International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 11 Issue: 07 | July 2024
www.irjet.net
p-ISSN: 2395-0072
AN ANALYSIS OF THE LITERATURE ON ARTIFICIAL INTELLIGENCE IN AGRICULTURAL SETTINGS Dr.1Rajesh Kumar HOD-BCA, Mrs. 2Geeta Rani Assistant Professor, 1Department of Information, Communication & Technology (DICT).
Tecnia Institute of Advanced Studies (TIAS) PSP, Institutional Area, Madhuban Chowk, Rohini, New Delhi-110085 2Department of Information, Communication & Technology (DICT). Tecnia Institute of Advanced Studies (TIAS) PSP, Institutional Area, Madhuban Chowk, Rohini, New Delhi-110085 ---------------------------------------------------------------------***--------------------------------------------------------------------a constantly evolving field, there is no silver bullet answer. Abstract - This study offers a thorough literature review on
Through the use of AI, we are now able to fully understand each scenario and deliver a tailored response. With the development of new AI systems, more difficult issues are being resolved.
the topic of artificial intelligence methods and their use in farming. Disease and insect infestation, poor soil treatment, insufficient drainage and irrigation, and several other issues plague the agricultural sector. Excessive use of pesticides causes these problems, which in turn cause agricultural loss and environmental dangers. To tackle these challenges, several studies have been carried out. Thanks to its powerful learning capabilities, artificial intelligence has emerged as a crucial tool for addressing a wide range of issues in the agricultural sector. Experts in agriculture are working on systems to help them find better answers globally. This literature review encompasses one hundred significant contributions that tackled agricultural difficulties with the use of artificial intelligence approaches. This study delves into the use of AI methods in the primary area of agriculture, allowing readers to follow the multi-faceted evolution of agrointelligent systems over the last four decades, from 1983 to 2023.
This literature review encompasses two hundred significant papers that tackled the difficulties in agriculture by using AI approaches. The areas of concentration are three main AI techniques: expert systems, artificial neural networks, and fuzzy systems. This study tracks the use of AI methods in agriculture, a key subdomain, from 1983 to 2023, to help readers understand the slow but steady evolution of agrointelligent systems.
OVERALL MANAGEMENT OF CROPS Typically, crop management systems provide a platform for comprehensive crop management, including all facets of farming. When McKinion and Lemmon published their 1985 article "Expert Systems for Agriculture", they were the first to suggest using AI techniques in crop management. In his PhD thesis, Boulanger put out an alternative expert system for protecting maize crops. The POMME expert system was first suggested by Roach et al. in 1987 for use in apple orchard management. The COTFLEX expert system was developed by Stone and Toman for the management of cotton crops. For the purpose of managing cotton crops, Lemmon developed an additional rule-based expert system called COMAX.
Key Words: Artificial Intelligence; Agriculture; Literature Survey; Fuzzy logic; Artificial Neural Networks
1.INTRODUCTION A major focus of computer science research is artificial intelligence (AI). Artificial intelligence (AI) is quickly becoming ubiquitous due to its large field of application and fast technical improvement. It is especially useful for issues that people and conventional computer systems struggle to address. An extremely important sector is agriculture, which employs over 30.7% of the global population on 27,81 million hectares of land. From planting seeds to reaping the rewards, such an enterprise encounters several obstacles. The most pressing concerns are infestations of pests and diseases, insufficient chemical treatment, poor drainage and irrigation, weed management, production projection, and so forth
To prevent frost damage to citrus trees on the Italian island of Sicily, Robinson and Mort developed a system based on a multi-layered feed-forward artificial neural network. When training and testing the network, the parameters used for input and output were encoded in binary form. In order to get the most accurate model, the authors experimented with various input setups. The top-performing model that was discovered has a 94% accuracy rate, two output classes, and six inputs. In order to improve the image information, Li, S. K. et al. suggested an image-based AI method for wheat crops that uses a pixel-labeling algorithm and subsequently a Laplace transformation. With five hidden layers trained to 300,000 iterations, the top network achieved an average accuracy of 85.9%. In order to help farmers with decisions
In 1983, the first report on the use of computers in farming was made. Databases and decision support systems [4] are only two of the many proposed solutions to the current issues plaguing the agricultural sector. Regarding accuracy and robustness, systems that use AI have shown to be the best performers among these options. Because agriculture is
© 2024, IRJET
|
Impact Factor value: 8.226
|
ISO 9001:2008 Certified Journal
|
Page 62