A Smart Agricultural Framework for Soil Image Classification Using Modified DenseNet and Crop Recommendation System Using Random Forest

A Smart Agricultural Framework for Soil Image Classification Using Modified DenseNet and Crop Recommendation System Using Random Forest
  IJETT-book-cover           
  
© 2024 by IJETT Journal
Volume-72 Issue-10
Year of Publication : 2024
Author : Sreelata Alugoju, P. Praveen
DOI : 10.14445/22315381/IJETT-V72I10P112

How to Cite?
Sreelata Alugoju, P. Praveen, "A Smart Agricultural Framework for Soil Image Classification Using Modified DenseNet and Crop Recommendation System Using Random Forest," International Journal of Engineering Trends and Technology, vol. 72, no. 10, pp. 119-129, 2024. Crossref, https://doi.org/10.14445/22315381/IJETT-V72I10P112

Abstract
The way farming and agricultural practices are conducted has changed as a result of the use of the Internet of Things (IoT) and Artificial Intelligence (AI) technology. The development of smart agricultural systems, where automation and autonomous operations are possible, is made possible by IoT and AI technology. The proposed model’s goal is to classify soil images using deep learning methods in order to determine the type of soil. With the help of this proposed modified DenseNet model, an accurate assessment of soil characteristics, including fertility, moisture content, and nutrient levels, will be made possible. Modified DenseNet delivers enhanced feature propagation, effective parameter use, resistance against overfitting, and precise findings when used to classify soil image data. The categorized soil data will be used to create an automated crop recommendation system utilizing the random forest algorithm, together with meteorological data and other pertinent criteria. Multiple decision trees are used in the ensemble learning technique known as Random Forest. It uses the combined wisdom of these trees to provide reliable predictions. The Random Forest method’s averaging or voting process reduces the impact of individual trees’ biases and faults, producing more reliable crop selection suggestions. Based on specific soil characteristics, this technology will provide farmers with customized recommendations for acceptable crop selections. As a result, it will help farmers improve their land management techniques, allowing them to attain maximum production and sustainable results.

Keywords
Soil image classification, Crop recommendation, Artificial Intelligence, Internet of Things, DenseNet, Random Forest, Ensemble learning.

References
[1] A. Subeesh, and C.R. Mehta, “Automation and Digitization of Agriculture Using Artificial Intelligence and Internet of Things,” Artificial Intelligence in Agriculture, vol. 5, pp. 278-291, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Garima Singh, Anamika Singh, and Gurjit Kaur, “Role of Artificial Intelligence and the Internet of Things in Agriculture,” Artificial Intelligence to Solve Pervasive Internet of Things Issues, pp. 317-330, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[3] T. Saranya et al., “A Comparative Study of Deep Learning and Internet of Things for Precision Agriculture,” Engineering Applications of Artificial Intelligence, vol. 122, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Mohd Javaid et al., “Understanding the Potential Applications of Artificial Intelligence in Agriculture Sector,” Advanced Agrochem, vol. 2, no. 1, pp. 15-30, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Elsayed Said Mohamed et al., “Smart Farming for Improving Agricultural Management,” The Egyptian Journal of Remote Sensing and Space Science, vol. 24, no. 3, pp. 971-981, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Yaganteeswarudu Akkem, Saroj Kumar Biswas, and Aruna Varanasi, “Smart Farming Using Artificial Intelligence: A Review,” Engineering Applications of Artificial Intelligence, vol. 120, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Bam Bahadur Sinha, and R. Dhanalakshmi, “Recent Advancements and Challenges of Internet of Things in Smart Agriculture: A Survey,” Future Generation Computer Systems, vol. 126, pp. 169-184, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Puneet Kumar Aggarwal et al., “AIIoT for Development of Test Standards for Agricultural Technology,” Intelligence of Things: AI-IoT Based Critical-Applications and Innovations, pp. 77-99, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Christine Dewi, and Rung-Ching Chen, “Decision Making Based on IoT Data Collection for Precision Agriculture,” Intelligent Information and Database Systems: Recent Developments, pp. 31-42, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Gulbir Singh, and Kuldeep Kumar Yogi, “Internet of Things-Based Devices/Robots in Agriculture 4.0,” Sustainable Communication Networks and Application: Proceedings of ICSCN, pp. 87-102, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Tien-Heng Hsieh, and Jean-Fu Kiang, “Comparison of CNN Algorithms on Hyperspectral Image Classification in Agricultural Lands,” Sensors, vol. 20, no. 6, pp. 1-17, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Zhenrong Du et al., “Smallholder Crop Area Mapped with a Semantic Segmentation Deep Learning Method,” Remote Sensing, vol. 11, no. 7, pp. 1-21, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Vittorio Mazzia, Aleem Khaliq, and Marcello Chiab, “Improvement in Land Cover and Crop Classification Based on Temporal Features Learning From Sentinel-2 Data using Recurrent-Convolutional Neural Network (R-CNN),” Applied Sciences, vol. 10, no. 1, pp. 1-23, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Ce Zhang et al., “Scale Sequence Joint Deep Learning (SS-JDL) for Land Use and Land Cover Classification,” Remote Sensing of Environment, vol. 237, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Rahim Azadnia et al., “Developing an Automated Monitoring System for Fast and Accurate Prediction of Soil Texture Using an Image-Based Deep Learning Network and Machine Vision System,” Measurement, vol. 190, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Pallavi Srivastava, Aasheesh Shukla, and Atul Bansal, “A Comprehensive Review on Soil Classification using Deep Learning and Computer Vision Techniques,” Multimedia Tools and Applications, vol. 80, pp. 14887-14914, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Amit Bhola, and Prabhat Kumar, “Performance Evaluation of Different Machine Learning Models in Crop Selection,” Robotics, Control and Computer Vision, pp. 207-217, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Liheng Zhong, Lina Hu, and Hang Zhou, “Deep Learning Based Multi-Temporal Crop Classification,” Remote Sensing of Environment, vol. 221, pp. 430-443, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Zeel Doshi et al., “AgroConsultant: Intelligent Crop Recommendation System Using Machine Learning Algorithms,” Fourth International Conference on Computing Communication Control and Automation (ICCUBEA), Pune, India, pp. 1-6, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Andreas Kamilaris, and Francesc X. Prenafeta-Boldú, “Deep Learning in Agriculture: A Survey,” Computers and Electronics in Agriculture, vol. 147, pp. 70-90, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Krupa Patel, and Hiren B. Patel, “A State-of-the-Art Survey on Recommendation System and Prospective Extensions,” Computers and Electronics in Agriculture, vol. 178, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[22] P. Parameswari, and C. Tharani, “Crop Specific Cultivation Recommendation System Using Deep Learning,” Information and Communication Technology for Competitive Strategies, pp. 781-787, 2023.
[CrossRef] [Google Scholar] [Publisher Link]