Abstract: A thermal management system includes a baseplate assembly and a flow system. The baseplate assembly includes a baseplate and a semiconductor die arranged on the baseplate. The flow system includes a first flow path extending over and in thermal contact with the semiconductor die and a second flow path in thermal contact with the baseplate, the flow system including a fluid flowing through the first flow path and the second flow path. The flow system is configured to direct the fluid over the semiconductor die via the first flow path and to the baseplate via the second flow path so as to transfer heat away from the semiconductor die and from the baseplate so as to cool the baseplate assembly.

Abstract: A thermal management system includes a baseplate assembly and a flow system. The baseplate assembly includes a baseplate and a semiconductor die. The flow system includes a submerged jet impingement assembly for direct semiconductor die cooling, a first flow path extending over the semiconductor die via the submerged jet impingement assembly, and a second flow path in thermal contact with the baseplate, the flow system including a fluid flowing through the first flow path and the second flow path. The flow system is configured to direct the fluid to the upper semiconductor surface of the semiconductor die via the first flow path and to the baseplate via the second flow path so as to transfer heat away from the semiconductor die and from the baseplate so as to cool the baseplate assembly.

Abstract: A method for machine learning-based detection of an automated fraud or abuse attack includes: identifying, via a computer network, a digital event associated with a suspected automated fraud or abuse attack; composing, via one or more computers, a digital activity signature of the suspected automated fraud or abuse attack based on digital activity associated with the suspected automated fraud or abuse attack; computing, via a machine learning model, an encoded representation of the digital activity signature; searching, via the one or more computers, an automated fraud or abuse signature registry based on the encoded representation of the digital activity signature; determining a likely origin of the digital event based on the searching of the automated fraud or abuse signature registry; and selectively implementing one or more automated threat mitigation actions based on the likely origin of the digital event.

Abstract: A system and method for accelerated anomaly detection and replacement of an anomaly-experiencing machine learning-based ensemble includes identifying a machine learning-based digital threat scoring ensemble having an anomalous drift behavior in digital threat score inferences computed by the machine learning-based digital threat scoring ensemble for a target period; executing a tiered anomaly evaluation for the machine learning-based digital threat scoring ensemble that includes identifying at least one errant machine learning-based model of the machine learning-based digital threat scoring ensemble contributing to the anomalous drift behavior, and identifying at least one errant feature variable of the at least one machine learning-based model contributing to the anomalous drift behavior; generating a successor machine learning-based digital threat scoring ensemble to the machine learning-based digital threat scoring ensemble based on the tiered anomaly evaluation; and replacing the machine learning-based di

Abstract: A system and method for accelerated anomaly detection and replacement of an anomaly-experiencing machine learning-based ensemble includes identifying a machine learning-based digital threat scoring ensemble having an anomalous drift behavior in digital threat score inferences computed by the machine learning-based digital threat scoring ensemble for a target period; executing a tiered anomaly evaluation for the machine learning-based digital threat scoring ensemble that includes identifying at least one errant machine learning-based model of the machine learning-based digital threat scoring ensemble contributing to the anomalous drift behavior, and identifying at least one errant feature variable of the at least one machine learning-based model contributing to the anomalous drift behavior; generating a successor machine learning-based digital threat scoring ensemble to the machine learning-based digital threat scoring ensemble based on the tiered anomaly evaluation; and replacing the machine learning-based di

Abstract: A method for machine learning-based detection of an automated fraud or abuse attack includes: identifying, via a computer network, a digital event associated with a suspected automated fraud or abuse attack; composing, via one or more computers, a digital activity signature of the suspected automated fraud or abuse attack based on digital activity associated with the suspected automated fraud or abuse attack; computing, via a machine learning model, an encoded representation of the digital activity signature; searching, via the one or more computers, an automated fraud or abuse signature registry based on the encoded representation of the digital activity signature; determining a likely origin of the digital event based on the searching of the automated fraud or abuse signature registry; and selectively implementing one or more automated threat mitigation actions based on the likely origin of the digital event.

Abstract: A system and method for accelerated anomaly detection and replacement of an anomaly-experiencing machine learning-based ensemble includes identifying a machine learning-based digital threat scoring ensemble having an anomalous drift behavior in digital threat score inferences computed by the machine learning-based digital threat scoring ensemble for a target period; executing a tiered anomaly evaluation for the machine learning-based digital threat scoring ensemble that includes identifying at least one errant machine learning-based model of the machine learning-based digital threat scoring ensemble contributing to the anomalous drift behavior, and identifying at least one errant feature variable of the at least one machine learning-based model contributing to the anomalous drift behavior; generating a successor machine learning-based digital threat scoring ensemble to the machine learning-based digital threat scoring ensemble based on the tiered anomaly evaluation; and replacing the machine learning-based di

Abstract: A method for machine learning-based detection of an automated fraud or abuse attack includes: identifying, via a computer network, a digital event associated with a suspected automated fraud or abuse attack; composing, via one or more computers, a digital activity signature of the suspected automated fraud or abuse attack based on digital activity associated with the suspected automated fraud or abuse attack; computing, via a machine learning model, an encoded representation of the digital activity signature; searching, via the one or more computers, an automated fraud or abuse signature registry based on the encoded representation of the digital activity signature; determining a likely origin of the digital event based on the searching of the automated fraud or abuse signature registry; and selectively implementing one or more automated threat mitigation actions based on the likely origin of the digital event.

