Multiple Polynomial Regression Research Articles

Enhanced adsorption performance of tetracycline in aqueous solutions using Mg-Al-LDH/AC nanocomposite

Water contamination with antibiotics promotes environmental antibiotic resistance. Tetracycline(TC), commonly used in agriculture, pollutes water and enables bacteria to develop resistance genes. Mg-Al-layered double hydroxides/Activated carbon (Mg-Al-LDH/AC) nanocomposite effectively removes tetracycline from water in this study. The synthesized adsorbent was characterized using Brunauer–Emmett–Teller (BET), Fourier-transform Infrared Spectroscopy (FT-IR), Field Emission Scanning Electron Microscopy (FESEM), X-Ray Diffraction (XRD), and Energy-dispersive X-ray spectroscopy (EDS) tests, and exhibited a large surface area of 105.46 m2/g, a total pore volume of 0.4571 cm3/g, and an average pore diameter of 27.99 nm. The optimal conditions for eliminating TC using the Mg-Al-LDH/AC nanocomposite were determined via the central composite design response surface methodology (CCD-RSM) approach. The responses were evaluated using a second-order polynomial multiple regression model, which was found to be a satisfactory fit to the data based on the analysis of variance (R2 = 0.9690, R2Adj = 0.9478, and R2Pred = 0.9042). The ideal conditions were identified as pH = 5.1, 0.11 g of adsorbent, a TC concentration of 50 mg/L, and a contact time of 90 min. The adsorption isotherms showed that TC elimination follows the Langmuir model with a maximum adsorption capacity of 106.4 mg/g and a high R2 value of 0.9986. The kinetics of the TC adsorption process was found to fit the pseudo-second-order model with a correlation value of 0.9997. The values of ΔG, ΔH, and ΔS for TC were determined to be 1.90 kJ/mol (at 333.15 K), −41.97 kJ/mol, and −0.131 kJ/(mol·K), respectively. Additionally, the study showed that ionic strength did not affect the effectiveness of TC removal, and the adsorbent was effective in removing TC antibiotics in a range of ionic strengths. Finally, the study found that adding 20% by weight of AC to LDH resulted in the best TC removal efficiency.

Development of a Machine Learning Model to Estimate the Biotic Ligand Model-Based Predicted No-Effect Concentrations for Copper in Freshwater.

The copper (Cu) biotic ligand model (BLM) has been used for ecological risk assessment by taking into account the bioavailability of Cu in freshwater. The Cu BLM requires data for many water chemistry variables, such as pH, major cations, and dissolved organic carbon, which can be difficult to obtain from water quality monitoring programs. To develop an optimized predicted no-effect concentration (PNEC) estimation model based on an available monitoring dataset, we proposed an initial model that considers all BLM variables, a second model that requires variables excluding alkalinity, and a third model using electrical conductivity as a surrogate for the major cations and alkalinity. Furthermore, deep neural network (DNN) models have been used to predict the nonlinear relationships between the PNEC (outcome variable) and the required input variables (explanatory variables). The predictive capacity of DNN models was compared with the results of other existing PNEC estimation tools using a look-up table and multiple linear and multivariate polynomial regression methods. Three DNN models, using different input variables, provided better predictions of the Cu PNECs compared with the existing tools for the following four test datasets: Korean, United States, Swedish, and Belgian freshwaters. Consequently, it is expected that Cu BLM-based risk assessment can be applied to various monitoring datasets, and that the most applicable model among the three different types of DNN models could be selected according to data availability for a given monitoring database. Environ Toxicol Chem 2023;00:1-13. © 2023 SETAC.

