This document does not contain technology or technical data controlled under either the U.S. International Traffic in Arms Regulations or the U.S. Export Administration Regulations.With the development and widespread use of wireless devices in recent years (mobile phones, Internet of Things, Wi-Fi), the electromagnetic spectrum has become extremely crowded. In order to counter security threats posed by rogue or unknown transmitters, it is important to identify RF transmitters not by the data content of the transmissions but based on the intrinsic physical characteristics of the transmitters. RF waveforms represent a particular challenge because of the extremely high data rates involved and the potentially large number of transmitters present in a given location. These factors outline the need for rapid fingerprinting and identification methods that go beyond the traditional hand-engineered approaches. In this study, we investigate the use of machine learning (ML) strategies to the classification and identification problems, and the use of wavelets to reduce the amount of data required. Four different ML strategies are evaluated: deep neural nets (DNN), convolutional neural nets (CNN), support vector machines (SVM), and multi-stage training (MST) using accelerated Levenberg-Marquardt (A-LM) updates. The A-LM MST method preconditioned by wavelets was by far the most accurate, achieving 100% classification accuracy of transmitters, as tested using data originating from 12 different transmitters. We discuss strategies for extension of MST to a much larger number of transmitters.

Conventional image restoration algorithms use transform-domain filters, which separate the noise from the sparse signal among the transform components or apply spatial smoothing filters in real space whose design relies on prior assumptions about the noise statistics. These filters also reduce the information content of the image by suppressing spatial frequencies or by recognizing only a limited set of shapes. Here we show that denoising can be efficiently done using a nonlinear filter, which operates along patch neighborhoods and multiple copies of the original image. The use of patches enables the algorithm to account for spatial correlations in the random field whereas the multiple copies are used to recognize the noise statistics. The nonlinear filter, which is implemented by a hierarchical multistage system of multilayer perceptrons, outperforms state-of-the-art denoising algorithms such as those based on collaborative filtering and total variation. Compared to conventional denoising algorithms, our filter can restore images without blurring them, making it attractive for use in medical imaging where the preservation of anatomical details is critical.

Shear stress is an important physical factor that regulates proliferation, migration and morphogenesis. In particular, the homeostasis of blood vessels is dependent on shear stress. To mimic this process ex vivo, efforts have been made to seed scaffolds with vascular and other cell types in the presence of growth factors and under pulsatile flow conditions. However, the resulting bioreactors lack information on shear stress and flow distributions within the scaffold.Consequently, it is difficult to interpret the effects of shear stress on cell function. Such knowledge would enable researchers to improve upon cell culture protocols. Recent work has focused on optimizing the microstructural parameters of the scaffold to fine tune the shear stress.In this study, we have adopted a different approach whereby flows are redirected throughout the bioreactor along channels patterned in the porous scaffold to yield shear stress distributions that are optimized for uniformity centered on a target value. A topology optimization algorithm coupled to computational fluid dynamics simulations was devised to this end. The channel topology in the porous scaffold was varied using a combination of genetic algorithm and fuzzy logic. The method is validated by experiments using magnetic resonance imaging (MRI) readouts of the flow field.

Mechanical forces such as fluid shear have been shown to enhance cell growth and differentiation, but knowledge of their mechanistic effect on cells is limited because the local flow patterns and associated metrics are not precisely known. Here we present real-time, noninvasive measures of local hydrodynamics in 3D biomaterials based on nuclear magnetic resonance. Microflow maps were further used to derive pressure, shear and fluid permeability fields. Finally, remodeling of collagen gels in response to precise fluid flow parameters was correlated with structural changes. It is anticipated that accurate flow maps within 3D matrices will be a critical step towards understanding cell behavior in response to controlled flow dynamics.