Abstract: Software that performs the following operations: (i) receiving a set of graph predictions corresponding to an input text, where graph predictions of the set of graph predictions are generated by different respective machine learning models; (ii) blending the graph predictions of the set of graph predictions to generate a plurality of candidate blended graphs, where nodes and edges of the candidate blended graphs have respective selection metric values, generated using a selection metric function, that meet a minimum threshold; and (iii) selecting as an output blended graph a candidate blended graph of the plurality of candidate blended graphs having a highest total combination of selection metric values among the plurality of candidate blended graphs.

Abstract: Embodiments are provided for generating a reasonable language model learning for text data in a knowledge graph in a computing system by a processor. One or more data sources and one or more triples may be analyzed from a knowledge graph. Training data having one or more candidate labels associated with one or more of the triples may be generated. One or more reasonable language models may be trained based on the training data.

Abstract: A microfluidic viscometer measures the viscosity of a microliter-volume fluid sample using a microfluidic chip having a microchannel with a high aspect ratio (˜10), allowing the microflow therein to be approximated as a rectangular slit flow. The microfluidic chip is fabricated by stacking rigid sheet materials that can be laser cut to specified shapes and sizes. The microchannel, rendered smooth and hydrophobic by a repellant coating, provides a straight flow path for the sample to approach flow equilibrium as it moves through. By applying corrections related to the visual bias from the camera and the capillary pressure difference at the air-liquid interface, the viscosity of the fluid sample can be calculated based on differential pressure data, sample length, velocity, volumetric flow rate, and contact angle from captured video, and the channel dimension, given that the sample has reached a flow equilibrium condition.

Abstract: Systems, apparatuses and methods may provide for a verification system for an aircraft. The verification system includes a verification function subsystem to automatically verify an operational condition of one or more components of an aircraft based on airflow related signals, hydraulic related signals, and electrical signals and associated impedances and present the operational condition via a display. The airflow related signals may be obtained from a plurality of airflow fittings, the hydraulic related signals may be obtained from a plurality of hydraulic fittings, and the electrical signals and associated impedances may be obtained from a plurality of electrical connectors. At least two of the airflow fittings, at least two of the hydraulic fittings, and at least two of the electrical connectors may be positioned in different aircraft sections before additional aircraft sections are assembled.

Abstract: The present invention introduces drug-loaded vehicles conjugated with aptamers, comprising DNA, RNA, or modified nucleic acid sequences designed to selectively and strongly bind to specific target sites on the eye, as well as binding to an ocular device such as a contact lens. Additionally, this innovative approach offers a targeted and sustained drug delivery method, addressing issues such as burst release of drugs, poor affinity between drug and material, and non-targeted drug delivery, while maintaining non-invasiveness and convenience.

Abstract: A microfluidic viscometer measures the viscosity of a microliter-volume fluid sample using a microfluidic chip having a microchannel with a high aspect ratio (˜10), allowing the microflow therein to be approximated as a rectangular slit flow. The microfluidic chip is fabricated by stacking rigid sheet materials that can be laser cut to specified shapes and sizes. The microchannel, rendered smooth and hydrophobic by a repellant coating, provides a straight flow path for the sample to approach flow equilibrium as it moves through. By applying corrections related to the visual bias from the camera and the capillary pressure difference at the air-liquid interface, the viscosity of the fluid sample can be calculated based on differential pressure data, sample length, velocity, volumetric flow rate, and contact angle from captured video, and the channel dimension, given that the sample has reached a flow equilibrium condition.

Abstract: Among other things, techniques are described for predicting how an agent (e.g., a vehicle, bicycle, pedestrian, etc.) will move in an environment based on prior movement, the road network, the surrounding objects and/or other relevant environmental factors. One trajectory prediction technique involves generating a probability map for an agent's movement. Another trajectory prediction technique involves generating a trajectory lattice, for an agent's movement. In addition, a different trajectory prediction technique involves multi-modal regression where a classifier (e.g., a neural network) is trained to classify the probability of a number of (learned) modes such that each model produces a trajectory based on the current input.

Abstract: Among other things, techniques are described for predicting how an agent (e.g., a vehicle, bicycle, pedestrian, etc.) will move in an environment based on prior movement, the road network, the surrounding objects and/or other relevant environmental factors. One trajectory prediction technique involves generating a probability map for an agent's movement. Another trajectory prediction technique involves generating a trajectory lattice, for an agent's movement. In addition, a different trajectory prediction technique involves multi-modal regression where a classifier (e.g., a neural network) is trained to classify the probability of a number of (learned) modes such that each model produces a trajectory based on the current input.

Abstract: Among other things, techniques are described for predicting how an agent (e.g., a vehicle, bicycle, pedestrian, etc.) will move in an environment based on prior movement, the road network, the surrounding objects and/or other relevant environmental factors. One trajectory prediction technique involves generating a probability map for an agent's movement. Another trajectory prediction technique involves generating a trajectory lattice, for an agent's movement. In addition, a different trajectory prediction technique involves multi-modal regression where a classifier (e.g., a neural network) is trained to classify the probability of a number of (learned) modes such that each model produces a trajectory based on the current input.

Abstract: A trajectory planning system can be used to select a trajectory for an autonomous vehicle. The trajectory planning system may generate multiple trajectories and extract features from the generated trajectories. The trajectory planning system may evaluate the trajectories based on the extracted features and select a trajectory for the vehicle based on the evaluation. The selected trajectory may be used to control the vehicle.

