Nondestructive Detection Research Articles

Dendritic copper nanostructures for ultrasensitive detection of rhodamine 6G and Congo red

Surface-Enhanced Raman Scattering (SERS) is a fast-responding and non-destructive ultra-sensitive detection technique that can replace traditional chromatographic and spectroscopic analysis techniques. In this experiment, dendritic copper nanostructures were prepared by the solid-state ionics method and the vacuum hot evaporation process with an applied current of I=9μA. Using them as a SERS substrate, Raman detection was performed on the dye molecules Rhodamine 6G (R6G) and Congo Red (CR) to determine SERS enhancement performance. It is found that the growth of the prepared copper nanostructures has a top-end dominant phenomenon. The fractal dimension of the copper nanostructure was calculated using fractal theory, and it was revealed to be 1.560. Scanning electron microscopy (SEM) results showed that a large number of 60-80 nm regularly arranged copper nanoparticles were attached to the surface of the dendritic copper nanostructure. This is beneficial to increase the surface roughness of the substrate and improve the detection level of dye molecules. Subsequently, copper nanostructures can sensitively detect R6G and CR solutions as low as 1×10-13 mol/L and 1×10-7 mol/L, reaching single-molecule levels. The Raman mapping experiment showed that the mean relative standard deviation (RSD) values of R6G and CR were 12.3% and 12.9%, indicating high uniformity and reproducibility of the structure. This structure effectively achieves the fusion of uniformity, repeatability, and sensitivity, and shows broad application prospects in food detection.

Combining NIR spectroscopy with chemometrics for discriminating naturally ripened banana and calcium carbide ripened banana

Calcium carbide is prohibited as a fruit ripening agent in many countries due to its harmful effects. Current methods for detecting calcium carbide in fruit involve time-consuming and destructive chemical analysis techniques, necessitating the need for non-destructive and rapid detection techniques. This study combined near infrared (NIR) spectroscopy with chemometrics to detect two banana varieties ripened with calcium carbide in different forms when they are peeled or unpeeled. Sixteen linear discriminant analysis (LDA) models were developed with high average classification accuracies for classifying banana based on the mode used to ripen banana, type of carbide treatment and the duration of soaking banana in carbide solution. Banana colour was predicted with partial least squared regression (PLSR) models with R2CV > 0.74, RMSECV and <5.4 and RPD close to 3. NIR coupled with chemometrics has good potential as a technique for detecting carbide ripened banana even if the banana is peeled or not.

Estimation of the soluble solid content of citrus based on the fractional-order derivative and optimal band combination algorithm.

The soluble solid content (SSC) is a primary characteristic index for evaluating the internal quality of citrus fruits. The development of rapid and nondestructive SSC detection techniques can help address the current issues of postharvest quality grading in China's citrus industry. In this study, a total of 261 experimental samples, including 70 Murcott, 91 Clementine, and 100 Navel orange, were divided into prediction and validation sets in a 7:3 ratio. After obtaining the reflection spectra and SSCs, SNV-FOD (Standard Normal Variate-Fractional-Order Derivative) was used to process the spectra, and the optimal band combination algorithm was introduced to select SSC-sensitive bands. Then, the obtained optimal dual-band combination was input into eight regression models for comparison, and the best performing models stacked ensemble models was selected. Finally, the H-ELR (HyperOpt-optimized ensemble learning regression) model, optimized using a Bayesian function, was applied for the effective estimation of SSC for three common citrus varieties in Guangxi, Murcott, Clementine, and Navel oranges. The results show that (1) the SNV-FOD preprocessing method proposed in this study improved the correlation coefficient with the SSC from 0.546 to 0.836 compared to that of the original spectrum, (2) the optimal dual-band combination (969 and 1069nm) constructed by integrating the differential index and 1.2-order derivative yielded the most accurate results (RPD=2.13), and (3) the H-ELR model, based on HyperOpt optimization, achieved good estimated performance (RPD=2.46). PRACTICAL APPLICATION: This research contributes to the development of practical SSC prediction instruments with excellent universality and ease of application.

