Tartaric acid, as an important organic acid, is widely present in wine, fruit juice, carbonated beverages, and certain gonfectionery products. Its concentration directly influences the balance between sweetness and acidity as well as the stability of lavor. During food production, the tartaric acid concentration may fluctuate due to variations in raw materials and formulation Adjustments. Therefore, establishing a method for real-time online monitoring of tartaric acid concentration is crucial for insuring product quality and production consistency. However, conventional detection methods (e. g. titration, HPLC) suffer from response delays and are unsuitable for real-time monitoring. Considering the multivariate, nonlinear, and dynamic haracteristics of industrial processes, more accurate concentration prediction models are required. To address this, we integrate one-dimensional convolutional neural network (1D-CNN) with a feature-space attention (FSA) mechanism, resulting in a NN-FSA hybrid model. By conducting near-infrared (NIR) spectroscopy driven experiments to detect tartaric acid Concentration, this study explores the potential of CNN-FSA to improve prediction speed and model robustness, thereby Broviding an innovative approach for real-time online monitoring of solution-phase chemical processes, Spectral data were first processed using principal component analysis (PCA) combined with Mahalanobis distance to remove outliers, followed by standard normal variate (SNV) transformation to eliminate scattering and baseline drift. Subsequently, the proposed CNN-FSA hodel and the traditional partial least squares regression (PLSR) model were trained and evaluated. Model performance was Comprehensively assessed using the coefficient of determination (R), root mean square error (RMSE), and mean absolute error MAF). Six rounds of experiments were designed, with each round starting with 500 g of a mixed solution (water, ethanol, glucose, malic acid, and citric acid) as the initial substrate, supplemented with 500 g of a solution (475 g water 25 g tartaric Acid). Data from the first four rounds were randomly split into training and test sets at a 7: 3 ratio, In comparison, data from the last two rounds were used as independent test sets to evaluate the model's generalization ability rigorously. On the independent prediction sets, the CNN-FSA model achieved outstanding performance: R <^> 2 = 0 ,989 6 , RMSE 0.000 702, and MAE 0.000 580, In contrast, the PLSR model yielded R <^> 2 = 0 , RMSE-0.001 214, and MAE 0.001 059. Compared With PLSR. CNN-FSA reduced RMSE by 42. 17% and MAE by 45. 23% on the independent prediction sets. The CNN-FSA model significantly outperforms PLSR in tartaric acid concentration prediction, demonstrating superior generalization and Fobustness on independent prediction datasets.
Soil dry density directly influences the mechanical properties of compacted soil. To explore a hyperspectral-based detection method for compacted soil dry density, this study thoroughly analyzed the influence patterns of soil moisture content and dry density on soil spectra. A spectral dewatering method was proposed to improve the accuracy of soil dry density estimation. This study obtained relevant parameters and corresponding spectral data through integrated soil moisture gradient experiments, soil static compaction tests, and soil spectral measurements. By combining spectral processing analysis methods. and correlation analysis algorithms, the spectral response characteristics of soil moisture content and dry density were analyzed, leading to the proposal of the spectral dewatering method. Subsequently, optimal feature hands were screened and extracted using correlation analysis algorithms and optimal subset construction algorithms. A soil dry density estimation model was constructed using partial least squares regression. Key findings include: (1) Soil moisture content is the primary factor influencing compacted soil spectra, with dry density being a secondary factor, both significantly affect the overall compacted soil spectral signature, (2) Compared to raw spectra and soil compaction coefficients, spectra corrected by the Spectral Dewatering method exhibit significantly higher sensitivity to soil dry density. The maximum correlation coefficient R reached 0. 858, with an average correlation coefficient improvement of 33.7% (wavelet transform). This indicates that the spectral dewatering method - employed in this study effectively mitigates moisture's influence on soil spectra and enhances spectral sensitivity to soil dry density, (3) Compared to the soil compaction coefficient, the model constructed based on SD showed an average increase of 36% in R-2 and an average decrease of 9.985% in RMSE. The optimal model (7 scales) constructed using the Spectral Dewatering method achieved R-2 = 0.79Z and RMSE 0.184. demonstrating that the proposed Spectral Dewatering technique further enhances the ability of spectral data to estimate soil dry density. The conclusions drawn in this study provide fundamental. heoretical and methodological support for rapid, non-destructive monitoring of soil dry density in engineering foundations,
Powdery mildew (PM) is a common foliar disease that negatively impacts the health of rubber trees and the yield of natural rubber. Rapid and accurate disease diagnosis is essential for implementing precise control measures and ensuring optimal rubber production. This study employed hyperspectral imaging technology to analyze infected leaves in Hainan rubber plantations. Samples of rubber leaves at various infection levels were collected, and hyperspectral reflectance data ranging from 965.4 to 1 668.0 nm were obtained using hyperspectral imaging equipment. The hyperspectral data contained noise and redundant information. Three traditional models, namely Support Vector Machine (SVM), Random Forest (RF), and Multi-Layer Perceptron (MLP), as well as the Tabular Prior Data Fitting Network (TabPFN), which incorporates automatic feature weighting, were used to model and analyze both the raw spectral data and the full-band data preprocessed by Savitzky-Golay smoothing, Standard Normal Variate (SNV), and Fractional Order Differentiation (FOD). A multi-model evaluation identified the optimal spectral preprocessing method. To assess the feature weighting capability of TabPFN, Principal Component Analysis (PCA), ReliefF, Maximum Relevance Minimum Redundancy (mRMR), and HSICLasso algorithms were employed for feature selection, extracting sensitive bands associated with powdery mildew grading. The performance of the whole band and feature subsets was compared across different classifiers to determine the optimal model architecture, Finally, Shapley Additive Explanationswas used to analyze the key features and their influence on disease grading. The results showed that TabPFN butperformed all other models, demonstrating superior robustness and effective feature weighting selection, FOD preprocessing effectively reduced spectral noise and enhanced the extraction of essential detail features, resulting in the highest data quality improvement. The full-band TabPFN model with FOD preprocessing achieved a classification accuracy of 95.27%, surpassing Braditional methods by 3.24% similar to 13.24% After applying HSICLasso to select 20 critical features, the accuracy remained at 94.31%, while reducing model complexity by nearly 90% and only decreasing accuracy by 1.01%. SHAP analysis identified the 1 160 nm and 1400 nm regions as key discriminatory bands, linked to C-H and O-H chemical bond vibrations. These bands correspond to the leaf's carbohydrate, lignin, and water content, indicating the model's ability to capture spectral responses related to physicochemical changes caused by powdery mildew. This study validates the integration of FOD and TabPFN for PM Hetection, providing an accurate model for assessing disease severity, which can aid in precise pesticide application and promote the health of rubber trees, ultimately improving rubber production.
