High Speed Railway Fastener Defect Detection by Using Improved YoLoX-Nano Model.

Rails play a vital role in the bearing and guidance of high-speed trains, and the normal condition of rail components is the guarantee of the operation and maintenance safety. Fasteners are critical components for fixing the rails, so it is particularly important to detect whether they are in a normal state or not. The current rail-fastener detection models have some drawbacks, including poor generalization ability, large model volume and low detection efficiency. In view of this, an improved YoLoX-Nano rail-fastener-defect-detection method is proposed in this paper. The CA attention mechanism is added to the three output feature maps of CSPDarknet and the enhanced feature extraction part of the Path Aggregation Feature Pyramid Network (PAFPN); the Adaptively Spatial Feature Fusion (ASFF) is added after the PAFPN output feature map, which enables the semantic information of the high-level features and the fine-grained features of the bottom layer to be further enhanced. The improved YoLoX-Nano model has improved the AP value by 27.42% on fractured fasteners, 15.88% on displacement fasteners and 12.96% on normal fasteners. Moreover, the mAP value is improved by 18.75%, and it is 14.75% higher than the two-stage model Faster-RCNN on mAP. In addition, compared with YoLov7-tiny, the improved YoLoX-Nano model achieves 13.56% improvement on mAP. Although the improved model increases a certain amount of calculation, the detection speed of the improved model has been increased by 30.54 fps and by 32.33 fps when compared with that of the Single-Shot Multi-Box Detector (SSD) model and the You Only Look Once v3 (YoLov3) model, reaching 54.35 fps. The improved YoLoX-Nano model enables accurate and rapid identification of the defects of rail fasteners, which can meet the needs of real-time detection. Furthermore, it has advantages in lightweight deployment of terminals for rail-fastener detection, thus providing some reference for image recognition and detection in other fields.

Research on highly sensitive quantitative detection of aflatoxin B2 solution based on THz metamaterial enhancement.

Food such as cereal crops, oil crops and dairy products are very easy to produce highly toxic and carcinogenic aflatoxins during inappropriate storage. Therefore, it is of great significance to achieve rapid, non-destructive and highly sensitive detection of aflatoxin. A terahertz metamaterial sensor with "X" compound double-peak structure is designed based on electromagnetic theory to realize highly sensitive detection of aflatoxin B2 solution. It is found that the amplitude of the transmission peak of the terahertz transmission spectrum of aflatoxin B2 (AFB2) solution around 1.2 THz and 2.0 THz gradually decreased with the increase of the concentration of aflatoxin B2 solution, and the frequency of the transmission peak gradually shifted to high frequency with the increase of the concentration of aflatoxin B2 solution, hence a full concentration model was established. And a strategy of first classifying concentration intervals and then building a grouped quantitative model was proposed. The Limit of Detection (LOD) of the interval sub-model of low and medium concentration of aflatoxin B2 solution has been greatly improved with the LOD of the optimal grouping model was 7.28 × 10-11 mg/ml, 4.19 × 10-9 mg/ml and 1.22 × 10-7 mg/ml, respectively. This research verifies the feasibility of terahertz metamaterial sensor based on "X" composite double-peak structure combined with THz-TDS technology for highly sensitive detection of aflatoxin B2 solution. And it provides a new rapid, non-destructive and highly sensitive detection of aflatoxin in food.

Study on qualitative identification of aflatoxin solution based on terahertz metamaterial enhancement.

