Assist. Prof. Dr. Hossein Bagherpour | Machine Learning Awards | Best Researcher Award

Assist. Prof. Dr. Hossein Bagherpour, Department of Biosystems Engineering, Bu-Ali Sina Universit, Iran

Dr. Hossein Bagherpour is an accomplished Assistant Professor in the Department of Biosystems Engineering at Bu-Ali Sina University, where he has served since 2013. Holding a Ph.D. and M.Sc. in Biosystems and Agricultural Machinery Engineering from Tarbiat Modares University and a B.Sc. in Mechanical Engineering from the University of Tehran, his interdisciplinary expertise bridges advanced engineering with agricultural innovation. Dr. Bagherpour is a leading researcher in the application of artificial intelligence and machine vision in precision agriculture, with a focus on plant disease detection, crop quality assessment, and robotic harvesting. He has supervised multiple Ph.D. and M.Sc. theses on deep learning, image processing, and AI-driven diagnostics for crops like rose, wheat, hazelnut, and quince. His contributions significantly advance smart farming technologies, offering solutions for enhanced productivity and sustainable agriculture in small and large-scale systems.

Professional Profile:

GOOGLE SCHOLAR

ORCID

Summary of Suitability for Best Researcher Award – Dr. Hossein Bagherpour

Dr. Hossein Bagherpour is an exemplary candidate for the Best Researcher Award, recognized for his pioneering work at the intersection of biosystems engineering, artificial intelligence, and precision agriculture. As an Assistant Professor at Bu-Ali Sina University since 2013, Dr. Bagherpour has made significant contributions to the development and application of intelligent systems in agricultural automation and food quality assessment.

🎓 Education

🧪 Ph.D. in Biosystems Engineering – Tarbiat Modares University, Tehran, Iran
🚜 M.Sc. in Agricultural Machinery Engineering – Tarbiat Modares University, Tehran, Iran
⚙️ B.Sc. in Mechanical Engineering (Design of Machinery) – University of Tehran, Tehran, Iran

🏢 Work Experience

👨‍🏫 Assistant Professor, Department of Biosystems Engineering, Bu-Ali Sina University (2013–Present)
- 📍 Faculty of New Agriculture, Room 207
- 📍 Business Incubator Center No. 2, Room 7

🏆 Achievements & Contributions

📊 Supervised numerous Ph.D. and M.Sc. theses focusing on AI, deep learning, and smart agricultural systems
🤖 Developed algorithms for robotic harvesting, crop disease detection, and quality inspection using machine learning and computer vision
📚 Published multiple research papers (see Google Scholar) in areas such as AI-based phenotyping, intelligent sensors, and agricultural robotics

🎖 Awards & Honors

🌟 Recognized for advancing smart agriculture through AI integration
🧠 Leader in AI-driven research in agricultural biosystems

Publication Top Notes:

Hyperparameter Optimization of ANN, SVM, and KNN Models for Classification of Hazelnuts Images Based on Shell Cracks and Feature Selection Method

Enhancing the Performance of YOLOv9t Through a Knowledge Distillation Approach for Real-Time Detection of Bloomed Damask Roses in the Field

Development and Optimization of a Novel Deep Learning Model for Diagnosis of Quince Leaf Diseases

Detection of different adulteration in cinnamon powder using hyperspectral imaging and artificial neural network method

Design, Construction, and Evaluation of a Precision Vegetable Reaper to Use in Small Plots

A New Method to Optimize Deep CNN Model for Classification of Regular Cucumber Based on Global Average Pooling

Mr. Zhongwen Hao, Cranfield University, China

Zhongwen Hao is a Master’s candidate in Aerospace Manufacturing at Cranfield University, UK, and concurrently pursuing a Master of Mechanical Engineering at Nanjing University of Aeronautics and Astronautics, China. He completed his Bachelor’s degree in Electronic Information with a focus on Image Processing from China University of Mining and Technology. His research interests include robot control, visual servoing, image processing, and deep learning. Zhongwen has led notable projects such as visual servoing of robotic arms using deep learning techniques and galaxy image classification. His proficiency in programming with C++, Python, and MATLAB, coupled with his skills in deep learning and image processing, underscores his technical expertise. He has published research on motion prediction and object detection in visual servoing systems. Zhongwen is known for his strong project execution abilities, team spirit, and resilience.

Summary of Suitability:

Hao’s research direction aligns well with cutting-edge fields such as robot control, visual servoing, image processing, and deep learning. These areas are highly relevant and significant in contemporary technological advancements. Hao has a solid educational foundation with advanced studies in Aerospace Manufacturing and Mechanical Engineering, complemented by a bachelor’s degree in Electronic Information with a focus on Image Processing. This diverse yet interconnected educational background enhances his research capabilities.

Education

Cranfield University, Bedford, UK
Master’s Candidate of Aerospace Manufacturing
Major: Deep Learning and Image Processing
September 2023 – September 2024

Nanjing University of Aeronautics and Astronautics, Nanjing, China
Master of Mechanical Engineering
Major: Mechanical
September 2022 – June 2025 (Expected)

China University of Mining and Technology, Xuzhou, China
Bachelor of Electronic Information
Major: Image Processing
September 2017 – June 2021

Work Experience

Project Leader
Research on Visual Servoing of Robotic Arms Based on Deep Learning
June 2024 – September 2024

Led research on target detection using the DETR model, trajectory planning with the PSO algorithm, and motion prediction using BiLSTM and KAN neural networks.
Integrated and simulated algorithms in ROS using Gazebo to validate their effectiveness.

Participator
Galaxy Image Classification Based on Deep Learning
February 2024 – March 2024

Handled image preprocessing and reconstruction, and implemented galaxy image classification using the VIT model, achieving a classification accuracy of 90%.