Abstract: One or more machine learning models for a network of tensor time series can be provided. Co-evolving time series having multiple modes can be received. A tensor graph convolutional network can be trained, using the co-evolving time series and adjacency matrices associated with the multiple modes in the co-evolving time series, to generate node embeddings associated with a snapshot of the co-evolving time series at time t. A tensor recurrent neural network can be trained to generate temporal dynamics associated with the co-evolving time series based on the generated node embeddings. A neural network model can be trained to forecast a prediction for the co-evolving time series based on the generated node embeddings and the generated temporal dynamics. The tensor graph convolutional network, the tensor recurrent neural network and the neural network model can be trained jointly.

Abstract: A hypergraph is constructed based on historical shopping cart data. A node of the hypergraph corresponds to a shopping basket, and a hyperedge of the hypergraph corresponds to a unique product, the hyperedge connecting all nodes of the hypergraph representing baskets containing the unique product. A hypergraph partition algorithm identifies a cluster of shopping baskets represented in the hypergraph and determined to be similar to a given basket. Based on the cluster of shopping baskets a dual-level return prediction is performed. The dual-level return prediction includes predicting whether the given basket will be returned, and based on predicting that the given basket will be returned, predicting a probability that a product in the given basket will be returned. Based on predicting that the given basket will be returned, an ameliorative action is performed to reduce the probability.

Abstract: A hypergraph is constructed based on historical shopping cart data. A node of the hypergraph corresponds to a shopping basket, and a hyperedge of the hypergraph corresponds to a unique product, the hyperedge connecting all nodes of the hypergraph representing baskets containing the unique product. A hypergraph partition algorithm identifies a cluster of shopping baskets represented in the hypergraph and determined to be similar to a given basket. Based on the cluster of shopping baskets a dual-level return prediction is performed. The dual-level return prediction includes predicting whether the given basket will be returned, and based on predicting that the given basket will be returned, predicting a probability that a product in the given basket will be returned. Based on predicting that the given basket will be returned, an ameliorative action is performed to reduce the probability.

Abstract: Embodiments of the disclosure relate to a biosample plate that includes a memory component for storing information related to the biosample, biosample plate and biosample analysis data, and a wireless communication interface for transferring information to and from the biosample plate. The biosample plate may be used with an analyzing and data recording system such as an electromagnetic tape drive. The disclosed biosample plate facilitates the correlation between a large number of biosample plates and data as data remains with the corresponding biosamples both when the biosample plates are in use and when they are in storage. The wireless communication interface may comprise an antenna disposed in a biosample plate for data transmission to and from the biosample plate by radio signals.

Abstract: Described are embodiments of an invention for a sample assembly with trenches for detection of analytes with electromagnetic read heads. The sample assembly includes an outer layer with at least one sample trench. The sample trench includes a first set of antibodies that are bonded on a first surface of a base layer. Target antigens are bonded with the first set of antibodies, and a second set of antibodies are bonded to the target antigens. Further, the sample trench includes nanoparticles that are bonded to the second set of antibodies. A head module includes a write head for magnetizing nanoparticles and a read sensor for detecting the magnetized nanoparticles, and thus, the target antigens. The sample trench constrains the biological sample, and thus the target antigen, during the preparation and subsequent analysis of the biological sample. Accordingly, the target antigen is aligned with read elements of a head module such that the target antigen is reliably and accurately detected.

Abstract: Embodiments of the disclosure relate to a cartridge that includes slots for storing biosample capillary tubes. The cartridge has the same form factor as data tape cartridges to allow the cartridge to be handled by the same robotic mechanisms that handle data cartridges in an automated tape library. One aspect of the disclosure concerns a cartridge comprising an enclosure that includes a movable door to provide access to a tube holder in the enclosure. The tube holder includes cylindrical holes or slots for receiving capillary tubes which contain biosamples scanned and analyzed an automated tape library.

Abstract: The invention relates to the identification of molecules using electromagnetic write-heads and magneto-resistive sensors. In one embodiment, an electromagnetic write-head magnetically excites a molecule with an alternating magnetic field. A magneto-resistive sensor measures the resonant response of the magnetically excited molecule. A processor compares the resonant response to a table of known responses of different molecules to identify the chemical composition of the target molecule.

Abstract: Described are embodiments to ensure that the equipment utilized to detect antigens is reliable and accurate. Accordingly, one embodiment of the invention includes a calibration assembly having nanoparticles, with known magnetic properties, spaced apart at known y-axis locations along the calibration assembly. In one embodiment, the calibration assembly may be used to calibrate a matched filter of the write and read circuitry. Because the calibration assembly comprises nanoparticles with known magnetic properties the read response of the read circuitry to a particular nanoparticle may be stored in the matched filter as an ideal signal for that nanoparticle. The ideal signal stored in the matched filter may then be utilized for reliably and accurately detecting antigens.

Abstract: Described are embodiments to ensure that the equipment utilized to detect antigens is reliable and accurate. If it is determined that a read sensor is degraded a method of calibrating a read sensor of a read head is described. In one embodiment, a method of calibrating a magnetic read sensor includes measuring a first resistance of the magnetic read sensor upon an application of a forward bias current to the magnetic read sensor and measuring a second resistance of the magnetic read sensor upon an application of a reverse bias current to the magnetic read sensor. A calibration constant is determined based on at least the first measured resistance and the second measured resistance. In one embodiment the method further includes storing the determined calibration constant for the magnetic read sensor in memory. Further, in one embodiment the head module having the magnetic read sensor is swept over at least one nanoparticle to obtain a read response of the magnetic read sensor to the nanoparticle.

