Dual-optimized adaptive Kalman filtering algorithm based on BP neural network and variance compensation for laser absorption spectroscopy

Real-time breath gas analysis of methane using a multipass cell-based near-infrared gas sensor

We demonstrated a near-infrared exhaled breath sensor for real-time methane measurements by using tunable diode laser absorption spectroscopy (TDLAS), which can enable the noninvasive diagnosis of intestinal tract problems. The core component of the near-infrared TDLAS sensor is a two-mirror-based multipass cell with nine-circle patterns. An optical path length of 23.4 m was achieved in a volume of 233.3 cm3, which effectively improved the detection sensitivity and shortened the gas exchange time. The minimum detection limit was 0.37 ppm by applying wavelength modulation spectroscopy, which was 12.4 times greater than that of direct absorption spectroscopy. In addition, combined with wavelength modulation spectroscopy, the two-mirror-based multipass cell enabled sub-second gas exchange time of 0.6 s. Methane breath experiments were conducted with six volunteers, and the real-time measurement results and concentrations at the end of exhalation were analyzed. This study demonstrates that the developed sensor has high sensitivity, high selectivity, and fast response for breath methane measurements and has promising potential for noninvasive, real-time, and point-of-care disease diagnosis in clinical applications.

Highly sensitive mid-infrared methane remote sensor using a deep neural network filter

A novel mid-infrared methane remote sensor integrated on a movable platform based on a 3.291-µm interband cascade laser (ICL) and wavelength modulation spectroscopy (WMS) is proposed. A transmitting-receiving coaxial, visualized optical layout is employed to minimize laser energy loss. Using a hollow retro-reflector remotely deployed as a cooperative target, the atmospheric average methane concentration over a 100-meter optical range is measured with high sensitivity. A deep neural network (DNN) filter is used for second harmonic (2f) signal denoising to compensate for the performance shortcomings of conventional filtering. Allan deviation analysis indicated that after applying the DNN filter, the limit of detection (LOD) of methane was 86.62 ppb with an average time of 1 s, decreasing to 12.03 ppb with an average time of 229 s, which is a significant promotion compared to similar work reported. The high sensitivity and stability of the proposed sensor are shown through a 24-hour continuous monitoring experiment of atmospheric methane conducted outdoors, providing a new solution for high-sensitivity remote sensing of atmospheric methane.

End-to-end methane gas detection algorithm based on transformer and multi-layer perceptron

In this paper, an end-to-end methane gas detection algorithm based on transformer and multi-layer perceptron (MLP) for tunable diode laser absorption spectroscopy (TDLAS) is presented. It consists of a Transformer-based U-shaped Neural Network (TUNN) filtering algorithm and a concentration prediction network (CPN) based on MLP. This algorithm employs an end-to-end architectural design to extract information from noisy transmission spectra of methane and derive the CH4 concentrations from denoised spectra, without intermediate steps. The results demonstrate the superiority of the proposed TUNN filtering algorithm over other typically employed digital filters. For concentration prediction, the determination coefficient (R2) reached 99.7%. Even at low concentrations, R2 remained notably high, reaching up to 89%. The proposed algorithm results in a more efficient, convenient, and accurate spectral data processing for TDLAS-based gas sensors.

Method of adaptive wide dynamic range gas concentration detection based on optimized direct absorption spectroscopy

For wide dynamic range gas concentration detection based on tunable diode laser absorption spectroscopy (TDLAS), direct absorption spectroscopy (DAS) and wavelength modulation spectroscopy (WMS) are usually used in combination. However, in some application scenarios such as high-speed flow field detection, natural gas leakage, or industrial production, the requirements of wide-range, fast response and calibration-free must be met. Taking applicability and cost of TDALS-based sensor into consideration, a method of optimized direct absorption spectroscopy (ODAS) based on signal correlation and spectral reconstruction is developed in this paper. This method can achieve adaptive selection of the optimal benchmark spectrum for spectral reconstruction. Moreover, methane (CH₄) is taken as an example to carry out the experimental verification. Experimental results proved that the method satisfies wide dynamic range detection of more than 4 orders of magnitude. It is worth noting that when measuring large absorbance with concentration of 75 × 10⁴ppm with DAS and ODAS method, respectively, the maximum value of residual is reduced from 3.43 to 0.07. Furthermore, whether measuring gas of small or large absorbance with different concentrations, which vary from 100 ppm to 75 × 10⁴ppm, the correlation coefficient between standard concentrations and inverted concentrations is 0.997, showing the linear consistency of the method in wide dynamic range. In addition, the absolute error is 1.81 × 10⁴ppm when measuring large absorbance of 75 × 10⁴ppm. It greatly improves the accuracy and reliability with the new method. In summary, the ODAS method can not only fulfill the measurement of gas concentration in wide range, but also further expand the application prospects of TDLAS.

