In my research, I explore the growing impact of Artificial Intelligence (AI), particularly deep learning, across healthcare, energy systems, and power electronics. Alongside other researchers, I investigate how advanced neural networks, multimodal imaging, and intelligent optimization techniques can be applied to solve complex and practical challenges.
In the medical domain, other studies have demonstrated how deep learning improves cancer detection and classification from histopathological, MRI, and CT images. Building on this foundation, I apply similar techniques to ovarian cancer detection, prostate cancer classification, and kidney disease analysis, while also extending my work to chest radiographs for the classification of Covid-19, pneumonia, and lung cancer. Like many researchers, I also recognize the importance of multimodal imaging and patient-specific factors, such as gender identity, in improving diagnostic performance and clinical relevance.
Beyond medicine, both my work and that of other researchers focus on energy and electronics. Regression-based approaches have been widely used to analyze solar irradiance for power forecasting, and I contribute to this field by exploring surface longwave downward irradiance impacts. Likewise, AI-driven optimization in power electronics—particularly in inverter design and DC-AC voltage conditioning—has been an active research area, and I investigate how cascaded multilevel inverters and AI-based control strategies can improve performance and efficiency.
Here are the list of my works that reflect these research directions:
