Boosting of fruit choices using machine learning‑based pomological recommendation system

Dutta, Monica and Gupta, Deepali and Juneja, Sapna and Shah, Asadullah and Shaikh, Asadullah and Shukla, Varun and Kumar, Mukesh (2023) Boosting of fruit choices using machine learning‑based pomological recommendation system. SN Applied Sciences, 5 (9). pp. 1-17. ISSN 2523-3963 E-ISSN 2523-3971

	PDF (Journal) - Published Version Restricted to Repository staff only Download (2MB) | Request a copy
Preview	PDF (Scopus) - Supplemental Material Download (820kB) | Preview

Abstract

Pomology, also known as fruticulture, is a significant contributor to the economies of many nations worldwide. While vertical farming methods are not well-suited for fruit cultivation, substrate-based cultivation is commonly practiced. Vertical farming methods use no soil for cultivation of the plants, and the cultivation is done in vertically stacked layers. Therefore, smaller herbs are best suited for such cultivation, whereas, the majority of the fruit trees are big and woody. Therefore, vertical farming methods are not well suited for fruit trees. However, to maximize fruit production, smarter substrate cultivation methods are needed. Utilizing remote sensing techniques, such as Internet of Things (IoT) devices, agriculture sensors, and cloud computing, allows for precision agriculture and smart farming in autonomous systems. Nevertheless, a lack of understanding of fruit nutrient requirements, growing conditions, and soil health conditions can result in reduced fruit production. To address these challenges, this paper proposes an intelligent model based on machine learning that recommends the best fruit to grow based on prevailing soil and climatic conditions. The system is trained on a dataset that includes details on eleven different fruits, such as Nitrogen (N), Phosphorous (P), Potassium (K), temperature, humidity, pH, and rainfall. The model takes into account the soil type and nutrient contents to recommend the most suitable fruit to grow in the prevailing climate. To enhance the model’s efficiency, two novel techniques, Gradient-based Side Sampling (GOSS) and Exclusive Feature Bundling (EFB), have been incorporated. The results show that the proposed system has achieved 99% accuracy in recommending the right fruit based on the given environmental conditions. As a result, this system has the potential to significantly improve the profitability of the pomology industry and boost national economies.

Item Type:	Article (Journal)
Uncontrolled Keywords:	Precision agriculture · Cloud computing · Internet of Things · Machine learning · Agricultural productivity · Pomology
Subjects:	T Technology > T Technology (General) > T10.5 Communication of technical information
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Information and Communication Technology Kulliyyah of Information and Communication Technology Kulliyyah of Information and Communication Technology > Department of Information System Kulliyyah of Information and Communication Technology > Department of Information System
Depositing User:	Prof Asadullah Shah
Date Deposited:	08 Sep 2023 09:46
Last Modified:	22 Jan 2024 14:29
URI:	http://irep.iium.edu.my/id/eprint/106429

Actions (login required)

View Item