Stepwise Polynomial Regression Research Articles

Harnessing machine learning for accurate estimation of compressive strength of high-performance self-compacting concrete from non-destructive tests: A comparative study

Harnessing machine learning for accurate estimation of compressive strength of high-performance self-compacting concrete from non-destructive tests: A comparative study

Synergistic effect and compatibility structure of active anti-inflammatory ingredients from Lamiophlomis rotata based on network pharmacology and component structure theory

The synergistic effect and compatibility structure of active anti-inflammatory ingredients(iridoid glycosides: shanzhiside methylester and 8-O-acetylshanzhiside methyl ester, flavonoid glycoside: luteoloside, and phenylethanoid glycoside: forsythoside B) from Lamiophlomis rotata were explored based on network pharmacology and component structure theory. In network pharmacology, CTD, SwisseTargetPrediction, and PharmMapper databases were used to collect and screen the targets of all active ingredients. The inflammation-related targets were obtained from CTD and GeneCards databases. The core targets were obtained by Venny 2.1.0, STRING, and Cytoscape 3.9.1. Core targets were annotated by the GO function and enriched by the KEGG pathway based on the DAVID database. In terms of component structure, based on a uniform design method and xylene-induced ear swelling model in mice, tumor necrosis factor-α and interleukin-6 were taken as the dependent variables, and the compatibility relationship among anti-inflammatory ingredients from L. rotata was explored through the quadratic polynomial stepwise regression. In addition, in vivo pharmacological experiments were conducted to verify the results. A network pharmacology study showed that compared with a single ingredient, the combined action of the three ingredients can synergistically exert anti-inflammatory effects through more biological processes, pathways, and targets. Component structure study showed that the optimal structural ratio of shanzhiside methylester and 8-O-acetylshanzhiside methyl ester in the iridoid glycoside ingredient was 1.21∶1. The optimal structural ratio among the three types of ingredients(iridoid glycosides∶phenylethanol glycoside∶flavonoid glycoside) was 4.8∶1.6∶1. In conclusion, each anti-inflammatory ingredient from L. rotata can work synergistically, and there is an optimal compatibility ratio relationship among these ingredients. This work provides a new experimental basis for the intrinsic quality control of L. rotata.

Machine Learning for Prediction of Energy Consumption and Broken Force in the Chopping Process of Maize Straw

The main causes of high productional costs and greenhouse gas emissions in the chopping process of maize straws are high energy consumption and breaking force. Addressing these issues, this paper proposes a solution that leverages machine-learning algorithms to select appropriate operational parameters for chopping devices, thereby reducing energy consumption and the cutting force. In this study, the peak breaking force of the stalk (PB), the energy consumption of the stalk chopping (EC) and the slide-cutting momentum of the disc blade (SM) were set as dependent variables, and the rotation speed of the Y-type blade (RSY), transmission ratio (TR) and slide-cutting angle (SA) were set as independent variables. Various techniques, including back-propagation (BP), a radial basis function (RBF), an artificial neural network (ANN), support vector regression and a stepwise polynomial regression model, were applied using a 6-fold cross-validation approach to determine the most effective predictive models. The results indicated that the BP-ANN model performs best in predicting the PB (R2Test = 0.9860) and SM (R2Test = 0.9561), while the RBF-ANN model yields the highest accuracy in predicting the EC (R2Test = 0.9255) under the optimal parameters. Subsequently, a verification test was conducted using randomly selected training and testing data based on the selected predicted functions. The results demonstrated that the R2Train and R2Test data for PB, EC and SM are all above 0.95, indicating that the BP and RBF neural networks are capable of accurately predicting the nonlinear relationship between the dependent variables (EC, SM and PB) and independent variables (RSY, TR and SA) in practical applications.

Isolation and Optimization of Aflatoxin B1 Degradation by Uniform Design and Complete Genome Sequencing of Novel Deep-Sea Kocuria rosea Strain 13.

