Research Fellow at Islamic Azad University Science and Research Branch, Iran📖
Dr. Manijeh Emdadi is an accomplished Data Scientist and AI Specialist with 8 years of experience in designing, developing, and deploying machine learning models and data-driven solutions. Currently pursuing her Ph.D. in Artificial Intelligence at the Islamic Azad University, Tehran, her research focuses on exploring explainable AI models for healthcare decision support systems. Dr. Emdadi has a robust background in machine learning, neural networks, and deep learning, and she actively collaborates with cross-disciplinary teams to develop innovative AI solutions.
Profile
Scopus Profile
Google Scholar Profile
Education Background🎓
- Ph.D. in Artificial Intelligence (In Progress)
Islamic Azad University Science and Research Branch, Tehran, Iran
Research Focus: Exploring Explainable AI Models for Healthcare Decision Support Systems
- Master of Science in Data Science / Artificial Intelligence
Islamic Azad University Qazvin Branch, Qazvin, Iran
Thesis: Optimizing Neural Network Architectures for Image Recognition Tasks
- Bachelor of Science in Computer Engineering
Iran University of Science and Technology (IUST), Tehran, Iran
Relevant Courses: Advanced Algorithms
Professional Experience🌱
Dr. Emdadi has a strong professional background as a Data Scientist, collaborating with cross-functional teams to integrate predictive analytics into business workflows. Her expertise spans programming in Python, SQL, and Java, as well as working with data science tools such as Pandas, NumPy, Scikit-Learn, TensorFlow, and PyTorch. Additionally, she has experience deploying AI/ML models on cloud platforms like Google Cloud. She also serves as a teaching assistant for graduate-level courses on deep learning, sharing her knowledge and expertise with the next generation of AI professionals.
Dr. Emdadi’s primary research interests lie in the intersection of Artificial Intelligence, Machine Learning, and healthcare applications. She is particularly focused on exploring explainable AI models for decision support systems in healthcare, using machine learning and neural networks to solve complex problems in medical data analysis. Her research also includes advancements in deep learning and reinforcement learning, and she is dedicated to creating innovative AI solutions with real-world applications.
Author Metrics
Publications Top Notes 📄
1. “Introducing effective genes in lymph node metastasis of breast cancer patients using SHAP values based on the mRNA expression data”
- Authors: SZ Vahed, SMH Khatibi, YR Saadat, M Emdadi, B Khodaei, MM Alishani, et al.
- Journal: Plos One
- Volume: 19
- Issue: 8
- Article Number: e0308531
- Year: 2024
- DOI: 10.1371/journal.pone.0308531
- Summary: This paper applies SHAP (Shapley Additive Explanations) values to identify genes associated with lymph node metastasis in breast cancer patients, utilizing mRNA expression data for enhanced model interpretability.
2. “D-estimation method for grid synchronization of single-phase power converters: analysis, linear modeling, tuning, and comparison with SOGI-PLL”
- Authors: H Sepahvand, M Emdadi
- Journal: Electrical Engineering
- Year: 2023
- Summary: The study proposes a D-estimation method for grid synchronization in single-phase power converters. It provides a detailed analysis, linear modeling, tuning methods, and compares the performance with the traditional SOGI-PLL (Second-Order Generalized Integrator Phase-Locked Loop).
3. “Uncovering key molecular mechanisms in the early and late-stage of papillary thyroid carcinoma using association rule mining algorithm”
- Authors: SM Hosseiniyan Khatibi, S Zununi Vahed, H Homaei Rad, M Emdadi, et al.
- Journal: Plos One
- Volume: 18
- Issue: 11
- Article Number: e0293335
- Year: 2023
- DOI: 10.1371/journal.pone.0293335
- Summary: This research uses association rule mining to explore the molecular mechanisms involved in papillary thyroid carcinoma at various stages. The findings aim to reveal biomarkers for early diagnosis and targeted treatment strategies.
4. “Graph Fuzzy Attention Network Model for Metastasis Prediction of Prostate Cancer Based on mRNA Expression Data”
- Journal: International Journal of Fuzzy Systems
- Year: 2024
- Summary: This paper introduces a Graph Fuzzy Attention Network (GFAN) model for predicting metastasis in prostate cancer using mRNA expression data. The model leverages the strengths of fuzzy logic and graph-based learning for enhanced prediction accuracy.
5. “Load-aware Channel Assignment and Routing in Clustered Multichannel and Multi-radio Mesh Networks”
- Authors: M Emdadi, MR Shahsavari, MD TakhtFouladi
- Year: Unspecified
- Summary: This work discusses the optimization of channel assignment and routing protocols in clustered multi-channel and multi-radio mesh networks, with a focus on load-awareness for efficient resource utilization and network performance.
Conclusion
Dr. Manijeh Emdadi is exceptionally well-suited for the Best Researcher Award due to her pioneering work in artificial intelligence and its application to healthcare decision-making systems. Her strong academic background, innovative research, and commitment to advancing AI for healthcare make her an outstanding candidate. By enhancing collaborations with the industry and expanding her research scope, Dr. Emdadi can continue to build upon her current achievements and make even more significant contributions to both academic and real-world advancements in AI and healthcare.
In summary, Dr. Emdadi’s impressive AI expertise, innovative healthcare solutions, and strong academic contributions strongly align with the qualities sought for the Best Researcher Award.