Hybrid Filtering Compensation Algorithm for Suppressing Random Errors in MEMS Arrays

To solve the high error phenomenon of microelectromechanical systems (MEMS) due to their poor signal-to-noise ratio, this paper proposes an online compensation algorithm wavelet threshold back-propagation neural network (WT-BPNN), based on a neural network and designed to effectively suppress the random error of MEMS arrays. The algorithm denoises MEMS and compensates for the error using a back propagation neural network (BPNN). To verify the feasibility of the proposed algorithm, we deployed it in a ZYNQ-based MEMS array hardware. The experimental results showed that the zero-bias instability, angular random wander, and angular velocity random wander of the gyroscope were improved by about 12 dB, 10 dB, and 7 dB, respectively, compared with the original device in static scenarios, and the dispersion of the output data was reduced by about 8 dB in various dynamic environments, which effectively verified the robustness and feasibility of the algorithm.

Sensitivity Analysis of Influencing Factors and Two-Stage Prediction of Frost Resistance of Active-Admixture Recycled Concrete Based on Grey Theory-BPNN

Sensitivity analysis of influencing factors on frost resistance is carried out in this paper, and a two-stage neural network model based on grey theory and Back Propagation Neural Networks (BPNNs) is established for the sake of predicting the frost resistance of active-admixture recycled concrete quickly and accurately. Firstly, the influence degree of cement, water, sand, natural aggregate, recycled aggregate, mineral powder, fly ash, fiber and air-entraining agent on the frost resistance of active-admixture recycled-aggregate concrete was analyzed based on the grey system theory, and the primary and secondary relationships of various factors were effectively distinguished. Then, the input layer of the model was determined as cement, water, sand, recycled aggregate and air-entraining agent, and the output layer was the relative dynamic elastic modulus. A total of 120 datasets were collected from the experimental data of another author, and the relative dynamic elastic modulus was predicted using the two-stage BPNN prediction model proposed in this paper and compared with the BPNN prediction results. The results show that the proposed two-stage BPNN model, after removing less-sensitive parameters from the input layer, has better prediction accuracy and shorter run time than the BPNN model.

The optimization of college tennis training and teaching under deep learning

To enhance the integration of deep learning into tennis education and instigate reforms in sports programs, this paper employs deep learning techniques to analyze tennis tactics. The experiments initially introduce the concepts of sports science and backpropagation neural networks. Subsequently, these theories are applied to formulate a comprehensive system of tennis tactical diagnostic indicators, encompassing construction principles, basic requirements, diagnostic indicator content, and evaluation indicator design. Simultaneously, a Back Propagation Neural Network (BPNN) is utilized to construct a tennis tactical diagnostic model. The paper concludes with a series of experiments conducted to validate the effectiveness of the constructed indicator system and diagnostic model. The results indicate the excellent performance of the neural network model when trained on tennis match data, with a mean squared error of 0.00037146 on the validation set and 0.0104 on the training set. This demonstrates the outstanding predictive capability of the model. Additionally, the system proves capable of providing detailed tactical application analysis when employing the tennis tactical diagnostic indicator system for real-time athlete diagnosis. This functionality offers robust support for effective training and coaching during matches. In summary, this paper aims to evaluate athletes' performance by constructing a diagnostic system, providing a solid reference for optimizing tennis training and education. The insights offered by this paper have the potential to drive reforms in sports programs, particularly in the realm of tennis education.

Anti-interference detection of mixed NOX via In2O3-based sensor array combining with neural network model at room temperature

Herein, we report a noble metal doped In2O3-based sensor array applying back propagation neural network (BPNN) combined with whale optimization algorithm (WOA) toward anti-interference detection of mixed NOX. The synthesis (simple hydrothermal methods) and characterization (XRD, SEM, EDS and XPS) of Pt, Au and Pd doped In2O3 with different morphologies were reported. The three of In2O3-based sensors were systematically tested at room temperature to investigate the performance of sensitivity, response-recovery time, repeatability and selectivity to NO and NOX. Based on the sensor array composed of Pt, Au, and Pd doped In2O3 sensors combining WOA-BPNN prediction model, this work finally achieved the quantitative prediction of the components in the mixed NO and NOX under the influence of cross interference.

Comprehensive safety risk evaluation of fireworks production enterprises using the frequency-based ANP and BPNN

