Abstract: One embodiment provides an apparatus for fluorescence lifetime imaging (FLI). The apparatus includes a deep neural network (DNN). The DNN includes a first convolutional layer, a plurality of intermediate layers and an output layer. The first convolutional layer is configured to receive FLI input data. Each intermediate layer is configured to receive a respective intermediate input corresponding to an output of a respective prior layer. Each intermediate layer is further configured to provide a respective intermediate output related to the received respective intermediate input. The output layer is configured to provide estimated FLI output data corresponding to the received FLI input data. The DNN is trained using synthetic data.

Abstract: A deep neural network for metal artifact reduction is described. A method for computed tomography (CT) metal artifact reduction (MAR) includes receiving a first CT image data; receiving a second CT image data; and generating, by an artificial neural network (ANN), CT output image data configured to include fewer artifacts compared to the first and second CT image data. The ANN includes at least two parallel CT image data streams and a CT output image data stream. A first of the at least two parallel CT image data streams is based, at least in part, on the first CT image data, a second of the at least two parallel CT image data stream is based, at least in part, on the second CT image data. The CT output image data stream is based, at least in part, on respective outputs of the at least two parallel CT image data streams.

Abstract: Embodiments of the invention relate generally to electrospun fibers and, more particularly, to the controlled release of an active pharmaceutical ingredient (API) from electrospun fiber scaffolds (EFSs).

Abstract: Generate, for each of the words of a common vocabulary of first and second text corpora, a first word embedding vector in the first text corpus and a second word embedding vector in the second text corpus. Generate, for each word in a random sample of non-landmark words, an artificially shifted word embedding vector by modifying the first word embedding vector for that word. Train a machine learning classifier to predict whether an artificial shift has been injected for a given word, based on the artificially shifted word embedding vector and the second word embedding vector for the given word. Predict semantic shifts for at least a plurality of the words of the common vocabulary by providing the first word embedding vectors and the second word embedding vectors for at least the plurality of the words of the common vocabulary as input to the trained machine learning classifier.

Abstract: A system for generating a high resolution (HR) computed tomography (CT) image from a low resolution (LR) CT image is described. The system includes a first generative adversarial network (GAN) and a second GAN. The first GAN includes a first generative neural network (G) configured to receive a training LR image dataset and to generate a corresponding estimated HR image dataset, and a first discriminative neural network (DY) configured to compare a training HR image dataset and the estimated HR image dataset. The second GAN includes a second generative neural network (F) configured to receive the training HR image dataset and to generate a corresponding estimated LR image dataset, and a second discriminative neural network (DX) configured to compare the training LR image dataset and the estimated LR image dataset.

Abstract: A machine-learning-based monochromatic CT image reconstruction method is described for quantitative CT imaging. The neural network is configured to learn a nonlinear mapping function from a training data set to map a CT image, which is reconstructed from a single spectral current-integrating projection data set, to monochromatic projections at a pre-specified energy level, realizing monochromatic CT imaging and overcoming beam hardening. An apparatus, method and/or system are configured to determine, by a trained artificial neural network (ANN), a monochromatic projection data set based, at least in part, on a measured CT image. The measured CT image may be reconstructed based, at least in part, on measured projection data. The measured projection data may be polychromatic. The apparatus, method and/or system may be further configured to reconstruct a monochromatic CT image based, at least in part, on the monochromatic projection data set.

Abstract: One embodiment provides a method of training an artificial neural network (ANN) for denoising. The method includes generating, by a similarity module, a respective set of similar elements for each noisy input element of a number of noisy input elements included in a single noisy input data set. Each noisy input element includes information and noise. The method further includes generating, by a sample pair module, a plurality of training sample pairs. Each training sample pair includes a pair of selected similar elements corresponding to a respective noisy input element. The method further includes training, by a training module, an ANN using the plurality of training sample pairs. Each set of similar elements is generated prior to training the ANN. The plurality of training sample pairs is generated during training the ANN. The training is unsupervised.

Abstract: A luminescent solar concentrator including a light propagation device, one or more photovoltaic cells, and one or more waveguides is provided. The light propagation device includes a plurality of nanostructures configured to permit preferential propagation of a wavelength range of light in one direction. The one or more photovoltaic cells are positioned adjacent an end of the light propagation device. The one or more waveguides are configured to guide light toward the one or more photovoltaic cells via total internal reflection within the luminescent solar concentrator.

Abstract: Embodiments of the invention relate to a novel class of polymers with superior mechanical properties and chemical stability, as compared to known polymers. These polymers are particularly well suited for use in anion exchange membranes (AEMs), including those employed in fuel cells. Novel methods for the manufacture of these polymers are also described.

Abstract: One embodiment provides a broadband signal source. The broadband signal source includes a number, n, signal paths and a combiner circuitry. Each signal path, i, includes a programmable phase shifter circuitry, an amplifier circuitry and a harmonic generation circuitry. The programmable phase shifter circuitry is configured to phase shift a path input signal by a respective phase angle, ?i. The path input signal corresponds to a source input signal having a fundamental frequency, f, and an input signal bandwidth. The amplifier circuitry is configured to amplify the phase shifted path input signal. The harmonic generation circuitry is configured to generate a path output signal including a plurality of harmonics of the amplified phase shifted path input signal.