Predicting spatiotemporal soil organic carbon responses to management using EPIC-IIASA meta-models

The management of Soil Organic Carbon (SOC) is a critical component of both nature-based solutions for climate change mitigation and global food security. Agriculture has contributed substantially to a reduction in global SOC through cultivation, thus there has been renewed focus on management practices which minimize SOC losses and increase SOC gain as pathways towards maintaining healthy soils and reducing net greenhouse gas emissions. Mechanistic models are frequently used to aid in identifying these pathways due to their scalability and cost-effectiveness. Yet, they are often computationally costly and rely on input data that are often only available at coarse spatial resolutions. Herein, we build statistical meta-models of a multifactorial crop model in order to both (a) obtain a simplified model response and (b) explore the biophysical determinants of SOC responses to management and the geospatial heterogeneity of SOC dynamics across Europe. Using 5600 unique simulations of crop growth from the gridded Environmental Policy Integrated Climate-based Gridded Agricultural Model (EPIC-IIASA GAM) covering 86,000 simulation units across Europe, we build multiple polynomial regression ensemble meta-models for unique combinations of climate and soil across Europe in order to predict SOC responses to varying management intensities. We find that our biophysically-explicit meta models are highly accurate (R2 = 0.97) representations of the full mechanistic model and can be used in lieu of the full EPIC-IIASA GAM model for the estimation of SOC responses to cropland management. Model stratification by means of climate and soil clustering improved the performance of the meta-models compared to the full EU-scale model. In regional and local validations of the meta-model predictions, we find that the meta-models largely capture broad SOC dynamics such as the linear nature of SOC responses to residue application, yet they often underestimate the magnitude of SOC responses to management. Furthermore, we find notable differences between the results from the biophysically-specific models throughout Europe, which point to spatially-distinct SOC responses to management choices such as nitrogen fertilizer application rates and residue retention that illustrate the potential for these models to be used for future management applications. While more accurate input data, calibration, and validation will be needed to accurately predict SOC change, we demonstrate the use of our meta-models for biophysical cluster and field study scale analyses of broad SOC dynamics with basically zero fine-tuning of the models needed. This work provides a framework for simplifying large-scale agricultural models and identifies the opportunities for using these meta-models for assessing SOC responses to management at a variety of scales.

Comparative Study on Regression Algorithms for Predicting Price of Online Course: Udemy Case Study

Talent in the field of information technology is much needed. However, studying in the field of information technology requires a sizable fee. Online courses are a cost-effective option for learning. Online course sites like Udemy provide and sell hundreds of thousands of courses and have thousands of trusted instructors. With so many Udemy instructors, prices vary widely because the course pricing system is completely set by the teaching instructor. This means that the selling price of the course is not affected by the quality of the course, so not all courses are recommended to be purchased. To overcome this problem, a system is needed that can predict course prices so that it can advise instructors in determining selling prices. To compare the best algorithms used to create this system, three algorithms are used in this study: multiple linear regression, polynomial regression, and K-Nearest Neighbors Regression. The researcher uses 1200 data sample from web scraping results from the Udemy site, with one test for each algorithm. As a result, the K-Nearest Neighbors Regression got the best evaluation results with a root mean squared error value of 231659.49, a mean absolute percentage error of 0.43, and a coefficient of determination of 0.18.

Modeling and optimizing concentration of exogenous application of γ-aminobutyric acid on NaCl-stressed pineapple mint (Mentha suaveolens) using response surface methodology: an investigation into secondary metabolites and physiological parameters

