Abstract: Described herein are means for generation of self-taught generic models, named Models Genesis, without requiring any manual labeling, in which the Models Genesis are then utilized for the processing of medical imaging. For instance, an exemplary system is specially configured for learning general-purpose image representations by recovering original sub-volumes of 3D input images from transformed 3D images. Such a system operates by cropping a sub-volume from each 3D input image; performing image transformations upon each of the sub-volumes cropped from the 3D input images to generate transformed sub-volumes; and training an encoder-decoder architecture with skip connections to learn a common image representation by restoring the original sub-volumes cropped from the 3D input images from the transformed sub-volumes generated via the image transformations.

Abstract: A method estimates an intention of a lead vehicle by an ego vehicle. The method includes: (a) receiving, from at least one of a first plurality of sensors coupled to the ego vehicle, information associated with a parametric variable, (b) selecting a partition of an operating region of the parametric variable based on the parametric variable information, wherein the operating region includes a predetermined range of values for the parametric variable, wherein the partition includes a subset of the predetermined range of values and being associated with a predetermined ego vehicle input, and wherein the predetermined vehicle input includes at least one value for a parameter corresponding to dynamics of the ego vehicle, and (c) causing a vehicle control system of the ego vehicle to perform a vehicle maneuver based on the predetermined ego vehicle input.

Abstract: Disclosed are compositions for generating an immune response against human immunodeficiency virus (HIV) and their methods of uses.

Abstract: A method includes simulating diffraction in a transmission geometry of relativistic electron bunches from a crystallographic structure of a crystal thereby simulating diffraction of the relativistic electron bunches into a plurality of Bragg peaks. The method includes selecting a range of angles between a direction of propagation of the relativistic electron bunches and a normal direction of crystal including an angle at which a diffraction portion is maximized. The method includes sequentially accelerating a plurality of physical electron bunches to relativistic energies toward a physical crystal having the crystallographic structure and diffracting the plurality of physical electron bunches off the physical crystal at different angles and measuring the diffraction portion into the respective Bragg peak at the different angles. The method includes selecting a final angle based on the measured diffraction portion into the respective Bragg peak at the different angles and generating a pulse of light.

Abstract: A computer-implemented framework and/or system for cyberbullying detection is disclosed. The system includes two main components: (1) A representation learning network that encodes the social media session by exploiting multi-modal features, e.g., text, network, and time; and (2) a multi-task learning network that simultaneously fits the comment inter-arrival times and estimates the bullying likelihood based on a Gaussian Mixture Model. The system jointly optimizes the parameters of both components to overcome the shortcomings of decoupled training. The system includes an unsupervised cyberbullying detection model that not only experimentally outperforms the state-of-the-art unsupervised models, but also achieves competitive performance compared to supervised models.

Abstract: The present disclosure provides devices, systems, and methods related to sequencing a biopolymer. In particular, the present disclosure provides methods of obtaining a bioelectronic signature based on current fluctuations that correspond to the activity of an enzyme-of-interest. As described herein, certain aspects of the bioelectronic signature can be used to determine the sequence of a biopolymer.

Abstract: Described herein are means for training a deep model to learn contrastive representations embedded within part-whole semantics via a self-supervised learning framework, in which the trained deep models are then utilized for the processing of medical imaging. For instance, an exemplary system is specifically configured for performing a random cropping operation to crop a 3D cube from each of a plurality of medical images received at the system as input; performing a resize operation of the cropped 3D cubes; performing an image reconstruction operation of the resized and cropped 3D cubes to predict the resized whole image represented by the original medical images received; and generating a reconstructed image which is analyzed for reconstruction loss against the original image representing a known ground truth image to the reconstruction loss function. Other related embodiments are disclosed.

Abstract: Methods for screening of affinity reagents for many target proteins of interest simultaneously. Arrayed targets (e.g., peptide, protein, RNA, cell, etc.) are used in affinity selection experiments to reduce the amount of target needed and to improve the throughput of discovering recombinant affinity reagents to a large collection of targets.

Abstract: Various embodiments of a system and associated method for anonymization of text without losing semantic utility of text by extracting a latent embedding representation of content with respect to a given task and by learning an optimal strategy for text embedding manipulation to satisfy both privacy and utility requirements are disclosed herein. In particular, the system balances private attribute obfuscation with retained semantic utility.

Abstract: A system includes a Bayesian Spatiotemporal Graph Transformer (B-STAR) architecture that models spatial and temporal relationship of multiple agents under uncertainties. The system enables Multi-Agent Trajectory Prediction for safety-critical engineering applications, (e.g., autonomous driving and flight systems) and considers the impact of various sources, such as environmental conditions, pilot/controller behaviors, and potential conflicts with nearby aircraft. It is shown that B-STAR achieves state-of-the-art performance on the ETH/UCY pedestrian dataset with UQ competence.