Aflatoxin B1 is a natural carcinogenic mycotoxin. The biological detoxification of aflatoxin could result in less environmental pollution, more moderate conditions, and less impact on food and feed, and be more convenient than physical and chemical methods. In this study, strain 13 with aflatoxin B1 degradation activity (67.47 ± 1.44%) was isolated and identified as Kocuria rosea. A uniform design was applied to optimize the degradation activity using a software Data Processing System, and a quadratic polynomial stepwise regression model was selected to investigate the relationships between the degradation rate and five independent variables. Furthermore, the optimal degradation conditions (culture temperature of 30 °C, culture time of 4.2 days, seawater ratio of 100%, pH of 7.11, and inoculation dosage of 0.09%) were verified with a degradation rate of 88 ± 0.03%, which was well matched with the predicted value (92.97%) of the model. Complete genome sequencing of Kocuria rosea, conducted with a combination of Illumina and single-molecule real-time sequencing, was used to analyze the genomic features and functions of the strain, which were predicted by the annotation based on seven databases, and may provide insights into the potential of Kocuria rosea, as well as providing a reference for degradation gene and protein mining. These results indicate that Kocuria rosea strain 13 has the ability to degrade aflatoxin B1 efficiently, and it also has the potential to provide aflatoxin-degrading enzymes.

Attribution analysis of lake surface water temperature changing —taking China’s six main lakes as example

• The stepwise polynomial regression analysis was used to analyze factors impact LSWT. • LSWT is important for evaluating climate change and urbanization impacts on lakes. • Air temperature is still the most important factor affecting the change of LSWT. • The intensity of human disturbance varies among different types of lakes. Currently, lake surface water temperature (LSWT), as one of the most important indicators for evaluating lake health, is rapidly rising due to the influence of large-scale climate change and regional human activities in rapidly developing urban areas. The variety of LSWT will affect water environment problems such as lake water quality, aquatic organism growth and reproduction. Therefore, this study selected six lakes that play a crucial role in China’s economic and social development, and explored the causes and driving mechanisms of LSWT changes, which would provide support for the governance and protection of the ecological environment. Meanwhile, according to the fluctuation of lake boundary, the lakes were divided into two types, A and B. Based on the classification, the changing characteristics of LSWT from 2001 to 2018 were analyzed, and the stepwise polynomial regression analysis was used as new method to quantify the contribution from each driving factor to LSWT. Then, the driving mechanisms of natural and anthropogenic factors to LSWT was discussed. Results show that (1) the mean comprehensive change rates of LSWT-day and LSWT-night showed an upward trend in the past 18 years. The correlation between near surface air temperature (NSAT) and the annual average LSWT of the 6 lakes was higher than that of other factors, and this feature was most significant in spring, autumn and winter. The correlation between anthropogenic factors and annual average LSWT was affected by lake type, NSAT and precipitation in the basin. (2) Natural factors (especially NSAT) had higher contribution rates to LSWT. The contribution from anthropogenic factors to LSWT-night was higher than that in the daytime. For lakes classified in type B, the effect intensity of anthropogenic factors on LSWT-day was affected by NSAT, precipitation and lake area. The contribution rate to LSWT-night was related to the growth rate of the impervious surface area in the basin.

Machine learning and experimental testing for prediction of breakage rate of maize kernels based on components contents

A high breakage rate (BR) of maize kernels is the main problem during the direct harvest of maize kernels which causes massive grain losses. Thus, a solution was provided for reducing BR in harvest by predicting BR to select a suitable harvest time. The BR prediction models of maize kernels based on moisture, protein and starch contents were studied by using multivariate polynomial regression, stepwise polynomial regression, support vector regression (SVR) and extreme learning regression. SVR with radial basis function (rbf-SVR) was selected for further analysis. The performances of 7 different rbf-SVR models with single and multiple combinations of three components contents were evaluated. The rbf-SVR model constructed with moisture, protein and starch contents (rbf-SVR Ms + Pr + St ), which were regarded as predictor variables, generated the most accurate BR estimate. The correlation coefficients of the correction set and prediction set were 0.8921 and 0.8776, respectively. The root mean square errors of the correction set and prediction set were 1.3898% and 1.3767%, respectively. The adjusted R 2 was 0.7851. The average classification accuracy was 82.17%. As a result, the rbf-SVR Ms + Pr + St model can comprehensively evaluate BR and guide the selection of appropriate harvest time, to reduce the BR. • The relationships between components contents and BR of maize kernels were studied. • The BR prediction models were built by machine learning (MPR, SPR, SVR and ELR). • The rbf-SVR Ms + Pr + St model achieved the highest accuracy in predicting BR. • A solution was provided for reducing BR in harvest.

