Search

Over the past several decades the dramatic increase in the availability of computational resources, coupled with the maturation of machine learning, has profoundly impacted sensor technology. In this Perspective, we discuss computational sensing with a focus on intelligent sensor system design. By leveraging inverse design and machine learning techniques, data acquisition hardware can be fundamentally redesigned to ‘lock-in’ to the optimal sensing data with respect to a user-defined cost function or design constraint. We envision a new generation of computational sensing systems that reduce the data burden while also improving sensing capabilities, enabling low-cost and compact sensor implementations engineered through iterative analysis of data-driven sensing outcomes. We believe that the methodologies discussed in this Perspective will permeate the design phase of sensing hardware, and thereby will fundamentally change and challenge traditional, intuition-driven sensor and readout designs in favour of application-targeted and perhaps highly non-intuitive implementations. Such computational sensors enabled by machine learning can therefore foster new and widely distributed applications that will benefit from ‘big data’ analytics and the internet of things to create powerful sensing networks, impacting various fields, including for example, biomedical diagnostics, environmental sensing and global health, among others. Traditional sensing techniques apply computational analysis at the output of the sensor hardware to separate signal from noise. A new, more holistic and potentially more powerful approach proposed in this Perspective is designing intelligent sensor systems that ‘lock-in’ to optimal sensing of data, making use of machine leaning strategies.

Conventional spectrometers are limited by trade-offs set by size, cost, signal-to-noise ratio (SNR), and spectral resolution. Here, we demonstrate a deep learning-based spectral reconstruction framework, using a compact and low-cost on-chip sensing scheme that is not constrained by the design trade-offs inherent to grating-based spectroscopy. The system employs a plasmonic spectral encoder chip containing 252 different tiles of nanohole arrays fabricated using a scalable and low-cost imprint lithography method, where each tile has a unique geometry and, thus, a unique optical transmission spectrum. The illumination spectrum of interest directly impinges upon the plasmonic encoder, and a CMOS image sensor captures the transmitted light, without any lenses, gratings, or other optical components in between, making the entire hardware highly compact, light-weight and field-portable. A trained neural network then reconstructs the unknown spectrum using the transmitted intensity information from the spectral encoder in a feed-forward and non-iterative manner. Benefiting from the parallelization of neural networks, the average inference time per spectrum is ~28 microseconds, which is orders of magnitude faster compared to other computational spectroscopy approaches. When blindly tested on unseen new spectra (N = 14,648) with varying complexity, our deep-learning based system identified 96.86% of the spectral peaks with an average peak localization error, bandwidth error, and height error of 0.19 nm, 0.18 nm, and 7.60%, respectively. This system is also highly tolerant to fabrication defects that may arise during the imprint lithography process, which further makes it ideal for applications that demand cost-effective, field-portable and sensitive high-resolution spectroscopy tools., Comment: 18 pages, 6 figures

Understanding the organization and mechanical function of the extracellular matrix (ECM) is critical for the development of therapeutic strategies that regulate wound healing following disease or injury. However, these relationships are challenging to elucidate during remodeling following myocardial infarction (MI) due to rapid changes in cellularity and an inability to characterize both ECM microstructure and function non-destructively. In this study, we overcome those challenges through whole organ decellularization and non-linear optical microscopy to directly relate the microstructure and mechanical properties of myocardial ECM. We non-destructively quantify collagen organization, content, and cross-linking within decellularized healthy and infarcted myocardium using second harmonic generation (SHG) and two photon excited autofluorescence. Tensile mechanical testing and compositional analysis reveal that the cumulative SHG intensity within each image volume and the average collagen autofluorescence are significantly correlated with collagen content and elastic modulus of the ECM, respectively. Compared to healthy ECM, infarcted tissues demonstrate a significant increase in collagen content and fiber alignment, and a decrease in cross-linking and elastic modulus. These findings indicate that cross-linking plays a key role in stiffness at the collagen fiber level following infarction, and highlight how this non-destructive approach to assessing remodeling can be used to understand ECM structure-function relationships.