Abstract: A compound property prediction method is provided for an electronic device. The method includes obtaining chemical structure information of a target compound, the chemical structure information including an atom and a chemical bond, modeling a chemical structure graph according to the chemical structure information, the chemical structure graph including a first node corresponding to the atom and a first edge corresponding to the chemical bond, constructing an original node feature of the first node and an original edge feature of the first edge, performing a message propagation on the first edge according to the original node feature of the first node and the original edge feature of the first edge to obtain propagation state information of the first edge, and predicting properties of the target compound according to the propagation state information of the first edge.

Abstract: A package structure including a semiconductor die, a redistribution circuit structure and an electronic device is provided. The semiconductor die is laterally encapsulated by an insulating encapsulation. The redistribution circuit structure is disposed on the semiconductor die and the insulating encapsulation. The redistribution circuit structure includes a colored dielectric layer, inter-dielectric layers and redistribution conductive layers embedded in the inter-dielectric layers. The electronic device is disposed over the colored dielectric layer and electrically connected to the redistribution circuit structure.

Abstract: A semiconductor device includes a substrate having a logic region and a magnetoresistive random access memory (MRAM) region, a MTJ on the MRAM region, a metal interconnection on the MTJ, and a blocking layer on the metal interconnection. Preferably, the blocking layer includes a stripe pattern according to a top view and the blocking layer could include metal or a dielectric layer.

Abstract: A multiple die container load port may include a housing with an opening, and an elevator to accommodate a plurality of different sized die containers. The multiple die container load port may include a stage supported by the housing and moveable within the opening of the housing by the elevator. The stage may include one or more positioning mechanisms to facilitate positioning of the plurality of different sized die containers on the stage, and may include different portions movable by the elevator to accommodate the plurality of different sized die containers. The multiple die container load port may include a position sensor to identify one of the plurality of different sized die containers positioned on the stage.

Abstract: The present disclosure provides organic-inorganic hybrid polymer particles, which have desirable surface chemistry and optical properties that make them particularly suitable for biological and optical applications. The present disclosure also provides methods of making organic-inorganic hybrid polymer particles. The present disclosure also provides methods of using the organic-inorganic hybrid polymer particles for biological and optical applications.

Abstract: A backup power system and method of use is provided for powering at least one load wherein the at least one load is normally connected to grid power at a grid frequency. The system and method include providing a generator powered by a fuel in gas phase, such as natural gas; detecting loss of grid power to the at least one load; driving the generator to an operating frequency equal to a predetermined driven frequency that is greater than the grid frequency; and selectively coupling the at least one load to the generator via a load controller while the generator is at the predetermined driven frequency.

Abstract: A method and an apparatus for identifying a heterogeneous graph and a property corresponding to a molecular space structure and a computer device are provided. The method includes: characterizing a topology structure included in a heterogeneous graph to generate feature information; generating feature vectors corresponding to key nodes on the topology structure included in the heterogeneous graph according to sampling information obtained by sampling the heterogeneous graph and the feature information; aggregating the feature vectors to generate a graph representation vector corresponding to the heterogeneous graph; and classifying the heterogeneous graph according to the graph representation vector to obtain a classification prediction result of the heterogeneous graph.

Abstract: The present disclosure describes methods, apparatus, and storage medium for node classification and training a node classification model. The method includes obtaining a target node subset and a neighbor node subset corresponding to the target node subset from a sample node set labeled with a target node class, a neighbor node in the neighbor node subset being associated with a target node in the target node subset; extracting a feature subset of the target node subset based on the neighbor node subset by using a node classification model, the feature subset comprising a feature vector of the target node; performing class prediction for the target node subset according to the feature subset, to obtain a predicted class probability subset; and training the node classification model with a target model parameter according to the predicted class probability subset and a target node class subset of the target node subset.

Abstract: The present disclosure provides organic-inorganic hybrid polymer particles, which have desirable surface chemistry and optical properties that make them particularly suitable for biological and optical applications. The present disclosure also provides methods of making organic-inorganic hybrid polymer particles. The present disclosure also provides methods of using the organic-inorganic hybrid polymer particles for biological and optical applications.

Abstract: Detecting abnormalities in vital signs of subjects of videos is provided. Aspects of the present disclosure include methods, apparatuses, and systems to detect and measure vital sign information of one or more human subjects of a video and detect abnormalities in the vital sign information. In some examples, such abnormalities can be used to indicate video data is likely altered or fraudulent. In this regard, imaging photophlethysmography (IPPG) and advanced signal processing techniques, including adaptive color beamforming, can be used to extract the vital signs of the video subjects.

Abstract: A vital sign monitoring system using an optical sensor is provided. The vital sign monitoring system, and related methods and devices described herein, is equipped with a camera or other optical sensor to remotely detect and measure one or more physiological parameters (e.g., vital signs) of a subject. For example, the vital sign monitoring system can detect, measure, and/or monitor heart rates and respiration rates from one or multiple subjects simultaneously using advanced signal processing techniques, including adaptive color beamforming to more accurately detect and measure the vital sign(s) of interest.

Abstract: Polymers, monomers, chromophoric polymer dots and related methods are provided. Highly fluorescent chromophoric polymer dots with narrow-band emissions are provided. Methods for synthesizing the chromophoric polymers, preparation methods for forming the chromophoric polymer dots, and biological applications using the unique properties of narrow-band emissions are also provided.