The fireworks industry has long struggled with the problem of safety. Scientific, reasonable, and operable evaluation models are prerequisites of reducing risk. Based on the data from over 100 fireworks production safety accidents in China from 2010 to 2022, two evaluation models were established from the perspective of safety risk definition. Firstly, a weight calculation derivative method, the frequency-based analytic network process (ANP), was proposed creatively. This method optimized the importance ranking index calculation process in the ANP by considering the causal frequency of risk factors in the historical accident samples, thus determining how much each indicator affects the likelihood of accidents. Secondly, utilizing the historical accident samples as the dataset, a back propagation neural network (BPNN) model was developed to extract the mathematical relationship between each risk factor and the severity of accident consequence. Finally, the frequency-based ANP and BPNN models were combined to determine the safety risk level of the fireworks production enterprises. Meanwhile, the safety evaluation research samples were used as the comparison set for empirical study with historical accident samples, involving 100 fireworks production enterprises in China evaluated from 2017 to 2020. The significance result of zero shows that there is a statistically significant difference between the likelihood evaluation results of the accident and non-accident companies. Additionally, the severity evaluation model exhibits an excellent result, revealing a classification accuracy of 98.21 %, a mean square error of 8.97 × 10-4, a percent bias of 1.24 %, and a correlation coefficient and Nash-Sutcliffe efficiency coefficient both of 0.96. The frequency-based ANP and BPNN models integrate self-learning, self-adaptive, and fuzzy information processing, obtaining more accurate and objective evaluation results. This work provides a new strategy for the promotion and application of artificial intelligence in the field of safety risk evaluation, thus offering real-time safety risk evaluation and decision support of the safety management for the enterprises.

Study on extraction technology and antioxidant activity of total alkaloids from Hemsleya chinensis based on orthogonal design and BP neural network

In this study, total alkaloids from Hemsleya chinensis were extracted and tested for their antioxidant properties. To optimize extraction methods, a single factor experiment was conducted to determine the total alkaloid concentrations of H. chinensis using the L9 (34) orthogonal design test method and the BP neural network (BPNN), resulting in the optimum extraction conditions for total alkaloids. The optimal conditions for H. chinensis alkaloids extraction with acid water are: HCl concentration is 0.50 %, extraction temperature is 85 °C, material-liquid ratio is 1:64.5, and extraction rate of alkaloids is 0.2785 ± 0.0003 mg/mL. The alkaloid from H. chinensis exhibited antioxidant activity in a quantity-effect relationship with activity. These findings showed that the procedure to be reasonable, the alkaloid extraction efficiency to be high, and the method could be used to extract the alkaloids of H. chinensis, improving the development of natural and healthy medicinal resources for the pharmaceutical and food industries.

A Double-Layer Vehicle Speed Prediction Based on BPNN-LSTM for Off-Road Vehicles

The accurate prediction of vehicle speed is crucial for the energy management of vehicles. The existing vehicle speed prediction (VSP) methods mainly focus on road vehicles and rarely on off-road vehicles. In this paper, a double-layer VSP method based on backpropagation neural network (BPNN) and long short-term memory (LSTM) for off-road vehicles is proposed. First of all, considering the motion characteristics of off-road vehicles, the VSP problem is established and the relationship between the variables in the problem is carefully analyzed. Then, the double-layer VSP framework is presented, which consists of speed prediction and information update layers. The speed prediction layer established by using LSTM is to predict vehicle speed in the horizon, and the information update layer built by BPNN is to update the prediction information. Finally, with the help of mining truck and loader operation scenarios, the proposed VSP method is compared with the analytical method, BPNN prediction method, and recurrent neural network (RNN) prediction method in terms of speed prediction accuracy. The results show that, under the premise of ensuring the real-time prediction performance, the average prediction error of the proposed BPNN-LSTM prediction method under two operation scenarios reduces by 48.14%, 35.82% and 30.09% compared with the other three methods, respectively. The proposed speed prediction method provides a new solution for predicting the speed of off-road vehicles, effectively improving the speed prediction accuracy.

A BPNN-based ecologically extended input-output model for virtual water metabolism network management of Kazakhstan

In this study, a back-propagation-neural-network-based ecologically extended input-output model (abbreviated as BPNN-EIOM) is developed for virtual water metabolism network (VWMN) management. BPNN-EIOM can identify key consumption sectors, simulate performance of VWMN, and predict water consumption. BPNN-EIOM is then applied to analyzing VWMN of Kazakhstan, where multiple scenarios under different gross domestic production (GDP) growth rates, sectoral added values, and final demands are designed for determining the optimal management strategies. The major findings are (i) Kazakhstan typically relies on net virtual water import (reaching 1497.9 × 10⁶ m³ in 2015); (ii) agriculture is the major exporter and advanced manufacture is the major importer; (iii) by 2025, Kazakhstan's water consumption would increase to [19322, 22016] × 10⁶ m³ under multiple scenarios; (iv) when Kazakhstan's GDP growth rate, manufacturing's added value, and final demand are scheduled to 5.5%, 8.5%, and 5.8%, its VWMN can reach the optimum. The findings are useful for decision makers to optimize Kazakhstan's industrial structure, mitigate the national water scarcity, and promote its socio-economic sustainable development.

Prediction Models of Shielding Effectiveness of Carbon Fibre Reinforced Cement-Based Composites against Electromagnetic Interference

With the rapid development of communication technology as well as a rapid rise in the usage of electronic devices, a growth of concerns over unintentional electromagnetic interference emitted by these devices has been witnessed. Pioneer researchers have deeply studied the relationship between the shielding effectiveness and a few mixed design parameters for cementitious composites incoporating carbon fibres by conducting physical experiments. This paper, therefore, aims to develop and propose a series of prediction models for the shielding effectiveness of cementitious composites involving carbon fibres using frequency and mixed design parameters, such as the water-to-cement ratio, fibre content, sand-to-cement ratio and aspect ratio of the fibres. A multi-variable non-linear regression model and a backpropagation neural network (BPNN) model were developed to meet the different accuracy requirements as well as the complexity requirements. The results showed that the regression model reached an R² of 0.88 with a root mean squared error (RMSE) of 2.3 dB for the testing set while the BPNN model had an R² of 0.96 with an RMSE of 2.64 dB. Both models exhibited a sufficient prediction accuracy, and the results also supported that both the regression and the BPNN model are reasonable for such estimation.

