Near-Infrared Spectral Characteristic Extraction and Qualitative Analysis Method for Complex Multi-Component Mixtures Based on TRPCA-SVM

Artificial intelligence-driven electrochemical immunosensing biochips in multi-component detection

Electrochemical Immunosensing (EI) combines electrochemical analysis and immunology principles and is characterized by its simplicity, rapid detection, high sensitivity, and specificity. EI has become an important approach in various fields, such as clinical diagnosis, disease prevention and treatment, environmental monitoring, and food safety. However, EI multi-component detection still faces two major bottlenecks: first, the lack of cost-effective and portable detection platforms; second, the difficulty in eliminating batch differences and accurately decoupling signals from multiple analytes. With the gradual maturation of biochip technology, high-throughput analysis and portable detection utilizing the advantages of miniaturized chips, high sensitivity, and low cost have become possible. Meanwhile, Artificial Intelligence (AI) enables accurate decoupling of signals and enhances the sensitivity and specificity of multi-component detection. We believe that by evaluating and analyzing the characteristics, benefits, and linkages of EI, biochip, and AI technologies, we may considerably accelerate the development of EI multi-component detection. Therefore, we propose three specific prospects: first, AI can enhance and optimize the performance of the EI biochips, addressing the issue of multi-component detection for portable platforms. Second, the AI-enhanced EI biochips can be widely applied in home care, medical healthcare, and other areas. Third, the cross-fusion and innovation of EI, biochip, and AI technologies will effectively solve key bottlenecks in biochip detection, promoting interdisciplinary development. However, challenges may arise from AI algorithms that are difficult to explain and limited data access. Nevertheless, we believe that with technological advances and further research, there will be more methods and technologies to overcome these challenges.

Using Fuzzy Logic to Increase Accuracy in Mango Maturity Index Classification: Approach for Developing a Portable Near-Infrared Spectroscopy Device

Grading is a decisive step in the successful distribution of mangoes to customers according to their preferences for the maturity index. A non-destructive method using near-infrared spectroscopy has historically been used to predict the maturity of fruit. This research classifies the maturity indexes in five classes using a new approach involving classification modeling and the application of fuzzy logic and indirect classification by measuring four parameters: total acidity, soluble solids content, firmness, and starch. These four quantitative parameters provide guidelines for maturity indexes and consumer preferences. The development of portable devices uses a neo spectra micro development kit with specifications for the spectrum of 1350-2500 nm. In terms of computer technology, this study uses a Raspberry Pi and Python programming. To improve the accuracy performance, preprocessing is carried out using 12 spectral transformation operators. Next, these operators are collected and combined to achieve optimal performance. The performance of the classification model with direct and indirect approaches is then compared. Ultimately, classification of the direct approach with preprocessing using linear discriminant analysis offered an accuracy of 91.43%, and classification of the indirect approach using partial least squares with fuzzy logic had an accuracy of 95.7%.

Rapid detection of talc content in flour based on near-infrared spectroscopy combined with feature wavelength selection

Excessive illegal addition of talc in flour has always been a serious food safety issue. To achieve rapid detection of the talc content in flour (TCF) by near-infrared spectroscopy (NIRS), this study used a Fourier transform near-infrared spectrometer technique. The identification of efficient spectral feature wavelength selection (FWS), such as backward interval partial-least-square (BiPLS), competitive adaptive reweighted sampling (CARS), hybrid genetic algorithm (HGA), and BiPLS combined with CARS; BiPLS combined with HGA; and CARS combined with HGA, was also discussed in this paper, and the corresponding partial-least-square regression models were established. Comparing with whole spectrum modeling, the accuracy and efficiency of regressive models were effectively improved using feature wavelengths of TCF selected by the above algorithms. The BiPLS, combined with HGA, had the best modeling performance; the determination coefficient, root-mean-squared error (RMSE), and residual predictive deviation of the validation set were 0.929, 1.097, and 3.795, respectively. BiPLS combined with CARS had the best dimensionality reduction effect. Through the FWS by BiPLS combined with CARS, the number of modeling wavelengths decreased to 72 from 1845, and the RMSE of the validation set was reduced by 11.6% compared with the whole spectra model. The results showed that the FWS method proposed in this paper could effectively improve detection accuracy and reduce modeling wavelength variables of quantitative analysis of TCF by NIRS. This provides theoretical support for TCF rapid detection research and development in real-time.

Rapid Determination of Cellulose and Hemicellulose Contents in Corn Stover Using Near-Infrared Spectroscopy Combined with Wavelength Selection

The contents of cellulose and hemicellulose (C and H) in corn stover (CS) have an important influence on its biochemical transformation and utilization. To rapidly detect the C and H contents in CS by near-infrared spectroscopy (NIRS), the characteristic wavelength selection algorithms of backward partial least squares (BIPLS), competitive adaptive reweighted sampling (CARS), BIPLS combined with CARS, BIPLS combined with a genetic simulated annealing algorithm (GSA), and CARS combined with a GSA were used to select the wavelength variables (WVs) for C and H, and the corresponding regression correction models were established. The results showed that five wavelength selection algorithms could effectively eliminate irrelevant redundant WVs, and their modeling performance was significantly superior to that of the full spectrum. Through comparison and analysis, it was found that CARS combined with GSA had the best comprehensive performance; the predictive root mean squared errors of the C and H regression model were 0.786% and 0.893%, and the residual predictive deviations were 3.815 and 12.435, respectively. The wavelength selection algorithm could effectively improve the accuracy of the quantitative analysis of C and H contents in CS by NIRS, providing theoretical support for the research and development of related online detection equipment.