Data underlying the publication: A zone-based Wi-Fi fingerprinting indoor positioning system for factory noise mapping

<strong># Dataset and scripts: A zone-based Wi-Fi fingerprinting indoor positioning system for factory noise mapping</strong><br><strong>## Overview</strong>This dataset supports research on zone-based Wi-Fi fingerprinting indoor positioning systems and factory noise mapping. It includes Wi-Fi RSSI (Received Signal Strength Indicator) data, noise levels, zone information, and timestamps, which can be used to develop models for indoor positioning, zone classification, and noise mapping within factory environments.<br><strong>## Dataset</strong>1. RSSI_rawdata_4days_sample200_37zone.csvRaw RSSI measurements collected across 37 zones over four days. Each row contains RSSI values from six access points (AP1-AP6) and the corresponding zone label.<br>Columns:<br>AP1-AP6: RSSI values (in dBm) for six Wi-Fi access points.label: Zone ID (integer) where the data was collected.Purpose:Used for training and evaluating machine learning models for indoor positioning and zone classification.<br>2. RSSI_fluctuate_6AP_Sample400.csvWi-Fi RSSI fluctuations collected from six access points (AP1-AP6) at the same location, with 400 samples to analyze signal stability.<br>Columns:<br>AP1-AP6: RSSI values (in dBm) for six access points.Purpose:Analyzed for signal stability and noise mapping, supporting indoor positioning and signal fluctuation evaluation in factory environments.<br><strong>## Scripts</strong>1. model.pyProcesses the RSSI_rawdata_4days_sample200_37zone.csv file and evaluates machine learning model performance for indoor positioning and zone classification.This script evaluates machine learning model performance as discussed in<em> Section 4.3</em> ("ML Model Performance Evaluation"). <br>2. logic.pyProcesses the RSSI_fluctuate_6AP_Sample400.csv file to evaluate Wi-Fi signal fluctuations, supporting signal stability analysis for noise mapping and positioning.This script analyzes Wi-Fi signal fluctuations as discussed in <em>Section 4.2</em> ("Wi-Fi Signal Analysis") of the paper.<br><strong>## Citation</strong>If you use this dataset, please cite:"A zone-based Wi-Fi fingerprinting indoor positioning system for factory noise mapping," Journal of Intelligent Manufacturing, 2025.<br><strong>## License</strong>This project is licensed under the MIT License. See the LICENSE file for details.<br>

# 数据集与脚本：面向工厂噪声制图的基于区域的Wi-Fi指纹（Wi-Fi fingerprinting）室内定位系统
## 概述
本数据集可支撑基于区域的Wi-Fi指纹室内定位系统与工厂噪声制图相关研究。数据集包含Wi-Fi接收信号强度指示（Received Signal Strength Indicator, RSSI）数据、噪声水平、区域信息与时间戳，可用于开发工厂环境下的室内定位、区域分类以及噪声制图相关模型。
## 数据集
1. **RSSI_rawdata_4days_sample200_37zone.csv**
采集自37个区域、为期4天的原始RSSI测量数据。每一行包含6个无线访问点（Access Point, AP）AP1至AP6的RSSI值，以及对应的区域标签。
字段说明：
AP1-AP6：6个Wi-Fi访问点的RSSI值，单位为dBm（分贝毫瓦）。
label：数据采集所在的区域ID，为整数类型。
用途：用于训练与评估室内定位及区域分类的机器学习模型。
2. **RSSI_fluctuate_6AP_Sample400.csv**
从同一位置的6个访问点AP1至AP6采集的Wi-Fi RSSI波动数据，含400个样本，用于分析信号稳定性。
字段说明：
AP1-AP6：6个访问点的RSSI值，单位为dBm。
用途：用于分析信号稳定性与噪声制图，支撑工厂环境下的室内定位与信号波动评估。
## 脚本
1. **model.py**
处理`RSSI_rawdata_4days_sample200_37zone.csv`文件，并评估用于室内定位与区域分类的机器学习模型性能。本脚本实现了论文4.3节「机器学习模型性能评估」中讨论的模型性能评估流程。
2. **logic.py**
处理`RSSI_fluctuate_6AP_Sample400.csv`文件，以评估Wi-Fi信号波动情况，支撑噪声制图与定位所需的信号稳定性分析。本脚本实现了论文4.2节「Wi-Fi信号分析」中讨论的Wi-Fi信号波动分析流程。
## 引用说明
若使用本数据集，请引用以下文献："A zone-based Wi-Fi fingerprinting indoor positioning system for factory noise mapping", *Journal of Intelligent Manufacturing*, 2025年。
## 许可协议
本项目采用MIT许可协议，详细信息请参见LICENSE文件。