Quantitative Analysis of Gas Phase IR Spectra Based on Extreme Learning Machine Regression Model

An Artificial Neural Network to Eliminate the Detrimental Spectral Shift on Mid-Infrared Gas Spectroscopy

We demonstrate the successful implementation of an artificial neural network (ANN) to eliminate detrimental spectral shifts imposed in the measurement of laser absorption spectrometers (LASs). Since LASs rely on the analysis of the spectral characteristics of biological and chemical molecules, their accuracy and precision is especially prone to the presence of unwanted spectral shift in the measured molecular absorption spectrum over the reference spectrum. In this paper, an ANN was applied to a scanning grating-based mid-infrared trace gas sensing system, which suffers from temperature-induced spectral shifts. Using the HITRAN database, we generated synthetic gas absorbance spectra with random spectral shifts for training and validation. The ANN was trained with these synthetic spectra to identify the occurrence of spectral shifts. Our experimental verification unambiguously proves that such an ANN can be an excellent tool to accurately retrieve the gas concentration from imprecise or distorted spectra of gas absorption. Due to the global shift of the measured gas absorption spectrum, the accuracy of the retrieved gas concentration using a typical least-mean-squares fitting algorithm was considerably degraded by 40.3%. However, when the gas concentration of the same measurement dataset was predicted by the proposed multilayer perceptron network, the sensing accuracy significantly improved by reducing the error to less than ±1% while preserving the sensing sensitivity.

The research on TBATS and ELM models for prediction of human brucellosis cases in mainland China: a time series study

BACKGROUND

Human brucellosis is a serious public health concern in China. The objective of this study is to develop a suitable model for forecasting human brucellosis cases in mainland China.

METHODS

Data on monthly human brucellosis cases from January 2012 to December 2021 in 31 provinces and municipalities in mainland China were obtained from the National Health Commission of the People's Republic of China website. The TBATS and ELM models were constructed. The MAE, MSE, MAPE, and RMSE were calculated to evaluate the prediction performance of the two models.

RESULTS

The optimal TBATS model was TBATS (1, {0,0}, -, {< 12,4 >}) and the lowest AIC value was 1854.703. In the optimal TBATS model, {0,0} represents the ARIMA (0,0) model, {< 12,4 >} are the parameters of the seasonal periods and the corresponding number of Fourier terms, respectively, and the parameters of the Box-Cox transformation ω are 1. The optimal ELM model hidden layer number was 33 and the R-squared value was 0.89. The ELM model provided lower values of MAE, MSE, MAPE, and RMSE for both the fitting and forecasting performance.

CONCLUSIONS

The results suggest that the forecasting performance of ELM model outperforms the TBATS model in predicting human brucellosis between January 2012 and December 2021 in mainland China. Forecasts of the ELM model can help provide early warnings and more effective prevention and control measures for human brucellosis in mainland China.

Infrared Spectroscopy–Quo Vadis?

Given the exquisite capability of direct, non-destructive label-free sensing of molecular transitions, IR spectroscopy has become a ubiquitous and versatile analytical tool. IR application scenarios range from industrial manufacturing processes, surveillance tasks and environmental monitoring to elaborate evaluation of (bio)medical samples. Given recent developments in associated fields, IR spectroscopic devices increasingly evolve into reliable and robust tools for quality control purposes, for rapid analysis within at-line, in-line or on-line processes, and even for bed-side monitoring of patient health indicators. With the opportunity to guide light at or within dedicated optical structures, remote sensing as well as high-throughput sensing scenarios are being addressed by appropriate IR methodologies. In the present focused article, selected perspectives on future directions for IR spectroscopic tools and their applications are discussed. These visions are accompanied by a short introduction to the historic development, current trends, and emerging technological opportunities guiding the future path IR spectroscopy may take. Highlighted state-of-the art implementations along with novel concepts enhancing the performance of IR sensors are presented together with cutting-edge developments in related fields that drive IR spectroscopy forward in its role as a versatile analytical technology with a bright past and an even brighter future.

Nondestructive determination of SSC in an apple by using a portable near-infrared spectroscopy system

The soluble solids content (SSC) is an important factor in the internal quality detection of apples. It is essential to have reliable and high-speed measurement of the SSC. However, almost all traditional equipment is inconvenient and expensive. We designed a handheld nondestructive SSC detector based on near-infrared (NIR) spectroscopy, which is composed of a portable NIR spectrometer, cloud server, smartphone app, and prediction model of SSC. We preprocessed the spectrum with multiplicative scatter correction (MSC), standard normal variable transformation (SNV), and Savitzky-Golay (S-G) smoothing algorithms. Besides, the linear weight reduction of the particle swarm optimization algorithm is carried out, and we establish the model of an extreme learning machine optimized with the improved particle swarm optimization (IPSO-ELM) algorithm. The R², root mean square error of prediction (RMSEP), and residual prediction deviation (RPD) of the model are 0.993, 0.0155, and 11.6, respectively, which are better than the traditional model obviously. In addition, the number of wavelengths reduced from 228 to 70 as the model is simplified with the uninformative variable elimination (UVE) method. The time of training is reduced by 29.30% compared with the original spectrum. It can be verified that the IPSO-ELM model has good prediction performance, and the NIR diffuse reflectance spectroscopy is a reliable nondestructive measurement of SSC in apples.