Abstract: Embodiments of the disclosure relate to a biosample cartridge that includes storage slots for holding biosample plates. The cartridge has the same form factor as data tape cartridges to allow the cartridge to be handled by the same robotic mechanisms that handle data cartridges in an automated tape library. One aspect of the disclosure concerns a biosample storage cartridge that has a movable door to provide access to inside the cartridge and a plate holder disposed inside the cartridge. The plate holder includes a plurality of slots for receiving biosample plates that are scanned and processed by the automated tape library.

Abstract: Embodiments of the disclosure relate to a biosample cartridge that includes storage slots for holding biosample plates. The cartridge has the same form factor as data tape cartridges to allow the cartridge to be handled by the same robotic mechanisms that handle data cartridges in an automated tape library. One aspect of the disclosure concerns a biosample storage cartridge that has a movable door to provide access to inside the cartridge and a plate holder disposed inside the cartridge. The plate holder includes a plurality of slots for receiving biosample plates that are scanned and processed by the automated tape library.

Abstract: Embodiments of the disclosure relate to a cartridge that includes slots for storing biosample capillary tubes. The cartridge has the same form factor as data tape cartridges to allow the cartridge to be handled by the same robotic mechanisms that handle data cartridges in an automated tape library. One aspect of the disclosure concerns a cartridge comprising an enclosure that includes a movable door to provide access to a tube holder in the enclosure. The tube holder includes cylindrical holes or slots for receiving capillary tubes which contain biosamples scanned and analyzed an automated tape library.

Abstract: Embodiments of the disclosure relate to a biosample plate that includes a memory component for storing information related to the biosample, biosample plate and biosample analysis data, and a wireless communication interface for transferring information to and from the biosample plate. The biosample plate may be used with an analyzing and data recording system such as an electromagnetic tape drive. The disclosed biosample plate facilitates the correlation between a large number of biosample plates and data as data remains with the corresponding biosamples both when the biosample plates are in use and when they are in storage. The wireless communication interface may comprise an antenna disposed in a biosample plate for data transmission to and from the biosample plate by radio signals.

Abstract: The invention relates to the identification of molecules using electromagnetic write-heads and magneto-resistive sensors. In one embodiment, an electromagnetic write-head magnetically excites a molecule with an alternating magnetic field. A magneto-resistive sensor measures the resonant response of the magnetically excited molecule. A processor compares the resonant response to a table of known responses of different molecules to identify the chemical composition of the target molecule.

Abstract: Described are embodiments to ensure that the equipment utilized to detect antigens is reliable and accurate. If it is determined that a read sensor is degraded a method of calibrating a read sensor of a read head is described. In one embodiment, a method of calibrating a magnetic read sensor includes measuring a first resistance of the magnetic read sensor upon an application of a forward bias current to the magnetic read sensor and measuring a second resistance of the magnetic read sensor upon an application of a reverse bias current to the magnetic read sensor. A calibration constant is determined based on at least the first measured resistance and the second measured resistance. In one embodiment the method further includes storing the determined calibration constant for the magnetic read sensor in memory. Further, in one embodiment the head module having the magnetic read sensor is swept over at least one nanoparticle to obtain a read response of the magnetic read sensor to the nanoparticle.

Abstract: Described are embodiments to ensure that the equipment utilized to detect antigens is reliable and accurate. Accordingly, one embodiment of the invention includes a calibration assembly having nanoparticles, with known magnetic properties, spaced apart at known y-axis locations along the calibration assembly. In one embodiment, the calibration assembly may be used to calibrate a matched filter of the write and read circuitry. Because the calibration assembly comprises nanoparticles with known magnetic properties the read response of the read circuitry to a particular nanoparticle may be stored in the matched filter as an ideal signal for that nanoparticle. The ideal signal stored in the matched filter may then be utilized for reliably and accurately detecting antigens.

Abstract: Described are embodiments of an invention for a sample assembly with trenches for detection of analytes with electromagnetic read heads. The sample assembly includes an outer layer with at least one sample trench. The sample trench includes a first set of antibodies that are bonded on a first surface of a base layer. Target antigens are bonded with the first set of antibodies, and a second set of antibodies are bonded to the target antigens. Further, the sample trench includes nanoparticles that are bonded to the second set of antibodies. A head module includes a write head for magnetizing nanoparticles and a read sensor for detecting the magnetized nanoparticles, and thus, the target antigens. The sample trench constrains the biological sample, and thus the target antigen, during the preparation and subsequent analysis of the biological sample. Accordingly, the target antigen is aligned with read elements of a head module such that the target antigen is reliably and accurately detected.

Abstract: Techniques for the fabrication of semiconductor devices are provided. In one aspect, a layer transfer structure is provided. The layer transfer structure comprises a carrier substrate having a porous region with a tuned porosity in combination with an implanted species defining a separation plane therein. In another aspect, a method of forming a layer transfer structure is provided. In yet another aspect, a method of forming a three dimensional integrated structure is provided.

Abstract: Techniques for the fabrication of semiconductor devices are provided. In one aspect, a layer transfer structure is provided. The layer transfer structure comprises a carrier substrate having a porous region with a tuned porosity in combination with an implanted species defining a separation plane therein. In another aspect, a method of forming a layer transfer structure is provided. In yet another aspect, a method of forming a three dimensional integrated structure is provided.

Abstract: A carrier for a semiconductor component is provided having passive components integrated in its substrate. The passive components include decoupling components, such as capacitors and resistors. A set of connections is integrated to provide a close electrical proximity to the supported components.