Abstract: Embodiments of the present disclosure provide systems and methods for implementing self-bias detection based on performance and importance. A disclosed computer implemented method aggregates continuous input data through a K-means clustering algorithm to reduce the number of aggregated sub-group data pairs, enabling a reduced calculation time for computing bias and enhanced performance. The self-bias detection identifies a scale factor and a balance factor of aggregated sub-group data pairs, which indicate the importance of the detected bias.

Abstract: Embodiments of the present disclosure provide systems and methods for implementing self-bias detection based on performance and importance. A disclosed computer implemented method aggregates continuous input data through a K-means clustering algorithm to reduce the number of aggregated sub-group data pairs, enabling a reduced calculation time for computing bias and enhanced performance. The self-bias detection identifies a scale factor and a balance factor of aggregated sub-group data pairs, which indicate the importance of the detected bias.

Abstract: A computer-implemented method, a system and a computer program product for device failure detection are disclosed. In the method, phase-based predictions may be performed on a plurality of storage devices to determine a plurality of sampling scopes and corresponding sampling ratios. The respective sampling scopes may comprise at least one storage device of the plurality of storage devices. A sampling dataset may be obtained by selecting a group of storage devices from the respective sampling scopes with the corresponding sampling ratios. Device failure may be detected for the group of storage devices based on the sampling dataset.

Abstract: A method is disclosed. The method comprises receiving, by a server computer comprising an auto-encoder module, a first dataset containing first feature values corresponding to features of an interaction. The first dataset may be input into the auto-encoder module. The auto-encoder module may output a second dataset, the second dataset containing a second feature values corresponding to features of the interaction. The server computer may then compute a feature deviation dataset using the first dataset and the second dataset. The method can then comprise determining a type of activity based on the feature deviation dataset.

Abstract: Methods and systems for quickly and accurately training machine learning models to perform tasks related to new contexts are disclosed, particularly new contexts for which there is little available training data. One or more source data sets can be divided into a plurality of source sub-sets, which can be used to train a plurality of source sub-models. From this plurality of source sub-models, an estimate parameter set can be determined. The estimate parameter set and a target data set (which may comprise a comparatively small number of data elements) can be used to train a target model to perform some task. In this way, the source data set can be leveraged to train the target model. Additionally disclosed is a novel method of generating color maps, image representations of non-image data. These color maps can be used to train the sub-models and target model, improving model performance.

Abstract: Methods of manufacturing a light-activated powder are provided which provide solid-state generation and release of chlorine dioxide without detectable amounts of any toxic by-products such as chlorine gas, chlorites, or chlorates. The powder need not be exposed to moisture, relative humidity, or an acid before or during exposure of the powder to visible light to generate the gas. The powder can also be prepared under conditions that minimize or prevent decomposition or oxidation of sodium chlorite or premature light activation of the powder during the manufacturing process to maximize its activity.

Abstract: This provides a flexible, porous, dissolvable solid sheet article having large pores on its top surface as well as a method of making the same.

Abstract: This provides a flexible, porous, dissolvable solid sheet article having large pores on its top surface as well as a method of making the same.

Abstract: Methods of manufacturing a light-activated powder are provided which provide solid-state generation and release of chlorine dioxide without detectable amounts of any toxic by-products such as chlorine gas, chlorites, or chlorates. The powder need not be exposed to moisture, relative humidity, or an acid before or during exposure of the powder to visible light to generate the gas. The powder can also be prepared under conditions that minimize or prevent decomposition or oxidation of sodium chlorite or premature light activation of the powder during the manufacturing process to maximize its activity.

Abstract: Methods, systems, and computer program products for learning continuous embedding space of real time payment (RTP) transactions are provided. A method may include receiving RTP data including a plurality of attributes, including a sender and a receiver. One attribute is selected as a target attribute. The remaining attributes are input into a first machine learning model (e.g., NLP model), comprising at least one embedding layer and one hidden layer, which is trained to predict the target attribute. After the model is trained, each of the remaining attributes are converted to a first vector using the at least one embedding layer of the machine learning model to form a first set of vectors. The first set of vectors are stored and subsequently input into a second machine learning model to perform at least one second task different than the first task.

Abstract: Provided is a computer-implemented method for generating synthetic graphs that simulate real-time payment transactions that includes generating a base payment graph includes a plurality of nodes and a plurality of edges connecting the plurality of nodes, wherein each node represents an entity and each edge represents a probability that a real-time-payment transaction may be conducted involving two entities that are connected by the edge, wherein the real-time payment transaction is artificially created, generating a plurality of dynamic payment graphs based on the base payment graph, inserting patterns representing adversarial activity into the plurality of dynamic payment graphs, and performing an action associated with a machine learning technique using the plurality of dynamic payment graphs. Systems and computer program products are also provided.

