International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 11 Issue: 04 | Apr 2024
p-ISSN: 2395-0072
www.irjet.net
DEEP NEURAL NETWORK BASED CROP RECOMMENDATION SYSTEM Bhavani R1, Agalya V2, Kiruthika N3, Sugapriya C4 1234Dept. of Computer Science and Engineering, Government College of Engineering Srirangam,TamilNadu, India
---------------------------------------------------------------------***--------------------------------------------------------------------2. RELATED WORKS
Abstract - Agriculture is a critical sector that
significantly relies on accurate and timely decision-making for optimal crop yield and resource utilization. This paper presents a novel approach to crop recommendation by leveraging the power of deep neural networks (DNNs) to analyze soil properties and climatic conditions. The proposed system aims to enhance the efficiency of crop selection, thereby contributing to sustainable and productive farming practices. The system utilizes a comprehensive dataset comprising soil characteristics and environmental characteristics. A deep neural network architecture is designed to process and learn complex relationships within a dataset, enabling the model to capture intricate patterns and dependencies that influence crop suitability.
The recommender model is built as a hybrid model using classifier algorithms such as Naive Bayes, J48, and association rules. Based on the appropriate parameters, the system will recommend the crop. The paper aims to create a hybrid model for recommending crops to south Indian states by considering various attributes [1]. A crop recommendation system has been developed that employs machine learning algorithms to recommend the crop that can be harvested in that particular soil. There are several machine learning algorithms available in this system, including KNN, Decision Tree, Random Forest, Naive Bayes, and Gradient Boosting to recommend the crop.[2] Crop recommendation systems can help farmers and agricultural organizations make informed decisions about crop selection and maximize yields and profits. This technology is increasingly important as the world population continues to grow, and agricultural productivity needs to keep up with demand. To recommend the best crop to plant, the SVM algorithm is utilized [3]. The motive of the system is to enhance accuracy, so a hybrid approach using K-nearest neighbor (KNN) and Random Forest (RF) algorithms is employed. It introduces an accessible and user-friendly solution for crop recommendations and yield predictions. Users provide inputs such as temperature, humidity, soil pH, and rainfall [4]. The AI system helps precision agriculture improve overall crop harvest quality and accuracy. This research feature selection, Industry 4.0, proposes one solution, such as a recommendation system, using AI and a family of machine learning algorithms. Crop recommendation for an effective prediction system using machine learning is first to gather and preprocess the data from the relevant research institutions of Bangladesh and then propose an ensemble machine learning approach, called K-nearest Neighbour Random Forest Ridge Regression (KRR), to effectively predict the production of the major crops (three different kinds of rice, potato, and wheat). KRR is designed after investigating five existing traditional machine learning (Support Vector Regression, Naïve Bayes, and Ridge Regression) and ensemble learning (Random Forest and Cat Boost) algorithms.[5]
Key Words: Deep Neural Network, Crop recommendation System, Machine learning, Deep Learning.
1.INTRODUCTION Crop recommendation systems are very useful technologies that help farmers choose crops that will maximize yields by providing them with information. To provide tailored suggestions, these systems make use of a multitude of data, such as past crop performance, soil properties, and weather patterns. The suggested technique will help farmers maximize agricultural productivity, reduce nutrient loss in crop fields, and use less fertilizers in crop production by using an artificial neural network to suggest a suitable crop based on various factors like the composition of phosphorus, potassium, and nitrogen in the soil, the pH value of the soil, rainfall, temperature, and humidity. Neural networks are used by Deep Learning to model and resolve complicated issues. An artificial neural network (ANN) having several layers between them is called a deep neural network (DNN). In the past, farmers have made crop selection decisions based on their own experiences, local expertise, and broad recommendations. But now that cutting-edge technologies, especially neural networks, emerged, accurate farming is entering a new phase. As we continue to innovate in agricultural technology, neural network-based crop recommendation systems represent a promising step towards a more resilient and sustainable future in farming.
© 2024, IRJET
|
Impact Factor value: 8.226
3. PROPOSED SYSTEM The overall architecture of the proposed recommendation model is given in figure(1). This proposed approach utilizes classification approach in content based recommendation system.
|
ISO 9001:2008 Certified Journal
|
Page 278