An extreme learning machine optimized by differential evolution and artificial bee colony for predicting the concentration of whole blood with Fourier Transform Raman spectroscopy

XGBoost algorithm assisted multi-component quantitative analysis with Raman spectroscopy

To improve prediction performance and reduce artifacts in Raman spectra, we developed an eXtreme Gradient Boosting (XGBoost) preprocessing method to preprocess the Raman spectra of glucose, glycerol and ethanol mixtures. To ensure the robustness and reliability of the XGBoost preprocessing method, an X-LR model (which combined XGBoost preprocessing and a linear regression (LR) model) and a X-MLP model (which combined XGBoost preprocessing and a multilayer perceptron (MLP) model) were developed. These two models were used to quantitatively analyze the concentrations of glucose, glycerol and ethanol in the Raman spectra of mixed solutions. The proportion map of hyperparameters was firstly used to narrow down the search range of hyperparameters in the X-LR and the X-MLP models. Then the correlation coefficients (R2), root mean square of calibration (RMSEC), and root mean square error of prediction (RMSEP) were used to evaluate the models' performance. Experimental results indicated that the XGBoost preprocessing method achieved higher accuracy and generalization capability, with better performance than those of other preprocessing methods for both LR and MLP models.

Research on non-destructive and rapid detection technology of foxtail millet moisture content based on capacitance method and Logistic-SSA-ELM modelling

Moisture content testing of agricultural products is critical for quality control, processing efficiency and storage management. Testing foxtail millet moisture content ensures stable foxtail millet quality and helps farmers determine the best time to harvest. A differential capacitance moisture content detection device was designed based on STM32 and PCAP01 capacitance digital converter chip. The capacitance method combined with the back-propagation(BP) algorithm and the extreme learning machine(ELM) algorithm was chosen to construct an analytical model for foxtail millet moisture content, temperature, and volume duty cycle. This work performs capacitance measurements on foxtail millet with different moisture contents, temperatures, and proportions of the measured substance occupying the detection area (that is, the volumetric duty cycle). On this foundation, the sparrow search algorithm (SSA) is used to optimize the BP and ELM models. However, SSA may encounter problems such as falling into local optimization solutions due to the reduction of population diversity in the late iterations. As a consequence, Logistic algorithm is introduced to optimize SSA, making it more appropriate for solving specific problems. Upon comparative analysis, the model predicted using the Logistic-SSA-ELM algorithm was more accurate. The results indicate that the predicted values of prediction set coefficient of determination (RP), prediction set root mean square error (RMSEP) and prediction set ratio performance deviation (RPDP) were 0.7016, 3.7150 and 1.4035, respectively. This algorithm has excellent prediction performance and can be used as a model for detection of foxtail millet moisture content. In view of the important role of foxtail millet moisture content detection in acquisition and storage, it is particularly important to study a nondestructive and fast online real-time detection method. The designed capacitive sensor with differential structure has well stabilization and high accuracy, which can be further studied in depth and gradually move towards the general trend of agricultural development of smart agriculture and precision agriculture.

Handcrafted silver substrates boost surface plasmon resonance for ultra-sensitive lipid analysis

Lipid monitoring plays a crucial role in biomedical research, particularly in the areas of cardiovascular health, metabolic disorders and nutrition. However, direct and highly sensitive detection of lipids poses significant challenges due to the interference of high SERS background noise in lipid samples. In this study, we present a SERS platform for the quantitative analysis of lipids. By harnessing the Surface Plasmon Resonance (SPR) effect of nanostructured grooves and leveraging deuterium oxide, a remarkable enhancement of in-situ Raman signals originating from cholesterol is achieved. This approach yielded an impressive average enhancement factor of 7.3 × 105 and a detection limit of 1.9 × 10-4 mg/mL, highlighting the exceptional sensitivity and precision of our method. We have obtained high quality, in-situ SERS signals for six distinct lipid molecules. Rapid identification of lipid samples in mixed systems has been achieved through the combination of characteristic peak analysis and PCA-LDA, including the detection of SERS signals from lipids in milk. Notably, univariate monitoring of in-situ cholesterol in human serum was successfully achieved for the first time using deuterium water as an internal standard. In addition, silver substrate demonstrated outstanding reproducibility, maintaining consistent SERS activity even after more than 10 repetitions. Therefore, this platform offers the distinct advantages of high sensitivity, specificity and cost-effectiveness for lipid detection. These findings enable dietary management and blood lipid monitoring, and therefore hold crucial implications for the early prevention of lipid-related disorders and diseases.

