An Analysis Study Based on Linear Regression Model for Changes of Fruit Size over Plum Diseases

Rahman, A.B.M. Salman; Vasanth, R.; Lee, Myeongbae; Park, Jang Woo; Yun, Cho Yong; Lee, Meonghun; Shin, Chang-Sun

doi:10.34163/jkits.2018.13.5.001

Cited by 5 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, all predictions' average RMSE and error (%) were ≤ ± 20. The tted line graphs indicated that most of the predicted values were in between 95% CI and PI, this also corroborated the good e ciency of the DPM in predicting the RBD 33 . All ve environmental factors, max and min temps, RF, RH and WS, found signi cant in the model.…”

Section: Discussionsupporting

confidence: 67%

Predicting Rice Blast (Pyriculariaoryzae) Severity Using Epidemiological Data with Advanced Regression Modeling Strategies

Arooj,

Ahmad,

Ali

et al. 2024

Preprint

View full text Add to dashboard Cite

Rice blast is a detrimental disease widely prevalent in the world. Many disease predictive models have been developed for Rice blast disease (RBD) in different regions, but the disease prediction modeling in semi-arid areas is less characterized. Here, we focused on developing a disease predictive model (DPM) for rice blast disease (RBD) based on eight-year (2009–2016) environmental variables and their correlation with the RBD severity data, followed by validation with two-year (2017–2018) field trial data in a semi-arid region of Pakistan. Besides the correlation analysis, the model implied multiple linear regression analysis. The DPM indicated that five environmental variables maximum (Max) and minimum (Min) temperature, rainfall (RF), relative humidity (RH) and windspeed (WS), significantly contributed to the development of RBD during eight years. The obtained values of standard statistical indicators, coefficient of determination (R2) low standard error (SE) ≤ 10, and significance of F-distribution of regression statistics proved the effectiveness in predicting RBD for eight years. Furthermore, the criteria of root-mean square error (RMSE) and error (%) of 8 year data and observed data suggested a striking closeness between old and observed values of RBD severity, indicating the effective reliability of the model in both contexts. The analysis of 8 year DPM data showed that five environmental variables (max and min temps, RF, RH and WS) could cause up to 92% variability in RBD. Except for min temp, which showed a negative correlation suggesting a minor influence on disease development, the other four environmental factors exhibited a positive correlation with RBD severity, indicating the maximum contributing factors in disease development. The developed model helped us to predict the ranges of environmental factors, Max and Min temp 40–42°C and 22–24°C, RF 2-2.5 mm, RH 50–70%, and WS 9–11 Km/h, significantly favorable for RBD. The current prototype DPM of RBD has the potential for practical application if combined with a weather prediction system, which could be useful in developing rice blast disease warning system in the semi-arid zone of Punjab and predicting the appropriate time of the fungicidal sprays.

show abstract

Section: Discussionsupporting

confidence: 67%

Predicting Rice Blast (Pyriculariaoryzae) Severity Using Epidemiological Data with Advanced Regression Modeling Strategies

Arooj,

Ahmad,

Ali

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…This linear line helps in prediction of protein content values (Y variable). [12,13] 3. Non-Linear Regression Model-is also used as a tool to predict one parameter from the other known parameter.…”

Section: Part B: Dry Lab Studiesmentioning

confidence: 99%

Predictive Modeling of Different Treatments for Physiological and Nutritional Parameters of Ocimum Sanctum

Rao¹,

Sharma²,

Anala³

et al. 2022

ECS Trans.

View full text Add to dashboard Cite

An increasing demand for superior quality crops has led to investigating the current trends in agriculture. One of the main factors impacting this is environmental stress. Even with certain plant defense mechanisms to combat stress, not all plants can tolerate the impact induced by abiotic stress, therefore compromising the overall physiological and nutritional parameters greatly. This research focuses on the effects of stress on the Ocimum sanctum plant, its corresponding parametric variation data is further processed and analyzed by predictive models. Abiotic stress: Plants were exposed to drought, jasmonic acid, potassium nitrate, hydrogen peroxide, at varied intensities, and parameters - plant height, relative water capacity, protein, chlorophyll content, and photosynthetic rate were subsequently recorded for 50 days. KNN classification model was used to predict the treatment required for any given parameter. A comparative study between Linear and Non-Linear Regression models with a common goal of predicting one parameter from the other known parameter was done and inferred that the Non-Linear Regression model performed well and had better accuracy.

show abstract

“…Multiple linear regression is considered the technique with two or more explanatory variables (A.B.M. Salman Rahman et al, 2018). Data in linear regression is built using linear predictor functions, and unspecified model parameters are determined from the data.…”

Section: General Linear Regressionmentioning

confidence: 99%

A Comparative Study of Energy Big Data Analysis for Product Management in a Smart Factory

Salman

Lee

Lim

et al. 2021

Journal of Organizational and End User Computing

View full text Add to dashboard Cite

Energy has been obtained as one of the key inputs for a country's economic growth and social development. Analysis and modeling of industrial energy are currently a time-insertion process because more and more energy is consumed for economic growth in a smart factory. This study aims to present and analyse the predictive models of the data-driven system to be used by appliances and find out the most significant product item. With repeated cross-validation, three statistical models were trained and tested in a test set: 1) General Linear Regression Model (GLM), 2) Support Vector Machine (SVM), and 3) boosting Tree (BT). The performance of prediction models measured by R2 error, Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Variation (CV). The best model from the study is the Support Vector Machine (SVM) that has been able to provide R2 of 0.86 for the training data set and 0.85 for the testing data set with a low coefficient of variation, and the most significant product of this smart factory is Skelp.

show abstract

An Analysis Study Based on Linear Regression Model for Changes of Fruit Size over Plum Diseases

Cited by 5 publications

References 0 publications

Predicting Rice Blast (Pyriculariaoryzae) Severity Using Epidemiological Data with Advanced Regression Modeling Strategies

Predicting Rice Blast (Pyriculariaoryzae) Severity Using Epidemiological Data with Advanced Regression Modeling Strategies

Predictive Modeling of Different Treatments for Physiological and Nutritional Parameters of Ocimum Sanctum

A Comparative Study of Energy Big Data Analysis for Product Management in a Smart Factory

Contact Info

Product

Resources

About