A Prognostic Reasoning Model for Improving Areacanut Crop Productivity using Data Analytics Approach DOI
Permanki Guthu Rithesh Pakkala,

Bellipady Shamantha

Published: Oct. 14, 2022

A proactive decision-making process relies heavily on prognostic reasoning models. Due to the evolving agronomic conditions, models are now required in agricultural sector for risk management and increase productivity of most important plantation crops. The major goal this study is maximize areca nut crop by identifying various combinations best features using formal statistical test chi-square. By giving questionnaires farmers growing Arecanut Mangaluru area Karnataka, study's real data set created. Nave Bayes, Random Forest, Logistic Regression, Decision Tree classifiers used evaluate discovered chi-square test. With a prediction accuracy 99.67%, it has been that random forest outperforms other when comes yield.

Language: Английский

Developing a machine learning prediction model for honey production DOI Open Access
Berkant İsmail Yıldız, Kemal Eskioğlu, Kemal Karabağ

et al.

Mediterranean Agricultural Sciences, Journal Year: 2024, Volume and Issue: 37(2), P. 105 - 110

Published: Aug. 1, 2024

Türkiye, with its rich flora diversity, holds a significant share in global honey production. However, bee populations, essential for agricultural ecosystems, face multifaceted threats such as climate change, habitat degradation, diseases, parasites, and exposure to pesticides. Alongside the increasing food demand driven by population growth, there is pressing need substantial increase In this context, advances machine learning algorithms offer tools predict future needs production levels. The objective of work develop predictive model using techniques Türkiye's output next years. To achieve goal, range including K-Nearest Neighbor, Random Forest, Linear Regression, Gaussian Naive Bayes were employed. Following investigations, Regression emerged most effective method predicting levels (R2= 0.97).

Language: Английский

Citations

1
Machine Learning Ensemble Classifiers for Feature Selection in Rice Cultivars DOI Creative Commons

Chandrakumar Thangavel,

Dhinakaran Sakthipriya

Applied Artificial Intelligence, Journal Year: 2024, Volume and Issue: 38(1)

Published: Sept. 4, 2024

Language: Английский

Citations

1
Application of Machine Learning Algorithms to Describe the Characteristics of Dairy Sheep Lactation Curves DOI Creative Commons
Lilian Paola Guevara Muñetón, Félix Castro-Espinoza, Alberto Magno Fernandes

et al.

Animals, Journal Year: 2023, Volume and Issue: 13(17), P. 2772 - 2772

Published: Aug. 31, 2023

In recent years, machine learning (ML) algorithms have emerged as powerful tools for predicting and modeling complex data. Therefore, the aim of this study was to evaluate prediction ability different ML a traditional empirical model estimate parameters lactation curves. A total 1186 monthly records from 156 sheep lactations were used. The development process involved training testing models using algorithms. addition these algorithms, curves also fitted Wood model. goodness fit assessed correlation coefficient (r), mean absolute error (MAE), root square (RMSE), relative (RAE), (RRSE). SMOreg algorithm with best estimates characteristics curve, higher values r compared (0.96 vs. 0.68) milk yield. results current showed that are able adequately predict relatively small number input Some provide an interpretable architecture, which is useful decision-making at farm level maximize use available information.

Language: Английский

Citations

3
Effect of Vermicompost and Organic Matter in Enhancing Wheat Tolerance against Drought Stress DOI Open Access

Shair Ahmad,

Atiq Ur,

Rehman Aziz

et al.

International Journal of Agriculture and Biosciences, Journal Year: 2022, Volume and Issue: 11(3), P. 165 - 167

Published: Jan. 1, 2022

An experiment was conducted during rabi season of 2021-2022 at the Agronomy Research Farm, Department Agronomy, Faculty Agriculture, University Faisalabad, Punjab, Pakistan, to study appropriate dosage Organic matter and vermicompost for wheat germination growth under drought conditions. The laid out in a randomized complete block design (RCBD) with twelve treatments (1) clay Soil 100% field capacity (F.C) (T1: control, T2: V.C@ 5g/2kg soil, T3: O.M@15g/2kg soil), (2) sandy soil F.C (T4: T5: T6: (3) 50% (T7: Control, T8: T9: (4) (T10: T11: T12: replicated three times. Results indicate that parameters, have (109.34 t/ha) found highest combined application organic matter@15g/2kg + @5g/2kg.

Language: Английский

Citations

5
A Prognostic Reasoning Model for Improving Areacanut Crop Productivity using Data Analytics Approach DOI
Permanki Guthu Rithesh Pakkala,

Bellipady Shamantha

Published: Oct. 14, 2022

A proactive decision-making process relies heavily on prognostic reasoning models. Due to the evolving agronomic conditions, models are now required in agricultural sector for risk management and increase productivity of most important plantation crops. The major goal this study is maximize areca nut crop by identifying various combinations best features using formal statistical test chi-square. By giving questionnaires farmers growing Arecanut Mangaluru area Karnataka, study's real data set created. Nave Bayes, Random Forest, Logistic Regression, Decision Tree classifiers used evaluate discovered chi-square test. With a prediction accuracy 99.67%, it has been that random forest outperforms other when comes yield.

Language: Английский

Citations

3