Terahertz Non-Destructive Testing of Porosity in Multi-Layer Thermal Barrier Coatings Based on Small-Sample Data

Accurately characterizing the internal porosity rate of thermal barrier coatings (TBCs) was essential for prolonging their service life. This work concentrated on atmospheric plasma spray (APS)-prepared TBCs and proposed the utilization of terahertz non-destructive detection technology to evaluate their internal porosity rate. The internal porosity rates were ascertained through a metallographic analysis and scanning electron microscopy (SEM), followed by the reconstruction of the TBC model using a four-parameter method. Terahertz time-domain simulation data corresponding to various porosity rates were generated employing the time-domain finite difference method. In simulating actual test signals, white noise with a signal-to-noise ratio of 10 dB was introduced, and various wavelet transforms were utilized for denoising purposes. The effectiveness of different signal processing techniques in mitigating noise was compared to extract key features associated with porosity. To address dimensionality challenges and further enhance model performance, kernel principal component analysis (kPCA) was employed for data processing. To tackle issues related to limited sample sizes, this work proposed to use the Siamese neural network (SNN) and generative adversarial network (GAN) algorithms to solve this challenge in order to improve the generalization ability and detection accuracy of the model. The efficacy of the constructed model was assessed using multiple evaluation metrics; the results indicate that the novel hybrid WT-kPCA-GAN model achieves a prediction accuracy exceeding 0.9 while demonstrating lower error rates and superior predictive performance overall. Ultimately, this work presented an innovative, convenient, non-destructive online approach that was safe and highly precise for measuring the porosity rate of TBCs, particularly in scenarios involving small sample sizes facilitating assessments regarding their service life.

Research on Non-Destructive Testing of Log Knot Resistance Based on Improved Inverse-Distance-Weighted Interpolation Algorithm

The objective of this paper is to propose a non-destructive resistance detection imaging algorithm for log knots based on improved inverse-distance-weighted interpolation algorithm, i.e., the eccentric circle-based inverse-distance-weighted (ECIDW) method, to predict the size, shape, and position of internal knots of logs; evaluate its precision and accuracy; and both lay a theoretical foundation and provide a scientific basis for predicting and assessing knots in standing trees. Six sample logs with natural knots were selected for this study. Resistance measurements were performed on the log cross-sections using a digital bridge, and resistance tomography was conducted using the improved ECIDW algorithm, which combines the azimuth search method with the eccentric circle search method. The results indicated that both the conventional inverse-distance-weighted (IDW) algorithm and the ECIDW algorithm accurately predicted the positions of the knots. However, neither algorithm was able to predict the shape of the knots with high precision, leading to some discrepancies between the predicted and actual knot shapes. The relative error (Dt1) between the knot areas measured by the IDW algorithm and the actual knot areas ranged from 18.97% to 88.34%. The relative error (Dt2) for the knot areas predicted by the ECIDW algorithm ranged from 1.82% to 74.16%. The average prediction accuracy for the knot areas using the IDW algorithm was 51.58%, compared to 72.90% using the ECIDW algorithm. This indicates that the ECIDW algorithm has higher accuracy in predicting knot areas compared to the conventional IDW algorithm. The ECIDW algorithm proposed in this paper provides a more reasonable and accurate prediction and evaluation of knots inside logs. Compared to the conventional IDW algorithm, the ECIDW algorithm demonstrates greater precision and accuracy in predicting the shape and size of knots. While the resistance method shows significant potential for predicting internal knots in logs and standing trees, further improvements to the algorithm were needed to enhance the imaging effects and the precision and accuracy of knot area and shape predictions.

