Taye Mengistu | Machine learning | Best Researcher Award

Posted on by Invention Awards

Mr. Taye Mengistu | Machine learning | Best Researcher Award

IT engineer, Jigjiga University, Ethiopia

Mr. Taye Mengistu is an innovative researcher and lecturer based at Jigjiga University, Ethiopia. With a strong foundation in computer science and information technology, he is making notable strides in applying machine learning to real-world challenges. His pioneering work includes utilizing ensemble convolutional neural networks (CNNs) for the classification of mango diseases, a significant advancement in agricultural technology aimed at enhancing crop health and productivity.

Profile

Google Scholar

Education 🎓

Mr. Taye Mengistu holds a Master’s degree in Computer Science from Jimma University, Ethiopia, where he graduated in January 2022 with a GPA of 3.58. Prior to this, he completed his Bachelor’s degree in Information Technology at Jigjiga University, Ethiopia, graduating in July 2017 with a GPA of 3.84. His strong academic background underscores his deep understanding and expertise in his field.

Experience 🏢

Mr. Taye Mengistu has been serving as a Lecturer at Jigjiga University, Ethiopia, since October 2017. With over five years of experience, he has played a crucial role in both teaching and research. His responsibilities include delivering lectures, supervising student projects, and conducting research in various domains. His tenure at the university reflects his dedication to academic excellence and his ongoing commitment to advancing knowledge in his field.

Research Interests 🔬

Classification of Mango Disease Using Ensemble Convolutional Neural Network

The classification of mango diseases using ensemble convolutional neural networks (CNNs) represents a cutting-edge research area at the intersection of agriculture and artificial intelligence. This research focuses on leveraging advanced machine learning techniques to accurately identify and categorize diseases affecting mango crops, which is crucial for improving agricultural productivity and sustainability.

Key Aspects of Research Interests:

Ensemble Convolutional Neural Networks (CNNs): Utilizing ensemble methods to combine multiple CNN models to enhance classification accuracy. This approach improves the robustness and reliability of disease detection systems by aggregating predictions from different models.

Disease Classification: Developing algorithms to classify various mango diseases based on visual symptoms captured in images. Accurate classification helps in timely diagnosis and effective management strategies, minimizing crop loss and ensuring better yield.

Image Processing and Analysis: Applying image processing techniques to preprocess and analyze mango leaf and fruit images. This includes noise reduction, feature extraction, and image augmentation to improve model performance.

Machine Learning in Agriculture: Exploring the application of machine learning models to agricultural problems, particularly in disease detection and management. This research aims to bridge the gap between AI technology and practical agricultural needs.

Sustainable Agriculture: Enhancing disease management practices to promote sustainable agriculture. By accurately classifying and managing diseases, farmers can reduce the reliance on chemical treatments, leading to more eco-friendly farming practices.

Awards 🏆

Certification in HDP, Jigjiga University (May 2022) – Recognized for his advanced skills and knowledge in his field.

Publications 📚

Classification of mango disease using ensemble convolutional neural network– JSmart Agricultural Technology 2024. link

 

 

 

 

 

Seyed Mahmoud | Machine learning | Best Researcher Award

Posted on by Invention Awards

🌟Mr. Seyed Mahmoud, Machine learning, Best Researcher Award🏆

Seyed Mahmoud at Sajjadi Mohammadabadi University of Nevada Reno, United States

Mahmoud Sajjadi is a motivated Ph.D. student in Computer Science and Engineering at the University of Nevada, Reno, with extensive experience in machine learning, electrical and control engineering, and data center design and management. He has a proven track record of success in research, teaching, and industry roles, applying privacy-preserving distributed systems, federated learning, and optimization to solve power system challenges. Mahmoud has a strong foundation in mathematics and proficiency in various programming languages and tools.

Author Metrics

ORCID Profile

Mahmoud Sajjadi has contributed to several high-impact research papers and conferences, with publications under review in notable journals and conferences. His work has been accepted at prestigious venues such as the IEEE International Conference on Distributed Computing Systems (ICDCS) and the IEEE PES General Meeting. His contributions have an acceptance rate of around 21.9% in highly competitive conferences, reflecting the quality and significance of his research.