Salinity, a severe worldwide issue, compromises the economic production of medicinal plants including mints and causes drug-yield decline. γ-Aminobutyric acid (GABA) is a tolerance-inducing signaling bio-molecule in various plant physiological processes. Pineapple mint (Mentha suaveolens Ehrh.) is a valuable medicinal herb with an exhilarating scent of citrus fruit. Piperitenone oxide is the major bioactive constituent of its essential oil, having significant demand by pharmaceutical industries. Nonetheless, modeling and optimizing the effective concentration of GABA remain within twin foci of interest. Therefore, a two factor-five level (NaCl 0-150 mM and GABA 0-2.4 mM) central composite design was conducted to model and optimize drug yield and physiological responses of M. suaveolens. Based on the design of experiments (DoE) approach, different linear, quadratic, cubic, and quartic models were assigned to the response variables. Change trends of shoot and root dry weights followed a simple linear model, whereas sophisticated models (i.e., multiple polynomial regression) were fitted to the other traits. NaCl stress inevitably reduced root and shoot dry weight, piperitenone oxide content, relative water content, pigments content, and maximum quantum yield of PSII. However, content of malondialdehyde (MDA) and total flavonoid, and DPPH radical scavenging activity were increased under salinity. Under severe NaCl stress (150 mM), the essential oil content (0.53%) was increased three times in comparison with control (0.18%). Optimization analysis demonstrated that the highest amount of essential oil (0.6%) and piperitenone oxide (81%) as a drug yield-determining component would be achievable by application of 0.1–0.2 mM GABA under 100 mM NaCl. The highest dry weight of root and shoot was predicted to be achieved at 2.4 mM GABA. Overall, extremely severe NaCl stress (i.e., more than 100 mM) in which a sharp drop in yield components value was observed seemed to be out of M. suaveolens salinity tolerance range. Hence, it is rationale to compensate the decrease of drug yield by foliar application of a dilute GABA solution (i.e., 0.1–0.2 mM) under 100 mM NaCl stress or lower levels.

Predict the thyroid abnormality particular disease likelihood of the symptoms’ certainty factor value and its confidence level: A regression model analysis

The traditional expert system (TES) in the medical field commonly uses a certainty factor (CF) rule-based algorithm that can be calculated several symptoms to determine the inference solutions. The main issue for this TES included a prediction for some particular disease likelihood in the cases of new patients. CF is calculated based on symptoms related to clinical signs in patients’ diagnoses. For some reason, this TES probably won’t predict uncertain things, such as particular disease likelihood of some diseases. So, supervised learning, such as linear regression, can solve this problem. We tried to analyse the existing TES for thyroid disorders due to modelling the regression equation to predict the thyroid abnormality particular disease likelihood, based on the symptoms’ CF value and its confidence level. We used multiple linear regression (MLR) and multiple polynomial regression (MPR) to analyse the best regression model to solve the problem. The results show that the MPR model indicates the best regression model for predicting particular disease likelihood of thyroid abnormality, supported by R-squared 94.7%, R-squared adjusted 94.4%, F-value 265.925, and p-value < 0.05, which are higher than MLR model. Our study proposed a foundation for expert system development by focusing more on machine learning expert system (MLES) analysis approaches than TES.

Comparing Machine Learning Strategies for SoH Estimation of Lithium-Ion Batteries Using a Feature-Based Approach

Lithium-ion batteries play a vital role in many systems and applications, making them the most commonly used battery energy storage systems. Optimizing their usage requires accurate state-of-health (SoH) estimation, which provides insight into the performance level of the battery and improves the precision of other diagnostic measures, such as state of charge. In this paper, the classical machine learning (ML) strategies of multiple linear and polynomial regression, support vector regression (SVR), and random forest are compared for the task of battery SoH estimation. These ML strategies were selected because they represent a good compromise between light computational effort, applicability, and accuracy of results. The best results were produced using SVR, followed closely by multiple linear regression. This paper also discusses the feature selection process based on the partial charging time between different voltage intervals and shows the linear dependence of these features with capacity reduction. The feature selection, parameter tuning, and performance evaluation of all models were completed using a dataset from the Prognostics Center of Excellence at NASA, considering three batteries in the dataset.

Meteorological Variables Forecasting System Using Machine Learning and Open-Source Software

The techniques for forecasting meteorological variables are highly studied since prior knowledge of them allows for the efficient management of renewable energies, and also for other applications of science such as agriculture, health, engineering, energy, etc. In this research, the design, implementation, and comparison of forecasting models for meteorological variables have been performed using different Machine Learning techniques as part of Python open-source software. The techniques implemented include multiple linear regression, polynomial regression, random forest, decision tree, XGBoost, and multilayer perceptron neural network (MLP). To identify the best technique, the mean square error (RMSE), mean absolute percentage error (MAPE), mean absolute error (MAE), and coefficient of determination (R2) are used as evaluation metrics. The most efficient techniques depend on the variable to be forecasting, however, it is noted that for most of them, random forest and XGBoost techniques present better performance. For temperature, the best performing technique was Random Forest with an R2 of 0.8631, MAE of 0.4728 °C, MAPE of 2.73%, and RMSE of 0.6621 °C; for relative humidity, was Random Forest with an R2 of 0.8583, MAE of 2.1380RH, MAPE of 2.50% and RMSE of 2.9003 RH; for solar radiation, was Random Forest with an R2 of 0.7333, MAE of 65.8105 W/m2, and RMSE of 105.9141 W/m2; and for wind speed, was Random Forest with an R2 of 0.3660, MAE of 0.1097 m/s, and RMSE of 0.2136 m/s.

