Abstract: A method and apparatus for estimating depth information of an image are disclosed. The depth information estimation method of the image includes providing a confidence map for a ground truth depth map; and learning a depth information estimation model for estimating depth information of an image based on the ground truth depth map and the confidence map.

Abstract: A method for determining a recurrence of a disease in a patient is presented. The method includes generating a plurality of medical images of an organ of the patient and determining a plurality of recurrence probabilities from the plurality of medical images. A recurrence of the disease is determined based on the plurality of recurrence probabilities and clinicopathological data of the patient using a Bayesian network.

Abstract: Systems and methods for generating an enhanced audio signal comprise a trained neural network configured to receive an input audio signal and generate an enhanced target signal, the trained neural network comprising a pre-processing neural network configured to receive a segment of the input audio signal and output an audio classification, the pre-processing neural network including at least one hidden layer comprising an embedding vector, and a noise reduction neural network configured to receive the segment of the input audio signal, and the embedding vector and generate the enhanced target signal. The pre-processing neural network may comprise a target signal pre-processing neural network configured to output a target signal classification and comprising at least one hidden layer comprising a target embedding vector.

Abstract: The present invention relates to pharmaceutical formulations for long-term ocular delivery of the active agents. The present invention further provides the long-term ocular delivery of griseofulvin with specific in vitro release profile. These formulations are used for the treatment of neovascular eye diseases and age-related macular degeneration (AMD). In particular, the present invention provides microparticles & nanoparticles of griseofulvin for the long-term ocular delivery and methods of preparation of such formulations.

Abstract: A therapeutic method for catalytically forming persulfide and/or polysulfide from hydrogen sulfide in vitro and in vivo using endogenously or exogenously released hydrogen sulfide is disclosed. That method comprises contacting cells in need including those under oxidative stress, traumatic brain injury (TBI) and hypoxia, or have an excess of hydrogen sulfide or deficiency of protein persulfidation with oxidized carbon nanoparticulate material in which the particles contain a plurality of carbonyl, hydroxyl and carboxyl substituents. Oxidized carbon nanoparticulate (OCN) material can be prepared from any of a variety of sources of which activated charcoal is preferred. A water-dispersible OCN material is described that does not need added hydrophilic polymers to provide dispersibility for at least 7 days at a concentration of about 1-5 mg/mL. These OCN materials also have a UV absorbance maximum in water of about 220 nm and pass through a 0.22 µm pore PES membrane.

Abstract: Surrogates for roadside objects, such as concrete curbs, can be used for vehicle testing. A surrogate for a concrete curb can substantially be similar in size and/or shape as the concrete curb that the surrogate is mimicking. The surrogate can be configured to exhibit substantially the same characteristics as their actual counterpart concrete curb when sensed by one or more vehicle sensors (e.g., cameras, radar sensors, and/or LIDAR sensors). Such surrogates can be used to test automated vehicles, one or more vehicle sensors, a vehicle sensor system, and/or one or more vehicle system (e.g., a road departure mitigation system). The surrogates can be configured to withstand being impacted by a test vehicle without being damaged and without damaging the test vehicle.

Abstract: A method of treating a human patient identified as having an injury to a body region includes receiving CT images, where the CT images were generated by performing a CT angiography of an injured body region of the human patient. The method further includes determining, based on the CT images, a total volumetric rate of active bleeding in the injured body region; and recommending at least one treatment approach for the human patient based on the total volumetric rate of active bleeding.

Abstract: In some examples, a microstructured fiber comprises a cladding material surrounding at least one core material, wherein the at least one core material comprises an array of discrete devices contacted in parallel. A method of producing a microstructured fiber may include 3D-printing a fiber preform, thermally drawing the fiber preform into a fiber that preserves the cross-sectional geometry of the fiber preform, and axially patterning the fiber into a microstructured fiber comprising an array of discrete devices contacted in parallel. In some embodiments, microstructured fibers may be integrated into a sensory textile that includes at least one of an electrooptic portion, a sonar portion, a magnetic gradiometer portion, and a piezogenerating portion. In some embodiments, microstructured fibers may be formed into an in-fiber integrated quantum device circuit or an in-fiber ion trap.

Abstract: Systems and methods for multimodal classification include a plurality of expert modules, each expert module configured to receive data corresponding to one of a plurality of input modalities and extract associated features, a plurality of class prediction modules, each class prediction module configured to receive extracted features from a corresponding one of the expert modules and predict an associated class, a gate expert configured to receive the extracted features from the plurality of expert modules and output a set of weights for the input modalities, and a fusion module configured to generate a weighted prediction based on the class predictions and the set of weights. Various embodiments include one or more of an image expert, a video expert, an audio expert, class prediction modules, a gate expert, and a co-learning framework.

Abstract: A system for separating ions may include an ion source configured to generate ions from a sample, at least one ion separation instrument configured to separate the generated ions as a function of at least one molecular characteristic, and an orbitrap in which a rotating and oscillating ion induces charges on inner and outer electrode halves of the orbitrap, and wherein charge detection circuitry is configured to detect the charges induced on each of the inner electrode halves and on each of the outer electrode halves, and to combine the detected charges for each oscillation to produce a measured ion charge signal.

