postdoc, Technical University of Denmark.
Dr. Ashkan Tashk is a highly accomplished electrical engineer and postdoctoral researcher with deep expertise in telecommunications, machine learning, and biomedical imaging. With a strong academic and teaching background, he has worked across multiple prestigious institutions in Denmark, Germany, and Iran. His career blends theoretical knowledge with applied innovations, particularly in AI-driven healthcare technologies, contributing significantly to interdisciplinary research and development. He is known for his dedication to science communication, teaching, and AI-based applications in medicine.
Publication Profile
Google scholar
🎓 Education Background:
Ashkan Tashk received his Ph.D. in Electrical Engineering with a focus on Telecommunications in 2015, following his M.Sc. (2010) and B.Sc. (2006) in the same field. His undergraduate project involved designing and constructing a prototype sunlight tracking platform—an early indication of his strong interest in applied engineering and innovation. His academic journey provided a solid foundation in electronics, signal processing, and machine learning, which continues to influence his research today.
💼 Professional Experience:
Dr. Tashk currently serves as a Postdoctoral Researcher at Denmark’s leading universities (2019–present). Prior to that, he worked as a telecommunications expert at FREC and completed a research internship at Karlsruhe Institute of Technology (KIT), Germany. His career includes teaching roles at the University of Southern Denmark, University of Copenhagen, and various Iranian academic institutions. He has taught courses in electrical circuits, microprocessors, statistics, numerical analysis, and MATLAB programming, while also publishing Persian-language technical tutorials and conducting workshops in Europe and Iran.
🏆 Awards and Honors:
Dr. Ashkan Tashk became an IEEE Senior Member in 2022, recognizing his professional maturity and significant contributions to electrical engineering. He has served as a session chair at multiple international conferences such as ACSIT2020 in Copenhagen and ICCAIRO2019 in Athens. He has also completed prestigious programs like the “Science Communication” course by the Royal Danish Academy of Sciences and Letters and the RCR workshop at the University of Copenhagen, demonstrating his commitment to ethical and effective scientific practice.
🔬 Research Focus:
Ashkan’s research centers on the application of artificial intelligence and machine learning in biomedical engineering, particularly in image processing, ultrasound tomography, and cancer diagnostics. Notable projects include developing LSTM-RF models for metastatic prostate cancer prediction, CNN-based biomedical segmentation tools, and advanced metabolomics data imputation methods. His work also spans sonar signal processing, image-based fingerprint recognition, and microprocessor-controlled automation systems. These interdisciplinary projects reflect his strong problem-solving abilities and technological foresight.
🧩 Conclusion:
Dr. Ashkan Tashk is a dynamic academic, educator, and innovator whose work bridges electrical engineering and biomedical science using modern AI tools. His technical skill set, coupled with his teaching excellence and global collaborations, position him as a thought leader in the integration of engineering and healthcare. Fluent in Persian, English, and Danish, and proficient in tools like Python, MATLAB, and various PLC programming languages, he continues to impact both academia and industry with his visionary contributions.
📚 Top Publications & Citations:
Semantic Segmentation of Biomedical Images Using Deep Convolutional Neural Networks
Journal: Journal of Medical Imaging and Health Informatics
Cited by: 24 articles
Predicting Metastatic Prostate Cancer via Biochemical Parameters Using LSTM and RF
Journal: Computers in Biology and Medicine
Cited by: 18 articles
Machine Learning Imputation for Large-scale Metabolomics Data
Journal: Metabolomics
Cited by: 10 articles
Eye-Tracking Data Analysis Using AI for Cognitive Study
Journal: IEEE Transactions on Affective Computing
Cited by: 7 articles