Green Supply Chain Optimization Based on BP Neural Network

With the emergence and development of the Back Propagation neural network (BPNN), its unique learning, generalization, and non-linear characteristics have been gradually excavated and fully applied in the field of prediction. To improve the economic and green benefits of enterprises, the BPNN algorithm is applied to the green supply chain assisted by intelligent logistics robots. The BPNN algorithm can be used to output the characteristics of different information and optimize the green supply chain according to the input parameters and the influencing factors in the network. Firstly, an evaluation index system is established for selecting suppliers, which includes 4 first-level indicators: operational indicators, economic indicators, green indicators, social indicators, and 14 corresponding secondary indicators. Secondly, the evaluation indicator system is modeled through the BPNN. Finally, using the BPNN model, a supply chain enterprise's selection of cooperative enterprises in Xi'an is taken as the research object and simulation. Finally, the output results of the five alternative enterprises are 0.77, 0.75, 0.68, 0.72, and 0.65, respectively. The enterprise with the highest output results is selected as the cooperative enterprise and the enterprise with the second highest output results as an alternate. The green supply chain model based on the proposed BPNN is scientific and effective through specific simulation experiments. It has certain reference significance for the relevant issues related to subsequent optimization of the green supply chain.

The Construction of an Action-Speech Feature-Based School Violence Recognition Algorithm and Occupational Therapy Education Model for Adolescents

This paper constructs an algorithm for youth school violence recognition and an occupational therapy education model for victims through the extraction of action speech features. For the characteristics of violent actions and daily actions, action features in time and frequency domains are extracted and action categories are recognized by BP neural network; for complex actions, it is proposed to decompose complex actions into basic actions to improve the recognition rate; then, LDA dimensionality reduction algorithm is introduced for the problem of the high complexity of algorithm due to high dimensionality of features, and the feature dimensionality is reduced to 8 dimensions by LDA dimensionality reduction algorithm, which reduces the system running time by about 51% and improves the accuracy of violent action recognition by 3.3% while ensuring the overall performance of the system. The LDA dimensionality reduction algorithm reduces the number of features to 8 dimensions, which reduces the running time of the system by 51%, increases the accuracy rate of violent action recognition by 3.3%, and increases the recall rate of violent action recognition by 8.86% while ensuring the overall performance of the system. Based on the classical D-S theory, we proposed an improved D-S evidence fusion algorithm by modifying the original evidence model with a new probability distribution function and constructing new fusion rules, which can solve the fusion conflict problem well. The recall rate for violent actions is increased to 90.0%, thus reducing the missed alarm rate of the system.

Polarized light compass-aided inertial navigation under discontinuous observations environment