Multiple Quadratic Polynomial Regression Models and Quality Maps for Tensile Mechanical Properties and Quality Indices of Cast Aluminum Alloys according to Artificial Aging Heat Treatment Condition

To evaluate the quality of cast aluminum alloys quantitatively and intuitively, quality index and quality map have been used. Quality index and quality map are to quantitatively evaluate the quality of cast aluminum alloys according to yield strength (YS), ultimate tensile strength (UTS), elongation to fracture (Ef), and strain energy density (W). There are some quality indices such as Q, QR, QC, and Q0. The quality maps are generated to intuitively evaluate the quality level based on the quality indices. These quality indices and quality maps show the quality levels according to the pairs of tensile mechanical properties such as UTS and Ef, or YS and Ef, or YS and W. By using these quality maps, it is impossible to directly evaluate the quality levels according to the artificial aging heat treatment condition. We develop multiple quadratic polynomial regression models and quality maps for tensile mechanical properties and quality indices of the cast aluminum alloys according to artificial aging heat treatment condition. The performances of the regression models are evaluated using the mean absolute errors, mean relative errors, and coefficients of determination. The regression models and quality maps could be widely used to evaluate the quality of the cast aluminum alloys according to the aging heat treatment conditions and determine the rational aging heat treatment condition.

Prediction of rotor slot width in induction motor using Dyadic wavelet transform and softmax regression

Abstract Predictive maintenance is required for Induction Motor (IM) to avoid sudden breakdown. In this paper, multimodal sensor data are used for prediction of the rotor slot width variation during runtime of IM. Moreover sensor data are visualized through visual image obtained using Scale Invariant Feature Transform (SIFT) and matching dictionary for various faults in motor such as overload, high speed, Broken Rotor bar (BRB), and unbalance magnetic pull. The multimodal sensor signals data acquired from different parts of three phase induction motor are analysed using various transforms such as Over Complete Rational Dilation Wavelet Transform (ORaDWT), Tuneable Q Wavelet Transform (TQWT), Polynomial Chirplet Transform (PCT) and Dyadic Wavelet Transform (Dyadic WT) for various fault conditions and rotor slot width mentioned during runtime condition of motor. The rotor slot width is predicted using Multiple Linear Regression (MLR), Polynomial Regression (PR), Logistic Regression (LR) and Soft-max Regression (SR) methods through the mean value and energy band of the acquired sensor signal. The Dyadic WT and SR perform better for rotor width prediction. The proposed method such as Dyadic WT and SR provides the prediction accuracy of about 95.2%. From experimental results the rotor slot width expansion more than 2% needs immediate attention to avoid breakdown of motor.

Forecasting GHG emissions for environmental protection with energy consumption reduction from renewable sources: A sustainable environmental system

The long-term viability of energy resources as a main input is essential to achieve long-term economic growth of a country and the energy efficiency significantly reduces energy consumption and greenhouse gas emissions, supporting environmental sustainability. As a result, a number of governments, led by those in the developed world, are making an effort to enact laws governing energy efficiency. This study suggests cutting-edge methods for forecasting greenhouse gas emissions and reducing energy demand from renewable sources based on a sustainable environment. Utilizing the statistical regression neural network (SRNN), greenhouse gas emissions have been predicted, and the deep neural network's (DNN) energy efficiency has increased. The SRNN_DNN intensity method out predicts evaluated MLR (multiple linear regression) and second- and third-order non-linear MPR (multiple polynomial regression) techniques according to MAPE (mean absolute percentage error) results. Furthermore, presented methods are considered suitable for computing GHG emissions due to the high accuracy of the SRNN DNN model. The anticipated greenhouse gas emissions related to energy were remarkably similar to the actual emissions of EU (European Union) nations.