Aflatoxin is the main carcinogen that contaminates agricultural products and foods such as peanuts and corn. There are many kinds of aflatoxins, mainly including aflatoxin B1 (AFB1), aflatoxin B2 (AFB2), aflatoxin G1 (AFG1) and aflatoxin G2 (AFG2). Different types of aflatoxins have different toxicity and different levels of contamination to agricultural products as well as food. Therefore, the rapid, non-destructive and highly sensitive qualitative identification of aflatoxin species is of great significance to maintain people's life and health. The conventional terahertz detection method can only qualitatively identify the samples at the milligram level, but it is not suitable for the qualitative analysis of trace samples. In this paper, a terahertz metamaterial sensor with "X" composite double-peak structure was designed based on electromagnetic theory to investigate the feasibility of THz-TDS technology based on a metamaterial sensor for the qualitative identification of trace aflatoxin B2, G1 and G2 solutions. Firstly, the terahertz transmission spectra of eight different concentrations of aflatoxin B2, G1 and G2 were collected respectively, and then the differences of terahertz transmission spectra of different aflatoxin species were investigated. Finally, the terahertz transmission spectra of aflatoxin B2, G1 and G2 solutions were modeled and analyzed using chemometric methods. It was found that there were significant differences in the transmission peak curves of different kinds of aflatoxin. Through the comparative analysis of different models, it was concluded that the prediction accuracy of the CARS-RBF-SVM model was the highest, and the accuracy of the calibration set reached 100%. 119 out of 120 predicted samples were correctly predicted, and the prediction accuracy was 99.17%. This study verified the feasibility of qualitative identification of trace aflatoxin B2, G1 and G2 solutions by a metamaterial sensor based on the "X" composite double-peak structure combined with THz-TDS technology, and provided a theoretical basis and a new detection method for the qualitative identification of trace aflatoxins. This will facilitate the rapid, non-destructive and highly sensitive qualitative detection of different kinds of aflatoxins in food and agricultural products. At the same time, this study has important implications for promoting the qualitative detection of other trace substances.

[Partial least squares regression variable screening studies on apple soluble solids NIR spectral detection].

Abstract To improve the predictive ability and robustness of the NIR correction model of the soluble solid content (SSC) of apple, the reverse interval partial least squares method, genetic algorithm and the continuous projection method were implemented to select variables of the NIR spectroscopy of the soluble solid content (SSC) of apple, and the partial least squares regression model was established. By genetic algorithm for screening of the 141 variables of the correction model, prediction has the best effect. And compared to the full spectrum correction model, the correlation coefficient increased to 0.96 from 0.93, forecast root mean square error decreased from 0.30 degrees Brix to 0.23 degrees Brix. This experimental results show that the genetic algorithm combined with partial least squares regression method improved the detection precision of the NIR model of the soluble solid content (SSC) of apple.

[Research on optimization of model for detecting sugar content of navel orange by online near infrared spectroscopy].

The objective of the present research was to optimize the model of sugar content in navel orange for improving the detection presicion by the online near infrared spectroscopy. The reference wavelength was chosen by coefficient of variation of the different wavelengths in the calibration set in the wavelength range of 700.28 - 933.79 nm. Then the spectra were transformed into ratio specra. The absorbance and ration spectra were pretreated by different preprocessing methods. The models of sugar content were developed by partial least squares (PLS) and least squares support vector regression (LSSVR). The 30 unknown navel orange samples were applied to evaluate the performance of the models. By comparison of the predictive performances, the LSSVR model was the best among the models with the first derivative preprocessing and ration spectra. The correlation coeffiecient (R(P)) of the best model was 0.85, the root mean square error of prediction (RMSEP) was 0.41 Brix. The results suggested that it was feasible to improve the precision of online near infrared spectroscopy detecting sugar content in navel orange by the optimization of reference wavelengths, the first derivative preprocessing and LSSVR.

3D printed high-resolution scaffold with hydrogel microfibers for providing excellent biocompatibility.

Melt electrowriting (MEW) can print high-resolution scaffolds with the ultrafine fibers from 800 nm to 20 µm. However, the cell seeding efficiency relatively low due to the large pore size of the MEW scaffold. Here, we reported a method to solve this dilemma by electrospinning a gelatin methacrylate (GelMA) hydrogel fibers membrane (HFM) on the MEW scaffold. This composite scaffold can own the controlled structures and porosity and excellent cell seeding performance. We systematically investigate the fabrication, morphology, and biocompatibility of composite scaffolds. The implanting of human umbilical vein endothelial cells(HUVES) showed excellent adhesion and biocompatibility on the composite scaffold. Moreover, the cells migrated gradually into the MEW scaffold along the GelMA HFM to form the cell sheet. We hold the opinion that the composite scaffolds have potential applications in the field of tissue engineering repair.