Abstract: Provided herein are synthetic nucleic acid molecules and methods of using such synthetic nucleic acid molecules for strong repression of target gene expression. In particular, provided herein are methods for altering expression of a protein in a cell, where the method comprises introducing into a cell a protein coding sequence operably linked to a near-threshold translational repressor having first and second trigger recognition sequences that are fully or partially complementary to a repressing trigger RNA; and introducing into a cell the repressing trigger RNA.

Abstract: Compositions and methods for genetically modifying at least one nucleic acid sequence of interest in a polyploid organism.

Abstract: A wound dressing includes: a structural material formed into a dressing; at least one immunomodulatory agent associated with the dressing; and a growth factor associated with the dressing. A wound dressing kit includes: a structural material formed into a wound dressing; an immunomodulatory agent; and a growth factor composition, wherein the structural material contains the immunomodulatory agent and/or the immunomodulatory agent in a separate composition. A method of treating a wound in a tissue includes: applying an immunomodulatory agent to the wound; applying a wound dressing to the wound; and allowing the wound to heal with the immunomodulatory agent and wound dressing. The application of a growth factor can be before, during and/or after applying the wound dressing to the wound.

Abstract: Fabricating a nanopore sensor includes depositing a first and second oxide layers on first and second sides of a sapphire substrate. The second oxide layer is patterned to form an etch mask having a mask opening in the second oxide layer. A crystalline orientation dependent wet anisotropic etch is performed on the second side of the sapphire substrate using the etch mask to form a cavity having sloped side walls through the sapphire substrate to yield an exposed portion of the first oxide layer, each of the sloped side walls being a crystalline facet aligned with a respective crystalline plane of the sapphire substrate. A silicon nitride layer is deposited on the first oxide layer. The exposed portion of the first oxide layer in the cavity is removed, thereby defining a silicon nitride membrane in the cavity. An opening is formed through the silicon nitride membrane.

Abstract: Various embodiments for predicting which software vulnerabilities will be exploited by malicious hackers and hence prioritized by patching are disclosed.

Abstract: A neural network accelerator architecture for multiple task adaptation comprises a volatile memory comprising a plurality of subarrays, each subarray comprising M rows and N columns of volatile memory cells; a source line driver connected to a plurality of N source lines, each source line corresponding to a column in the subarray; a binary mask buffer memory having size at least N bits, each bit corresponding to a column in the subarray, where a 0 corresponds to turning off the column for a convolution operation and a 1 corresponds to turning on the column for the convolution operation; and a controller configured to selectively drive each of the N source lines with a corresponding value from the mask buffer; wherein each column in the subarray is configured to store a convolution kernel.

Abstract: Described herein are polyhedral, three-dimensional tunable nanocages assembled with a multimeric protein covalently linked to a polynucleotide handle and a DNA origami base assembly including sequences complementary to the polynucleotide handles, wherein the polynucleotide handle and the complementary sequences hybridize to for double-stranded DNA helices.

Abstract: Provided herein are CRISPR-based synthetic repression systems as well as methods and compositions using the synthetic repression systems to treat septicemia, an adverse immune response in a subject and Waldenström macroglobulinemia.

Abstract: A series of functionalized imidazophenthridine analogue-based blue phosphorescent emitters have been designed, where bulky substituents (e.g., tetrabutyl, phenyl, mesityl, triisopropylbenzene, etc.) are introduced on an imidazophenthridine fragment of the emitters. Bulky substituents may suppress potential excimer formation, as well as improve the solubility of the complexes. This class of emitters may be utilized in luminescent labels, emitters for organic light emitting devices, and lighting applications.

Abstract: Tracking-based motion deblurring via coded exposure is provided. Fast object tracking is useful for a variety of applications in surveillance, autonomous vehicles, and remote sensing. In particular, there is a need to have these algorithms embedded on specialized hardware, such as field-programmable gate arrays (FPGAs) or application-specific integrated circuits (ASICs), to ensure energy-efficient operation while saving on latency, bandwidth, and memory access/storage. In an exemplary aspect, an object tracker is used to track motion of one or more objects in a scene captured by an image sensor. The object tracker is coupled with coded exposure of the image sensor, which modulates photodiodes in the image sensor with a known exposure function (e.g., based on the object tracking). This allows for motion blur to be encoded in a characteristic manner in image data captured by the image sensor. Then, in post-processing, deblurring is performed using a computational algorithm.