Effect of Pulsed Electric Fields (PEF) Pre-Treatment on the Quality of Sous Vide (SV) Processed Beef Short Ribs and Optimisation of PEF and SV Process Parameters Using Multiple Polynomial Regression Model

To maximise tenderness, minimise cooking loss, and decrease the adverse effects on the colour of beef short ribs, third-order multiple regression models were used to optimise the processing parameters during the pulsed electric fields (PEF) followed by sous vide (SV) processing. Electric field strength (EFS) and specific energy (SE) of PEF ranged from 0 to 0.85 kV/cm and 0 to 110.96 kJ/kg, respectively, and SV processing for 12, 24, or 36 h at 60 °C was applied. The optimum PEF-SV processing conditions for short ribs were found at EFS of 0.85 kV/cm and SE of 110.96 kJ/kg with SV processing at 60 °C for 23.96 h. In the absence of PEF pre-treatment, the optimum SV time at 60 °C was 36 h. PEF pre-treatments (SE, 99–110.96 kJ/kg) followed by SV (24 h) at 60 °C resulted in a significantly lower cooking loss (%) and texture profile analysis hardness compared to PEF at all treatment intensities, followed by SV at 60 °C for 36 h. Furthermore, significant differences were not observed in the redness, hue angle, and chroma at different PEF-SV processing parameters. Therefore, for industrial applications, PEF-SV processing with EFS (0.85 kV/cm), pulse width (20 µS), pulse frequency (50 Hz) and SE (110.96 kJ/kg), and SV temperature–time combination of 60 °C and 23.96 h is highly recommended.

Humoral and cellular immune response after severe acute respiratory syndrome coronavirus 2 messenger ribonucleic acid vaccination in heart transplant recipients: An observational study in France.

Heart transplant (HT) recipients have a high risk of developing severe COVID-19. Immunoglobulin G antibodies are considered to provide protective immunity and T-cell activity is thought to confer protection from severe disease. However, data on T-cell response to mRNA vaccination in a context of HT remains limited. In 96 HT patients, a IFN-γ release assay and an anti-Spike antibody test were used to evaluate the ability of SARS-CoV-2 mRNA vaccines to generate cellular and humoral immune response. Blood samples were collected few weeks to 7 months after vaccination. Multiple fractional polynomial and LASSO regression models were used to define predictors of T-cell response. Three to five months after vaccination, three doses of vaccine induced a positive SARS-CoV-2 T-cell response in 47% of recipients and a positive humoral response in 83% of recipients, 11.1% of patients remained negative for both T and B cell responses. Three doses were necessary to reach high IgG response levels (>590 BAU/mL), which were obtained in a third of patients. Immunity was greatly amplified in the group who had three vaccine doses plus COVID-19 infection. Our study revealed that T and B immunity decreases over time, leading us to suggest the interest of a booster vaccination at 5 months after the third dose. Moreover, a close follow-up of immune response following vaccination is needed to ensure ongoing immune protection. We also found that significant predictors of higher cellular response were infection and active smoking, regardless of immunosuppressive treatment with mycophenolate mofetil (MMF).

DUAL-CHANNEL MODEL FOR SHALLOW WATER DEPTH RETRIEVAL FROM WORLDVIEW-3 IMAGERY A CASE STUDY OF KARIMUNJAWA WATERS, CENTRAL JAVA, INDONESIA

This research aims to estimate shallow water depth using Worldview 3 satellite imagery and dual-channel models in Karimunjawa waters, Central Java – Indonesia. To build dual-channel models, we used spectral data that had been validated in the field. Twenty-three depth data were recorded synchronous to the spectral data used in forming the semianalytical dual-channel models. Twelve models were tested using 633 depth data with a non-linear model using multiple polynomial regression analysis degrees 1 and 2. This research has shown that the proposed model has been confirmed to improve depth accuracy. Models using blue and green channels of Worldview 3 image result in good accuracies especially for estimating depths with interval from 5 to 20 meters with RMSE of 1,592 meters (5–10 meters), 2,099 meters (10–15 meters), and 1,239 meters (15–20 meters). The wavelengths of two channels have a low absorption rate to penetrate deeper waters than other wavelengths. The research also finds out that there are still models that meet the IHO standard criteria.

