cs.LG提交于 2026-10-27已译

长期 LoRaWAN 网络的数据质量审计与温湿度双变量分析：异常检测、PCA、聚类与机器学习

Data Quality Audit and Bivariate Temperature-Humidity Analysis of a Long-Term LoRaWAN Network: Anomaly Detection, PCA, Clustering and Machine Learning

Mamadou Sow

中文摘要

针对 Tour Perret LoRaWAN 数据集，构建了 C++17 处理流程，对 421,937 帧数据（2021 年 6 月至 2023 年 6 月、5 台设备）开展逐变量覆盖审计。结果显示，CO2 数据完全缺失，覆盖率为 0%；气压仅由孤立的 Wyres 基础模块上报，占语料的 4.24%，因此无法开展原定的四变量联合分析。研究转而分析 4 个 Elsys EMS 传感器共同提供的温湿度数据，共覆盖 205,005 帧，占 95.76%。流程依次采用修正 Z-score 与 Isolation Forest 检测异常，实施双变量主成分分析(PCA)，使用 K-means 与 DBSCAN 聚类，并通过多层感知机(MLP)根据温度和时间预测湿度，以残差检测缓慢漂移。温湿度相关系数为 r=-0.662；双变量 PCA 的 PC1 解释 83.1% 方差；Isolation Forest 检出 2.12% 的多变量异常，而单变量 Z-score 未检出异常；校准后的 DBSCAN 在 13 个簇中识别出 0.17% 的噪声；MLP 交叉验证取得 R²=0.672、RMSE=10.54%。

关键要点

01逐变量覆盖审计发现 CO2 完全缺失，气压仅覆盖 4.24%
02温湿度数据覆盖 95.76%，支持将联合分析重新聚焦于双变量
03Isolation Forest 检出 2.12% 多变量异常，单变量 Z-score 未检出
04DBSCAN 在 13 个簇中识别出 0.17% 噪声
05MLP 预测湿度的交叉验证结果为 R²=0.672、RMSE=10.54%

解读

尚无解读。

原始英文摘要

arXiv:2610.32438v1 Announce Type: new Abstract: Long-term environmental IoT/LPWAN deployments often aggregate heterogeneous data streams from diverse devices without systematic auditing of each variable's actual coverage prior to analysis-an increased risk when multiple sensor types coexist within the same network. This work proposes a C++17 processing pipeline applied to the Tour Perret LoRaWAN dataset (421 937 frames, June 2021--June 2023, 5 devices). A systematic coverage audit integrated into the extraction phase reveals that CO2 is completely missing (0% coverage) and pressure is reported only by an isolated base module (Wyres, 4.24% of the corpus), invalidating the initial hypothesis of a joint four-variable analysis. The analysis is refocused on the Temperature--Humidity pair, jointly available across 205{,}005 frames (95.76%) from 4 Elsys EMS sensors. The pipeline sequentially performs anomaly detection (modified Z-score, Isolation Forest), bivariate Principal Component Analysis, clustering (K-means, DBSCAN), and a multilayer perceptron predicting humidity from temperature and time, whose residuals serve as a detector for slow drift. On real-world data: Temperature--Humidity correlation r=-0.662, two-component PCA (PC1 =83.1% of variance), Isolation Forest detects 2.12% multivariate anomalies while univariate Z-score detects none, calibrated DBSCAN isolates 0.17% noise across 13 clusters, and the MLP achieves $R^2=0.672$ (RMSE =10.54%) in cross-validation. This work demonstrates that per-variable coverage auditing prior to modeling is a necessary methodological step for heterogeneous multi-sensor IoT datasets.