Multiple regression models and Artificial Neural Network (ANN) as prediction tools of changes in overall quality during the storage of spreadable processed Gouda cheese

Modeling and Optimization of Herb-Fortified Fresh Kombucha Cheese: An Artificial Neural Network Approach for Enhancing Quality Characteristics

In this study, an Artificial Neural Network (ANN) model is used to solve the complex task of producing fresh cheese with the desired quality parameters. The study focuses on kombucha fresh cheese samples fortified with ground wild thyme, supercritical fluid extract of wild thyme, ground sage and supercritical fluid extract of sage and optimizes the parameters of chemical composition, antioxidant potential and microbiological profile. The ANN models demonstrate robust generalization capabilities and accurately predict the observed results based on the input parameters. The optimal neural network model (MLP 6-10-16) with 10 neurons provides high r2 values (0.993 for training, 0.992 for testing, and 0.992 for validation cycles). The ANN model identified the optimal sample, a supercritical fluid extract of sage, on the 20th day of storage, showcasing specific favorable process parameters. These parameters encompass dry matter, fat, ash, proteins, water activity, pH, antioxidant potential (TP, DPPH, ABTS, FRAP), and microbiological profile. These findings offer valuable insights into producing fresh cheese efficiently with the desired quality attributes. Moreover, they highlight the effectiveness of the ANN model in optimizing diverse parameters for enhanced product development in the dairy industry.

Application of regression and artificial neural network analysis of Red-Green-Blue image components in prediction of chlorophyll content in microalgae

This study presented a novel methodology to predict microalgae chlorophyll content from colour models using linear regression and artificial neural network. The analysis was performed using SPSS software. Type of extractant solvents and image indexes were used as the input data for the artificial neural network calculation. The findings revealed that the regression model was highly significant, with high R² of 0.58 and RSME of 3.16, making it a useful tool for predicting the chlorophyll concentration. Simultaneously, artificial neural network model with R² of 0.66 and low RMSE of 2.36 proved to be more accurate than regression model. The model which fitted to the experimental data indicated that acetone was a suitable extraction solvent. In comparison to the cyan-magenta-yellow-black model in image analysis, the red-greenblue model offered a better correlation. In short, the estimation of chlorophyll concentration using prediction models are rapid, more efficient, and less expensive.

Development and comparative analysis of ANN and SVR-based models with conventional regression models for predicting spray drift

As monitoring of spray drift during application can be expensive, time-consuming, and labor-intensive, drift predicting models may provide a practical complement. Several mechanistic models have been developed as drift prediction tool for various types of application equipment. Nevertheless, mechanistic models are quite often intricate and complex with a large number of input parameters required. Quite often, the detailed data needed for such models are not readily available. In this study, two advanced machine learning models (artificial neural network (ANN) and support vector regression (SVR)) were developed for pesticide drift prediction and compared with three conventional regression-based models: multiple linear regression (MLR), generalized linear model (GLM), and generalized nonlinear least squares (GNLS). The models were evaluated in fivefold cross-validation and by external validation using the coefficient of determination (R²), root mean square error (RMSE), mean absolute error (MAE), and mean absolute bias (MAB). From regression-based models, GLM and GNLS models performed very well when evaluated by cross-validation with R² = 0.96 and 0.95 and RMSE = 0.70 and 0.82 respectively, while MLR performed less with R² of 0.65 and RMSE of 2.25. Simultaneously, ANN and SVR models performed very well with R² = 0.98 and 0.97 and RMSE = 0.58 and 0.71 respectively. Overall, ANN model performed best compared to the other four models followed by SVR. A comparison was also made between the high-performing model, ANN, and two previously published empirical models. The ANN model outperformed the two previously published empirical models and can be used to predict pesticide drift. Therefore, the ANN model is a potentially promising new approach for predicting ground drift that merits further study. In conclusion, our work demonstrated that the new approach, ANN and SVR-based models, for pesticide drift modeling has better predictive power than conventional regression models. Their ability to model complex relationships is a clear benefit in pesticide drift modeling where the variability in pesticide drift is often affected by a number of variables and the relationships between drift and predictors are very complicated. We believe such insights will pave better way for the application of machine learning towards spray drift modeling.

