Intelligent Techniques for Prediction of Kharif Food Grains Yield in Gujarat| Chapter 11 | Research Highlights in Agricultural Sciences Vol. 9

 Machine learning is a lively decision support finish for crop yield prediction. Yield prognosis could be a very important land issue. Any farmer is curious about knowing what pile of yield he's getting ready for. In the past, yield guess was performed by seeing farmers' expertise in particular fields and crops. Based on previous dossier, we are able to think crop yield victimization utilizing a machine-knowledge technique. Crop yield guess is an important area of research that helps in guaranteeing food freedom all around the planet. Developing higher methods to predict crop output in several climates can assist farmers and different stakeholders in making main decisions in conditions of scientific farming and crop choice. This paper reports on the utilization of diversified linear regression (MLR), Gaussian Process, SMOreg and chance forest to think Kharif food seed crop yield for Gujrat state, India. The parameters preferred for the study were precipitation, minimum hotness, average temperature, maximum hotness, reference crop evapotranspiration, area, result, and yield for the Kharif season (June to November) for the years 2000 to 2020. The dataset was treated victimisation the WEKA tool.

Author(s) Details:

Patadiya Jaykin,
Smt. Chandaben Mohanbhai Patel Institute of Computer Applications, CHARUSAT, Changa, Gujarat, India.

Mittal Desai,
Smt. Chandaben Mohanbhai Patel Institute of Computer Applications, CHARUSAT, Changa, Gujarat, India.

Dip Patel,
Smt. Chandaben Mohanbhai Patel Institute of Computer Applications, CHARUSAT, Changa, Gujarat, India.

Bhargav Vayas.,
Smt. Chandaben Mohanbhai Patel Institute of Computer Applications, CHARUSAT, Changa, Gujarat, India.

Please see the link here: https://stm.bookpi.org/RHAS-V9/article/view/9477

Quantitative Structure Activity Relationship (QSAR) Analysis on Substituted Pyrimidine Derivatives as Corticotropin-Releasing Factor1 Receptor Antagonists| Chapter 7 | Challenges and Advances in Pharmaceutical Research Vol. 9

 The corticotropin-issuing factor 1 receptor (CRF1R) antagonist is secondhand in the treatment of victims having anxiety, cavity and stress-related affecting animate nerve organs disorders. Various pyrimidine derivatives reported as CRF1R antagonists were picked for Quantitative structure venture relationship (QSAR) analysis in consideration of find out determinable relationship between organic activity and differing descriptors representing physicochemical and topological properties of the particles. Significant statistical model was create using Multiple Linear Regression (MLR) method bearing higher prognosis value (predicted_r2= 0.7708). The developed MLR model tells that the descriptor 4PathCount plays most influential role (59%) in determining CRF1R adversary activity while T_C_S_7 and SsssCHE-index have 24% and 18% offering, respectively. Absorption, distribution, absorption, excretion, toxicity (ADMET) possessions, drug likeness and drug score were also computed. The compounds 1a, 1b, 8d, and 9e have secondary hepatotoxicity and mutagenicity. The compounds 6a and 8a have good pharmacokinetics properties; secondary toxicity and good Drug likeness (DL) score, suggesting they may be drug-like compounds.

Author(s) Details:

Sanmati Kumar Jain,
Drug Discovery and Research Laboratory, Department of Pharmacy, Guru GhasidasVishwavidyalaya (A Central University), Bilaspur, Chhattisgarh- 495009, India.

Ajay Kumar Gupta,
Drug Discovery and Research Laboratory, Department of Pharmacy, Guru GhasidasVishwavidyalaya (A Central University), Bilaspur, Chhattisgarh- 495009, India.

Sanjay Kumar Lanjhiyana,
Drug Discovery and Research Laboratory, Department of Pharmacy, Guru GhasidasVishwavidyalaya (A Central University), Bilaspur, Chhattisgarh- 495009, India.

Please see the link here: https://stm.bookpi.org/CAPR-V9/article/view/8676