Plasmonic chitosan cross-linked dialdehyde chitosan aerogels as 3D surface-enhanced Raman scattering substrates for sensitive and reliable detection

Surface Enhanced Raman Scattering (SERS) has the advantages of non-destructive detection and high sensitivity, however, low hotspots utilisation and inhomogeneous distribution limit its application. In response to the problem of underutilization of hotspots in most SERS substrates, a crosslinking of chitosan with dialdehyde chitosan aerogels loaded with Ag NPs (CDSA) as SERS substrates with chitosan (CS) as the main body and dialdehyde chitosan (DACS) as the reducing and cross-linking agent were prepared. Unlike other 3D structures such as hydrogels, CDSA can capture probe molecules in a much shorter period of time and enhance SERS signals by collapse. The SERS performance of CDSA was evaluated by rhodamine 6 G (R6G) and methylene blue (MB), indicating that the CDSA substrate has good stability (90 days), repeatability (RSD=4.15 %) and reproducibility (RSD=4.86 %). The enhancement factors (EFs) was 1.3×108 for R6G and 9.2×107 for MB. Both gas sample and liquid sample were detected to evaluate the performances of CDSA in practical application. 4-Aminothiophenol (4-ATP) was utilized to test the efficacy of CDSA on gas-phase to-be-tested substances and the limit of detection (LOD) was 0.59 mg/L. The tests performed on sildenafil (SD) in real samples showed recoveries ranging from 97.5 % to 103.4 % with a LOD of 0.055 mg/L. It was indicated that the CDSA substrate could serves as a satisfactory SERS sensor for sensitive and rapid detection for both gas phase and liquid samples.

Dadnet: dual-attention detection network for crack segmentation on tomb murals

Many tomb murals have punctate losses, cracks, and craquelure due to underground subsidence and changes in their physical support. Visual non-destructive detection techniques enable rapid assessment of how much tomb murals are affected by cracking, providing suggestions for their conservation. However, tomb murals are typically created by sketching outlines and then colored. Detailed sketches can easily interfere with crack detection work, requiring the use of deep learning network to better learn crack features and improve detection accuracy. At the same time the limited data of tomb mural presents a challenge to build a deep learning network. To address these issues, this paper introduces a novel dual-attention detection network (DADNet) for crack segmentation of tomb murals. In this work, a customized dataset is first constructed by collecting mural images from the Tang Dynasty tombs. Then the ConvNeXt framework serves as the basis for feature extraction, enhancing the process. Lastly, a dual-attention module utilizing neighborhood attention and biaxial attention is employed to accurately identify the crack regions. Neighborhood attention performs a local self-attention operation around the pixel point, addressing the limitations of self-attention. This approach significantly reduces computational demands as the image size increases. Biaxial attention performs attention calculations in the horizontal and vertical directions. This compensates for the limitation of neighborhood attention in capturing global dependencies. Our DADNet outperformed the competing methods, achieving the highest recorded scores of 78.95% for MIoU and 61.05% for the Jaccard index.

Non-Invasive Detection of Nitrogen Deficiency in Cannabis sativa Using Hand-Held Raman Spectroscopy

Proper crop management requires rapid detection methods for abiotic and biotic stresses to ensure plant health and yield. Hemp (Cannabis sativa L.) is an emerging economically and environmentally sustainable crop capable of yielding high biomass. Nitrogen deficiency significantly reduces hemp plant growth, affecting photosynthetic capacity and ultimately decreasing yield. When symptoms of nitrogen deficiency are visible to humans, there is often already lost yield. A real-time, non-destructive detection method, such as Raman spectroscopy, is therefore critical to identify nitrogen deficiency in living hemp plant tissue for fast, precise crop remediation. A two-part experiment was conducted to investigate portable Raman spectroscopy as a viable hemp nitrogen deficiency detection method and to compare the technique’s predictive ability against a handheld SPAD (chlorophyll index) meter. Raman spectra and SPAD readings were used to train separate nitrogen deficiency discrimination models. Raman scans displayed characteristic spectral markers indicative of nitrogen deficiency corresponding to vibrational modes of carotenoids, essential pigments for photosynthesis. The Raman-based model consistently predicted nitrogen deficiency in hemp prior to the onset of visible stress symptoms across both experiments, while SPAD only differentiated nitrogen deficiency in the second experiment when the stress was more pronounced. Our findings add to the repertoire of plant stresses that hand-held Raman spectroscopy can detect by demonstrating the ability to provide assessments of nitrogen deficiency. This method can be implemented at the point of cultivation, allowing for timely interventions and efficient resource use.