In recent years, integrated polarized light/inertial heading measurement systems have been widely used to obtain autonomous heading measurements of small unmanned combat platforms in the case of satellite navigation rejection. However, existing polarized light/inertial heading measurement systems have certain limitations. For example, they can only measure the heading angle in environments where continuous observations can be obtained. When encountering a complex environment with trees and/or tall buildings, the measured heading angle will contain sharp noise which greatly affects its accuracy. In particular, when encountering an underpass, it will lead to the complete loss of lock of the polarized light compass signal. Therefore, for the problem of sharp noise arising from a complex environment, a robust Cubature Kalman filter (CKF) data-fusion algorithm is proposed and verified by experiments. It is proved that the robust CKF algorithm has a certain ability to filter out the effects of poor measurements. After application of the robust CKF algorithm, the Root Mean Square Error (RMSE) of the heading angle reaches 0.3612°. This method solves the problem of low precision and poor stability of the polarized light/inertial system when high buildings and/or trees are contained in a complex environment. Next, in view of the problem that the polarized light compass signal is completely lost due to passing through an underground passage, a random forest regression (RFR) neural network model is established and introduced into the combined system. Simulated and outdoor experiments are carried out to verify the designed model using data obtained with a vehicle. The RMSE of the heading angle obtained in the experiment is 1.1894°, which solves the problem that the polarized light/inertial system cannot utilize discontinuous observations when attempting to detect the carrier heading angle.

A multiobjective prediction model with incremental learning ability by developing a multi-source filter neural network for the electrolytic aluminium process

Improving current efficiency and reducing energy consumption are two important technical goals of the electrolytic aluminum process (EAP). However, because the process involves complex noise characteristics (i.e., unknown types, redundant distributions and variable forms), it is very difficult to accurately develop a multiobjective prediction model. To overcome this problem, in this paper, a novel framework of multiobjective incremental learning based on a multi-source filter neural network (MSFNN) is presented. The proposed framework first presents a “multi-source filter” (MSF) technique that utilizes the mean and variance in the unscented Kalman filter (UKF) to guide the importance function of the particle filter (PF) based on a density kernel estimation method. Then, the MSF is embedded in the mutated neural network to adjust weights in real time. Third, weights are calculated and normalized by a modified importance function, which is the basis for further optimizing a secondary sampling based on sampling importance resampling (SIR). Finally, the incremental learning model with two objectives (i.e., process power consumption and current efficiency) based on the MSFNN in the EAP is established. The presented framework has been verified by the real-world EAP and some closely related methods. All test results indicate that the MSFNN’s relative prediction errors of the above two objectives are controlled within 0.51% and 0.38%, respectively and prove that MSFNN has significant competitive advantages over other recent filtering network models. Successfully establishment of the proposed framework provides a model foundation for multiobjective optimization problems in the EAP.

Analysis and Design Multiple Layer Adaptive Kalman Filter Applied to Electro-Optical Infrared Payload Vision System

This study designs a trigger to determine the number of layers of a multi-layer adaptive Kalman filter and applies it to optoelectronic infrared payload system vision. This feature reduces the number of mechanically stabilized motors, equipment weight, CPU resources, and power for an electro-optical infrared payload system. The goal is to reduce the traditional use of multiple gyroscopes to perform calibration measurements on different gimbal frames by this design. In this study, mathematical modeling was carried out for the three-axis, three-frame camera stabilizer system, and the system foundation without motor and gimbal frame was established to achieve aperture-type camera mode. The exposure of the drone’s payload structure outside the aircraft can be reduced. This study provides the adaptive Kalman filter with the offset parameters of the camera image Minimum Output Sum of Squared Error and the three-axis degrees of freedom vector and angle data on the gyroscope. By using the image processing unit, the offset was corrected at each frame per second. The experimental results show that under the same hardware, failure limit and camera field of view constraints. The processing time by this method was compared to the traditional frame correction and full image stabilization methods. The results show that the proposed method can shorten 6 microseconds under the traditional method and can be used to provide lower power consumption, lower image delay, and a larger viewing angle range.

Adaptively Optimized Gas Analysis Model with Deep Learning for Near-Infrared Methane Sensors