Component analysis and risk assessment of biogas slurry from biogas plants

Massive amounts of biogas slurry are produced due to the development of biogas plants. The pollution features and the risk of biogas slurry were fully evaluated in this work. Thirty-one biogas slurry samples were collected from sixteen different cities and five different raw materials biogas plants ( e . g . cattle manure, swine manure, straw-manure mixture, kitchen waste and chicken manure). The chemical oxygen demand (COD), ammonia nitrogen ( NH 4 + ‐ N ), anions ( e . g . Cl − , SO 4 2 ‐ , NO 3 ‐ and PO 4 3 ‐ ), antibiotics ( e . g . sulphonamides, quinolones, β 2 -receptor agonists, macrolides, tetracyclines and crystal violet) and heavy metals ( e . g . Cu, Cd, As, Cr, Hg, Zn and Pb) contents from these biogas slurry samples were systematically investigated. On this basis, risk assessment of biogas slurry was also performed. The concentrations of COD, NH 4 + ‐ N and PO 4 3 ‐ in biogas slurry samples with chicken manure as raw material were significantly higher than those of other raw materials. Therefore, the biogas slurry from chicken manure raw material demonstrated the most serious eutrophication threat. The antibiotic contents in biogas slurry samples from swine manure were the highest among five raw materials, mostly sulphonamides, quinolones and tetracyclines. Biogas slurry revealed particularly serious arsenic contamination and moderate potential ecological risk. The quadratic polynomial stepwise regression model can quantitatively describe the correlation among NH 4 + ‐ N , PO 4 3 ‐ and heavy metals concentration of biogas slurry. This work demonstrated a universal potential threat from biogas slurry that can provide supporting data and theoretical basis for harmless treatment and reuse of biogas slurry.

Research on the critical equipment parameter control technology of slim cigarette rod forming

In order to obtain the optimal control of the parameters of the critical equipment for the formation of a slim cigarette rod. In this study, the loose-end rate and weight stability are taken as the measurement indicators. According to the five factors that affect the control parameters of the critical equipment of tobacco forming, the “Uniform Design Method” is used to set up different control parameter combinations. The stepwise function is used to analyze the quadratic polynomial stepwise regression analysis, and the control parameter model is established and verified and optimized. The results show that the negative pressure of the suction chamber is 90Mbar, the proportion coefficient of the needle roller is 78%, the thickness of the block above the cleaver disc (the rail of the suction) is 2.5mm, the gap between the wire pressing wheel and the rail of the cigarette gun is 4.3mm, and the height of the cigarette tongue outlet is 4.3mm. The optimal range of the forming parameters of the cigarette rod can be obtained, which can effectively reduce the loose-end rate of the slim cigarette rod and improve the stability of the cigarette weight.

Optimization of hard modified asphalt formula for gussasphalt based on uniform experimental design

Abstract Surfacing steel decks is one of the key technical issues facing engineers during construction of long-span steel bridges. The objective of this study was to improve the high-temperature performance of gussasphalt (GA), one of the preferred surfacing materials for steel deck bridges around the world, by optimizing its binder formula. Three types of asphalt binders (i.e., styrene-butadienestyrene [SBS] modified asphalt, Trinidad lake asphalt [TLA], and NES-1 rock asphalt) were selected as basic constituents to achieve an optimized asphalt binder, which is known as hard modified asphalt. Abiding by the principles of uniform experimental design, a series of laboratory tests for penetration, ductility, ring-and-ball (R&B) softening point, and viscosity were conducted to assess and optimize the binder performance. With the laboratory testing results, quadratic polynomial stepwise regression analysis was performed to obtain four nonlinear multiple regression models for the relationships between performance and compositions of the hard modified asphalt. It is shown that NES-1 rock asphalt has more significant influence than Trinidad lake asphalt on improving the high-temperature performance of the hard modified asphalt. In order to ensure mixing workability and low-temperature performance of gussasphalt, the contents of NES-1 rock asphalt and Trinidad lake asphalt should not exceed 5% and 30%, respectively. The optimum formula of hard modified asphalt for gussasphalt is 75% SBS modified asphalt, 20% Trinidad lake asphalt, and 5% NES-1 rock asphalt. The performance of the optimized hard modified asphalt was validated by laboratory tests.