[Application of Raman spectroscopy technique to food quality and safety determination].

With the merits of doing without sample pretreatment, easy operation, short response time and high sensitivity, Raman spectroscopy technique can acquire samples' physical chemistry and the deep structure information. It has been widely applied in petrol chemical, biomedicine, geoarchaeology, criminal justice, gem identification, etc. Raman spectroscopy has good application prospect in food quality and safety determination, for its spectra are not extremely sensitive to polar materials such as water. The detection principle, classification and the system composition of Raman spectroscopy technique were introduced briefly. The latest research progress in food constituent analysis and pesticide residue determination by Raman spectroscopy was reviewed. Finally, its key technologies for food quality and safety determination were pointed out and the future research was prospected.

[Visible transmittance techniques for rapid analysis of sugar content of fresh navel orange juices].

The feasibility of visible spectroscopic technology for rapid quantifying sugar content (SC) of navel orange fresh juices was investigated by means of spectral transmittance technique. A total of 55 juice samples were used to develop the calibration and prediction models. Calibration models based on different spectral ranges and different spectral pretreatment were compared in the precent research. Performance of different models was investigated in terms of root mean square errors of prediction (RMSEP) and correlation coefficient (r) of validation set of samples. The correlation coefficient of calibration model for SC was 0.965, the correlation coefficient of prediction model for SC was 0.857, and the corresponding RMSEP was 0.562. The results show that visible transmittance technique is a feasible method for non-invasive estimation of fruit juice SC.

[Near infrared diffuse reflectance spectroscopy for rapid analysis of soluble solids content in navel orange].

The potential of using visible and near infrared diffuse reflectance spectroscopy to assess soluble solids content (SSC) of intact navel orange was examined. A total 40 samples were used to develop the calibration and prediction models. NIR spectral data were collected in the spectral region between 350 and 2 500 nm and their second derivative spectra were used for the present study. Different scattering correction algorithms (no preprocessing and multiplicative scattering correction (MSC)) were compared. Camibration models based on different spectral ranges, different derivatives and different kinds of statistical models including partial least square (PLS) and principal component regression (PCR) were also compared. The best results of PLS models with the second derivative spectra are r = 0.929, RMSEC = 0.517 and RMSEP = 0.592 in the wavelength range of 361-2 488 nm. The results show that this method is feasible for non destructive assessing of SSC of the navel orange.

Determination of copper and zinc pollutants in Ludwigia prostrata Roxb using near-infrared reflectance spectroscopy (NIRS).

The feasibility of using near-infrared reflectance spectroscopy (NIRS) to determine the concentrations of copper (Cu) and zinc (Zn) in Ludwigia prostrata Roxb plants was investigated. Ludwigia prostrata Roxb plants were grown over a full growth cycle under controlled laboratory conditions in soils contaminated with heavy metals. The Cu and Zn concentrations in 72 L. prostrata Roxb samples were analyzed using flame atomic absorption spectrometry, and NIRS spectra were collected in the 1099-2500 nm range. Five mathematical treatments of the spectral data were compared prior to developing the calibration models (n = 48) using partial least squares regression methods. The two calibration models for Cu and Zn concentrations were evaluated according to the correlation coefficient of cross-validation (R(cv)) and root mean squares error of cross-validation. The highest R(cv) and the lowest RMSECV were obtained for Cu (0.9 and 7.24 mg kg(-1)) and Zn (0.94 and 19.17 mg kg(-1)), respectively. The results showed that near-infrared diffuse reflectance spectroscopy can be used for the rapid determination of Cu and Zn in leaves of L. prostrata Roxb plants.