In this study, we address the challenge of estimating the resonance frequency of a photoacoustic detector (PAD) gas cell under varying temperature conditions, which is crucial for improving the accuracy of gas concentration measurements. We introduce a novel approach that uses a long short-term memory network and a self-attention mechanism to model resonance frequency shifts based on temperature data. To investigate the impact of the gas mixture temperature on the resonance frequency, we modified the PAD to include an internal temperature sensor. Our experiments involved multiple heating and cooling cycles with varying methane concentrations, resulting in a comprehensive dataset of temperature and resonance frequency measurements. The proposed models were trained and validated on this dataset, and the results demonstrate real-time prediction capabilities with a mean absolute error of less than 1 Hz for frequency shifts exceeding 30 Hz over four-hour periods. This approach allows continuous, real-time tracking of the resonance frequency without interrupting the laser operation, significantly enhancing gas concentration measurements and contributing to the long-term stabilization of the sensor. The results suggest that the proposed approach is effective in managing temperature-induced frequency shifts, making it a valuable tool for improving the accuracy and stability of gas sensors in practical applications.

Distributed acoustic sensing (DAS) systems enable real-time monitoring of physical events across extended areas using optical fiber that detects vibrations through changes in backscattered light patterns. In perimeter security applications, these systems must accurately distinguish between legitimate activities and potential security threats by analyzing complex spatio-temporal data patterns. However, the high dimensionality and noise content of raw DAS data presents significant challenges for effective feature extraction and event classification, particularly when computational efficiency is required for real-time deployment. Traditional approaches or current machine learning methods often struggle with the balance between information preservation and computational complexity. This study addresses the critical need for efficient and accurate feature extraction methods that can identify informative signal components while maintaining real-time processing capabilities in DAS-based security systems. Here we show that wavelet packet decomposition (WPD) combined with a cascaded machine learning approach achieves 98% classification accuracy while reducing computational load through intelligent channel selection and preliminary filtering. Our modified peak signal-to-noise ratio metric successfully identifies the most informative frequency bands, which we validate through comprehensive neural network experiments across all possible WPD channels. The integration of principal component analysis with logistic regression as a preprocessing filter eliminates a substantial portion of non-target events while maintaining high recall level, significantly improving upon methods that processed all available data. These findings establish WPD as a powerful preprocessing technique for distributed sensing applications, with immediate applications in critical infrastructure protection. The demonstrated gains in computational efficiency and accuracy improvements suggest broad applicability to other pattern recognition challenges in large-scale sensor networks, seismic monitoring, and structural health monitoring systems, where real-time processing of high-dimensional acoustic data is essential.