In Vitro Study on the Carotenoid Cleavage Enzyme from <i>S</i><i>taphylicoccus Pasteuri </i>Cleaving Different Substrates

In this work, the reaction of a S. pasteuri carotenoid cleavage enzyme (SpCCE) was elucidated by using bicyclic and monocyclic substrates to produce products. The optimal conditions were obtained to increase the product contents by applying quadratic polynomial stepwise regression analysis. Four mathematical models were established. The effect of pH, temperature (T), time (t), and their interaction on the amounts of apocarotenoids was investigated by path coefficient analyses under the optimized analytical conditions. The largest direct path coefficient in products cleaved from β-carotene (-25.9647, p < 0.01) and canthaxanthin (9.1153, p < 0.01) by SpCCE were explained by incubation time. While, pH×T interaction contributed more in total z1 and z2 contents (40.7541, p < 0.01), and pH×t interaction affected more on the contents of a1 and a2 (40.5796, p < 0.01). Moreover, the optimal pH values were 4.5, 4.5, 4.5 and 4.0 for getting the maximal contents of β1, z1 and z2, a1 and a2, c1 and c2 respectively. Analogously, the optimal values of temperature for products of β1, z1 and z2, a1 and a2, c1 and c2 were 30, 30, 33 and 30C. The optimal incubation time was 15, 13, 45 and 41 min respectively.

Combination of uniform design with artificial neural network coupling genetic algorithm: an effective way to obtain high yield of biomass and algicidal compound of a novel HABs control actinomycete.

Controlling harmful algae blooms (HABs) using microbial algicides is cheap, efficient and environmental-friendly. However, obtaining high yield of algicidal microbes to meet the need of field test is still a big challenge since qualitative and quantitative analysis of algicidal compounds is difficult. In this study, we developed a protocol to increase the yield of both biomass and algicidal compound present in a novel algicidal actinomycete Streptomyces alboflavus RPS, which kills Phaeocystis globosa. To overcome the problem in algicidal compound quantification, we chose algicidal ratio as the index and used artificial neural network to fit the data, which was appropriate for this nonlinear situation. In this protocol, we firstly determined five main influencing factors through single factor experiments and generated the multifactorial experimental groups with a U15(155) uniform-design-table. Then, we used the traditional quadratic polynomial stepwise regression model and an accurate, fully optimized BP-neural network to simulate the fermentation. Optimized with genetic algorithm and verified using experiments, we successfully increased the algicidal ratio of the fermentation broth by 16.90% and the dry mycelial weight by 69.27%. These results suggested that this newly developed approach is a viable and easy way to optimize the fermentation conditions for algicidal microorganisms.

Optimization of Protection Condition for Composite Freeze-Dried Starter of Paocai

To obtain the better formula of the biomaterials lyoprotectant for composite starter of Paocai, five lyoprotectants were studied with math method those are orthogonal design, Quadratic polynomial stepwise regression and etc. The results showed, 14.7% of hydrolyzate of skim milk, 1.1% of amount of glucose, 3.4% of amount of glycerol, 5.0% of amount of sodium glutamate, 1.2% of amount of Vc were added to the culture of Lactobacillus. After lyophilized, colonies of freeze-dried starters can reach 3.25×1010 cfu/mL. Response surfaces are drawn according to the mathematical model among factors, and it was discussed the impact of lyoprotectants.

Determination of Total Arsenic in Wastewater and Sewage Sludge Samples by Using Hydride-Generation Atomic Fluorescence Spectrometry Under the Optimized Analytical Conditions

