no signal is received from the specific AP. Citation request When using this dataset, please cite the following two items: Feng, X., Nguyen, K. A., & Luo, Z. (2024). WiFi RTT RSS dataset for indoor positioning [Data set]. Zenodo. https://doi.org/10.5281/zenodo.11558192 @article{feng2023wifi, title={WiFi round-trip time (RTT) fingerprinting: an analysis of the properties and the performance in non-line-of-sight environments}, author={Feng, Xu and Nguyen, Khuong an and Luo, Zhiyuan}, journal={Journal of Location Based Services}, volume={17}, number={4}, pages={307--339}, year={2023}, publisher={Taylor \& Francis} }

本数据集为我们发布的首批支持视距（Line-of-Sight, LOS）条件的WiFi接收信号强度（Received Signal Strength, RSS）与往返时间（Round-Trip Time, RTT）数据集。第二批数据集请访问 https://doi.org/10.5281/zenodo.11558792 获取。

本团队提供三种不同室内场景的公开数据集：楼宇楼层、办公室与公寓。所有数据集均包含WiFi RSS与RTT信号测量数据，并标注有真实坐标（ground truth coordinates）与视距条件标签。

1. 楼宇楼层场景
本数据集为某高校整层楼宇的详细WiFi RTT与RSS数据集，覆盖面积超过92×15平方米。我们将目标区域划分为离散网格，并为每个网格标注准确的真实坐标以及该网格对应的视距接入点（Line-of-Sight APs, LOS APs）。本数据集在642个参考点（Reference Points, RPs）上连续3天采集了WiFi RTT与RSS信号测量数据，且训练集与测试集无重叠划分。

2. 办公室场景
场景覆盖面积超过4.5×5.5平方米，部署了3台接入点（Access Point, AP）以实现全空间覆盖。任意参考点均可至少检测到2台视距接入点。

3. 公寓场景
场景覆盖面积超过7.7×9.4平方米，部署了4台接入点以采集WiFi信号数据。需注意：公寓数据集中的第1台接入点的部署位置使其与绝大多数参考点之间存在非视距（Non-Line-of-Sight, NLOS）传输路径。

### 数据采集方法
本次采集使用的接入点为Google WiFi Router AC-1304，数据采集所用智能手机为搭载Android 9系统的Google Pixel 3。真实坐标通过地面固定瓷砖尺寸结合手动便签标记进行采集。本数据集仅包含支持RTT功能的接入点数据。

### 数据集参数详情
#### 楼宇楼层数据集参数
测试区域：92 × 15 m²
网格尺寸：0.6 × 0.6 m²
接入点数量：13
参考点数量：642
每个参考点采样数：120
总数据样本数：77040
训练样本数：57960
测试样本数：19080
信号测量类型：WiFi RTT、WiFi RSS
采集时间间隔：3天

#### 办公室数据集参数
测试区域：4.5 × 5.5 m²
网格尺寸：0.455 × 0.455 m²
接入点数量：3
参考点数量：37
每个参考点采样数：120
总数据样本数：4440
训练样本数：3240
测试样本数：1200
信号测量类型：WiFi RTT、WiFi RSS
附加信息：每台接入点的视距条件
采集时长：1天
备注：全视距场景

#### 公寓数据集参数
测试区域：7.7 × 9.4 m²
网格尺寸：0.48 × 0.48 m²
接入点数量：4
参考点数量：110
每个参考点采样数：120
总数据样本数：13200
训练样本数：9720
测试样本数：3480
信号测量类型：WiFi RTT、WiFi RSS
附加信息：每台接入点的视距条件
采集时长：1天
备注：包含1台与绝大多数参考点存在非视距传输路径的接入点

### 数据集字段说明
数据集中各字段含义如下：
- 字段'X'：样本的X坐标
- 字段'Y'：样本的Y坐标
- 字段'AP1 RTT(mm)'、'AP2 RTT(mm)'……'AP13 RTT(mm)'：对应接入点在该参考点处的RTT测量值，单位为毫米
- 字段'AP1 RSS(dBm)'、'AP2 RSS(dBm)'……'AP13 RSS(dBm)'：对应接入点在该参考点处的RSS测量值，单位为dBm
- 字段'LOS APs'：标注与该参考点存在视距传输路径的接入点

注意：RSS值为-200 dBm表示该接入点距离当前参考点过远，无法检测到信号；RTT值为100000 mm表示未从该接入点接收到信号。

### 引用要求
使用本数据集时，请引用以下两篇文献：
1. Feng, X., Nguyen, K. A., & Luo, Z. (2024). WiFi RTT RSS dataset for indoor positioning [Data set]. Zenodo. https://doi.org/10.5281/zenodo.11558192
2. @article{feng2023wifi, title="WiFi round-trip time (RTT) fingerprinting: an analysis of the properties and the performance in non-line-of-sight environments", author={Feng, Xu and Nguyen, Khuong an and Luo, Zhiyuan}, journal={Journal of Location Based Services}, volume={17}, number={4}, pages={307--339}, year={2023}, publisher={Taylor & Francis} }

搜集汇总

背景与挑战

背景概述

该数据集包含三种室内场景（建筑楼层、办公室和公寓）的WiFi RSS和RTT信号测量数据，附带地面真实坐标和LOS条件标签，适用于室内定位研究。数据集由皇家霍洛威大学的研究团队收集，使用Google WiFi路由器和Pixel 3智能手机进行数据采集，覆盖不同面积和网格大小的测试区域。