Prediction of production facility priorities using Back Propagation Neural Network for bus body building industries: a post pandemic research article

The pandemic recession has caused enormous disturbances in many industrialized countries. The massive disruption of the supply chain of production is affecting manufacturing companies operating in and around India. Particularly the medium-sized bus body building works have been reduced, due to its compound anomalies. The integrated view of the production facility priorities is not an easy task. Since it is difficult for available labour to conduct an entire project, the completion of a production process is delayed. But still, the dilemma remains as to how production managers can correctly interpret the priorities of the facility. Indeed, this is a problem missing from the previous study. Fortunately, in the current competitive environment, it is essentially needed. This study has been used Back Propagation Neural Network (BPNN) approach for predicting production facility priorities. The experimental results confirm the suitability of the model for predicting priorities. A real-world problem is taken into account in making use of the model output. In this sense, this total solution facilitates production managers in assessing and enhancing the production facilities. The findings emphasize the priority of "equipment effectiveness, labour scheduling and communication" in order to strengthen the post-pandemic production facility.

BPNN-Based Behavioral Modeling of the S-Parameter Variation Characteristics of PAs with Frequency at Different Temperatures

To address the issue of frequency nonlinearity modeling of RF PAs, which is rarely seen in the literature, a BPNN is applied to model the frequency nonlinearity of RF PAs in this paper. The BPNN is used to model the frequency nonlinearity of the RF PA, based on the actual measured S-parameter data at different ambient temperatures. The modeling results show that BPNN shows the advantage of a high accuracy in modeling the frequency nonlinearity of RF PAs. It is expected that a BPNN will also show the advantages of a high accuracy in the modeling process of other RF devices or circuits.

Probing 1D convolutional neural network adapted to near-infrared spectroscopy for efficient classification of mixed fish

Salmon and Cod are economically significant world-class fish that have high economic value. It is difficult to accurately sort and process them by appearance during harvest and transportation. Conventional chemical detection means are time-consuming and costly, which greatly affects the cost and efficiency of Fishery production. Therefore, there is an urgent need for smart Fisheries methods which use for the classification of mixed fish. In this paper, near-infrared spectroscopy (NIRS) was used to assess salmon and cod samples. This study aims to evaluate feasibility of a back-propagation neural network (BPNN) and a convolutional neural network (CNN) for identifying different species of fishes by the corresponding spectra in comparison to traditional chemometrics Partial Least Squares. After comparing the effects of different batch sizes, number of convolutional kernels, number of convolutional layers, and number of pooling layers on the classification of NIRS spectra comparing different structures of one-dimensional (1D)-CNN, we propose the 1D-CNN-8 model that is most suitable for the classification of mixed fish. Compared with the results of traditional chemometrics methods and BPNN, the prediction model of the 1D-CNN model can reach 98.00% Accuracy and the parameters are significantly better than others. Meanwhile, the parameters and floating-point operations of the optimal model are both small. Therefore, the improved CNN model based on the NIRS can effectively and quickly identify different kinds of fish samples and contribute to realizing edge computing at the same time.

Time series analysis of rubella incidence in Chongqing, China using SARIMA and BPNN mathematical models

INTRODUCTION

Chongqing is among the areas with the highest rubella incidence rates in China. This study aimed to analyze the temporal distribution characteristics of rubella and establish a forecasting model in Chongqing, which could provide a tool for decision-making in the early warning system for the health sector.

METHODOLOGY

The rubella monthly incidence data from 2004 to 2019 were obtained from the Chongqing Center of Disease and Control. The incidence from 2004 to June 2019 was fitted using the seasonal autoregressive integrated moving average (SARIMA) model and the back-propagation neural network (BPNN) model, and the data from July to December 2019 was used for validation.

RESULTS

A total of 30,083 rubella cases were reported in this study, with a significantly higher average annual incidence before the nationwide introduction of rubella-containing vaccine (RCV). The peak of rubella notification was from April to June annually. Both SARIMA and BPNN models were capable of predicting the expected incidence of rubella. However, the linear SARIMA model fits and predicts better than the nonlinear BPNN model.

CONCLUSIONS

Based on the results, rubella incidence in Chongqing has an obvious seasonal trend, and SARIMA (2,1,1) × (1,1,1) 12 model can predict the incidence of rubella well. The SARIMA model is a feasible tool for producing reliable rubella forecasts in Chongqing.