In this work, an improved hydride-generation atomic fluorescence spectrometry (HG-AFS) method for the determination of total arsenic (As) in wastewater and sewage sludge samples was applied. The samples were digested completely with mixtures of HNO3 and HClO4. Analytical conditions were studied and optimized through uniform experimental design U*10(108) combined with a single factor test. A mathematical model was established, and a quadratic polynomial stepwise regression analysis by using the DPS software was employed to obtain the factors that impact the fluorescence intensity. This technique is then combined with a single factor test. The optimized experimental conditions were obtained as follows: PMT voltage was 305 V, lamp current was 70 mA, KBH4 concentration was 2.0% (m/v), carrier liquid (HCl) concentration was 5% (v/v), carrier gas (Ar) flow rate was 300 mL min−1, and reaction acidity was 10% (v/v) HCl. The pre-reduction of all forms of As to As(III) was performed by using a mixed solution of 1% thiourea and 1% ascorbic acid. The content of total As was determined under the optimized experimental conditions. The detection limits for total As in wastewater and sewage sludge were 0.09 µg L−1 and 0.01 mg kg−1, respectively. The linear ranges were 0.24–100 µg L−1, and the recovery was 91.0–102.0%. The relative standard deviation (RSD, n = 5) for eleven replicate measurements of the certified reference materials containing 60.6 ± 4.2 µg L−1 As (certified sample of water) and 10.7 ± 0.8 mg kg−1 As (certified sample of soil) were 3.1% and 1.6%, respectively. The proposed method was validated by the analysis of certified reference materials and was successfully applied to the determination of total As in real samples of wastewater and sewage sludge with satisfactory results.

PERIPHERAL ARTERIAL REMODELLING AND STIFFNESS IN PATIENTS WITH SYMPTOMATIC LOWER EXTREMITY PERIPHERAL ARTERIAL DISEASE

ObjectivesTo evaluate the alterations of peripheral arterial structures and stiffness in patients suffering from symptomatic lower extremity arterial disease (PAD), as well as the factors correlated with femoral arterial stiffness.MethodsThirty-one...

Study on Spray Drying Process of Characteristics of Distillers’ Hops

Abstract To increase use range of distillers’ hops, and to retain the original nutrients and characteristics of distillers’ hops, inlet temperature and outlet temperature and sample concentration has been studied of yield and rehydration rate with orthogonal design, quadratic polynomial stepwise regression, and response surfaces. The results showed that optimum conditions of spray drying is when inlet temperature is 162°C, outlet temperature is 84°C, sample concentration is 3.4g/200ml, feed temperature is 70 ∼ 80°C, fan power is 95%, fluid flow rate is 0.25L/h. In this condition, product yield is 56.432%, rehydration rate is 183.647%.

Study on the relationship between glial fibrillary acidic protein and non-thrombolytic hemorrhagic transformation

Objective To study the predictive effect of glial fibrillary acidic protein (GFAP) on the non ⁃ thrombolytic hemorrhagic transformation in brain infarction patients. Methods In this study there were 78 acute brain infarct patients at the mean age of (62.85 ± 11.18) years old. Fifty⁃two patients were males (66.67%) and 26 were females (33.33%). All patients were admitted to the hospital less than 72 hours after onset. No hemorrhagic findings were seen on the head magnetic resonance imaging (MRI) (including multiplanar gradient ⁃ recalled echo) in the patients. All of them were not selected for thrombolytic therapy. On 7-10 d after the first MRI at the onset, low signal for hemorrhagic transformation was seen on multiplanar gradient⁃recalled echo. The patients were divided into 2 groups based on whether patients presented hemorrhagic transformation or not, and 60 healthy volunteers [35 (58.33%) males and 25 (41.67%) females] without history of cerebrovascular diseases were selected as control group with mean age of (64.02 ± 13.97) years old. The plasma GFAP level in the hemorrhagic transformation group, the non⁃hemorrhagic transformation group and the control group was quantitatively analysed by enzyme ⁃ linked immunosorbent assay (ELISA), the differences between groups were compared, and the factors that may affect the hemorrhagic transformation were explored. Results Among 78 patients, low signals on gradient⁃echo MR image were found in 11 cases. Plasma GFAP level in brain infarct patients [(2798.46 ± 1072.66) ng/L] were significantly higher than that in the control group [(2173.37 ± 867.77) ng/L, P = 0.000]. Plasma GFAP level in hemorrhagic transformation group (3660.03 ± 629.64) ng/L were significantly higher than that in non⁃ hemorrhagic transformation group (2657.01 ± 1066.89) ng/L and control group (P = 0.000, P = 0.005, respectively). GFAP levels in plasma were correlated with hemorrhagic transformation (P = 0.005). Atrial fibrillation was correlated with hemorrhagic transformation (P = 0.017). Logistic stepwise polynomial regression analysis indicated that plasma GFAP level and atrial fibrillation were risk factors for hemorrhage transformation. Conclusion Plasma GFAP concentration higher than 2856.90 ng/L may predict the occurrence of non ⁃ thrombolysis hemorrhagic transformation in acute brain infarction patients admitted within 72 hours after onset. The plasma GFAP level may be one of the markers for the prediction of non ⁃ thrombolytic hemorrhagic transformation. DOI：10.3969/j.issn.1672-6731.2011.06.008

