More information
Description
The project will push the frontiers of AI and Big Data and take important steps towards making the hyperspectral technologies of tomorrow possible, with direct impact in various parts of environment, health and industry sectors. To address these difficulties, we propose novel learning and optimization techniques for hyperspectral imaging systems. First novelty consists in defining appropriate models (loss functions), which include additional data representations, relational information about data or ways of removing the influence of noise from predictor performance, boosting performance even when dealing with small datasets. However, high-quality models based on these new features would require hard Big Data (possibly nonconvex) optimization formulations, which further need fast and scalable algorithms with proper convergence guarantees. The second novelty consists of developing fast optimization algorithms (e.g. higher order, projection or stochastic splitting methods) having low complexity per iteration and scalability. In conclusion, we aim to create, analyze and implement efficient learning and optimization algorithms for hyperspectral imaging models with applications to ocean monitoring and medical imaging. We will implement the algorithms, benchmark them using real datasets, ensure the algorithms’ interoperability, and produce free software.
The results will have immediate impact in several fields. Our research is oriented towards the environment and health sectors, in which there is a real need for AI and Big Data technologies. In addition to the papers, submitted to top ICT conferences and journals, that our scientific work will generate, our experiments will include specific tests to answer the needs of our collaborators in the ocean monitoring and medical imaging. Our approach to learning and optimization in the hyperspectral world and the results of our objectives will make a direct impact in the science and practice of AI and Big Data.