A Design of FPGA-Based Neural Network PID Controller for Motion Control System

In the actual industrial production process, the method of adaptively tuning proportional–integral–derivative (PID) parameters online by neural network can adapt to different characteristics of different controlled objects better than the controller with PID. However, the commonly used microcontroller unit (MCU) cannot meet the application scenarios of real time and high reliability. Therefore, in this paper, a closed-loop motion control system based on BP neural network (BPNN) PID controller by using a Xilinx field programmable gate array (FPGA) solution is proposed. In the design of the controller, it is divided into several sub-modules according to the modular design idea. The forward propagation module is used to complete the forward propagation operation from the input layer to the output layer. The PID module implements the mapping of PID arithmetic to register transfer level (RTL) and is responsible for completing the output of control amount. The main state machine module generates enable signals that control the sequential execution of each sub-module. The error backpropagation and weight update module completes the update of the weights of each layer of the network. The peripheral modules of the control system are divided into two main parts. The speed measurement module completes the acquisition of the output pulse signal of the encoder and the measurement of the motor speed. The pulse width modulation (PWM) signal generation module generates PWM waves with different duty cycles to control the rotation speed of the motor. A co-simulation of Modelsim and Simulink is used to simulate and verify the system, and a test analysis is also performed on the development platform. The results show that the proposed system can realize the self-tuning of PID control parameters, and also has the characteristics of reliable performance, high real-time performance, and strong anti-interference. Compared with MCU, the convergence speed is far more than three orders of magnitude, which proves its superiority.

Classification modeling method for hyperspectral stamp-pad ink data based on one-dimensional convolutional neural network

In the questioned document, the examination of stamp-pad ink is crucial scientific evidence to discern the difference between genuine and forged documents. In this study, a new method for rapid and non-destructive identification of types of stamp-pad inks by combining hyperspectral imaging (HSI) technology and deep learning was developed. Twenty stamp-pad inks of different brands and models were collected and numbered in turn, and then, each of them was sealed six times repeatedly on the A4 printing paper for the test. After that, the hyperspectral imager was used to collect the hyperspectral images and the reflectance spectral data were obtained after pixel fusion. Principal component analysis (PCA) and non-negative matrix factorization (NMF) were used to deal with the dataset, but visual results were not good. Then, back propagation neural network (BPNN) and one-dimensional convolutional neural network (1D-CNN) were constructed and their merits and drawbacks were compared. The final loss function of the BPNN of training set and validation set was stable at 0.27 and 0.42, and the classification accuracy of the training set and validation set reached 90.02% and 83.99%, respectively. Compared with the BPNN, the 1D-CNN had better stability and efficiency for the classification. The loss function of the training set and validation set was as low as 0.068 and 0.075, and the final classification accuracy reached 98.30% and 97.94%, respectively. Therefore, the combination of hyperspectral imaging technology and 1D-CNN represents a potentially simple, non-destructive, and rapid method for stamp-pad inks detection and classification.

Pathways to progress sustainability: an accurate ecological footprint analysis and prediction for Shandong in China based on integration of STIRPAT model, PLS, and BPNN

The world has been challenged by achieving the plausible goal of sustainable development. This study aims to evaluate the ecological footprint and ecological carrying capacity and their driving factors of Shandong province in China from 1994 to 2017. Back propagation neural network method is adopted to predict the ecological footprint from 2018 to 2030. The findings are as follows: (1) The growth of ecological footprint has caused the ecological deficit in Shandong. (2) With regards to population, the increase of total population and the urbanization rate will incur the expansion of ecological footprint. (3) In terms of affluence, the elasticity coefficients of GDP per capita, the production value of industrial sectors, and the proportion of output value of the secondary industry in GDP are 0.068, 0.064, and 0.130 respectively. (4) In terms of technology, the elasticity coefficients of internal expenditure on R&D in GDP and patent number are 0.096 and 0.047 respectively, indicating that technological progress can promote ecological footprint in a short term. (6) The results of the prediction show that the ecological footprint of Shandong from 2018 to 2030 in the policy-regulation scenario is far less than that of the business-as-usual scenario. The policy recommendations are suggested to tackle the sustainable development challenges.

Comparison of Back-Propagation Neural Network, LACE Index and HOSPITAL Score in Predicting All-Cause Risk of 30-Day Readmission

Background

The main purpose of this study is to predict the all-cause risk of 30-day readmission by employing the back-propagation neural network (BPNN) in comparison with traditional risk assessment tools of LACE index and HOSPITAL scores.

Methods

This was a retrospective cohort study from January 1st, 2018 to December 31st, 2019. A total of 55,688 hospitalizations from a medical center in Taiwan were examined. The LACE index (length of stay, acute admission, Charlson comorbidity index score, emergency department visits in previous 6 months) and HOSPITAL score (hemoglobin level at discharge, discharge from an Oncology service, sodium level at discharge, procedure during hospital stay, Index admission type, number of hospital admissions during the previous year, length of stay) are calculated. We employed variables from LACE index and HOSPITAL score as the input vector of BPNN for comparison purposes.

