Dr. Emadeldeen is a researcher focused on time series data analysis using deep learning. My work focuses on developing models that can learn effectively with limited labels, adapt to changes in data over time, and generalize across diverse domains. I’m especially interested in self-supervised and domain adaptation methods, as well as designing architectures that combine temporal, frequency, and structural insights. I’ve applied these ideas to real-world problems such as sleep stage classification and machine fault diagnosis, and published in top venues like ICML, KDD, AAAI, TPAMI, and TNNLS.