Consult an Expert
Trademark
Design Registration
Consult an Expert
Trademark
Copyright
Patent
Infringement
Design Registration
More
Consult an Expert
Consult an Expert
Trademark
Design Registration
Login
Development of Machine Learning Model for agriculture Pest Detection and Classification
Extensive patent search conducted by a registered patent agent
Patent search done by experts in under 48hrs
₹999
₹399
Abstract
Information
Inventors
Applicants
Specification
Documents
ORDINARY APPLICATION
Published
Filed on 13 November 2024
Abstract
This invention presents an advanced machine learning-based pest detection and classification system tailored for agricultural applications, offering real-time, precise pest management solutions. Designed to operate on edge devices such as drones and mobile phones, the system enables immediate, on-site pest identification without dependence on cloud infrastructure, making it accessible for remote farming areas. By integrating IoT environmental sensors, the system contextualizes pest findings with real-time data on temperature, humidity, and soil conditions, providing farmers with targeted, actionable recommendations. Leveraging transfer learning, the model adapts to diverse pest species and regional differences with minimal retraining, enhancing its flexibility across varying agricultural contexts. A user-friendly mobile interface delivers pest alerts, infestation levels, and specific control measures, supporting timely, informed decisions for farmers. Additionally, a predictive component uses historical pest and environmental data to forecast potential pest outbreaks, enabling proactive pest management. Continuous feedback from users further refines the model, ensuring its adaptability to changing pest patterns and conditions. This system promotes sustainable agriculture by optimizing pesticide application, reducing crop damage, and supporting efficient, eco-friendly pest management practices.
Patent Information
Application ID | 202441087668 |
Invention Field | COMPUTER SCIENCE |
Date of Application | 13/11/2024 |
Publication Number | 47/2024 |
Inventors
Name | Address | Country | Nationality |
---|---|---|---|
Krishna Rupendra Singh Assistant professor, VIEW, AP | Vignan’s Institute of Engineering for Women, Visakhapatnam, AP | India | India |
Dr. Mohammad Nasar Assistant Professor, Mazoon College, Muscat, Oman | Village Balwabari, Salimpur, Bhagalpur, 813105 | India | India |
DR.M.M.YAMUNA DEVI Associate Professor, KLEF | Koneru Lakshmaiah Education Foundation | India | India |
DR. MD. ARSHAD ANWER Asst. Prof. cum Jr. Scientist, MBAC-BAU, Bihar | Mandan Bharti Agricultural College, Bihar Agricultural University, Sabour, Bihar | India | India |
Dr. P. B. Nirpal Assistant Professor & Head, Dept of Computer Science, SRTMUN’s NMDC, Maharashtra | SRTMUN’s New Model Degree College Hingoli-431513, Maharashtra | India | India |
Mahesh Ashok Mahant Assistant Professor, WIT, Solapur | Walchand Institute of Technology, Solapur | India | India |
Krishnakant Chaubey Assistant Professor, GEC, Bihar | Government Engineering College Aurangabad (Bihar) | India | India |
Dr. CH. ASHA IMMANUEL RAJU Associate Professor, AUCE, AP | Andhra University College of Engineering, Andhra University, Visakhapatnam, Andhra Pradesh, India | India | India |
Dr. SVS Ramakrishna Raju Professor, SMEC, Telangana | St. Martin’s Engineering College, Dhulapally, Telangana-500100 | India | India |
Applicants
Name | Address | Country | Nationality |
---|---|---|---|
Krishna Rupendra Singh Assistant professor, VIEW, AP | Vignan’s Institute of Engineering for Women, Visakhapatnam, AP | India | India |
Dr. Mohammad Nasar Assistant Professor, Mazoon College, Muscat, Oman | Village Balwabari, Salimpur, Bhagalpur, 813105 | India | India |
DR.M.M.YAMUNA DEVI Associate Professor, KLEF | Koneru Lakshmaiah Education Foundation | India | India |
DR. MD. ARSHAD ANWER Asst. Prof. cum Jr. Scientist, MBAC-BAU, Bihar | Mandan Bharti Agricultural College, Bihar Agricultural University, Sabour, Bihar | India | India |
Dr. P. B. Nirpal Assistant Professor & Head, Dept of Computer Science, SRTMUN’s NMDC, Maharashtra | SRTMUN’s New Model Degree College Hingoli-431513, Maharashtra | India | India |
Mahesh Ashok Mahant Assistant Professor, WIT, Solapur | Walchand Institute of Technology, Solapur | India | India |
Krishnakant Chaubey Assistant Professor, GEC, Bihar | Government Engineering College Aurangabad (Bihar) | India | India |
Dr. CH. ASHA IMMANUEL RAJU Associate Professor, AUCE, AP | Andhra University College of Engineering, Andhra University, Visakhapatnam, Andhra Pradesh, India | India | India |
Dr. SVS Ramakrishna Raju Professor, SMEC, Telangana | St. Martin’s Engineering College, Dhulapally, Telangana-500100 | India | India |
Specification
Description:The system in Fig. 1 for agricultural pest detection and classification consists of several key components:
1. Image Capture and Data Collection: High-resolution images of crops are captured using digital cameras, drones, or smartphones. These images provide data on various pest types across different stages and environmental conditions.
