Search for: All records

This work proposes a deep learning (DL)-based framework, namely Sim2Real, for spectral signal reconstruction in reconstructive spectroscopy, focusing on efficient data sampling and fast inference time. The work focuses on the challenge of reconstructing real-world spectral signals in an extreme setting where only device-informed simulated data are available for training. Such device-informed simulated data are much easier to collect than real-world data but exhibit large distribution shifts from their real-world counterparts. To leverage such simulated data effectively, a hierarchical data augmentation strategy is introduced to mitigate the adverse effects of this domain shift, and a corresponding neural network for the spectral signal reconstruction with our augmented data is designed. Experiments using a real dataset measured from our spectrometer device demonstrate that Sim2Real achieves significant speed-up during the inference while attaining on-par performance with the state-of-the-art optimization-based methods. 

Experiments successfully established the feasibility of a nanopillar-LED-based tactile sensor showing tactile perception at extremely cold temperatures. 

A chip-scale spectrometer is proposed to resolve linear polarization information in the visible-wavelength range. The design was supported with preliminary experimental data based on elliptical cross-section nanopillar-shaped GaN photodetectors.