With the increasing number of document forgery and economic dispute cases, the accurate identification of homochromy inks is of great significance in judicial expertise. Traditional methods (such as thin-layer chromatography and Raman spectroscopy) have limitations including sample destruction and time-consuming procedures. At the same time, hyperspectral imaging (HSI) has emerged as a promising alternative due to its advantages of image-spectrum integration and non-destructive detection, However, the existing ink classification methods based on "dimension reduction and clustering" are difficult to fully explore the nonlinear characteristics of high-dimensional data, and shallow machine learning models have limited expressive ability and are susceptible to information loss and error accumulation. Therefore, a deep learning model H-CNN integrating multi-scale convolution and channel attention mechanism is proposed in this paper, and it is combined with hyperspectral imaging for the identification of homochromy inks. The model employs multi-branch parallel convolution to extract spectral features at different scales, comprehensively capturing spectral information across hands. And a channel attention mechanism dynamically enhances discriminative bands, focusing on key spectral information. Residual connection optimization gradient propagation is adopted to avoid gradient explosion and gradient vanishing, thereby reducing error accumulation and improving training efficiency, Experiments were conducted on the UWA Writing Ink Hyperspectral Image (WIHSI) dataset to determine the optimal training data partitioning and parameter settings. Ablation studies were designed to validate the effectiveness of the multi-branch parallel convolution structure, channel attention mechanism, and residual connections in improving model performance. Finally, the performance of the model proposed in this paper was compared with that of other model architectures on the current dataset. The experimental results show that the multi-branch structure and the channel attention mechanism improved the accuracy rates by 4.6% and 1.0% respectively, and the training cycle was shortened by 34% through the residual network connection, For the most challenging identification of the black ink, HI-CNN achieved an accuracy rate of 98.07% (an improvement of 5.3% compared to the optimal model CAE-LR), In comparison, for the identification of blue ink the accuracy rate reached 99.06%, which was generally superior to the existing methods. This study provided an accurate and efficient solution for identifying homochromy inks, thereby reducing reliance on professional expertise in forensic document examination. It had significant application value in the field of judicial expertise and promoted the leapfrog development of homochromy ink identification technology, transitioning from reliance on experience to scientific quantification,
Geological hazard prevention and control is a crucial national policy in China. Understanding the intrinsic driving factors of geological hazards is fundamental for disaster mitigation, As a province prone to geological hazards, previous studies in Guangdong have primarily focused on the physical and mechanical properties of rock and soil masses. At the same time. insufficient attention has been paid to the underlying causes of mechanical property deterioration chemical weathering. This study conducted statistical analyses on 6 841 slope hazard sites (collapses and landslides) in typical igneous and sedimentary rock regions of northern and eastern Guangdong. From the perspective of "chemical water-rock interaction (CWRI)", major chemical elements (including SiO2, Al2O, FeO, CaO, MgO, K2O, Na2O, and loss on ignition (LOI)) in 40 samples (weathered rocks, residual soils, and slope-residual soils) from 11 hazard sites were analyzed using X-ray luorescence spectrometry (XRF). Classic chemical weathering indices silica-alumina ratio (Si/Al), silica-sesquioxide ratio (Si/R2O), chemical index of alteration (CIA), and a newly proposed CIA-rate by the author were calculated to explore the driving mechanisms of chemical weathering intensity on slope hazards. Here, the CIA-rate is equal to the CIA value of the weathered product minus the CIA value of the fresh parent rock, then divided by the CIA value of the fresh parent rock. XRF results revealed that the average CIA-rate of igneous rock weathering products (71.28) was significantly higher than that of sedimentary rock products (21.26), consistent with the 1.4 times higher hazard density in igneous rock arcas. In igneous rock regions, slope hazards predominantly occur in fully weathered layers and residual soils with CIA values of 75 similar to 85 and CIA-rates of 50 similar to 70, particularly at sites with spheroidal weathering bodies or heterogeneous interlayers. In sedimentary rock regions, hazards are often observed in lower fully weathered layers and residual soils with CIA values of 75 similar to 85 and CIA-rates of 15 similar to 25, where bedding structures and "soft-hard interlayers" facilitate multi-stage or deep-seated landslides. This study demonstrates that the hot-humid climate and intense rainfall in South China enhance surface water and groundwater erosion and corrosion, accelerating chemical weathering. During desilication and enrichment of aluminum/iron, elements such as K, Na, Ca, and Mg are leached. In contrast, clay newbornminerals and iron hydroxides accumulate, weakening the mechanical properties and structural integrity of rock and soil masses. These processes serve as intrinsic drivers of geological hazards. The findings provide a scientific basis for early identification and warning of geological hazards.
