ToA estimation

This set of datasets is designed for the validation and testing of Time of Arrival (TOA) estimation methods in LoRa-based Low-Power Wide-Area Networks (LPWANs). The datasets cover SNR values of -10, 0, 10, and 20 dB, representing different noise levels that impact signal detection. Each dataset provides a structured representation of signal behavior over time in an LPWAN with a star topology, capturing realistic transmission conditions. This allows for a thorough evaluation of TOA estimation models across varying signal conditions, ensuring robustness and adaptability. The datasets support benchmarking, model validation, and comparative testing, enabling researchers and engineers to refine TOA detection techniques for improved accuracy and efficiency in resource-constrained IoT networks. By incorporating multiple SNR scenarios, this dataset helps in assessing model performance in both low and high signal quality environments, making it a valuable resource for the development of advanced ML-based TOA estimation methods.

本数据集套件专为基于LoRa的低功耗广域网（LoRa-based Low-Power Wide-Area Networks，LPWANs）中的到达时间（Time of Arrival，TOA）估计方法的验证与测试而设计。该数据集覆盖了-10、0、10、20 dB的信噪比（Signal-to-Noise Ratio，SNR）值，用以表征影响信号检测的不同噪声水平。每个数据集均以结构化形式呈现星型拓扑结构的LoRa LPWAN中信号随时间的变化特征，还原了真实的传输环境条件。这使得研究人员与工程师能够在多样的信号条件下对TOA估计模型开展全面评估，确保模型的鲁棒性与适应性。本数据集支持基准测试、模型验证与对比试验，可助力研究者与工程师优化TOA检测技术，以在资源受限的物联网（Internet of Things，IoT）网络中提升检测精度与运行效率。通过涵盖多种信噪比场景，该数据集可用于评估模型在低、高信号质量环境下的性能表现，是开发先进的基于机器学习（Machine Learning，ML）的TOA估计方法的宝贵资源。