İşler Buket, Kaya Şükrü Mustafa, Kılıç Fahreddin Raşit
Department of Software Engineering, Istanbul Topkapi University, Istanbul 34087, Türkiye.
Department of Computer Technologies, Istanbul Aydin University, Istanbul 34295, Türkiye.
Sensors (Basel). 2025 Jun 30;25(13):4070. doi: 10.3390/s25134070.
Temperature forecasting is critical for public safety, environmental risk management, and energy conservation. However, reliable forecasting becomes challenging in regions where governmental institutions lack adequate measurement infrastructure. To address this limitation, the present study aims to improve temperature forecasting by collecting temperature, pressure, and humidity data through IoT sensor networks. The study further seeks to identify the most effective method for the real-time processing of large-scale datasets generated by sensor measurements and to ensure data reliability. The collected data were pre-processed using Discrete Wavelet Transform (DWT) to extract essential features and reduce noise. Subsequently, three wavelet-processed deep-learning models were employed: Wavelet-processed Artificial Neural Networks (W-ANN), Wavelet-processed Long Short-Term Memory Networks (W-LSTM), and Wavelet-processed Bidirectional Long Short-Term Memory Networks (W-BiLSTM). Among these, the W-BiLSTM model yielded the highest performance, achieving a test accuracy of 97% and a Mean Absolute Percentage Error (MAPE) of 2%. It significantly outperformed the W-LSTM and W-ANN models in predictive accuracy. Forecasts were validated using data obtained from the Turkish State Meteorological Service (TSMS), yielding a 94% concordance, thereby confirming the robustness of the proposed approach. The findings demonstrate that the W-BiLSTM-based model enables reliable temperature forecasting, even in regions with insufficient governmental measurement infrastructure. Accordingly, this approach holds considerable potential for supporting data-driven decision-making in environmental risk management and energy conservation.
温度预测对于公共安全、环境风险管理和节能至关重要。然而，在政府机构缺乏足够测量基础设施的地区，可靠的预测变得具有挑战性。为了解决这一限制，本研究旨在通过物联网传感器网络收集温度、压力和湿度数据来改进温度预测。该研究还试图确定实时处理传感器测量生成的大规模数据集的最有效方法，并确保数据可靠性。收集到的数据使用离散小波变换（DWT）进行预处理，以提取基本特征并减少噪声。随后，采用了三种经过小波处理的深度学习模型：小波处理人工神经网络（W-ANN）、小波处理长短期记忆网络（W-LSTM）和小波处理双向长短期记忆网络（W-BiLSTM）。其中，W-BiLSTM模型表现最佳，测试准确率达到97%，平均绝对百分比误差（MAPE）为2%。在预测准确性方面，它显著优于W-LSTM和W-ANN模型。使用从土耳其国家气象服务局（TSMS）获得的数据对预测进行了验证，一致性达到94%，从而证实了所提方法的稳健性。研究结果表明，基于W-BiLSTM的模型即使在政府测量基础设施不足的地区也能实现可靠的温度预测。因此，这种方法在支持环境风险管理和节能中数据驱动的决策方面具有相当大的潜力。