Flexible X-ray Imaging and Stable Information Storage of SrF2:Eu Based on Radio-Photoluminescence.

X-ray imaging has garnered widespread interest in biomedical diagnosis and nondestructive detection. The exploration of radio-photoluminescence has hastened the advancement of X-ray information storage. However, significant challenges persist in achieving the prolonged imaging of curved objects without attenuation. Here, europium-doped strontium fluoride (SrF2:Eu) is meticulously created to exhibit a linear response to an extensive range of X-ray doses (maximum dose > 5000 Gy), showcasing excellent X-ray information reading/erasing reusability properties (10 cycles). This is accompanied by a red-to-blue emission transition under UV excitation, sustaining for 150 days without attenuation. To elucidate the phenomena of irradiated photoluminescent discoloration and the reversible X-ray storage of SrF2:Eu, we propose an electron-vacancy trap (valence conversion) mechanism, information stably retained by the SrF2:Eu-based device under ambient conditions due to high energy barriers. The time-lapse readout capability is further demonstrated for three-dimensional imaging of curved objects (10 lp mm-1) based on SrF2:Eu embedded within a polydimethylsiloxane (SrF2:Eu@PDMS). The SrF2:Eu demonstrates time-lapse imaging, reversible radio-photoluminescence, and recoverable X-ray storage, offering a promising avenue for optical information encryption and anticounterfeiting applications.

Quasi-visualizable detection of deep sub-wavelength defects in patterned wafers by breaking the optical form birefringence

Abstract In integrated circuit (IC) manufacturing, fast, nondestructive, and precise detection of defects in patterned wafers, realized by bright-field microscopy, is one of the critical factors for ensuring the final performance and yields of chips. With the critical dimensions of IC nanostructures continuing to shrink, directly imaging or classifying deep-subwavelength defects by bright-field microscopy is challenging due to the well-known diffraction barrier, the weak scattering effect, and the faint correlation between the scattering cross-section and the defect morphology. Herein, we propose an optical far-field inspection method based on the form-birefringence scattering imaging of the defective nanostructure, which can identify and classify various defects without requiring optical super-resolution. The technique is built upon the principle of breaking the optical form birefringence of the original periodic nanostructures by the defect perturbation under the anisotropic illumination modes, such as the orthogonally polarized plane waves, then combined with the high-order difference of far-field images. We validated the feasibility and effectiveness of the proposed method in detecting deep subwavelength defects through rigid vector imaging modeling and optical detection experiments of various defective nanostructures based on polarization microscopy. On this basis, an intelligent classification algorithm for typical patterned defects based on a dual-channel AlexNet neural network has been proposed, stabilizing the classification accuracy of λ/16-sized defects with highly similar features at more than 90%. The strong classification capability of the two-channel network on typical patterned defects can be attributed to the high-order difference image and its transverse gradient being used as the network's input, which highlights the polarization modulation difference between different patterned defects more significantly than conventional bright-field microscopy results. This work will provide a new but easy-to-operate method for detecting and classifying deep-subwavelength defects in patterned wafers or photomasks, which thus endows current online inspection equipment with more missions in advanced IC manufacturing.

Nutritional composition analysis in food images: an innovative Swin Transformer approach.

Accurate recognition of nutritional components in food is crucial for dietary management and health monitoring. Current methods often rely on traditional chemical analysis techniques, which are time-consuming, require destructive sampling, and are not suitable for large-scale or real-time applications. Therefore, there is a pressing need for efficient, non-destructive, and accurate methods to identify and quantify nutrients in food. In this study, we propose a novel deep learning model that integrates EfficientNet, Swin Transformer, and Feature Pyramid Network (FPN) to enhance the accuracy and efficiency of food nutrient recognition. Our model combines the strengths of EfficientNet for feature extraction, Swin Transformer for capturing long-range dependencies, and FPN for multi-scale feature fusion. Experimental results demonstrate that our model significantly outperforms existing methods. On the Nutrition5k dataset, it achieves a Top-1 accuracy of 79.50% and a Mean Absolute Percentage Error (MAPE) for calorie prediction of 14.72%. On the ChinaMartFood109 dataset, the model achieves a Top-1 accuracy of 80.25% and a calorie MAPE of 15.21%. These results highlight the model's robustness and adaptability across diverse food images, providing a reliable and efficient tool for rapid, non-destructive nutrient detection. This advancement supports better dietary management and enhances the understanding of food nutrition, potentially leading to more effective health monitoring applications.