Noise significantly limits the accuracy and stability of retrieving gas concentration with the traditional direct absorption spectroscopy (DAS). Here, we developed an adaptively optimized gas analysis model (AOGAM) composed of a neural sequence filter (NSF) and a neural concentration retriever (NCR) based on deep learning algorithms for extraction of methane absorption information from the noisy transmission spectra and obtaining the corresponding concentrations from the denoised spectra. The model was trained on two data sets, including a computationally generated one and the experimental one. We have applied this model for retrieving methane concentration from its transmission spectra in the near-infrared (NIR) region. The NSF was implemented through an encoder-decoder structure enhanced by the attention mechanism, improving robustness under noisy conditions. Further, the NCR was employed based on a combination of a principal component analysis (PCA) layer, which focuses the algorithm on the most significant spectral components, and a fully connected layer for solving the nonlinear inversion problem of the determination of methane concentration from the denoised spectra without manual computation. Evaluation results show that the proposed NSF outperforms widely used digital filters as well as the state-of-the-art filtering algorithms, improving the signal-to-noise ratio by 7.3 dB, and the concentrations determined with the NCR are more accurate than those determined with the traditional DAS method. With the AOGAM enhancement, the optimized methane sensor features precision and stability in real-time measurements and achieves the minimum detectable column density of 1.40 ppm·m (1σ). The promising results of the present study demonstrate that the combination of deep learning and absorption spectroscopy provides a more effective, accurate, and stable solution for a gas monitoring system.

Optimized adaptive Savitzky-Golay filtering algorithm based on deep learning network for absorption spectroscopy

An improved Savitzky-Golay (S-G) filtering algorithm was developed to denoise the absorption spectroscopy of nitrogen oxide (NO₂). A deep learning (DL) network was introduced to the traditional S-G filtering algorithm to adjust the window size and polynomial order in real time. The self-adjusting and follow-up actions of DL network can effectively solve the blindness of selecting the input filter parameters in digital signal processing. The developed adaptive S-G filter algorithm is compared with the multi-signal averaging filtering (MAF) algorithm to demonstrate its performance. The optimized S-G filtering algorithm is used to detect NO₂ in a mid-quantum-cascade-laser (QCL) based gas sensor system. A sensitivity enhancement factor of 5 is obtained, indicating that the newly developed algorithm can generate a high-quality gas absorption spectrum for applications such as atmospheric environmental monitoring and exhaled breath detection.

Optimization of Human Motion Recognition Information Processing System Based on GA-BP Neural Network Algorithm

At present, there are some problems in the process of human motion recognition, such as poor timeliness and low fault tolerance rate. How to effectively identify the motion process accurately has become a hot spot in the optimization system. In the existing research studies, the recognition accuracy is not very good and the response time is long. To end this issue, the paper proposed an information processing system and optimization method of human motion recognition based on the GA-BP neural network algorithm. Firstly, a human motion recognition system based on dynamic capture recognition technology is designed, which realizes the recognition of motion information from common postures such as action span, speed change, motion trajectory, and other aspects in the process of human motion. Secondly, the proposed algorithm is used to comprehensively analyse and evaluate the motion state. Finally, experiments are designed to verify and analyse the results. Compared to some baseline methods in human motion recognition information systems, the system in this paper based on the GA-BP neural network algorithm has the advantages of higher data accuracy and response speed, which can quickly and accurately identify the muscle group change in the process of human motion, and it can also provide customized motion suggestions based on the results.

Non-Local Patch Regression Algorithm-Enhanced Differential Photoacoustic Methodology for Highly Sensitive Trace Gas Detection

A non-local patch regression (NLPR) denoising-enhanced differential broadband photoacoustic (PA) sensor was developed for the high-sensitive detection of multiple trace gases. Using the edge preservation index (EPI) and signal-to-noise ratio (SNR) as a dual-criterion, the fluctuation was dramatically suppressed while the spectral absorption peaks were maintained by the introduction of a NLPR algorithm. The feasibility of the broadband framework was verified by measuring the C2H2 in the background of ambient air. A normalized noise equivalent absorption (NNEA) coefficient of 6.13 × 10−11 cm−1·W·Hz−1/2 was obtained with a 30-mW globar source and a SNR improvement factor of 23. Furthermore, the simultaneous multiple-trace-gas detection capability was determined by measuring C2H2, H2O, and CO2. Following the guidance of single-component processing, the NLPR processed results showed higher EPI and SNR compared to the spectra denoised by the wavelet method and the non-local means algorithm. The experimentally determined SNRs of the C2H2, H2O, and CO2 spectra were improved by a factor of 20. The NNEA coefficient reached a value of 7.02 × 10−11 cm−1·W·Hz−1/2 for C2H2. The NLPR algorithm presented good performance in noise suppression and absorption peak fidelity, which offered a higher dynamic range and was demonstrated to be an effective approach for trace gas analysis.

