resumo
This paper outlines the successful utilization of deep learning (DL) techniques to elevate data quality for assessing Au-TFBG (tilted fiber Bragg grating) sensor performance. Our approach involves a well-structured DL-assisted framework integrating a hierarchical composite attention mechanism. In order to mitigate high variability in experimental data, we initially employ seasonal decomposition using moving averages (SDMA) statistical models to filter out redundant data points. Subsequently, sequential DL models extrapolate the normalized transmittance (Tn) vs. wavelength spectra, which showcases promising results through our SpecExLSTM model. Furthermore, we introduce the AttentiveSpecExLSTM model, integrating a composite attention mechanism to improve Tn sequence prediction accuracy. Evaluation metrics demonstrate its superior performance, including a root mean square error of 1.73 +/- 0.05, a mean absolute error of 1.20 +/- 0.04, and a symmetric mean absolute percentage error of 2.22 +/- 0.05, among others. Additionally, our novel minima difference (Min. Dif.) metric achieves a value of 1.08 +/- 0.46, quantifying wavelength for the global minima within the Tn sequence. The composite attention mechanism in the AttentiveSpecExLSTM adeptly captures both high-level and low-level dependencies, refining the model's comprehension and guiding informed decisions. Hierarchical dot and additive attention within this model enable nuanced attention refinement across model layers; dot attention focuses on high-level dependencies, while additive attention fine-tunes its focus on low-level dependencies within the sequence. This innovative strategy enables accurate estimation of the spectral width (full-width half maxima) of the Tn curve, surpassing raw data's capabilities. These findings significantly contribute to data quality enhancement and sensor performance analysis. Insights from this study hold promise for future sensor applications, enhancing sensitivity and accuracy by improving experimental data quality and sensor performance assessment.
palavras-chave
ALGORITHM
categoria
Optics
autores
Tiwari, H; Dwivedi, YS; Singh, R; Sharma, AK; Sharma, AK; Krishna, R; Singha, NS; Prajapati, YK; Marques, C
nossos autores
Carlos Marques
Professor AuxiliarProjectos
Associated Laboratory CICECO-Aveiro Institute of Materials (LA/P/0006/2020)
agradecimentos
Anuj K. Sharma and Ajay Kumar Sharma received the funding from the Department of Science and Technology (India) through research grant (No. DST/ICD/BRICS/Call-5/3DBioPhoto/2023) under BRICS STI Framework Programme. The work of C. Marques was supported by the projects CICECO (LA/P/0006/2020, UIDB/50011/2020 & UIDP/50011/2020), DigiAqua (PTDC/EEI-EEE/0415/2021), financed by national funds through the (Portuguese Science and Technology Foundation/MCTES (FCT I.P.)). The research was co-funded by the financial support of the EU under the REFRESH-Research Excellence For REgion Sustainability and High-tech Industries project no. CZ.10.03.01/00/22_003/0000048 via the Operational Programme Just Transition.