Novel Hybridized Computational Paradigms Integrated with Five Stand-Alone Algorithms for Clinical Prediction of HCV Status among Patients: A Data-Driven Technique

The emergence of health informatics opens new opportunities and doors for different disease diagnoses. The current work proposed the implementation of five different stand-alone techniques coupled with four different novel hybridized paradigms for the clinical prediction of hepatitis C status among patients, using both sociodemographic and clinical input variables. Both the visualized and quantitative performances of the stand-alone algorithms present the capability of the Gaussian process regression (GPR), Generalized neural network (GRNN), and Interactive linear regression (ILR) over the Support Vector Regression (SVR) and Adaptive neuro-fuzzy inference system (ANFIS) models. Hence, due to the lower performance of the stand-alone algorithms at a certain point, four different novel hybrid data intelligent algorithms were proposed, including: interactive linear regression-Gaussian process regression (ILR-GPR), interactive linear regression-generalized neural network (ILR-GRNN), interactive linear regression-Support Vector Regression (ILR-SVR), and interactive linear regression-adaptive neuro-fuzzy inference system (ILR-ANFIS), to boost the prediction accuracy of the stand-alone techniques in the clinical prediction of hepatitis C among patients. Based on the quantitative prediction skills presented by the novel hybridized paradigms, the proposed techniques were able to enhance the performance efficiency of the single paradigms up to 44% and 45% in the calibration and validation phases, respectively.

TSF-transformer: a time series forecasting model for exhaust gas emission using transformer

Monitoring and prediction of exhaust gas emissions for heavy trucks is a promising way to solve environmental problems. However, the emission data acquisition is time delayed and the pattern of emission is usually irregular, which makes it very difficult to accurately predict the emission state. To deal with these problems, in this paper, we interpret emission prediction as a time series prediction problem and explore a deep learning model, a time-series forecasting Transformer (TSF-Transformer) for exhaust gas emission prediction. The exhaust emission of the heavy truck is not directly predicted, but indirectly predicted by predicting the temperature and pressure changes of the exhaust pipe under the working state of the truck. The basis of our research is based on real-time data feeds from temperature and pressure sensors installed on the exhaust pipe of approximately 12,000 heavy trucks. Therefore, the task of time series forecasting consists of two key stages: monitoring and prediction. The former utilizes the server to receive the data sent by the sensors in real-time, and the latter uses these data as samples for network training and testing. The training of the network throughout the prediction process is done in an unsupervised manner. Also, to visualize the forecast results, we weight the forecast data with the truck trajectories and present them as heatmaps. To the best of our knowledge, this is the first case of using the Transformer as the core component of the prediction model to complete the task of exhaust emissions prediction from heavy trucks. Experiments show that the prediction model outperforms other state-of-the-art methods in prediction accuracy.

Incorporation of information entropy theory, artificial neural network, and soft computing models in the development of integrated industrial water quality index

Keeping purpose and targeted end-users in perspective, several water quality indices have been developed over the past decades to summarily convey water quality information to decision-makers and the general public. Industrial water quality is often analyzed based on the corrosion and scaling potentials (CSPs) of water. The commonly used CSP index parameters are chloride-sulfate mass ratio, Langelier index, Larson-Skold index, aggressive index, Ryznar stability index, and Puckorius scaling index. Simultaneous application of these index parameters often classifies a sample into multiple water quality categories, thereby introducing bias in assessment and decision-making. No previous numerical model integrated the CSP indices to provide a single, composite index value for a more unbiased interpretation of industrial water quality. Therefore, this paper proposes an integrated industrial water quality index (IIWQI) that integrates the six CSP index parameters for direct and concise assessment of industrial water resources. To achieve its aim, this research incorporated information entropy theory and soft computing techniques. The developed IIWQI was applied to water samples from southeastern Nigeria. Different classification groups were observed based on the six CSP indices. However, the IIWQI summarized the classifications of the water samples into three categories: Class 1 (28.57%, slight-medium corrosivity, significant scaling potential); Class 2 (46.43%, medium-high corrosivity, no scaling); and Class 3 (25.00%, high-very high corrosion, no scaling). Correlation analysis revealed the relationships between the physicochemical variables, CSP index parameters, IIWQI, and the entropy-based variability of the IIWQI. The spatiotemporal water quality groups were revealed by Q-mode hierarchical dendrograms. Multiple linear regression and two multilayer perceptron neural networks accurately predicted the IIWQI. The findings of this paper could help in better evaluation, interpretation, and management of industrial water quality.