Vibrational Spectroscopy Can Be Vulnerable to Adversarial Attacks.

Nondestructive detection methods based on vibrational spectroscopy have been widely used in many critical applications in a variety of fields such as the chemical industry, pharmacy, national defense, security, and so on. As these methods/applications rely on machine learning models for data analysis, studying the threats associated with adversarial examples in vibrational spectroscopy and defenses against them is of great importance. In this paper, we propose a novel adversarial method to attack vibrational spectroscopy, named SynPat, where synthetic peaks produced by a physical model are placed at key locations to form adversarial perturbations. Our new attack generates perturbations that successfully deceive machine learning models for Raman and infrared spectrum analysis while they blend much better into the spectra and hence are unnoticeable to human operators, unlike the existing state-of-the-art adversarial attacking methods, e.g., images and audio. We verified the superiority of the proposed SynPat by an imperceptibility test conducted by human experts and of defense experiments by an AI detector. To the best of our knowledge, this is a first thorough study on the robustness of vibrational spectroscopic techniques against adversarial samples and defense mechanisms. Our extensive experiments show that machine learning models for vibrational spectroscopy, including conventional and deep models for Raman or infrared classification and regression, are all vulnerable to adversarial perturbations and thus may pose serious security threats to our society.

Dielectric spectroscopy technology combined with machine learning methods for nondestructive detection of protein content in fresh milk.

To quickly achieve nondestructive detection of protein content in fresh milk, this study utilized a network analyzer and an open coaxial probe to analyze the dielectric spectra of milk samples at 100 frequency points within the 2-20GHz range, focusing on the dielectric constant ε' and the dielectric loss factor ε''. Feature variables were extracted from the full dielectric spectra using the successive projections algorithm (SPA), uninformative variables elimination (UVE), and the combined UVE-SPA method. These variables were then used to develop partial least squares regression (PLSR), support vector machine (SVM), decision tree (DT), random forest (RF), and least squares boosting (LSBOOST) models for predicting protein content. The results showed that ε' decreased monotonically with increasing frequency, while ε'' increased monotonically. The UVE-SPA method for feature extraction demonstrated superior performance, with the UVE-SPA-PLSR model being the best for predicting milk protein content, achieving the highest RC 2=0.998 and RP 2=0.989 and the lowest RMSEC=0.019% and RMSEP=0.032%. This study provides a theoretical reference for evaluating milk quality and developing intelligent detection equipment for natural milk.

Combining Dielectric and Hyperspectral Data for Apple Core Browning Detection

Apple core browning not only affects the nutritional quality of apples, but also poses a health risk to consumers. Therefore, there is an urgent need to develop a fast and reliable non-destructive detection method for apple core browning. To deal with the challenges of the long incubation period, strong infectivity, and difficulty in the prevention and control of apple core browning, a novel non-destructive detection method for apple core browning has been developed through combining hyperspectral imaging and dielectric techniques. To reduce the computational complexity of high-dimensional multi-view data, canonical correlation analysis is employed for feature dimensionality reduction. Then, the two low-dimensional vectors extracted from two different sensors are concatenated into one united feature vector; therefore, the information contained in the hyperspectral and dielectric data is fused to improve the detection accuracy of the non-destructive method. At last, five traditional classifiers, such as k-Nearest Neighbors, a support vector machine with radial basis function kernel and polynomial kernel, Decision Tree, and neural network, are trained on the fused feature vectors to discriminate apple core browning. The experimental results on our own constructed dataset have shown that the sensitivity, specificity, and precision of SVM with RBF kernel based on concatenated 70-dimensional feature vectors extracted via canonical correlation analysis reached 99.98%, 99.70%, and 99.70%, respectively, which achieved better results than other models. This study can provide theoretical assurance and technical support for further development of higher accuracy and lower-cost non-destructive detection devices for apple core browning.