2. Machine Learning Model: A deep learning model, typically based on convolutional neural networks (CNNs), is trained on annotated datasets of pest images to identify and classify pest species accurately. Transfer learning is often employed to enhance model adaptability across different pests and regions.
3. Edge Computing: The system employs lightweight models for real-time, on-device processing, enabling farmers to detect pests on-site using mobile devices or drones, even without internet connectivity.
4. IoT Integration and Precision Agriculture: The system is integrated with IoT sensors and devices, allowing continuous crop monitoring and real-time pest detection updates. These insights inform precision agriculture practices, optimizing pesticide usage and improving crop health.
5. User Interface: Farmers access a user-friendly interface on mobile or desktop devices to receive pest alerts, classifications, and recommended actions for pest management.
The operation principle of the machine learning-based agricultural pest detection and classification system in Fig. 2 is based on image analysis and real-time data processing, following these core steps:
1. Data Acquisition: The system captures images of crops through cameras on drones, smartphones, or fixed IoT-enabled cameras in the field. These images form the raw input for the system.
2. Image Preprocessing: Captured images are processed to enhance quality and consistency by resizing, adjusting brightness, and removing noise. This step ensures the input data is optimal for analysis.
3. Feature Extraction via Deep Learning: The preprocessed images are fed into a deep learning model, such as a convolutional neural network (CNN), which has been pre-trained on a large dataset of labeled pest images. The model extracts unique visual features from the images, such as shapes, textures, and patterns, to distinguish between pest types.
4. Pest Detection and Classification: Based on the extracted features, the model identifies the presence of pests in the images and classifies them into specific pest categories. The system can also estimate pest density or infestation levels, helping prioritize treatment areas.
5. Real-time Processing with Edge Computing: For real-time, on-site use, the system uses lightweight models compatible with mobile devices or edge-computing drones. This setup enables the system to operate independently of cloud infrastructure, providing immediate pest alerts and insights.
6. Data Integration and Actionable Insights: Detected pest data is integrated with IoT sensors and environmental factors like temperature or humidity. This context enables the system to generate actionable insights, such as the timing for pest control, suggesting precise pesticide applications, and monitoring pest spread.
7. User Interaction and Alerts: Farmers receive pest detection updates and recommendations on mobile or desktop applications. Alerts inform them of immediate issues and optimal pest control measures to enhance crop health and yield.
, C , C , Claims:
1. We claim that this method will provide real-time pest analysis directly on drones, smart phones and tablets.
2. We claim that the invention generates context-aware and precise recommendations for pest control.
3. We claim that the invention will precise pest control insights that reduce pesticide.
4. We claim that the system is designed for ease of use without technical expertise.
Documents
Name | Date |
---|---|
202441087668-COMPLETE SPECIFICATION [13-11-2024(online)].pdf | 13/11/2024 |
202441087668-DECLARATION OF INVENTORSHIP (FORM 5) [13-11-2024(online)].pdf | 13/11/2024 |
202441087668-DRAWINGS [13-11-2024(online)].pdf | 13/11/2024 |
202441087668-FORM 1 [13-11-2024(online)].pdf | 13/11/2024 |
202441087668-FORM-9 [13-11-2024(online)].pdf | 13/11/2024 |
202441087668-REQUEST FOR EARLY PUBLICATION(FORM-9) [13-11-2024(online)].pdf | 13/11/2024 |
Talk To Experts
Calculators
Downloads
By continuing past this page, you agree to our Terms of Service,, Cookie Policy, Privacy Policy and Refund Policy © - Uber9 Business Process Services Private Limited. All rights reserved.
Uber9 Business Process Services Private Limited, CIN - U74900TN2014PTC098414, GSTIN - 33AABCU7650C1ZM, Registered Office Address - F-97, Newry Shreya Apartments Anna Nagar East, Chennai, Tamil Nadu 600102, India.
Please note that we are a facilitating platform enabling access to reliable professionals. We are not a law firm and do not provide legal services ourselves. The information on this website is for the purpose of knowledge only and should not be relied upon as legal advice or opinion.