Results

The BPNN constructed in the current study has a considerably better ability with a C statistics achieved 0.74 (95% CI 0.73 to 0.75), which is statistically significant larger than that of the other two models using DeLong’s test. Also, it was possible to achieve higher sensitivity (70.32%) without penalizing the specificity (71.76%) and accuracy (71.68%) at its optimal threshold, which is at the 20% of patients with the highest predicted risk. Moreover, it is much more informative than the other two methods because of a considerably higher LR+ and a lower LR-.

Conclusion

Our findings suggest that more attention should be paid to methods based on non-linear classification systems, as they lead to substantial differences in risk-scores.

Terahertz spectroscopy combined with data dimensionality reduction algorithms for quantitative analysis of protein content in soybeans

Protein content in soybean is a key determinant of its nutritional and economic value. The paper investigated the feasibility of terahertz (THz) spectroscopy and dimensionality reduction algorithms for the determination of protein content in soybean. First of all, the THz sample spectrum was data processed by pre-processing or dimensionality reduction algorithms. Secondly, by calibration set, using partial least squares regression (PLSR), genetic algorithms-support vector regression (GA-SVR), grey wolf optimizer-support vector regression (GWO-SVR) and back propagation neural network (BPNN) were respectively used to model protein content determination. Afterwards, the model was validated by the prediction set. Ultimately, the BPNN model combined with linear discriminant analysis (LDA) for related coefficient of prediction set (Rp), root mean square error of prediction set (RMSEP), relative standard deviation (RSD), the time required for the operation was respectively 0.9677, 1.2467%, 3.3664%, and 53.51 s. The experimental results showed that the rapid and accurate quantitative determination of protein in soybean using THz spectroscopy is feasible after a suitable dimensionality reduction algorithm.

Serum Raman spectroscopy combined with multiple algorithms for diagnosing thyroid dysfunction and chronic renal failure

In this study, 60 samples taken from patients with thyroid dysfunction, 40 samples taken from patients with chronic renal failure (CRF) and 60 samples taken from healthy people were classified. We used partial least squares (PLS) to extract features to reduce the dimension of the spectral data to discriminate among the different samples. The Decision Trees (DT), Extreme Learning Machine (ELM), Probabilistic Neural Network (PNN), Back Propagation Neural Network (BPNN) and Learning Vector Quantization (LVQ) algorithms were used to build classification models and compare the results. The PLS-PNN algorithm distinguished between patients with thyroid dysfunction and patients with chronic renal failure with up to a 96.67 % accuracy rate, the PLS-BP algorithm distinguished between patients with chronic renal failure and healthy people with up to a 98.33 % accuracy rate, and the PLS-PNN algorithm and the PLS-DT algorithm distinguished between healthy people and patients with chronic renal failure with up to a 100 % accuracy rate. The results showed that serum Raman spectroscopy can be used in conjunction with classification algorithms to rapidly and accurately diagnose and distinguish between thyroid dysfunction and chronic renal failure.

Water temperature forecasting based on modified artificial neural network methods: Two cases of the Yangtze River

Water temperature is a controlling indicator of river habitat since many physical, chemical and biological processes in rivers are temperature dependent. Highly precise and reliable predictions of water temperature are important for river ecological management. In this study, a hybrid model named BP_PSO3, based on the BPNN (back propagation neural network) optimized by the PSO (particle swarm optimization) algorithm, is proposed for water temperature prediction using air temperature (Ta), discharge (Q) and day of year (DOY) as input variables. The performance of the BP_PSO3 model was compared with that of the BP_PSO1 (with Ta as the input) and BP_PSO2 (with Ta and Q as the inputs) models to evaluate the importance of the inputs. In addition, a comparison among the BPNN, RBFNN (radial basis function neural network), WNN (wavelet neural network), GRNN (general regression neural network), ELMNN (Elman neural network), and BP_PSO-based models was carried out based on the MAE, RMSE, NSE and R². The eight artificial intelligence models were examined to predict the water temperature at the Cuntan and Datong stations in the Yangtze River. The results indicated that the hybrid BPNN-PSO3 model had a stronger ability to forecast water temperature under both normal and extreme drought conditions. Optimization by the PSO algorithm and the inclusion of Q and DOY could help capture river thermal dynamics more accurately. The findings of this study could provide scientific references for river water temperature forecasting and river ecosystem protection.

Estimating surface heat and water vapor fluxes by combining two-source energy balance model and back-propagation neural network

The accurate quantification of surface heat and water vapor fluxes is significantly essential for understanding water balance dynamics. In this study, 15-m spatial resolution turbulent fluxes (H and LE) in the Zhangye oasis situated the middle reaches of the Heihe River Basin (HRB) were estimated by the remote sensing-based two-source energy balance model (TSEB). The TSEB model uses temperature including land surface temperature (LST) and air temperature (T_a) as the main input variable to compute turbulent fluxes but their spatial resolution is rather limited. To overcome this shortcoming, the 15-m spatial resolution LST and T_a were obtained by using the back-propagation neural network (BPNN). The results indicated that the BPNN was able to obtain finer spatial resolution and LST and T_a; the root mean square error (RMSE) values of LST and T_a are 1.99 K and 0.50 K, respectively. The remotely sensed H and LE predicted by TSEB model utilizing the LST and T_a modeled by BPNN. The results showed that H and LE agreed well with the flux observations from multi-set eddy covariance (EC) systems installed at a number of sites and covering all representative land cover types; particularly for the latent heat flux, its estimates produced mean absolute percent errors (MAPE) of 8.76% for maize, 20.17% for vegetable, 29.06% for residential area, and 16.12% for orchard. This study obtained surface heat and water vapor fluxes at finer spatial resolution than the other flux estimates from the remote sensing models that have been used in the Zhangye oasis. The results produced by combining the TSEB model and BPNN can provide more information for drafting reliable sustainable water resource management schemes and improving the irrigation water use efficiency in arid and semi-arid regions.