Density Prediction in Powder Bed Fusion Additive Manufacturing: Machine Learning-Based Techniques

Machine learning (ML) is one of the artificial intelligence tools which uses past data to learn the relationship between input and output and helps to predict future trends. Powder bed fusion additive manufacturing (PBF-AM) is extensively used for a wide range of applications in the industry. The AM process establishment for new material is a crucial task with trial-and-error approaches. In this work, ML techniques have been applied for the prediction of the density of PBF-AM. Density is the most vital property in evaluating the overall quality of the AM building part. The ML techniques, namely, artificial neural network (ANN), K-nearest neighbor (KNN), support vector machine (SVM), and linear regression (LR), are used to develop a model for predicting the density of the stainless steel (SS) 316L build part. These four methods are validated using R-squared values and different error functions to compare the predicted result. The ANN and SVM model performed well with the R-square value of 0.95 and 0.923, respectively, for the density prediction. The ML models would be beneficial for the prediction of the process parameters. Further, the developed ML model would also be helpful for the future application of ML in additive manufacturing.

Investigation of rice performance characteristics: A comparative study of LR, ANN, and RSM

Parboiling is a type of heat pretreatment used in rice processing to reach higher head rice yield and improve the nutrition properties of raw rice. In this research, the goals were prediction and determination of optimum conditions for parboiled rice processing using the response surface method (RSM) as well as modeling the output values by linear regression (LR) and artificial neural networks (ANN). The parameters including steaming time (0, 5, 10, and 15 min), dryer type (solar and continuous dryers), and drying air temperature (35, 40, and 45°C) were employed as input values. In addition, the breakage resistance (BR) and head rice yield (HRY) were selected as output values. The ANN‐based nonlinear regression, the multi‐layer perceptron (MLP), and the radial basis function (RBF) have been developed to model the process parameters, as well as the central composite design (CCD) was conducted for optimization of BR and HRY values. The outputs of RBF network have been successfully applied to predict higher coefficient of determination of BR and HRY as 0.989 and 0.986, respectively, indicating the appropriateness of the model equation in predicting head rice yield and breakage resistance when the three processing variables (steaming time, dryer type, and drying air temperature) are mathematically combined. Also, the lower root mean square error (RMSE) was obtained for each one as 0.043 and 0.041. The optimum values of BR and HRY were obtained as 12.80 N and 67.3%, respectively, at 9.62 min and 36.9°C for a solar dryer with a desirability of 0.941. In addition, the same values were obtained as 14.50 N and 72.1%, respectively, at 8.77 min and 37.0°C for a continuous dryer with a desirability of 0.971.

Predictive modelling of TBARS changes in the intramuscular lipid fraction of raw ground pork enriched with plant extracts

The aim of the study was to develop and compare the predictive models of lipid oxidation in minced raw pork meat enriched with selected plant extracts (allspice, basil, bay leaf, black seed, cardamom, caraway, cloves, garlic, nutmeg, onion, oregano, rosemary and thyme) by investigation TBARS values changes during storage at different temperatures. Meat samples with extract addition were stored under various temperatures (4, 8, 12, 16, and 20°C). TBARS values changes in samples stored at 12°C were used as external validation dataset. Lipid oxidation was evaluated by the TBARS content. Lipid oxidation increased with storage time and temperature. The dependence of lipid oxidation on temperature was adequately modelled by the Arrhenius and log-logistic equation with high R² coefficients (0.98–0.99). Kinetic models and artificial neural networks (ANNs) were used to build the predictive models. The obtained result demonstrates that both kinetic Arrhenius (R² = 0.83) and log-logistic (R² = 0.84) models as well as ANN (R² = 0.99) model can predict TBARS changes in raw ground pork meat during storage.

Implementing Artificial Intelligence Techniques to Predict Environmental Impacts: Case of Construction Products

Nowadays, product designers, manufacturers, and consumers consider the environmental impacts of products, processes, and services in their decision-making process. Life Cycle Assessment (LCA) is a tool that assesses the environmental impacts over a product’s life cycle. Conducting a life cycle assessment (LCA) requires meticulous data sourcing and collection and is often time-consuming for both practitioner and verifier. However, predicting the environmental impacts of products and services can help stakeholders and decision-makers identify the hotspots. Our work proposes using Artificial Intelligence (AI) techniques to predict the environmental performance of a product or service to assist LCA practitioners and verifiers. This approach uses data from environmental product declarations of construction products. The data is processed utilizing natural language processing (NLP) which is then trained to random forest algorithm, an ensemble tree-based machine learning method. Finally, we trained the model with information on the product and their environmental impacts using seven impact category values and verified the results using a testing dataset (20% of EPD data). Our results demonstrate that the model was able to predict the values of impact categories: global warming potential, abiotic depletion potential for fossil resources, acidification potential, and photochemical ozone creation potential with an accuracy (measured using R2 metrics, a measure to score the correlation of predicted values to real value) of 81%, 77%, 68%, and 70%, respectively. Our method demonstrates the capability to predict environmental performance with a defined variability by learning from the results of the previous LCA studies. The model’s performance also depends on the amount of data available for training. However, this approach does not replace a detailed LCA but is rather a quick prediction and assistance to LCA practitioners and verifiers in realizing an LCA.