High sensitivity and ultra-low concentration range photoacoustic spectroscopy based on trapezoid compound ellipsoid resonant photoacoustic cell and partial least square

A high sensitivity and ultra-low concentration range photoacoustic spectroscopy (PAS) gas detection system, which was based on a novel trapezoid compound ellipsoid resonant photoacoustic cell (TCER-PAC) and partial least square (PLS), was proposed to detect acetylene (C2H2) gas. In the concentration range of 0.5 ppm ∼ 10.0 ppm, the limit of detection (LOD) values of TCER-PAC-based PAS system without data processing was 66.4 ppb, which was lower than that of the traditional trapezoid compound cylindrical resonant photoacoustic cell (TCCR-PAC). The experimental results indicated that the TCER-PAC had higher sensitivity than of TCCR-PAC. Within the concentration range of 12.5 ppb ∼ 125.0 ppb, the LOD and limit of quantification (LOQ) of TCER-PAC-based PAS system combined with PLS regression algorithm were 1.1 ppb and 3.7 ppb, respectively. The results showed that higher detection sensitivity and lower LOD were obtained by PAS system with TCER-PAC and PLS than that of TCCR-PAC-based PAS system.

Acoustofluidic patterning in glass capillaries using travelling acoustic waves based on thin film flexible platform

Surface acoustic wave (SAW) technology has been widely used to manipulate microparticles and biological species, based on acoustic radiation force (ARF) and drag force induced by acoustic streaming, either by standing SAWs (SSAWs) or travelling SAWs (TSAWs). These acoustofluidic patterning functions can be achieved within a polymer chamber or a glass capillary with various cross-sections positioned along the wave propagating paths. In this paper, we demonstrated that microparticles can be aligned, patterned, and concentrated within both circular and rectangular glass capillaries using TSAWs based on a piezoelectric thin film acoustic wave platform. The glass capillary was placed at different angles along with the interdigital transducer directions. We systematically investigated effects of tilting angles and wave characteristics using numerical simulations in both circular and square shaped capillaries, and the patterning mechanisms were discussed and compared with those agitated under the SSAWs. We then experimentally verified the particle patterns within different glass capillaries using thin film ZnO SAW devices on aluminum (Al) sheets. Results show that the propagating SAWs can generate acoustic pressures and patterns in the fluid due to the diffractive effects, drag forces and ARF, as functions of the SAW device's resonant frequency and tilting angle. We demonstrated potential applications using this multiplexing, integrated, and flexible thin film-based platform, including patterning particles (1) inside multiple and successively positioned circular tubes; (2) inside a solidified hydrogel in the glass capillary; and (3) by wrapping a flexible ZnO/Al SAW device around the glass capillary.

High-precision prediction of blood glucose concentration utilizing Fourier transform Raman spectroscopy and an ensemble machine learning algorithm

Raman spectroscopy has gained popularity in analyzing blood glucose levels due to its non-invasive identification and minimal interference from water. However, the challenge lies in how to accurately predict blood glucose concentrations in human blood using Raman spectroscopy. This paper researches a novel integrated machine learning algorithm called Bagging-ABC-ELM. The optimal input weights and biases of extreme learning machine (ELM) model are obtained by artificial bee colony (ABC) algorithm. The bagging algorithm is used to obtain a better the stability of the model and higher performance than ELM algorithm. The results show that the mean value of coefficient of determination is 0.9928, and root mean square error is 0.1928. Compared to other regression models, the Bagging-ABC-ELM model exhibited superior prediction accuracy, robustness, and generalization capability. The Bagging-ABC-ELM model presents a promising alternative for analyzing blood glucose levels in clinical and research settings.