Dr. Daniyah Alaswad
Ph.D. in Electrical and Computer Engineering | Oakland University
Daniyah Alaswad earned her Ph.D. at Oakland University under Mohamed A. Zohdy. Her research studies deep learning methods for generating images of Egyptian monuments and distinguishing synthetic images from authentic ones. Her work connects artificial intelligence, computer vision and the digital representation of cultural heritage.
Doctoral research (2025): Advanced deep learning to generate and detect fake images of Egyptian monuments
Research & Publications
2 verified research records · Newest first
Selected publications and doctoral research records. This list may not include every publication.
Advanced Deep Learning Methods to Generate and Discriminate Fake Images of Egyptian Monuments
View Publication ↗Start here · New researcher guide
A reading workflow, not an author-verified summary. Confirm all details in the original publication.
- Check the fit. Read the abstract and introduction. Write down the research question and explain how it relates to your idea.
- Understand the method. Identify the approach, assumptions, data and evaluation measures in the paper.
- Check reproducibility. Look for linked code, datasets and supplementary material. Availability has not been verified by ICCC.
- Find your next question. Read limitations and future work. Propose one extension and check newer literature before claiming a research gap.
- Plan a first experiment. Define a baseline, the change you will test and a measurable outcome. Discuss feasibility with your supervisor.
For questions or collaboration, visit the member profile and use a listed contact channel. Authorship and collaboration require agreement.
Advanced deep learning to generate and detect fake images of Egyptian monuments
View Doctoral Record ↗Start here · New researcher guide
A reading workflow, not an author-verified summary. Confirm all details in the original publication.
- Check the fit. Read the abstract and introduction. Write down the research question and explain how it relates to your idea.
- Understand the method. Identify the approach, assumptions, data and evaluation measures in the paper.
- Check reproducibility. Look for linked code, datasets and supplementary material. Availability has not been verified by ICCC.
- Find your next question. Read limitations and future work. Propose one extension and check newer literature before claiming a research gap.
- Plan a first experiment. Define a baseline, the change you will test and a measurable outcome. Discuss feasibility with your supervisor.
For questions or collaboration, visit the member profile and use a listed contact channel. Authorship and collaboration require agreement.
No publications match your search.