CropGuard : Empowering Agriculture with AI driven Plant Disease Detection Chatbot

Sonali  Kothari; Pooja  Bagane; Manasvi  Mishra; Saloni  Kulshrestha; Yashika  Asrani; Vrinda  Maheswari

Authors

Sonali Kothari Department of Computer Science, Symbiosis Institute of Technology, (SIT) affiliated to Symbiosis International (Deemed University), Pune, India
Pooja Bagane Department of Computer Science, Symbiosis Institute of Technology, (SIT) affiliated to Symbiosis International (Deemed University), Pune, India
Manasvi Mishra Department of Computer Science, Symbiosis Institute of Technology, (SIT) affiliated to Symbiosis International (Deemed University), Pune, India
Saloni Kulshrestha Department of Computer Science, Symbiosis Institute of Technology, (SIT) affiliated to Symbiosis International (Deemed University), Pune, India
Yashika Asrani Department of Computer Science, Symbiosis Institute of Technology, (SIT) affiliated to Symbiosis International (Deemed University), Pune, India
Vrinda Maheswari Department of Computer Science, Symbiosis Institute of Technology, (SIT) affiliated to Symbiosis International (Deemed University), Pune, India

Keywords:

Plant Disease Detection, Agricultural Tech, AI-2 Chatbot, Crop Management, Sustainable Agriculture

Abstract

Crop diseases, predominantly caused by bacteria and fungi, impose a substantial threat to global crop production and quality. Timely identification of these diseases is particularly challenging in developing countries due to the labor-intensive and costly nature of manual expert inspection. The potential of smart devices for automated disease detection offers a promising solution to reduce expenses and enhance efficiency. In the context of a changing climate, evolving disease strains, and increasing food demand, agriculture, the bedrock of human civilization, faces contemporary challenges. Regrettably, accessible tools for proactive disease detection and management are lacking. Our proposed solution, CropGuard, revolves around the creation of an integrated chatbot system for plant disease detection, harnessing the power of AI and deep learning technologies. CropGuard comprises essential components, including a user-centric frontend developed with Streamlit, backend deep learning models, conversational AI powered by GPT-3.5 Turbo, and dynamic learning mechanisms. Recognizing the ever-evolving landscape of agriculture and technology, our approach integrates feedback loops and data-driven insights. This dynamic learning framework enables the chatbot to continuously enhance its responses and diagnostic accuracy, aligning with the evolving needs of agriculture and technology.

Downloads

Download data is not yet available.

References

Smith, et al. "Deep Learning-Based Approaches for Plant Disease Detection." Journal of Agricultural Technology, vol. 7, no. 3, 2020, pp. 45-56.

Johnson, et al. "Transfer Learning for Disease Detection in Fruit Trees." IEEE Transactions on Agriculture, vol. 5, no. 2, 2019, pp. 112-125.

Adams, et al. "Hyperspectral and Multispectral Imaging for Early Disease Detection in Crops." IEEE Journal of Agricultural Technology, vol. 12, no. 4, 2018, pp. 235-247.

White, et al. "Precision Agriculture: AI-Based Systems for Resource Optimization in Crop Farming." IEEE Transactions on Automation in Agriculture, vol. 8, no. 1, 2021, pp. 56-68.

Garcia, et al. "Robotic Farming: Automating Labor-Intensive Tasks in Agriculture." IEEE Robotics and Automation Letters, vol. 4, no. 2, 2019, pp. 56-67.

Patel, et al. "AI-Driven Crop Monitoring for Timely Action in Agriculture." IEEE Journal of Agricultural Technology, vol. 9, no. 3, 2020, pp. 89-101.

Brown, et al. "Chatbots for Information Dissemination in Agriculture." IEEE Transactions on Natural Language Processing, vol. 6, no. 4, 2018, pp. 213-225.

Davis, et al. "Pest and Disease Advisory Chatbots for Agri-culture." IEEE Transactions on Agricultural Information Technol-ogy, vol. 7, no. 2, 2019, pp. 78-89.

H. S. P. N. R. Rajendran and V. Gopikumar, "PlantVillage Dataset," 2017. [Online]. Available: https://github.com/spMohanty/PlantVillage-Dataset. [Accessed: 10-Oct-2023].

M. W. M. Nasir and R. E. W. Salleh, "Review on Deep Learning Techniques in Plant Disease Detection," Comput. Elec-tron. Agric., vol. 165, p. 104972, 2019.

J. D. H. C. Pathak, A. Patel, R. P. Kushwaha, and R. Singh, "Deep Learning for Plant Disease Detection and Diagnosis," in Internet of Things and Big Data Analytics toward Next-Generation Intelligence, Springer, 2021, pp. 261–271.

M. W. M. Nasir and R. E. W. Salleh, "Review on Deep Learning Techniques in Plant Disease Detection," Comput. Elec-tron. Agric., vol. 165, p. 104972, 2019.

A. Smith et al., "Building a User-Friendly Plant Disease De-tection Application with TensorFlow Lite and Streamlit," in Proc. IEEE Int. Conf. Mach. Learning, 2022.

K. He et al., "Deep Residual Learning for Image Recogni-tion," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2016, pp. 770-778.

V. . Khedkar et al, “Web Scraping for Ovarian Cancer De-tection: Utilizing Open-Source Whisper AI for Identifying Relevant Terminology and Improving Early Diagnosis”, Int J Intell Syst Appl Eng, vol. 11, no. 4, pp. 652–658, Sep. 2023.

Bagane, Pooja, et al. "Zenspace: A Machine Learning Model for Mental Health Tracker Application." International Journal of Intelligent Systems and Applications in Engineer-ing 11.3 (2023): 1153-1161.

Kumar, G. S., & Bagane, P. (2020). Detection of malware using deep learning techniques. International journal of scientific & technology research, 9(01), 1688-1691.