Abstract: Smart fertilizers and method of using and manufacturing are provided that include nanocarbon solution mixed with nanocomposite hydrogels at predetermined percentage weight or volume ratio (% w/w or % v/v). The resulted smart fertilizers are characterized in biosensors for detecting electricity conductance (EC) and/or pH degree of the surrounding soil caused by the release of ATPase H+ from the plant roots and in bioactuators for chemically reacting with the surrounding hydron ions to release the nutrients once the biodetectors detect the stimuli conditions.

Abstract: Provided are methods for augmenting data related to generation of vehicle trajectories, which include predicting, using a machine learning model, a first trajectory of a vehicle at a first time in an environment surrounding the vehicle and including at least one object, detecting a deviation of the predicted first trajectory at the first time from a first ground truth trajectory of the vehicle and determining that, at the first time, the deviation satisfies a threshold, predicting, using the machine learning model, a second trajectory of the vehicle based on the predicted first trajectory of the vehicle and a second ground truth trajectory of at least one object at a second time being subsequent to the first time, and generating a training dataset for training the machine learning model using the predicted first and second trajectories of the vehicle. Systems and computer program products are also provided.

Abstract: Among other things, techniques are described for predicting how an agent (e.g., a vehicle, bicycle, pedestrian, etc.) will move in an environment based on prior movement, the road network, the surrounding objects and/or other relevant environmental factors. One trajectory prediction technique involves generating a probability map for an agent's movement. Another trajectory prediction technique involves generating a trajectory lattice, for an agent's movement. In addition, a different trajectory prediction technique involves multi-modal regression where a classifier (e.g., a neural network) is trained to classify the probability of a number of (learned) modes such that each model produces a trajectory based on the current input.

Abstract: Among other things, techniques are described for predicting how an agent (e.g., a vehicle, bicycle, pedestrian, etc.) will move in an environment based on prior movement, the road network, the surrounding objects and/or other relevant environmental factors. One trajectory prediction technique involves generating a probability map for an agent's movement. Another trajectory prediction technique involves generating a trajectory lattice, for an agent's movement. In addition, a different trajectory prediction technique involves multi-modal regression where a classifier (e.g., a neural network) is trained to classify the probability of a number of (learned) modes such that each model produces a trajectory based on the current input.

Abstract: A substrate flipping device includes a substrate securing assembly, a gripping actuator, and a rotary actuator. The gripping actuator is configured to pneumatically cause the substrate securing assembly to be in an open position to receive a substrate and configured to pneumatically cause the substrate securing assembly to be in a closed position to secure the substrate. The rotary actuator is configured to pneumatically cause the substrate securing assembly to rotate to a flipped position and to pneumatically rotate to a non-flipped position.

Abstract: 1,8-naphthyridinone compounds as modulators of an adenosine receptor are provided. The compounds may find use as therapeutic agents for the treatment of diseases mediated through a G-protein-coupled receptor signaling pathway and may find particular use in oncology.

Abstract: In some embodiments, a method of determining a molecular structure of a protein is provided. A computing system receives voxel data representing electron density obtained via cryo-electron microscopy. The computing system uses one or more neural networks to predict one or more likelihoods for each voxel. The computing system determines a backbone structure based on the predicted likelihoods. The computing system maps amino acid sequences to the backbone structure based on the predicted likelihoods. Mapping the amino acid sequences to the backbone structure based on the predicted likelihoods includes conducting an alignment technique that uses a reward function and a gap penalty. The computing system determines locations of carbon, nitrogen, and oxygen atoms within the backbone structure based on the predicted likelihoods. The computing system determines side-chain atoms based on the predicted backbone structure and the amino acid sequences to complete the molecular structure.

Abstract: Various embodiments are described herein for the fabrication enzyme degradable hydrogels useful as payload delivery systems. More particularly, embodiments disclosed herein relate to enzyme-degradable hydrogel systems comprising a crosslinkable polymer, such as a chemically-modified biopolymer, for example, chemically-modified gelatin, the hydrogel formed by a method comprising sequential physical and chemical crosslinking steps, for delivery of various payloads. Enzymes may be selected and administered to tune the release profile of the hydrogel. The payload can be, but not limited to, drugs, markers, cells, or these members encapsulated within another drug delivery such as a nanoparticle, or liposome. The hydrogel system can also be combined with another device such as a contact lens or bandage for wound healing.

Abstract: Systems, apparatuses and methods may provide for a verification system for an aircraft. The verification system includes a verification function subsystem to automatically verify an operational condition of one or more components of an aircraft based on airflow related signals, hydraulic related signals, and electrical signals and associated impedances and present the operational condition via a display. The airflow related signals may be obtained from a plurality of airflow fittings, the hydraulic related signals may be obtained from a plurality of hydraulic fittings, and the electrical signals and associated impedances may be obtained from a plurality of electrical connectors. At least two of the airflow fittings, at least two of the hydraulic fittings, and at least two of the electrical connectors may be positioned in different aircraft sections before additional aircraft sections are assembled.

Abstract: A substrate flipping device includes a substrate securing assembly, a gripping actuator, and a rotary actuator. The gripping actuator is configured to pneumatically cause the substrate securing assembly to be in an open position to receive a substrate and configured to pneumatically cause the substrate securing assembly to be in a closed position to secure the substrate. The rotary actuator is configured to pneumatically cause the substrate securing assembly to rotate to a flipped position and to pneumatically rotate to a non-flipped position.