Application of multiple linear and polynomial regression in the sustainable biodegradation process of crude oil

Statistical regression models have been applied in various biotechnical applications to determine the relationship between response and conditional factors as well as to facilitate prediction. This research focuses on sustainable biodegradation process of crude oil using native and recombinant microbial strains to alleviate the significant environmental threat posed by crude oil contamination. This sustainable process is energy and cost-efficient compared to the traditional measures adopted in the extermination of the contaminated soil due to crude oil. The reaction of the wild and recombinant microbial strains to biodegradation rate was detected in the experimental study. These experimental data were used to develop multiple linear regression (MLR) and polynomial regression models (PR). The coefficient of determination, or R2 value, was used to validate the constructed models. The PR model had a high R2 of 0.863, whereas the MLR model had a low value of 0.495. The PR model provided the best match, and it also explains the impact of conditioning factors on the biodegradation rate. To summarize, the recombinant microbial strain yielded a better biodegradation rate with increasing incubation days at lower crude oil contents.

Linear Regression Machine Learning Algorithms for Estimating Reference Evapotranspiration Using Limited Climate Data

A linear regression machine learning model to estimate the reference evapotranspiration based on temperature data for South Korea is developed in this study. FAO56 Penman–Monteith (FAO56 P–M) reference evapotranspiration calculated with meteorological data (1981–2021) obtained from sixty-two meteorological stations nationwide is used as the label. All study datasets provide daily, monthly, or annual values based on the average temperature, daily temperature difference, and extraterrestrial radiation. Multiple linear regression (MLR) and polynomial regression (PR) are applied as machine learning algorithms, and twelve models are tested using the training data. The results of the performance evaluation of the period from 2017 to 2021 show that the polynomial regression algorithm that learns the amount of extraterrestrial radiation achieves the best performance (the minimum root-mean-square errors of 0.72 mm/day, 11.3 mm/month, and 40.5 mm/year for daily, monthly, and annual scale, respectively). Compared to temperature-based empirical equations, such as Hargreaves, Blaney–Criddle, and Thornthwaite, the model trained using the polynomial regression algorithm achieves the highest coefficient of determination and lowest error with the reference evapotranspiration of the FAO56 Penman–Monteith equation when using all meteorological data. Thus, the proposed method is more effective than the empirical equations under the condition of insufficient meteorological data when estimating reference evapotranspiration.

Using Computer Vision to Track Facial Color Changes and Predict Heart Rate.

The current technological advances have pushed the quantification of exercise intensity to new era of physical exercise sciences. Monitoring physical exercise is essential in the process of planning, applying, and controlling loads for performance optimization and health. A lot of research studies applied various statistical approaches to estimate various physiological indices, to our knowledge, no studies found to investigate the relationship of facial color changes and increased exercise intensity. The aim of this study was to develop a non-contact method based on computer vision to determine the heart rate and, ultimately, the exercise intensity. The method was based on analyzing facial color changes during exercise by using RGB, HSV, YCbCr, Lab, and YUV color models. Nine university students participated in the study (mean age = 26.88 ± 6.01 years, mean weight = 72.56 ± 14.27 kg, mean height = 172.88 ± 12.04 cm, six males and three females, and all white Caucasian). The data analyses were carried out separately for each participant (personalized model) as well as all the participants at a time (universal model). The multiple auto regressions, and a multiple polynomial regression model were designed to predict maximum heart rate percentage (maxHR%) from each color models. The results were analyzed and evaluated using Root Mean Square Error (RMSE), F-values, and R-square. The multiple polynomial regression using all participants exhibits the best accuracy with RMSE of 6.75 (R-square = 0.78). Exercise prescription and monitoring can benefit from the use of these methods, for example, to optimize the process of online monitoring, without having the need to use any other instrumentation.