A Review of the Application of Hyperspectral Imaging Technology in Agricultural Crop Economics

China is a large agricultural country, and the crop economy holds an important place in the national economy. The identification of crop diseases and pests, as well as the non-destructive classification of crops, has always been a challenge in agricultural development, hindering the rapid growth of the agricultural economy. Hyperspectral imaging technology combines imaging and spectral techniques, using hyperspectral cameras to acquire raw image data of crops. After correcting and preprocessing the raw image data to obtain the required spectral features, it becomes possible to achieve the rapid non-destructive detection of crop diseases and pests, as well as the non-destructive classification and identification of agricultural products. This paper first provides an overview of the current applications of hyperspectral imaging technology in crops both domestically and internationally. It then summarizes the methods of hyperspectral data acquisition and application scenarios. Subsequently, it organizes the processing of hyperspectral data for crop disease and pest detection and classification, deriving relevant preprocessing and analysis methods for hyperspectral data. Finally, it conducts a detailed analysis of classic cases using hyperspectral imaging technology for detecting crop diseases and pests and non-destructive classification, while also analyzing and summarizing the future development trends of hyperspectral imaging technology in agricultural production. The non-destructive rapid detection and classification technology of hyperspectral imaging can effectively select qualified crops and classify crops of different qualities, ensuring the quality of agricultural products. In conclusion, hyperspectral imaging technology can effectively serve the agricultural economy, making agricultural production more intelligent and holding significant importance for the development of agriculture in China.

Rapid identification of cod authenticity based on hyperspectral imaging technology

The high economic value of Atlantic cod makes it prone to fraudulent activities in the market, thus achieving rapid and non-destructive identification of its authenticity has practical significance. This study investigated the hyperspectral imaging (HSI) systems with a Vis-NIR (400 – 1000 nm) and SWIR (900 – 1700 nm) spectral range, for determining the authenticity of Atlantic cod fillets in two frozen and thawed sample states. Results found that the model effect of Vis-NIR data was generally better than SWIR data. Random forest (RF) and Linear discriminant analysis (LDA) models of Vis-NIR data achieved 100 % accuracy. Variable screening algorithms of Successive projections algorithm (SPA) and Variable combination population analysis- iteratively retaining informative variables (VCPA-IRIV) maintained 100 % accuracy of the LDA model at VIS-NIR wavebands while simplifying the data operation burden. Overall, this study suggests that HSI is a promising solution for rapid and non-destructive detection of Atlantic cod authenticity.

Non-destructive detection of fructose solutions via Terahertz spectroscopy enhanced by Frequency Selective Surface (FSS)

Terahertz (THz) spectroscopy, combined with Frequency Selective Surfaces (FSS), is emerging as a powerful non-destructive technique for detecting and analysing the properties of biological samples. In this study, we explored the use of THz spectroscopy for detecting fructose solutions with concentrations ranging from 0.2 % to 10 %. Using femtosecond laser light sources, the THz transmission and absorption characteristics of fructose were investigated. The integration of FSS significantly enhanced the sensitivity of THz detection, yielding a 16 % improvement at 1.29 THz and 28 % at 1.67 THz. UV–Vis and Fourier Transform Infrared (FTIR) spectroscopy were employed to compare results with traditional methods, highlighting the superior sensitivity of THz spectroscopy, especially at low concentrations. The findings suggest that THz spectroscopy, enhanced by FSS, has strong potential for advancing non-invasive testing in biological and environmental applications.

