Developing a deep learning model to improve similarity detection in diverse biological samples, based on shared biological structures, disease-specific features, and molecular markers while eliminating demographic biases. This approach has the potential to significantly advance medical diagnostics by enabling more precise, and reliable disease detection.
Developed computational methods to simplify complex imaging mass spectrometry data and automatically detect isotope candidates in high-dimensional data. These techniques improved the understanding of molecular structures in biological tissues and enhanced data analysis accuracy and efficiency, enabling the identification of critical molecular markers vital for drug development. This research culminated in a drafted manuscript that addressed major challenges and advanced the state of the art.
Developed a robust sensing matrix based on an equiangular tight frame, reducing pairwise correlation and ensuring tightness. This advancement enhances compressive sensing in applications like wireless communication, medical imaging, satellite imaging, radar systems, and signal processing.
Proposed a representation-based feature extraction model to address challenges of insufficient inter-class margin and loss of manifold structure. This approach is particularly effective in classification and recognition tasks with limited training data.
A regression-based feature extraction model is developed to preserve the underlying structure of the data with sufficient inter-class margins.