The amputation and survival of patients with diabetic foot based on establishment of prediction model

OBJECTIVE

The objective of this paper is to study the establishment of predictive models and the amputation and survival of patients with diabetic foot.

METHODS

A total of 200 inpatients with diabetic foot were selected as the research subject in this study. The amputation and survival status of diabetic foot patients were followed up by telephone. The relevant indicators were screened by cluster analysis. The predictive model was established respectively based on proportional hazard regression analysis, back propagation neural network (BPNN) and BPNN based on genetic algorithm optimization, and the reliability of the three prediction models (PM) was evaluated and compared.

RESULTS

The risk factors for amputation were severe ulcer disease, glycosylated hemoglobin and low-density lipoprotein cholesterol. The risk factors for death were cerebrovascular disease, severe ulcer disease and peripheral arterial disease. In case that the outcome was amputation, the PM of BPNN and the PM of BPNN based on genetic algorithm optimization have obviously higher AUC (area under the receiver operating characteristic curve) than the PM of proportional hazard regression analysis, and the difference was statistically significant (P < 0.05). Among the three PMs, the PM based on BPNN had the highest AUC, sensitivity and specificity (SAS). In case that the outcome was death, the PM of BPNN and the PM of BPNN based on genetic algorithm optimization had almost the same AUC, and were obviously higher than the PM based on proportional hazard regression analysis. The difference was statistically significant (P < 0.05). The PM based on BPNN and the BPNN based on genetic algorithm optimization had higher SAS than the PM based on COX regression analysis.

CONCLUSION

The PM of BPNN and BPNN based on genetic algorithm optimization have better prediction effect than the PM based on proportional hazard regression analysis. It can be used for amputation and survival analysis of diabetic foot patients.

Quantitative Structure Activity/Pharmacokinetics Relationship Studies of HIV-1 Protease Inhibitors Using Three Modelling Methods

BACKGROUND

HIV-1 protease inhibitor (PIs) is a good choice for AIDS patients. Nevertheless, for PIs, there are several bugs in clinical application, like drug resistance, the large dose, the high costs and so on, among which, the poor pharmacokinetics property is one of the important reasons that leads to the failure of its clinical application.

OBJECTIVE

We aimed to build computational models for studying the relationship between PIs structure and its pharmacological activities.

METHODS

We collected experimental values of k_off/K_i and structures of 50 PIs through a careful literature and database search. Quantitative structure activity/pharmacokinetics relationship (QSAR/QSPR) models were constructed by support vector machine (SVM), partial-least squares regression (PLSR) and back-propagation neural network (BPNN).

RESULTS

For QSAR models, SVM, PLSR and BPNN all generated reliable prediction models with the r² of 0.688, 0.768 and 0.787, respectively, and r²_pred of 0.748, 0.696 and 0.640, respectively. For QSPR models, the optimum models of SVM, PLSR and BPNN obtained the r² of 0.952, 0.869 and 0.960, respectively, and the r²_pred of 0.852, 0.628 and 0.814, respectively.

CONCLUSION

Among these three modelling methods, SVM showed superior ability than PLSR and BPNN both in QSAR/QSPR modelling of PIs, thus, we suspected that SVM was more suitable for predicting activities of PIs. In addition, 3D-MoRSE descriptors may have a tight relationship with the Ki values of PIs, and the GETAWAY descriptors have significant influence on both koff and Ki in PLSR equations.

Forecasting the seasonality and trend of pulmonary tuberculosis in Jiangsu Province of China using advanced statistical time-series analyses

Objective

Forecasting the seasonality and trend of pulmonary tuberculosis is important for the rational allocation of health resources; however, this foresting is often hampered by inappropriate prediction methods. In this study, we performed validation research by comparing the accuracy of the autoregressive integrated moving average (ARIMA) model and the back-propagation neural network (BPNN) model in a southeastern province of China.

Methods

We applied the data from 462,214 notified pulmonary tuberculosis cases registered from January 2005 to December 2015 in Jiangsu Province to modulate and construct the ARIMA and BPNN models. Cases registered in 2016 were used to assess the prediction accuracy of the models. The root mean square error (RMSE), mean absolute percentage error (MAPE), mean absolute error (MAE) and mean error rate (MER) were used to evaluate the model fitting and forecasting effect.