Education

Mahmoud holds a Ph.D. in Computer Science and Engineering from the University of Nevada, Reno, expected to be completed in May 2025. He earned his M.Sc. in Electrical Engineering-Control Systems from the University of Tehran, Iran, in 2014, where he focused on simultaneous state estimation and reinforcement learning in stochastic matrix games. He also holds a B.Sc. in Electrical Engineering-Control Systems from Shiraz University of Technology, Iran, obtained in 2011.

Research Focus

Mahmoud’s research focuses on privacy-preserving machine learning, federated learning, and optimization, particularly in power systems. He has developed innovative algorithms and models to enhance the efficiency and security of distributed learning systems. His work includes designing and implementing tree-based and neural network-based event classifiers, improving federated learning privacy, and optimizing machine learning algorithms for heterogeneous clients.

Professional Journey

Mahmoud’s professional journey includes significant roles in academia and industry. As a Graduate Research Assistant at the University of Nevada, Reno, he has made substantial contributions to developing privacy-preserving ML algorithms and distributed learning techniques. Prior to this, he served as a Data Center Designer and Manager at Prochista (Sematec, MCI) in Tehran, Iran, where he led AI model development, data center infrastructure management, and cybersecurity initiatives. He also worked as a Power Specialist Engineer at Arya Heavy Machinery (Caterpillar) in Tehran, guiding technical aspects of generator sales and market analysis.

Honors & Awards

Mahmoud has received several honors and awards, including the GSA Outstanding Graduate Researcher Award from the University of Nevada, Reno, in 2024. He was awarded the TechWise program scholarship by TalentSprint Inc., supported by Google, for the period 2023-2024. He is a member of the National Organization for Development of Exceptional Talents of Iran and has earned multiple certifications in data center design and management.

Publications Noted & Contributions

Mahmoud has numerous publications to his credit, including works under review and accepted papers in prestigious journals and conferences. His notable publications include “Speed Up Federated Learning in Heterogeneous Environment: A Dynamic Tiering Approach,” “Communication-Efficient Training Workload Balancing for Decentralized Multi-Agent Learning,” and “Generative Artificial Intelligence for Distributed Learning to Enhance Smart Grid Communication.” His research contributions span across federated learning, distributed learning, and smart grid communication.

  • Title: Generative Artificial Intelligence for Distributed Learning to Enhance Smart Grid Communication
  • Journal: International Journal of Intelligent Networks
  • Year: 2024
  • DOI: 10.1016/j.ijin.2024.05.007
  • Contributors:
    • Seyed Mahmoud Sajjadi Mohammadabadi
    • Mahmoudreza Entezami
    • Aidin Karimi Moghaddam
    • Mansour Orangian
    • Shayan Nejadshamsi

Summary: The article likely explores the application of generative artificial intelligence (AI) techniques for distributed learning in improving communication within smart grid systems. Smart grids are modern electrical grids that incorporate digital communication technology to monitor and manage electricity supply more efficiently. Enhancing communication within smart grids is crucial for ensuring reliability, efficiency, and resilience in power distribution. By leveraging generative AI, the authors may propose innovative methods to optimize communication protocols, data transmission, or network management within smart grid infrastructures. This research could contribute to advancing the development and implementation of intelligent systems for future energy networks.

Research Timeline

Mahmoud’s research timeline is marked by continuous contributions from 2014 to the present. Starting with his work on simultaneous learning and state estimation during his M.Sc., he has progressively advanced to developing cutting-edge federated learning algorithms and models for power systems and smart grids. His ongoing projects and research efforts reflect his dedication to advancing the field of distributed learning and machine learning applications.

Collaborations and Projects

Throughout his career, Mahmoud has collaborated with esteemed researchers and institutions. At the University of Nevada, Reno, he worked with Dr. L. Yang, F. Yan, and J. Zhang on federated learning and decentralized multi-agent learning projects. His industry collaborations at Prochista involved leading R&D teams and supervising data center construction projects. Mahmoud has also been involved in cross-disciplinary research experiences for undergraduates on big data analytics in smart cities, funded by NSF.