Abstract: The electrochemical energy conversion system of the present disclosure includes an anode, a cathode, and an ion exchange membrane including a polymer having an aromatic polymer chain and an alkylated substrate including an alkyl chain, and at least one ionic group. The alkylated substrate is bound to at least one aromatic group in the polymer chain via Friedel-Crafts alkylation of the at least one aromatic group. The alkylation reaction utilizes a haloalkylated tertiary alcohol or a haloalkylated alkene as a precursor. In the presence of an acid catalyst, a carbocation is generated in the precursor which reacts with the aromatic rings of the polymer chain. The at least one ionic group is then replaced with a desired cationic or anionic group using a substitution reaction. The membranes exhibit advantageous stability achieved through a simplified and scalable reaction scheme.

Abstract: Compositions discussed herein are useful for treating a patient infected with a coronavirus, notably SARS-CoV-2 or COVID-19. The compositions to be administered to an infected patient utilize inhibitors of SARS-CoV-2 papain-like protease (PLpro). Several of these inhibitors include available hepatitis C virus (HCV) drugs that are already FDA-approved. These PLpro inhibitors have been found to be strongly synergistic with inhibitors of SARS-CoV-2 polymerases, such as RNA-dependent RNA polymerase (RdRp). One such polymerase inhibitor, remdesivir, is already in use as an anti-viral treatment of patients with COVID-19. The PLpro inhibitors, including repurposed HCV drugs such as grazoprevir, vaniprevir, and paritaprevir, increase remdesivir's ability to suppress coronavirus replication antiviral activity as much as 10-fold.

Abstract: For a passage text and a corresponding answer text, perform a word-level soft alignment to obtain contextualized passage embeddings and contextualized answer embeddings, and a hidden level soft alignment on the contextualized passage embeddings and the contextualized answer embeddings to obtain a passage embedding matrix. Construct a passage graph of the passage text based on the passage embedding matrix, and apply a bidirectional gated graph neural network to the passage graph until a final state embedding is determined, during which intermediate node embeddings are fused from both incoming and outgoing edges. Obtain a graph-level embedding from the final state embedding, and decode the final state embedding to generate an output sequence word-by-word. Train a machine learning model to generate at least one question corresponding to the passage text and the answer text, by evaluating the output sequence with a hybrid evaluator combining cross-entropy evaluation and reinforcement learning evaluation.

Abstract: A system for few-view computed tomography (CT) image reconstruction is described. The system includes a preprocessing module, a first generator network, and a discriminator network. The preprocessing module is configured to apply a ramp filter to an input sinogram to yield a filtered sinogram. The first generator network is configured to receive the filtered sinogram, to learn a filtered back-projection operation and to provide a first reconstructed image as output. The first reconstructed image corresponds to the input sinogram. The discriminator network is configured to determine whether a received image corresponds to the first reconstructed image or a corresponding ground truth image. The generator network and the discriminator network correspond to a Wasserstein generative adversarial network (WGAN). The WGAN is optimized using an objective function based, at least in part, on a Wasserstein distance and based, at least in part, on a gradient penalty.

Abstract: In one embodiment, there is provided a system for applying therapy to a human body. The system includes a coupling apparatus and a supporting apparatus. The coupling apparatus is configured to couple to an upper body portion of a user. The supporting apparatus is configured to support at least a portion of a weight of the user. An amount of weight that is supported is adjustable. In some embodiments, the system may further include a control apparatus configured to control at least one of a state and/or a position of the supporting apparatus.

Abstract: One embodiment provides a line of sight detector. The line of sight detector includes a first TeraFET (field effect transistor) including a first source, a first drain, a first gate, and a first channel having a first end and a second end. The line of sight detector further includes a first source antenna coupled to the first source; a first drain antenna coupled to the first drain; and a third antenna. Each antenna is configured to receive an incident radiation signal having a frequency in a sub terahertz or a terahertz frequency range. Each antenna is positioned a respective distance from each other antenna. Each distance is less than one wavelength of the incident radiation signal.

Abstract: Embodiments of the invention relate generally to electrospun fibers and, more particularly, to the controlled release of an active pharmaceutical ingredient (API) from electrospun fiber scaffolds (EFSs).

Abstract: A solar cell device having a solid state light absorber region that incorporates a donor-acceptor particle structure. The particle structure includes acceptor particles that generate a flow of electrons in the solid state light absorber region in response to absorbed photons; and donor particles comprising a phosphorescent material, wherein each donor particle is coupled to a group of acceptor particles, and wherein the phosphorescent material absorbs high energy photons and emits lower energy photons that are absorbed by the acceptor particles.

Abstract: A direct current-direct current (DC-DC) converter includes a plurality of switches configured to be coupled to a voltage source. The DC-DC converter also includes a transformer having a primary winding coupled to the plurality of switches and a secondary winding. The DC-DC converter further includes a first capacitor; and a second capacitor, wherein the first capacitor is coupled in series with the primary winding, the second capacitor is coupled in parallel with the secondary winding. The first capacitor, the second capacitor, and a leakage inductance of the transformer form a dual-capacitor resonant circuit.

Abstract: Systems and methods for lighting an environment are disclosed. A lighting system includes at least one light source and a control system in communication with the at least one light source. The light source is configured to emit light having a plurality of emission characteristics. The control system is configured to randomly vary at least one of the emission characteristics of the light emitted by the light source. A method for lighting an environment includes emitting light from a light source, and randomly varying at least one of the emission characteristics of the emitted light.