Cross-Linked Polyphosphazene Nanospheres Boosting Long-Lived Organic Room-Temperature Phosphorescence.

Long-lived organic room-temperature phosphorescence (RTP) has sparked intense explorations, owing to the outstanding optical performance and exceptional applications. Because triplet excitons in organic RTP experience multifarious relaxation processes resulting from their high sensitivity, spin multiplicity, inevitable nonradiative decay, and external quenchers, boosting RTP performance by the modulated triplet-exciton behavior is challenging. Herein, we report that cross-linked polyphosphazene nanospheres can effectively promote long-lived organic RTP. Through molecular engineering, multiple carbonyl groups (C═O), heteroatoms (N and P), and heavy atoms (Cl) are introduced into the polyphosphazene nanospheres, largely strengthening the spin-orbit coupling constant by recalibrating the electronic configurations between singlet (Sn) and triplet (Tn) excitons. In order to further suppress nonradiative decay and avoid quenching under ambient conditions, polyphosphazene nanospheres are encapsulated with poly(vinyl alcohol) matrix, thus synchronously prompting phosphorescence lifetime (173 ms longer), phosphorescence efficiency (∼12-fold higher), afterglow duration time (more than 20 s), and afterglow absolute luminance (∼19-fold higher) as compared with the 2,3,6,7,10,11-hexahydroxytriphenylene precursor. By measuring the emission intensity of the phosphorescence, an effective probe based on the nanospheres is developed for visible, quantitative, and expeditious detection of volatile organic compounds. More significantly, the obtained films show high selectivity and robustness for anisole detection (7.1 × 10-4 mol L-1). This work not only demonstrates a way toward boosting the efficiency of RTP materials but also provides a new avenue to apply RTP materials in feasible detection applications.

An integrated CBLA-Net with fractional discrete wavelet transform and frequency-based CARS to predict heavy metal elements by XRF.

BACKGROUND: X-ray fluorescence (XRF) emerges as a promising technique for estimating heavy metal elements. However, XRF spectra typically contain a significant amount of environmental information and signal noise, and the relationship between spectral intensity and element concentration is difficult to quantify using a single model, thereby reducing the predictive performance for low concentration elements. RESULTS: This paper proposed a comprehensive framework for predicting elemental concentrations, encompassing preprocessing, variable selection, decision-making, to enable fast, non-destructive, and accurate estimation of element concentrations in soil. Firstly, an optimal denoising method based on fractional discrete wavelet transform (FDWT) was introduced to enhance signal quality. Furthermore, the frequency-based competitive adaptive reweighted sampling (FCARS) algorithm was employed for feature selection of XRF spectral variables, allowing extraction of the most informative features from the complex spectral data. Finally, a novel deep learning network, called ConvBiLSTM-Attention (CBLA-Net), was designed to achieve precise estimation of heavy metal elements concentration. Compared with other advanced algorithms, The CBLA-Net demonstrated the highest accuracy for V, Cr, Mn, Zn, Cd, and Pb, achieving the coefficient of determination (R2) of 0.9730, 0.9874, 0.9952, 0.9921, 0.9518, and 0.9741, respectively. The CBLA-Net not only effectively extract local features and capture global information, but also combines attention mechanism to focus on key information. SIGNIFICANCE: The proposed novel deep learning quantitative framework, including preprocessing, feature selection, and CBLA-Net decision-making, significantly enhances the accuracy of elemental content prediction. It provides a new approach for accurately assessing the concentration of heavy metal elements in soil.

Peanut origin traceability: A hybrid neural network combining an electronic nose system and a hyperspectral system.

Peanuts, sourced from various regions, exhibit noticeable differences in quality owing to the impact of their natural environments. This study proposes a fast and nondestructive detection method to identify peanut quality by combining an electronic nose system with a hyperspectral system. First, the electronic nose and hyperspectral systems are used to gather gas and spectral information from peanuts. Second, a module for extracting gas and spectral information is designed, combining the lightweight multi-head transposed attention mechanism (LMTA) and convolutional computation. The fusion of gas and spectral information is achieved through matrix combination and lightweight convolution. A hybrid neural network, named UnitFormer, is designed based on the information extraction and fusion processes. UnitFormer demonstrates an accuracy of 99.06 %, a precision of 99.12 %, and a recall of 99.05 %. In conclusion, UnitFormer effectively distinguishes quality differences among peanuts from various regions, offering an effective technological solution for quality supervision in the food market.

AUNet: a deep learning method for spectral information classification to identify inks.

It is common to tamper with the contents of documents and forge contracts illegally. In this work, we propose a U-shaped network with attention modules (AUNet) and combine it with a hyperspectral system to effectively identify different inks. It provides an effective detection method for illegal tampering with documents and forging contract contents. First, the hyperspectral system obtains the spectral information of different pen inks without destroying the sample. Second, because the hyperspectral system's detection data have the characteristics of small samples, we introduce U-Net to conduct the deep fusion of multi-level spectral information to avoid feature degradation and fully mine the deep features hidden in the spectral information. Finally, spatial and channel attention modules are introduced to focus on the features affecting classification performance. The results show that AUNet effectively realizes the effective classification of ink spectral information and achieves 97.81% accuracy, 98.71% recall, 98.80% precision, and 98.71% F1-score.