The Application of Computed Tomography to Study the Soil Porosity of Mountain Red Earth

Mountain red soil, as a special type of soil in the South, has received widespread attention for its soil erosion problems. Its pore structure restricts water infiltration, thereby affecting the occurrence and development of soil erosion. In order to systematically obtain the distribution characteristics of the pore structure within the surface mountain red soil, this paper uses non-destructive CT detection technology to scan the soil column samples taken from the typical mountain red soil distribution area in Chenggong District, Kunming City, Yunnan Province. Image processing technology is applied to CT slices, and ImageJ (1.46r) software is used to obtain the distribution characteristics of pores within the soil column, including pore sizes and the number of pores at each depth, the proportion of pore area, roundness, and box-counting dimension. The results show that with the increase in depth, the proportion of pore area decreases linearly from the maximum value of 52.25% at the top to the minimum value of 2.02% at the bottom; the roundness of pores fluctuates between 0.8 and 0.9, overall increasing; the total number of pores generally first increases then decreases, and small pores are predominant, with the least number of large pores in the topsoil layer; the box-counting dimension shows a gradual linear decrease, with a maximum value of 1.7980 and a minimum value of 0.9878. The number of pores affects both roundness and the box-counting dimension, and the proportion of pore area also affects the box-counting dimension. There is a negative correlation between roundness and the box-counting dimension. The 3D visualization reconstruction of pores shows that most are interconnected, with the pore size significantly reducing with increasing depth. The quantitative analysis of parameters and 3D visualization reveal, to some extent, the impact of pore structure on the occurrence and development of soil erosion in mountain red soil. These research findings form the foundation for studying soil erosion in this region and provide a basis for systematically understanding its processes and mechanisms.

Non-destructive visual detection of fresh food spoilage

Two coumarin derivatives SWJT-33 and SWJT-34 were synthesized as probes for the detection of cadaverine (Cad). Among them, SWJT-34 exhibits high selectivity and low detection limits for Cad using fluorescence or UV–vis spectrum. The detection limits for Cad were calculated to be 0.018 μM by fluorescence spectrum and 0.34 μM by UV–vis spectrum, which was much lower than those of most of reported probes. The probe could realize colorimetric and ratiometric detection of Cad because an aza-Michael addition reaction occurred between SWJT-34 and Cad to form the Schiff base compound as a product. In addition, SWJT-34 could be fabricated as portable test strips for the selective detection of Cad in vapor, and the corresponding detection limits were calculated to be 1.88 ppm in the fluorescent mode and 57 ppm in UV–vis mode, respectively. Additionally, these test strips could be used to test the freshness of Rottweiler shrimp and pork at different temperatures.

Non-destructive detection of male and female information in ducklings based on near-infrared spectral wavelength selection and deep learning

The technology for sex identification in ducklings can contribute to increased revenue and cost savings in modern duck farming. However, traditional manual identification techniques require high skill levels and involve significant labor intensity. In this study, a non-destructive, user-friendly, and efficient duckling sex identification technique was proposed using near-infrared spectroscopy and deep learning algorithms. Spectral data from 600 groups of newly hatched ducklings were collected. These data were divided into training, testing, and validation sets in a ratio of 7:2:1. The raw spectral data was preprocessed using the Savitzky-Golay convolution derivative method, which was employed for subsequent spectral feature wavelength extraction and modeling. The characteristic wavelengths were extracted using competitive adaptive reweighted sampling (CARS), successive projections algorithm (SPA), and uninformative variable elimination combined with SPA (UVE-SPA). Conventional machine learning methods − support vector machine (SVM) and different deep learning models, including multilayer perceptron (MLP), mobile network version 2 (MobileNetV2), and residual neural network (ResNet), were studied and compared. The experiment showed that deep learning algorithms outperform traditional spectral analysis models in terms of classification performance. Furthermore, conducting feature wavelength extraction before constructing the classification model could reduce the model’s testing time and even improve its classification performance. Finally, the four models with better classification performance were validated using a validation set, and the combination of MobileNetV2 model UVE-SPA was selected as the optimized model for ducklings’ gender determination, with a classification accuracy of 98.3 % and an average validation time of 1.1 ms. In summary, the detection model established using near-infrared spectroscopy and MobileNetV2 can achieve non-destructive identification of the gender of ducklings. The findings can provide a preliminary research foundation and technical support for the subsequent design of related online intelligent detection systems.