Authors:
Pascal Faye
1
;
Jeanne Faye
2
and
Mariane Senghor
1
Affiliations:
1
Université du Sine Saloum El Hadj Ibrahima NIASS (USSEIN), Sing Sing, Kaolack, Senegal
;
2
Université Aix-Marseille, Institut de Management Public et Gouvernance Territoriale, Aix-Marseille, France
Keyword(s):
Conceptualization, Internet of Things Network, Data analysis, Artificial Intelligence, Multi-Agent System, Crop Yield.
Abstract:
This work proposes a model called AIMS (Agricultural Information and Management System) based on some Machine Learning Algorithm (ML) as CART (Classification And Regression Trees), KNN(K-nearest neighbors) and SVM(Support Vector Machine). It describes both a multi-agent system and Internet Of Things device that ensures data collection and control as well as a data monitoring system via our web platform for decision-making support in a real-world agricultural environments. This for a prompt, effective and sustainable agricultural development. We refer to cases in which agent collaboration is needed for efficient task execution (e. g. data processing and decision making). In our context, dynamics and uncertainty prohibit computation strategies ahead of task execution. Combining methods from Machine Learning (ML), Markov decision processes (MDP) and probability, we introduce an auto-stabilizing coordination mechanism.