A greedy algorithm for dimensionality reduction in polynomial regression to forecast the performance of a power plant condenser

Engineers and physicists agree in stating that the heat transfer rate and the cleanliness factor are good indicators of the thermal performance of a power plant condenser. Both, the heat transfer rate and the cleanliness factor depend on other physical variables such as mass flow rates, pressures and temperatures measured by several sensors in the power plant. There is no knowledge about the relationship beyond the intuition of the expert that it is polynomial, taking into account the flux and heat balances derived from the mass and energy conservation principles. Performing a common full polynomial regression of a certain degree-considering all possible monomials formed by the set of measured variables-leads to a NP-hard and NP-complete problem. Besides, it would be necessary to decide the degree of the polynomial beforehand. This paper overcomes this drawback by proposing a greedy algorithm based on polynomial stepwise regression. It previously selects relevant monomials from the set of possible ones and then performs a common polynomial regression with the relevant monomials. The method is tested on some artificial data sets and some UCI repository data sets before being applied to the power plant condenser. The results show that our method successfully outperforms other state-of-the-art learning methods, taking into account both effectiveness and efficiency.

Research on Wood Fiber Cushion Packaging Material

The new type of cushion packaging material that took wood fiber and starch as raw materials was investigated in this paper. Through compression molding, the effects of some parameters on material’s mechanical properties were studied to optimize the technical process, including the ratio of wood fiber to starch, the content of adhesive and foaming agent. Using DPS data processing system for Second-order Polynomial Stepwise Regression to analyze the effects of the different process parameters on the properties and establish mathematical model, so as to optimize the experimental program and ascertain the best conditions, at the same time to verify it. The results show that the ratio of wood fiber to starch is 1:2, 6% AC foaming agent, and 10% polyvinyl alcohol are the optimum parameter.

Prediction of Hardenability of Gear Steel Using Stepwise Polynomial Regression and Artificial Neural Network

The prediction of the hardenability of gear steel has been carried using stepwise polynomial regression and artificial neural networks (ANN). The software was programmed to quantitatively predict the hardenability of gear steel by its chemical composition using two calculating models respectively. The prediction results using artificial neural networks have more precise than the stepwise polynomial regression model. The predicted values of the ANN coincide well with the actual data. So an important foundation has been laid for prediction and controlling the production of gear steel.

Artificial neural network modelling of concentrations of nitrogen, phosphorus and dissolved oxygen in a non‐point source polluted river in Zhejiang Province, southeast China

AbstractA back‐propagation algorithm neural network (BPNN) was developed to synchronously simulate concentrations of total nitrogen (TN), total phosphorus (TP) and dissolved oxygen (DO) in response to agricultural non‐point source pollution (AGNPS) for any month and location in the Changle River, southeast China. Monthly river flow, water temperature, flow travel time, rainfall and upstream TN, TP and DO concentrations were selected as initial inputs of the BPNN through coupling correlation analysis and quadratic polynomial stepwise regression analysis for the outputs, i.e. downstream TN, TP and DO concentrations. The input variables and number of hidden nodes of the BPNN were then optimized using a combination of growing and pruning methods. The final structure of the BPNN was determined from simulated data based on experimental data for both the training and validation phases. The predicted values obtained using a BPNN consisting of the seven initial input variables (described above), one hidden layer with four nodes and three output variables matched well with observed values. The model indicated that decreasing upstream input concentrations during the dry season and control of NPS along the reach during average and flood seasons may be an effective way to improve Changle River water quality. If the necessary water quality and hydrology data are available, the methodology developed here can easily be applied to other case studies. The BPNN model is an easy‐to‐use modelling tool for managers to obtain rapid preliminary identification of spatiotemporal water quality variations in response to natural and artificial modifications of an agricultural drainage river. Copyright © 2009 John Wiley &amp; Sons, Ltd.