Implementation of Non-Invasive Blood Glucose Monitoring System

In the case of diabetes, measuring blood sugar levels is made challenging by the need to pick one's finger. Laboratory testing and one-touch glucometers are intrusive procedures that increase the risk of blood-related illnesses. In the current work, we propose a novel edge device with IoMT (Internet-of-Medical-Things) capabilities for precise, non-invasive blood glucose monitoring to solve this crucial issue. In this study, a NIR (Near-Infrared) spectroscopy method is used to identify the glucose molecule in human blood at two wavelengths (940 nm, and 1300 nm). The cutting-edge gadget known as iGLU is based on high-accuracy ML (Machine Learning) models and NIR spectroscopy. For accurate measurement, a DNN (Deep Neural Network) model and an ideal multiple polynomial regression model have been provided. An open IoT platform is used to evaluate the proposed gadget, and blood glucose levels are then saved there for endocrinologist remote monitoring. For device validation, the blood glucose measurements obtained from the invasive device and the projected blood glucose levels have been compared. The AvgE (Average Error) & MARD (Mean Absolute Relative Difference) of the predicted blood glucose concentration levels were determined to be 4.66 percent and 4.61 percent, respectively. There is a 0.81 regression coefficient. An accurate and economical solution for smart healthcare is offered by the suggested spectroscopic non-invasive gadget.

Prediction of Gross Calorific Value of Coal using Machine Learning Algorithm

Abstract: The rising number of occurrences of coal grade slippage among coal suppliers and users is causing worry in the Indian coal industry.One of the most important metrics for determining coal quality is the Gross Calorific Value (GCV). As a result, good GCV prediction is one of the essential techniques to boost heating value and coal output. This system aims to estimate the GCV of the coal samples from proximate and ultimate parameters of coal using machine learning regression algorithm: the Multiple Linear Regression (MLR) and Local Polynomial Regression (LPR). The performance of this system is evaluated using Coefficient of determination (R2 ), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) parameters. The results of the proposed system in terms of RMSE, MAE, and R2 of the MLR and LPR are observed as 0.124, 0.119, 0.414, and 0.654, 0.547, and 0.414, respectively.

Adsorptive removal of toxic malachite green from its aqueous solution by Bambusa vulgaris leaves and its acid-treated form: DFT, MPR and GA modeling

In the current investigation, bamboo leaves (BL), H2SO4 treated bamboo leaves (SBL), and H3PO4 treated bamboo leaves (PBL) were utilized as biosorbents for the elimination of Malachite Green (MG) from the synthetic medium. The adsorption study was executed under the variation of different experimental conditions like pH, biosorbent dosage, contact time, and the temperature on the MG. Langmuir isotherm fit the adsorption data with maximum monolayer adsorption capacity, 151.735 mg/g at 298 K − 168.339 mg/g at 318 K for PBL. The data fitted the pseudo-2nd -order kinetic model for all three adsorbents with a correlation coefficient greater than 0.99, indicating that chemisorption controls adsorption. The Dubinin-Radushkevich isotherm indicated that the mean sorption energy (E) is a physisorption mechanism. So, the process involves physical sorption as well as chemical sorption processes with negligible sorption energy. The FTIR, Raman Spectra, and 13C NMR results show that different functional groups of cellulose, hemicellulose and lignin are involved in MG elimination. The theoretical studies were applied for a deeper understanding of the adsorption mechanism of MG using semi-empirical quantum chemical calculations. The DFT Calculations yielded valuable information about quantum chemical properties, like EHOMO, ELUMO, electrophilicity, chemical reactivity, dipole moment, and hardness for adsorbent/adsorbate components and the binding energy from adsorbent/adsorbate interactions. Multiple polynomial regression and genetic algorithm also have been successfully applied to predict the removal percentage of malachite green.