Abstract: Methods and systems for remote sleep monitoring are provided. Such methods and systems provide non-contact sleep monitoring via remote sensing or radar sensors. In this regard, when processing backscattered radar signals from a sleeping subject on a normal mattress, a breathing motion magnification effect is observed from mattress surface displacement due to human respiratory activity. This undesirable motion artifact causes existing approaches for accurate heart-rate estimation to fail. Embodiments of the present disclosure use a novel active motion suppression technique to deal with this problem by intelligently selecting a slow-time series from multiple ranges and examining a corresponding phase difference. This approach facilitates improved sleep monitoring, where one or more subjects can be remotely monitored during an evaluation period (which corresponds to an expected sleep cycle).

Abstract: Vital sign monitoring via remote sensing on stationary exercise equipment is provided. A new non-contact approach described herein uses radio frequency (RF) radar (e.g., ultra-wide band (UWB) radar) to remotely monitor vital sign information (such as heartbeat and breathing) and human activity information of subjects using stationary exercise equipment. In some embodiments, a radar sensor captures micro-scale chest motions (corresponding to the vital sign information) as well as macro-scale body motions (corresponding to movements from exercise). A signal processor receives radar signals from the radar sensor and processes the radar signals to reconstruct vital sign information from the micro-scale chest motions and/or human activity information from the macro-scale body motions using a joint vital sign-motion model, which can be trained using machine learning and other approaches.

Abstract: A method for determining interaction information, a method for training interaction information prediction model, a device, and a medium are provided. The method includes obtaining basic information of a first target object, basic information of a second target object, and a target interaction information prediction model, the target interaction information prediction model being obtained through training by using a global-level loss function and a key local-level loss function, the key local-level loss function being determined based on attention information corresponding to one or more key sub-sample objects in one or more sample objects meeting a reference condition; and invoking the target interaction information prediction model to process the basic information of the first target object and the basic information of the second target object, and obtaining target interaction information between the first target object and the second target object.

Abstract: An electronic device generates, according to a connection graph structure corresponding to a reference drug molecule, an atomic latent vector corresponding to the reference drug molecule. The device performs atom masking processing on the atomic latent vector to obtain a scaffold latent vector and a sidechain latent vector included in the atomic latent vector. The device generates a target scaffold latent vector with a target transition degree between the scaffold latent vector and the target scaffold latent vector according to a spatial distribution of the scaffold latent vector. The device generates a transitioned drug molecule according to the target scaffold latent vector and the sidechain latent vector.

Abstract: Terahertz wave plethysmography provides a new principle of radar-based vital sign detection. This disclosure presents new applications at terahertz (THz) frequency band for non-contact cardiac sensing. For the first time, cardiac pulse information is shown to be simultaneously extracted based on two established principles using unique THz waves. A novel concept of Terahertz-Wave-Plethysmography (TPG) is introduced, which detects blood volume changes in the upper dermis tissue layer by measuring the reflectance of THz waves, similar to the existing remote photoplethysmography (rPPG) principle. A detailed analysis of pulse measurement using THz is provided. The TPG principle is justified by scientific deduction and carefully designed experimental demonstrations. Additionally, pulse measurements from various peripheral body regions of interest (ROIs), including palm, inner elbow, temple, fingertip, and forehead, are demonstrated using a novel ultra-wideband (UWB) THz sensing system.

Abstract: Methods and systems for remote sleep monitoring are provided. Such methods and systems provide non-contact sleep monitoring via remote sensing or radar sensors. In this regard, when processing backscattered radar signals from a sleeping subject on a normal mattress, a breathing motion magnification effect is observed from mattress surface displacement due to human respiratory activity. This undesirable motion artifact causes existing approaches for accurate heart-rate estimation to fail. Embodiments of the present disclosure use a novel active motion suppression technique to deal with this problem by intelligently selecting a slow-time series from multiple ranges and examining a corresponding phase difference. This approach facilitates improved sleep monitoring, where one or more subjects can be remotely monitored during an evaluation period (which corresponds to an expected sleep cycle).

Abstract: Remote recovery of acoustic signals from passive sources is provided. Wideband radars, such as ultra-wideband (UWB) radars can detect minute surface displacements for vibrometry applications. Embodiments described herein remotely sense sound and recover acoustic signals from vibrating sources using radars. Early research in this domain only demonstrated single sound source recovery using narrowband millimeter wave radars in direct line-of-sight scenarios. Instead, by using wideband radars (e.g., X band UWB radars), multiple sources separated in ranges are observed and their signals isolated and recovered. Additionally, the see-through ability of microwave signals is leveraged to extend this technology to surveillance of targets obstructed by barriers. Blind surveillance is achieved by reconstructing audio from a passive object which is merely in proximity of the sound source using clever radar and audio processing techniques.

Abstract: This disclosure provides a drug screening method and apparatus, an electronic device, and a computer-readable storage medium. The method includes: determining a structural feature of a protein molecule and a structural feature of a target molecule; obtaining a concatenated node feature corresponding to the protein molecule and the target molecule based on a node information passing sub-network in a drug screening model, the structural feature of the protein molecule, and the structural feature of the target molecule, the node information passing sub-network being a graph neural network; and predicting a first predicted activity value after the protein molecule and the target molecule are bound according to the concatenated node feature.