Towards the direct detection of viral materials at the surface of protective face masks via infrared spectroscopy

The ongoing COVID-19 pandemic represents a considerable risk for the general public and especially for health care workers. To avoid an overloading of the health care system and to control transmission chains, the development of rapid and cost-effective techniques allowing for the reliable diagnosis of individuals with acute respiratory infections are crucial. Uniquely, the present study focuses on the development of a direct face mask sampling approach, as worn (i.e., used) disposable face masks contain exogenous environmental constituents, as well as endogenously exhaled breath aerosols. Optical techniques—and specifically infrared (IR) molecular spectroscopic techniques—are promising tools for direct virus detection at the surface of such masks. In the present study, a rapid and non-destructive approach for monitoring exposure scenarios via medical face masks using attenuated total reflection infrared spectroscopy is presented. Complementarily, IR external reflection spectroscopy was evaluated in comparison for rapid mask analysis. The utility of a face mask-based sampling approach was demonstrated by differentiating water, proteins, and virus-like particles sampled onto the mask. Data analysis using multivariate statistical algorithms enabled unambiguously classifying spectral signatures of individual components and biospecies. This approach has the potential to be extended towards the rapid detection of SARS-CoV-2—as shown herein for the example of virus-like particles which are morphologically equivalent to authentic virus—without any additional sample preparation or elaborate testing equipment at laboratory facilities. Therefore, this strategy may be implemented as a routine large-scale monitoring routine, e.g., at health care institutions, nursing homes, etc. ensuring the health and safety of medical personnel.

Rapid Quantitative Analysis of IR Absorption Spectra for Trace Gas Detection by Artificial Neural Networks Trained with Synthetic Data

Infrared absorption spectroscopy is a widely used tool to quantify and monitor compositions of gases. The concentration information is often retrieved by fitting absorption profiles to the acquired spectra, utilizing spectroscopic databases. In complex gas matrices an expanded parameter space leads to long computation times of the fitting routines due to the increased number of spectral features that need to be computed for each iteration during the fit. This hinders the capability of real-time analysis of the gas matrix. Here, an artificial neural network (ANN) is employed for rapid prediction of gas concentrations in complex infrared absorption spectra composed of mixtures of CO and N₂O. Experimental data is acquired with a mid-infrared dual frequency comb spectrometer. To circumvent the experimental collection of huge amounts of training data, the network is trained on synthetically generated spectra. The spectra are based on simulated absorption profiles making use of the HITRAN database. In addition, the spectrometer’s influence on the measured spectra is characterized and included in the synthetic training data generation. The ANN was tested on measured spectra and compared to a non-linear least squares fitting algorithm. An average evaluation time of 303 µs for a single measured spectrum was achieved. Coefficients of determination were 0.99997 for the predictions of N₂O concentrations and 0.99987 for the predictions of CO concentrations, with uncertainties on the predicted concentrations between 0.04 and 0.18 ppm for 0 to 100 ppm N₂O and between 0.05 and 0.18 ppm for 0 to 60 ppm CO.

Machine Learning Predictions of Transition Probabilities in Atomic Spectra

Forward modeling of optical spectra with absolute radiometric intensities requires knowledge of the individual transition probabilities for every transition in the spectrum. In many cases, these transition probabilities, or Einstein A-coefficients, quickly become practically impossible to obtain through either theoretical or experimental methods. Complicated electronic orbitals with higher order effects will reduce the accuracy of theoretical models. Experimental measurements can be prohibitively expensive and are rarely comprehensive due to physical constraints and sheer volume of required measurements. Due to these limitations, spectral predictions for many element transitions are not attainable. In this work, we investigate the efficacy of using machine learning models, specifically fully connected neural networks (FCNN), to predict Einstein A-coefficients using data from the NIST Atomic Spectra Database. For simple elements where closed form quantum calculations are possible, the data-driven modeling workflow performs well but can still have lower precision than theoretical calculations. For more complicated nuclei, deep learning emerged more comparable to theoretical predictions, such as Hartree–Fock. Unlike experiment or theory, the deep learning approach scales favorably with the number of transitions in a spectrum, especially if the transition probabilities are distributed across a wide range of values. It is also capable of being trained on both theoretical and experimental values simultaneously. In addition, the model performance improves when training on multiple elements prior to testing. The scalability of the machine learning approach makes it a potentially promising technique for estimating transition probabilities in previously inaccessible regions of the spectral and thermal domains on a significantly reduced timeline.

FPGA-Based Implementation of Stochastic Configuration Networks for Regression Prediction

The implementation of neural network regression prediction based on digital circuits is one of the challenging problems in the field of machine learning and cognitive recognition, and it is also an effective way to relieve the pressure of the Internet in the era of intelligence. As a nonlinear network, the stochastic configuration network (SCN) is considered to be an effective method for regression prediction due to its good performance in learning and generalization. Therefore, in this paper, we adapt the SCN to regression analysis, and design and verify the field programmable gate array (FPGA) framework to implement SCN model for the first time. In addition, in order to improve the performance of the SCN model based on the FPGA, the implementation of the nonlinear activation function on the FPGA is optimized, which effectively improves the prediction accuracy while considering the utilization rate of hardware resources. Experimental results based on the simulation data set and the real data set prove that the proposed FPGA framework successfully implements the SCN regression prediction model, and the improved SCN model has higher accuracy and a more stable performance. Compared with the extreme learning machine (ELM), the prediction performance of the proposed SCN implementation model based on the FPGA for the simulation data set and the real data set is improved by 56.37% and 17.35%, respectively.