Abstract: A computer-implemented method for compressing a machine learning model includes converting an input machine learning model into a standard machine learning model. The method further includes converting the standard machine learning model into a plurality of pruned machine learning models, each of the pruned machine learning models converted using a corresponding pruning ratio from a pruning ratio candidate list. The method further includes determining, for each of the pruned machine learning models, a size-to-error ratio. The method further includes selecting, based on the size-to-error ratio of the pruned machine learning models, a first pruning ratio from the pruning ratio candidate list. The method further includes generating a compressed machine learning model by compressing the input machine learning model using the first pruning ratio that is selected. The method further includes deploying the compressed machine learning model for production.

Abstract: Methods of manufacturing a moisture-activated powder are provided which provide generation and release of chlorine dioxide without detectable amounts of any toxic by-products such as chlorine gas, chlorites, or chlorates. The powder need not be exposed to light before or during exposure of the powder to moisture or relative humidity to generate the gas. The powder can also be prepared under conditions that minimize or prevent decomposition or oxidation of sodium chlorite or premature moisture activation of the powder during the manufacturing process to maximize its activity.

Abstract: Methods, systems, and computer program products for learning continuous embedding space of real time payment (RTP) transactions are provided. A method may include receiving RTP data including a plurality of attributes, including a sender and a receiver. One attribute is selected as a target attribute. The remaining attributes are input into a first machine learning model (e.g., NLP model), comprising at least one embedding layer and one hidden layer, which is trained to predict the target attribute. After the model is trained, each of the remaining attributes are converted to a first vector using the at least one embedding layer of the machine learning model to form a first set of vectors. The first set of vectors are stored and subsequently input into a second machine learning model to perform at least one second task different than the first task.

Abstract: A charging cable device for intelligent new energy vehicle is provided, which includes: a charging cable, a charging cable protection device, an intelligent charging plug, charging cable support devices and a controller; the charging cable is provided in the charging cable protection device, a starting end of the charging cable is connected to a charging pile, and a terminal end of the charging cable is fixedly provided with the intelligent charging plug, multiple charging cable support devices are arranged at a bottom of the charging cable outside the charging cable protection device, all of the charging cable protection device, the intelligent charging plug and the charging cable support devices are electrically connected to the controller.

Abstract: Provided are a system, method, and computer program product for network anomaly detection. The method includes determining a plurality of nested groups based on event data associated with a plurality of communications in a computer network. The method also includes generating display data configured to cause a display of a computing device to show a first graphical representation of the event data including a plurality of nested graphical nodes. The method further includes receiving new event data associated with a plurality of new communications in the computer network in a subsequent time period and generating new display data configured to cause the display to show a new graphical representation of the new event data. The method further includes determining an anomalous graphical node based at least partly on a size of the anomalous graphical node being increased in the new graphical representation relative to the first graphical representation.

Abstract: Provided are a system, method, and computer program product for network anomaly detection. The method includes receiving event data associated with a plurality of events in a computer network. The method also includes determining nested groups of the event data representing tiers of an operational hierarchy. The method further includes generating display data to show a graphical representation of the event including a plurality of nested graphical nodes and at least one spline. Each graphical node is associated with a group or a computer node, each graphical node encompasses and/or is encompassed by another graphical node, a size of each graphical node is proportional to an aggregated parameter value of events associated therewith, each spline connects at least two graphical nodes and includes a curve that passes through a common graphical node, and each spline is associated with a communication between at least two computer nodes.

Abstract: Embodiments of the present disclosure relate to weight matrix prediction. In an embodiment, a computer-implemented method is disclosed. The method comprises sending a candidate weight matrix of a neural network to one of a plurality of computing nodes comprised in a computing system to perform a testing iteration. The method further comprises receiving a testing loss value from the one of the plurality of computing nodes based on the testing iteration. The method further comprises evaluating whether the testing loss value is applicable. The method further comprises determining that the candidate weight matrix is available to be employed in a new formal iteration in response to the testing loss value being applicable. In other embodiments, a system and a computer program product are disclosed.

Abstract: Methods of manufacturing a light-activated powder are provided which provide solid-state generation and release of chlorine dioxide without detectable amounts of any toxic by-products such as chlorine gas, chlorites, or chlorates. The powder need not be exposed to moisture, relative humidity, or an acid before or during exposure of the powder to visible light to generate the gas. The powder can also be prepared under conditions that minimize or prevent decomposition or oxidation of sodium chlorite or premature light activation of the powder during the manufacturing process to maximize its activity.