Results

During 2005–2015, the annual pulmonary tuberculosis notification rate in Jiangsu Province was 56.35/100,000, ranging from 40.85/100,000 to 79.36/100,000. Through screening and comparison, the ARIMA (0, 1, 2) (0, 1, 1)₁₂ and BPNN (3-9-1) were defined as the optimal fitting models. In the fitting dataset, the RMSE, MAPE, MAE and MER were 0.3901, 6.0498, 0.2740 and 0.0608, respectively, for the ARIMA (0, 1, 2) (0, 1, 1)₁₂ model, 0.3236, 6.0113, 0.2508 and 0.0587, respectively, for the BPNN model. In the forecasting dataset, the RMSE, MAPE, MAE and MER were 0.1758, 4.6041, 0.1368 and 0.0444, respectively, for the ARIMA (0, 1, 2) (0, 1, 1)₁₂ model, and 0.1382, 3.2172, 0.1018 and 0.0330, respectively, for the BPNN model.

Conclusion

Both the ARIMA and BPNN models can be used to predict the seasonality and trend of pulmonary tuberculosis in the Chinese population, but the BPNN model shows better performance. Applying statistical techniques by considering local characteristics may enable more accurate mathematical modeling.

Support Vector Machine for Regional Ionospheric Delay Modeling

The distribution of total electron content (TEC) in the ionosphere is irregular and complex, and it is hard to model accurately. The polynomial (POLY) model is used extensively for regional ionosphere modeling in two-dimensional space. However, in the active period of the ionosphere, the POLY model is difficult to reflect the distribution and variation of TEC. Aiming at the limitation of the regional POLY model, this paper proposes a new ionosphere modeling method with combining the support vector machine (SVM) regression model and the POLY model. Firstly, the POLY model is established using observations of regional continuously operating reference stations (CORS). Then the SVM regression model is trained to compensate the model error of POLY, and the TEC SVM-P model is obtained by the combination of the POLY and the SVM. The fitting accuracies of the models are verified with the root mean square errors (RMSEs) and static single-frequency precise point positioning (PPP) experiments. The results show that the RMSE of the SVM-P is 0.980 TECU (TEC unit), which produces an improvement of 17.3% compared with the POLY model (1.185 TECU). Using SVM-P models, the positioning accuracies of single-frequency PPP are improved over 40% compared with those using POLY models. The SVM-P is also compared with the back-propagation neural network combined with POLY (BPNN-P), and its performance is also better than BPNN-P (1.070 TECU).

Conformal Prediction Based on Raman Spectra for the Classification of Chinese Liquors

This work extends the conventional back-propagation neural network (BPNN) to the classification of Chinese liquors of different flavors according to their Raman spectra. Conformal prediction is applied to assign reliable confidence measures for each classification and support an effective framework to make the machine learning on classification trustable. The BPNN can be used to predict the flavors of Chinese liquors according to their Raman spectra, and a classification rate of 88.96% can be achieved. In order to evaluate each classification, a non-conformity score is defined to generate a P-value for each classification. Moreover, the validity of conformal prediction in online mode is discussed. The number of cumulative errors in the conformal prediction is much less than that without conformal prediction. The relationship between the cumulative error and confidence levels shows that a high confidence level leads to low cumulative errors, but many cumulative errors will occur under a very high confidence level. The result implies that conformal prediction is a useful framework, which can employ classification satisfying a certain level of confidence. Meanwhile, the conformal prediction can improve our classification using a BPNN, when the number of data points is limited.

Early discrimination and growth tracking of Aspergillus spp. contamination in rice kernels using electronic nose

Early detection of Aspergillus spp. contamination in rice was investigated by electronic nose (E-nose) in this study. Sterilized rice artificially inoculated with three Aspergillus strains were subjected to GC-MS and E-nose analyses. Principle Component Analysis (PCA), Partial Least Squares Regression (PLSR), Back-propagation neural network (BPNN), Support Vector Machine (SVM) and Learning Vector Quantization (LVQ) were employed for qualitative classification and quantitative regression. GC-MS analysis revealed a significant correlation between the volatile compounds and total amounts/species of fungi. While X-axis barycenters of PC1 scores were significantly correlated with fungal counts, logistic model could be employed to simulate the growth of individual fungus (R² = 0.978-0.996). Fungal species and counts in rice could be classified and predicted by BPNN (96.4%) and PLSR (R² = 0.886-0.917), respectively. The results demonstrated that E-nose combined with BPNN might offer the feasibility for early detection of Aspergillus spp. contamination in rice.