Abstract: A system and method for accelerated anomaly detection and replacement of an anomaly-experiencing machine learning-based ensemble includes identifying a machine learning-based digital threat scoring ensemble having an anomalous drift behavior in digital threat score inferences computed by the machine learning-based digital threat scoring ensemble for a target period; executing a tiered anomaly evaluation for the machine learning-based digital threat scoring ensemble that includes identifying at least one errant machine learning-based model of the machine learning-based digital threat scoring ensemble contributing to the anomalous drift behavior, and identifying at least one errant feature variable of the at least one machine learning-based model contributing to the anomalous drift behavior; generating a successor machine learning-based digital threat scoring ensemble to the machine learning-based digital threat scoring ensemble based on the tiered anomaly evaluation; and replacing the machine learning-based di

Abstract: The invention comprises a composition. The composition comprises a biodegradable polymer and a biodegradation catalyst comprising: (a) an inorganic compound selected from calcium phosphate, hydroxyapatite, calcium chloride, calcium sulfate, calcium citrate, calcium lactate, magnesium carbonate, magnesium hydroxide, magnesium oxide, magnesium lactate, magnesium sulfate, magnesium calcium carbonate, magnesium citrate or combinations or mixtures thereof; or (b) an organic component selected from bone meal, collagen, milk powder, egg shell reacted with phosphoric acid, egg shell reacted with phosphoric acid, keratin or combinations or mixtures thereof; or (c) combinations or mixtures of (a) and (b). The composition can also optionally include thermoplastic or recycled thermoplastic carrier polymers. Methods of making masterbatch pellets, fibers, yarns and textiles are also disclosed.

Abstract: A system and method for fast-detection and mitigation of emerging network fraud attacks includes sourcing digital event data samples associated with one or more online services; executing graph-rendering computer instructions that automatically construct a backbone graph using a subset of features extracted from the sourced digital event data samples, wherein the constructing includes: identifying, as graphical nodes, a first plurality of distinct features of the subset of features; identifying, as graphical edges, a second plurality of distinct features of the subset of features; generating a graphical edge between distinct pairs of graphical nodes comprising a same type of feature of the subset of features based on feature values associated with at least one distinct feature of the second plurality of distinct features; and mitigating, via a digital threat mitigation action, if one or more emerging network fraud attacks is identified based on an assessment of a cluster of networked nodes.

Abstract: A system and method for fast-detection and mitigation of emerging network fraud attacks includes sourcing digital event data samples associated with one or more online services; executing graph-rendering computer instructions that automatically construct a backbone graph using a subset of features extracted from the sourced digital event data samples, wherein the constructing includes: identifying, as graphical nodes, a first plurality of distinct features of the subset of features; identifying, as graphical edges, a second plurality of distinct features of the subset of features; generating a graphical edge between distinct pairs of graphical nodes comprising a same type of feature of the subset of features based on feature values associated with at least one distinct feature of the second plurality of distinct features; and mitigating, via a digital threat mitigation action, if one or more emerging network fraud attacks is identified based on an assessment of a cluster of networked nodes.

Abstract: A zero-sequence current balancer for a controlling zero-sequence current in a three-phase power system includes a cascade multilevel modular inverter (CMMI) coupled to the three-phase power system, wherein the CMMI has a plurality of modules, each module having a module capacitor, and a real power injector circuit provided between the three-phase power system and the CMMI, wherein the real power injector circuit is structured and configured to cause real power to injected into and/or absorbed from the CMMI to regulate a voltage of one or more of the module capacitors.

Abstract: A zero-sequence current balancer for a controlling zero-sequence current in a three-phase power system includes a cascade multilevel modular inverter (CMMI) coupled to the three-phase power system, wherein the CMMI has a plurality of modules, each module having a module capacitor, and a real power injector circuit provided between the three-phase power system and the CMMI, wherein the real power injector circuit is structured and configured to cause real power to injected into and/or absorbed from the CMMI to regulate a voltage of one or more of the module capacitors.

Abstract: In a three-phase, four-wire electrical distribution system, a zig-zag transformer and at least one Cascade Multilevel Modular Inverter (CMMI) is coupled between the distribution system and the neutral. A controller modulates the states of the H-bridges in the CMMI to build an AC waveform. The voltage is chosen by the controller in order to control an equivalent impedance that draws an appropriate neutral current through the zig-zag transformer. This neutral current is generally chosen to cancel the neutral current sensed in the line. In other embodiments, the chosen neutral current may be based on a remotely sensed imbalance, rather than on a local value, determined by the power utility as a critical load point in the system. The desired injection current is then translated by the controller into a desired zero-sequence reactive impedance, based on measurement of the local terminal voltage, allowing the controller to regulate the current without generating or consuming real power.

Abstract: In a three-phase, four-wire electrical distribution system, a zig-zag transformer and at least one Cascade Multilevel Modular Inverter (CMMI) is coupled between the distribution system and the neutral. A controller modulates the states of the H-bridges in the CMMI to build an AC waveform. The voltage is chosen by the controller in order to control an equivalent impedance that draws an appropriate neutral current through the transformer. This neutral current is generally chosen to cancel the neutral current sensed in the line. The chosen neutral current may be based on a remotely sensed imbalance, rather than on a local value, determined by the power utility as a critical load point in the system. The desired injection current is then translated by the controller into a desired zero-sequence reactive impedance, based on measurement of the local terminal voltage, allowing the controller to regulate the current without generating or consuming real power.