Music Emotion Analysis Based on PSO-BP Neural Network and Big Data Analysis

The current music teaching can effectively improve students' music emotional expression indirectly. How to use the PSO-BP neural network to realize the quantitative research of music emotional expression is the current development trend. Based on this, this paper studies the influence factors of music emotion expression based on PSO-BP neural network and big data analysis. Firstly, a music emotion expression analysis model based on PSO-BP neural network algorithm is proposed. The autocorrelation function is used to simulate the emotion expression information in music. Through the maximum value of the autocorrelation function curve in the detection process, the vocal music signal is restored, and then the emotion expressed is analyzed. Secondly, the influence factors of PSO-BP neural network algorithm in music emotion expression are analyzed. The improved PSO-BP neural network algorithm and multidimensional data model are used for comprehensive analysis to accurately analyze the emotion in music expression, and the fuzzy evaluation method and analytic hierarchy process are used for quality evaluation. Finally, the validity of the music emotion analysis model is verified by many experiments.

Sports Action Recognition Based on GB-BP Neural Network and Big Data Analysis

In recent years, the application of the gradient boosting-back propagation (GB-BP) neural network algorithm in many industries has brought huge benefits, so how to combine the GB-BP neural network algorithm with sports has become a research hotspot. Based on this, this paper studies the application of the GB-BP neural network algorithm in wrestling, designs the sports athletes action recognition and classification model based on the GB-BP neural network algorithm, first analyzes the research status of wrestling action recognition, and then optimizes and improves the shortcomings of action recognition and big data analysis technology. The GB-BP neural network algorithm can realize the accurate recognition and classification of wrestlers' training actions and carry out big data mining analysis with known action recognition, so as to achieve accurate classification. The experimental results show that the model can play a good role in wrestling and effectively improve the efficiency of wrestlers in training.

Determination of Bridge Prestress Loss under Fatigue Load Based on PSO-BP Neural Network

During the service period of a prestressed concrete bridge, as the number of cyclic loads increases, cumulative fatigue damage and prestress loss will occur inside the structure, which will affect the safety, durability, and service life of the structure. Based on this, this paper studies the loss of bridge prestress under fatigue load. First, the relationship between the prestress loss of the prestressed tendons and the residual deflection of the test beam is analyzed. Based on the test results and the main influencing factors of fatigue and creep, a concrete fatigue and creep calculation model is proposed; then, based on the static cracking check calculation method and POS-BP neural network algorithm, a prestressed concrete beam fatigue cracking check model under repeated loads is proposed. Finally, the mechanical performance of the prestressed concrete beam after fatigue loading is analyzed, and the influence of the fatigue load on the bearing capacity of the prestressed concrete beam is explored. The results show that the bridge prestress loss characterization model based on the POS-BP neural network algorithm has the advantages of high calculation efficiency and strong applicability.

A Critical Review of Methods for Analyzing Freshwater Eutrophication

Water eutrophication is a global environmental problem that poses serious threats to aquatic ecosystems and human health. The evaluation of eutrophication provides a theoretical basis and technical guidance for the management and rehabilitation of water ecosystems. In the last four decades, dozens of evaluation methods have been applied to freshwater eutrophication, but there is a clear need to optimize and standardize the most suitable methods. We have addressed this gap by presenting a systematic review of methodologies. Due to the diversity and complexity of water bodies, no single evaluation method was identified that would adequately represent eutrophication under all scenarios. We demonstrate that lakes can best be assessed using the trophic level index (TLI) method, reservoirs and wetlands the trophic state index (TSI) and fuzzy comprehensive evaluation (FCE) method, respectively, and rivers the FCE method or back propagation (BP) neural network methods. More recently applied methodologies including spectral imaging and 3-D mapping of water quality using underwater gliders allow greater resolution and can be effective in managing waterbodies to avoid future eutrophication. The aim of this review is to guide future studies on the most appropriate methods available for assessing and reporting water eutrophication.