Spectral Analysis and Sensitive Waveband Determination Based on Nitrogen Detection of Different Soil Types Using Near Infrared Sensors

Compared with the chemical analytical technique, the soil nitrogen acquisition method based on near infrared (NIR) sensors shows significant advantages, being rapid, nondestructive, and convenient. Providing an accurate grasp of different soil types, sensitive wavebands could enhance the nitrogen estimation efficiency to a large extent. In this paper, loess, calcium soil, black soil, and red soil were used as experimental samples. The prediction models between soil nitrogen and NIR spectral reflectance were established based on three chemometric methods, that is, partial least squares (PLS), backward interval partial least squares (BIPLS), and back propagation neural network (BPNN). In addition, the sensitive wavebands of four kinds of soils were selected by competitive adaptive reweighted sampling (CARS) and BIPLS. The predictive ability was assessed by the coefficient of determination R² and the root mean square error (RMSE). As a result, loess (0.93<Rp2<0.95,0.066 g/kg<RMSEp<0.075 g/kg) and calcium soil (0.95<Rp2<0.96, 0.080 g/kg<RMSEp<0.102 g/kg) achieved a high prediction accuracy regardless of which algorithm was used, while black soil (0.79<Rp2<0.86, 0.232 g/kg<RMSEp<0.325 g/kg) obtained a relatively lower prediction accuracy caused by the interference of high humus content and strong absorption. The prediction accuracy of red soil (0.86<Rp2<0.87, 0.231 g/kg<RMSEp<0.236 g/kg) was similar to black soil, partly due to the high content of iron–aluminum oxide. Compared with PLS and BPNN, BIPLS performed well in removing noise and enhancing the prediction effect. In addition, the determined sensitive wavebands were 1152 nm–1162 nm and 1296 nm–1309 nm (loess), 1036 nm–1055 nm and 1129 nm–1156 nm (calcium soil), 1055 nm, 1281 nm, 1414 nm–1428 nm and 1472 nm–1493 nm (black soil), 1250 nm, 1480 nm and 1680 nm (red soil). It is of great value to investigate the differences among the NIR spectral characteristics of different soil types and determine sensitive wavebands for the more efficient and portable NIR sensors in practical application.

Performance Evaluation of Machine Learning Methods for Leaf Area Index Retrieval from Time-Series MODIS Reflectance Data

Leaf area index (LAI) is an important biophysical parameter and the retrieval of LAI from remote sensing data is the only feasible method for generating LAI products at regional and global scales. However, most LAI retrieval methods use satellite observations at a specific time to retrieve LAI. Because of the impacts of clouds and aerosols, the LAI products generated by these methods are spatially incomplete and temporally discontinuous, and thus they cannot meet the needs of practical applications. To generate high-quality LAI products, four machine learning algorithms, including back-propagation neutral network (BPNN), radial basis function networks (RBFNs), general regression neutral networks (GRNNs), and multi-output support vector regression (MSVR) are proposed to retrieve LAI from time-series Moderate Resolution Imaging Spectroradiometer (MODIS) reflectance data in this study and performance of these machine learning algorithms is evaluated. The results demonstrated that GRNNs, RBFNs, and MSVR exhibited low sensitivity to training sample size, whereas BPNN had high sensitivity. The four algorithms performed slightly better with red, near infrared (NIR), and short wave infrared (SWIR) bands than red and NIR bands, and the results were significantly better than those obtained using single band reflectance data (red or NIR). Regardless of band composition, GRNNs performed better than the other three methods. Among the four algorithms, BPNN required the least training time, whereas MSVR needed the most for any sample size.

Recognition Method of Limb Motor Imagery EEG Signals Based on Integrated Back-propagation Neural Network

In this paper, in order to solve the existing problems of the low recognition rate and poor real-time performance in limb motor imagery, the integrated back-propagation neural network (IBPNN) was applied to the pattern recognition research of motor imagery EEG signals (imagining left-hand movement, imagining right-hand movement and imagining no movement). According to the motor imagery EEG data categories to be recognized, the IBPNN was designed to consist of 3 single three-layer back-propagation neural networks (BPNN), and every single neural network was dedicated to recognizing one kind of motor imagery. It simplified the complicated classification problems into three mutually independent two-class classifications by the IBPNN. The parallel computing characteristic of IBPNN not only improved the generation ability for network, but also shortened the operation time. The experimental results showed that, while comparing the single BPNN and Elman neural network, IBPNN was more competent in recognizing limb motor imagery EEG signals. Also among these three networks, IBPNN had the least number of iterations, the shortest operation time and the best consistency of actual output and expected output, and had lifted the success recognition rate above 97 percent while other single network is around 93 percent.

Molecular structure-adsorption study on current textile dyes

This study was performed to investigate the adsorption of a diverse set of textile dyes onto granulated activated carbon (GAC). The adsorption experiments were carried out in a batch system. The Langmuir and Freundlich isotherm models were applied to experimental data and the isotherm constants were calculated for 33 anthraquinone and azo dyes. The adsorption equilibrium data fitted more adequately to the Langmuir isotherm model than the Freundlich isotherm model. Added to a qualitative analysis of experimental results, multiple linear regression (MLR), support vector regression (SVR) and back propagation neural network (BPNN) methods were used to develop quantitative structure-property relationship (QSPR) models with the novel adsorption data. The data were divided randomly into training and test sets. The predictive ability of all models was evaluated using the test set. Descriptors were selected with a genetic algorithm (GA) using QSARINS software. Results related to QSPR models on the adsorption capacity of GAC showed that molecular structure of dyes was represented by ionization potential based on two-dimensional topological distances, chromophoric features and a property filter index. Comparison of the performance of the models demonstrated the superiority of the BPNN over GA-MLR and SVR models.