Modeling Industrial Energy Demand in Relation to Subsector Manufacturing Output and Climate Change: Artificial Neural Network Insights

The study aims to adopt an artificial neural network (ANN) for modeling industrial energy demand in Taiwan related to the subsector manufacturing output and climate change. This is the first study to use the ANN technique to measure the industrial energy demand–manufacturing output–climate change nexus. The ANN model adopted in this study is a multilayer perceptron (MLP) with a feedforward backpropagation neural network. This study compares the outcomes of three ANN activation functions with multiple linear regression (MLR). According to the estimation results, ANN with a hidden layer and hyperbolic tangent activation function outperforms other techniques and has statistical solid performance values. The estimation results indicate that industrial electricity demand in Taiwan is price inelastic or has a negative value of −0.17 to −0.23, with climate change positively influencing energy demand. The relationship between manufacturing output and energy consumption is relatively diverse at the disaggregated level.

Parsimonious Models of Precipitation Phase Derived from Random Forest Knowledge: Intercomparing Logistic Models, Neural Networks, and Random Forest Models

The precipitation phase (PP) affects the hydrologic cycle which in turn affects the climate system. A lower ratio of snow to rain due to climate change affects timing and duration of the stream flow. Thus, more knowledge about the PP occurrence and drivers is necessary and especially important in cities dependent on water coming from glaciers, such as Quito, the capital of Ecuador (2.5 million inhabitants), depending in part on the Antisana glacier. The logistic models (LM) of PP rely only on air temperature and relative humidity to predict PP. However, the processes related to PP are far more complex. The aims of this study were threefold: (i) to compare the performance of random forest (RF) and artificial neural networks (ANN) to derive PP in relation to LM; (ii) to identify the main drivers of PP occurrence using RF; and (iii) to develop LM using meteorological drivers derived from RF. The results show that RF and ANN outperformed LM in predicting PP in 8 out of 10 metrics. RF indicated that temperature, dew point temperature, and specific humidity are more important than wind or radiation for PP occurrence. With these predictors, parsimonious and efficient models were developed showing that data mining may help in understanding complex processes and complements expert knowledge.

Metaheuristic secured transmission in Telecare Medical Information System (TMIS) in the face of post-COVID-19

The outbreak of novel corona virus had led the entire world to make severe changes. A secured healthcare data transmission has been proposed through Telecare Medical Information System (TMIS) based on metaheuristic salp swarm. Patients need proper medical remote treatments in this Post-COVID-19 time from their quarantines. Secured transmission of medical data is a significant challenge of digitally overwhelmed environment. The objective is to impart the patients' data by encryption with confidentiality and integrity. Eavesdroppers can carry sniffing and spoofing in order to deluge the data. In this paper, a novel scheme on metaheuristic salp swarm based intelligence has been sculptured to encrypt electrocardiograms (ECG) for data privacy. Metaheuristic approach has been blended in cryptographic engineering to address the TMIS security issues. Session key has been derived from the weight vector of the fittest salp from the salp population. The exploration and exploitation control the movements of the salps. The proposed technique baffles the eavesdroppers by the key strength and other robustness factors. The results, thus obtained, were compared with some existing classical techniques with benchmark results. The proposed MSE and RMSE were 28,967.85, and 81.17 respectively. The time needed to decode 128 bits proposed session key was 8.66 × 1052 years. The proposed cryptographic time was 8.8 s.