Abstract: A charge detection mass spectrometer may include an electrostatic linear ion trap (ELIT) or orbitrap, a source of ions to supply ions to the ELIT or orbitrap, a processor operatively coupled to the ELIT or orbitrap, a display monitor coupled to the processor, and a memory having instructions stored therein executable by the processor to produce a control graphic user interface (GUI) on the display monitor, the control GUI including at least one selectable GUI element for at least one corresponding operating parameter of the ELIT or orbitrap, receive a first user command, via user interaction with the control GUI, corresponding to selection of the at least one selectable GUI element, and control the ELIT or orbitrap to control the at least one corresponding operating parameter of the ELIT or orbitrap in response to receipt of, and based on, the first user command.

Abstract: A system and method for detecting a suspicious object, including a wireless signal transmitter with first and second transmitter antennas, a first wireless signal receiver on an opposite side of the object from the transmitter having first and second receiver antennas, and a second wireless signal receiver on a same side of the object as the transmitter having a third receiver antenna. The transmitter may emit wireless signals from each of the transmitter antennas. The signals emitted by the first transmitter antenna may be received at the first and second receiver antennas. The signals emitted by both transmitter antennas may be received at the third receiver antenna. The object's material type may be determined based on channel state information of the wireless signals received at first receiver. A size of the object may be determined based on channel state information of the wireless signals received at the second receiver.

Abstract: The present disclosure relates to a method of identifying components present in a lipoprotein. Methods provided include single particle mass spectrometry, such as charge detection mass spectrometry (CDMS). Distinct subpopulations that exist within lipoprotein classes are determined by correlating m/z and mass.

Abstract: A depth estimation method and apparatus using a learning model are disclosed. A depth information estimation method may include identifying a plurality of image data, generating feature maps of the plurality of image data respectively, generating a cost volume using the feature maps, generating normalized cost volumes in different sizes by normalizing the cost volume, estimating disparity information from the normalized cost volumes, and generating depth information using the estimated disparity information.

Abstract: Methods of encoding and decoding a speech signal using a neural network model that recognizes sound sources, and encoding and decoding apparatuses for performing the methods are provided. A method of encoding a speech signal includes identifying an input signal for a plurality of sound sources; generating a latent signal by encoding the input signal; obtaining a plurality of sound source signals by separating the latent signal for each of the plurality of sound sources; determining a number of bits used for quantization of each of the plurality of sound source signals according to a type of each of the plurality of sound sources; quantizing each of the plurality of sound source signals based on the determined number of bits; and generating a bitstream by combining the plurality of quantized sound source signals.

Abstract: An instrument for separating ions may include an ion source configured to generate ions from a sample, at least one ion separation instrument configured to separate the generated ions as a function of at least one molecular characteristic and an electrostatic linear ion trap (ELIT) positioned to receive ions exiting the at least one ion separation instrument. The ELIT has first and second ion mirrors separated by a charge detection cylinder, and is configured such that an ion trapped therein oscillates back and forth through the charge detection cylinder between the first and second ion mirrors with a duty cycle, corresponding to a ratio of time spent by the trapped ion traversing the charge detection cylinder and total time spent by the trapped ion traversing a combination of the first and second ion mirrors and the charge detection cylinder during one complete oscillation cycle, of approximately 50%.

Abstract: A platform for testing cell response to biochemical agents. The TrophoWell™ includes a well which contains a gel, and a plurality of capillaries that open into it. Cells and various biochemical agents such as drugs and growth factors are flown through those capillaries. The platform allows for the evaluation of cell response by imaging. The platform is a cost effective testing platform and can be used in the fields for drug discovery and personalized medicine.

Abstract: Compositions and methods are provided for treating HPV infections including pre-malignant and cancers. Compounds that specifically bind to the HPV E6 protein and inactivate the protein are disclosed.

Abstract: A dichotic pulsatile and analog stimulation system, comprises a first cochlear implant device implanted in one ear of a patient; and a second cochlear implant device implanted in another ear of the patient; wherein the first cochlear implant device comprises a first speech processor configured to provide single channel analog stimulation to a first electrode array mounted to a cochlea of the one ear and the second cochlear implant device comprises a second speech processor configured to provide interleaved pulse stimulation to a second electrode array mounted to a cochlea of the other ear.

Abstract: Disclosed is a system and method for individualized hearing aid prescription which consists of a test procedure that enables the fitting of an individualized estimation of the SII model to individual listeners efficiently and an optimization process which translates the resulting individualized model to the prescribed gains across frequencies for programming into the user's hearing aids. The test involves the recognition of one or more words presented in background noise, which better approximates the daily listening experiences of hearing-aid users compared to the pure-tone detection in a silent environment task which is commonly utilized during conventional audiometric testing. In the estimated SII model, five parameters describe in a custom fashion the relative weights of speech information across the five frequency bands for a given listener. The results from the speech test is used to determine the desirable amount of gain for each frequency region to optimize the user's aided speech intelligibility.