Predictive Modeling of Thiol Changes in Raw Ground Pork as Affected by 13 Plant Extracts-Application of Arrhenius, Log-logistic and Artificial Neural Network Models

In this study, predictive models of protein oxidation, expressed as the content of thiol groups (SH), in raw ground pork were established and their accuracy was compared. The SH changes were monitored during, maximum, 11 days of storage at five temperature levels: 4, 8, 12, 16, and 20 °C. The effect of 13 plant extracts, including spices such as allspice, black seed, cardamom, caraway, cloves, garlic, nutmeg, and onion, and herbs such as basil, bay leaf, oregano, rosemary, and thyme, on protein oxidation in pork was studied. The zero-order function was used to described SH changes with time. The effect of temperature was assessed by using Arrhenius and log–logistic equations. Artificial neural network (ANN) models were also developed. The results obtained showed very good acceptability of the models for the monitoring and prediction of protein oxidation in raw pork samples. High average R² coefficients equal to 0.948, 0.957, and 0.944 were obtained for Arhhenius, log-logistic and ANN models, respectively. Multiple linear regression (MLR) was used to assess the influence of plant extracts on protein oxidation and showed oregano as the most potent antioxidant among the tested ones in raw ground pork.

Use of sugar mill wastewater for Agaricus bisporus cultivation: prediction models for trace metal uptake and health risk assessment

This study explored the sustainable use of treated sugar mill wastewater (SMW) to cultivate the White button (Agaricus bisporus J.E. Lange) mushroom and the attendant risk of trace metals accumulated in the fruiting bodies. The wheat straw substrate was loaded with a normal water supply and different doses of SMW to enhance its moisture and nutrient contents. The impact of the SMW amendment on A. bisporus yield, biological efficiency, and spawn-running time was assessed. Furthermore, the substrate properties (pH, organic matter, total nitrogen, total phosphorus, etc.) based prediction models for trace metal uptake by A. bisporus fruiting bodies were developed using multiple linear regression (MLR) and artificial neural network (ANN) approaches. The results showed that maximum A. bisporus yield (158.42 ± 8.74 g/kg fresh substrate), biological efficiency (105.61 ± 3.97%), and minimum time of spawn-running (15 days) were observed in 75% SMW enrichment. For the prediction of Cd, Cu, Cr, Fe, Mn, and Zn trace metal uptake, the ANN models showed better performance in terms of R² (> 0.995), root means square error (RMSE < 0.075), model efficiency (ME > 0.99), and model normalized bias (MNB < 0.009), as compared with those of MLR models with R² (0.972), RMSE (< 0.441), ME (> 0.96), and MNB (< 0.034), respectively. On the other hand, the target hazard quotient (THQ) showed no significant health risk associated with the consumption of trace metal-contaminated A. bisporus in both adult and child groups. Thus, the findings of this study present a novel, safe, and sustainable method of A. bisporus cultivation along with treated agro-based wastewater management.

Prediction of Thiol Group Changes in Minced Raw and Cooked Chicken Meat with Plant Extracts-Kinetic and Neural Network Approaches

Simple Summary

Demand for poultry meat (chickens and turkeys) is constantly increasing. The upward trend in the production and consumption of poultry meat has two reasons. The first is the financial aspect because chicken meat is relatively cheap. The second reason is the nutritional and health aspect. Although the meat has high nutritional, dietary, culinary, technological, and sensory values, it is very susceptible to undesirable changes during storage, mainly due to the growth of microflora but also due to lipid and protein oxidation. The use of plant extracts in food technology is multifunctional, as they exhibit antioxidant and antibacterial effects and have a beneficial effect on the texture of meat and meat products. Moreover, the antioxidant effect of compounds isolated from plants may influence consumer health. Antioxidants of plant origin can be used as an additive to animal feed, as well as a component of stuffing or marinating mixes for meat. In addition, they are used in the coating of raw materials or in active packaging for food products. So far, many studies have shown the positive effect of plant and plant extract addition to meat on the oxidative status of its protein. However, the predictive approach to protein oxidation in raw meat is still little described. This study has demonstrated the potential usefulness of the kinetic model as well as models based on artificial neural networks (ANNs) to the realistic prediction of protein oxidation expressed as thiol group (SH) changes in raw and cooked chicken meat during storage. Such predictive models allow us to predict oxidative changes in minced meat under different time and temperature conditions as minced meat is particularly susceptible to oxidation through exposure to oxygen during the mincing process itself and through the increased contact surface with oxygen. This knowledge is very useful in designing food products and predicting their shelf-life. Additionally, the effectiveness of various spices in the raw and cooked meat system were compared. Meat is a very complex system and, according to the research, there is no direct correlation between the anti-oxidant activity of the spice itself and its antioxidant effectiveness in the product.

Abstract

The aim of the study was to develop predictive models of thiol group (SH) level changes in minced raw and heat-treated chicken meat enriched with selected plant extracts (allspice, basil, bay leaf, black seed, cardamom, caraway, cloves, garlic, nutmeg, onion, oregano, rosemary, and thyme) during storage at different temperatures. Meat samples with extract addition were stored under various temperatures (4, 8, 12, 16, and 20 °C). SH changes were measured spectrophotometrically using Ellman’s reagent. Samples stored at 12 °C were used as the external validation dataset. SH content decreased with storage time and temperature. The dependence of SH changes on temperature was adequately modeled by the Arrhenius equation with average high R² coefficients for raw meat (R² = 0.951) and heat-treated meat (R² = 0.968). Kinetic models and artificial neural networks (ANNs) were used to build the predictive models of thiol group decay during meat storage. The obtained results demonstrate that both kinetic Arrhenius (R² = 0.853 and 0.872 for raw and cooked meat, respectively) and ANN (R² = 0.803) models can predict thiol group changes in raw and cooked ground chicken meat during storage.

A Low-Cost System for Measuring Wind Speed and Direction Using Thermopile Array and Artificial Neural Network

Recent developments in wind speed sensors have mainly focused on reducing the size and moving parts to increase reliability and stability. In this study, the development of a low-cost wind speed and direction measurement system is presented. A heat sink mounted on a self-regulating heater is used as means to interact with the wind changes and a thermopile array mounted atop of the heat sink is used to collect temperature data. The temperature data collected from the thermopile array are used to estimate corresponding wind speed and direction data using an artificial neural network. The multilayer artificial neural network is trained using 96 h data and tested on 72 h data collected in an outdoor setting. The performance of the proposed model is compared with linear regression and support vector machine. The test results verify that the proposed system can estimate wind speed and direction measurements with a high accuracy at different sampling intervals, and the artificial neural network can provide significantly a higher coefficient of determination than two other methods.

Comparative performance of extreme learning machine and Hammerstein-Weiner models for modelling the intestinal hyper-motility and secretory inhibitory effects of methanolic leaf extract of Combretumhypopilinum Diels (Combretaceae)

In this article, three data-driven approaches were explored, including two artificial intelligence (AI) based models namely; Extreme Learning Machine (ELM) and Hammerstein-Weiner (HW) models and a trivial linear model namely; multilinear regression (MLR). In this context, the models were developed using the onset of diarrhoea, the total number of wet faeces, total number of faeces, weight of intestinal content (g) and length of the small intestine (cm) as the independent variables. In contrast, distance travelled by charcoal meal (C) and volume of intestinal content (I) were considered as the dependent variables for the prediction of the intestinal hypermotility and secretory inhibitory effects of the methanol leaf extract of Combretum hypopilinum (MECH). Three different performance indicators including; mean absolute percentage error (MAPE), Nash-Sutcliffe efficiency (NSE) and Root mean square error (RMSE) were employed in this research to calculate and determine the performance skills of the models. The obtained results indicated the reliable capability of ELM and HW over MLR model having NSE-values higher than 0.90 in both the calibration and verification stages. The results further demonstrated that, in terms of MAPE and RMSE, ELM and HW models showed higher performance efficiency than the MLR model. Even though HW outperformed the ELM and MLR models in the prediction of I. Whereas, ELM outperformed HW and MLR models in the prediction of C. Overall; the results proved the satisfactory ability of the AI-based models (HW and ELM) for modelling the Intestinal hypermotility and secretory inhibitory effects of MECH.

A forecasting method with efficient selection of variables in multivariate data sets

Regression is a kind of data analysis technique in which the relationship between the independent variable(x) and dependent variable(y) is modeled and for polynomial regression it is up to the nth degree polynomial. Polynomial regression fits a nonlinear relationship between the value of x and the corresponding conditional mean of y, denoted by E (y|x). In this paper polynomial regression analysis has been improved through efficient selection of variables that is coefficient of determination. Coefficient of determination is a square of the correlation between new predicted y values and actual y values and its values are in the range from 0 to 1. The main purpose of regression analysis is to discover the relationship among the independent and dependent variables or in other words it is an explanation of variation in one variable with another variable. In this paper, the main focus is on Multivariate data sets that have many attributes and it is not necessary that all variables are required for data analysis purposes. Using coefficient of determination (COD) irrelevant attributes get eliminated during analysis. The main objective of research is to reduce the cost of data maintenance, reduce the execution time and improve the prediction accuracy rate. COD helps in selecting suitable independent variables. It is a notch that is used in statistical analysis that assesses how well a model explains and forecasts upcoming outcomes. This method also helps in eliminating the irrelevant variables which are not required for the prediction model by this maintenance cost and size of data sets can be reduced.