Abstract: Source and target vectors encode roles of a node in a directed graph as a source and a target role respectively. Source and target query matrices and source and target key matrices are learned based on the directed graph. The source query matrix and the target key matrix are projected and scaled to create a source-target attention matrix and the target query matrix and the source key matrix are projected and scaled to create a target-source attention matrix. The attention matrices are combined to generate a source-target vector-edge encoding and a target-source vector-edge encoding, and are also biased and gated to generate a modified source-target attention matrix and a modified target-source attention matrix, respectively. Source encodings and target encodings are generated using the modified attention matrices. A classification task is performed with respect to the obtained directed graph based on the generated source encodings and the generated target encodings.

Abstract: A flush toilet includes a reservoir tank, a bowl, a rim spout port, a discharge trap conduit, a jet spout port configured to spout flush water toward an inlet of the discharge trap conduit, a jet water conduit configured to supply the flush water from the reservoir tank to the jet spout port, and a discharge device configured to supply or stop supplying the flush water to the jet water conduit, wherein the flush water is spouted at a first flow rate from the jet spout port when the discharge device is driven and the flush water in the reservoir tank flows into the jet water conduit and, after spouting of the first flow rate ends, the flush water is spouted at a second flow rate from the jet spout port due to the flush water retained in the jet water conduit flowing toward the jet spout port.

Abstract: A computer-implemented method for discovering causality includes accessing time-series data describing past events. The time-series data is input into a machine learning model, the machine learning model implementing an intensity function including a kernel function, where the kernel function determines a causal strength value computed from a transformer model, and where the kernel function contributes to an additive function that sums intensity of repeated individual events of the past events. In response to the inputting, an output is received from the machine learning model that indicates a causality that links two or more events of the past events.

Abstract: A gas turbine combustor according to at least one embodiment is a gas turbine combustor that includes: a tubular member; a plurality of premixing tubes circumferentially arranged on an inner side of the tubular member, each of the plurality of premixing tubes forming an outlet portion of a premixing passage; and a base plate for supporting the plurality of premixing tubes. The base plate has: a plurality of through holes disposed corresponding to the plurality of premixing tubes, respectively, and allowing the premixing passage to pass through the base plate; and a plurality of oblique holes extending obliquely with respect to an axial direction of the gas turbine combustor in a region different from a region where the through holes are disposed.

Abstract: A directed graph autoencoder device includes one or more memories and a processor coupled to the one or more memories and configured to implement a graph convolutional layer. The graph convolutional layer comprises a plurality of nodes and is configured to generate transformed dual vector representations by applying a source weight matrix and a target weight matrix to input dual vector representations of the plurality of nodes. The input dual vector representations comprise, for each node of the plurality of nodes, a source vector representation that corresponds to the node in its role as a source and a target vector representation that corresponds to the node in its role as a target. The graph convolutional layer is further configured to scale the transformed dual vector representations to generate scaled transformed dual vector representations. The graph convolutional layer is further configured to perform message passing using the scaled transformed dual vector representations.

Abstract: An embodiment for generating causal association rankings for candidate events within a window of candidate events using dynamic deep neural network generated embeddings. The embodiment may automatically receive a window of candidate events including events of a first type preceding one or more target events of interest. The embodiment may automatically generate contrastive windows of candidate events, each of the contrastive windows of candidate events of the first type corresponding to a different dropped candidate event from the received window of candidate events. The embodiment may automatically identify matching historical windows of events having resulting embeddings that are close in distance to the embeddings corresponding to the embeddings of the contrastive windows and calculate a first score for each match. The embodiment may automatically identify matching incident windows and calculate a corresponding second score.

Abstract: Techniques for causal modeling. Historical feature data is received, relating to a plurality of nodes in a system. A machine learning (ML) model is generated, for a node of the plurality of nodes. The ML model is trained to predict a plurality of future feature values for the node based on at least a portion of the historical feature data. A causal graph is generated, for the plurality of nodes, using a feature selection mechanism within the ML model. The feature selection mechanism includes a regularization term encouraging sparsity of nodes in selected features in the ML model.

Abstract: A combustor component of a combustor for combusting fuel to produce a combustion gas includes a combustion cylinder forming a passage for the combustion gas, a first acoustic device which internally includes a first cavity communicating with the passage via a first through hole formed in the combustion cylinder, a second acoustic device which is located on a radially outer side of the first acoustic device so as to cover the first acoustic device, and internally includes a second cavity communicating with the passage via a second through hole formed in the combustion cylinder, and a first communication passage causing the first cavity and an outer space of the combustion cylinder to communicate with each other without via the first through hole and the second cavity.

Abstract: A gas turbine combustor according to at least one embodiment is a gas turbine combustor that includes: a tubular member; a plurality of premixing tubes circumferentially arranged on an inner side of the tubular member, each of the plurality of premixing tubes forming an outlet portion of a premixing passage; and a base plate for supporting the plurality of premixing tubes. The base plate has: a plurality of through holes disposed corresponding to the plurality of premixing tubes, respectively, and allowing the premixing passage to pass through the base plate; and a plurality of oblique holes extending obliquely with respect to an axial direction of the gas turbine combustor in a region different from a region where the through holes are disposed.

Abstract: The upstream-side wall portion 54 includes, in the circumferential direction thereof, a first region 31 where air inlets 30 are formed at a lower density, and a second region 32 which is disposed at a position offset from the first region 31 in the circumferential direction, and in which the air inlets 30 are formed at a higher density than in the first region 31.

Abstract: A computer-implemented method is provided that includes learning causal relationships between two or more application micro-services, and applying the learned causal relationships to dynamically localize an application fault. First micro-service error log data corresponding to selectively injected errors is collected. A learned causal graph is generated based on the collected first micro-service error log data. Second micro-service error log data corresponding to a detected application and an ancestral matrix is built using the learned causal graph and the second micro-service error log data. The ancestral matrix is leveraged to identify the source of the error, and the micro-service associated with the identified error source is also subject to identification. A computer system and a computer program product are also provided.

Abstract: Techniques for causal modeling. Historical feature data is received, relating to a plurality of nodes in a system. A machine learning (ML) model is generated, for a node of the plurality of nodes. The ML model is trained to predict a plurality of future feature values for the node based on at least a portion of the historical feature data. A causal graph is generated, for the plurality of nodes, using a feature selection mechanism within the ML model. The feature selection mechanism includes a regularization term encouraging sparsity of nodes in selected features in the ML model.

Abstract: A computer-implemented method, a computer program product, and a computer system for stochastic event triage. A computer receives an event log including timestamps and event types. The computer determines a sparse impact matrix representing causal relationships between the event types, via a cardinality regularization. The computer determines triggering probabilities representing causal association probabilities between individual event instances, by leveraging a variational bound of a likelihood function. The computer provides a user with the triggering probabilities for event triage. The computer learns model parameters by iterating type-level causal analysis and instance-level causal analysis.

Abstract: A combustor component of a combustor for combusting fuel to produce a combustion gas includes a combustion cylinder forming a passage for the combustion gas, a first acoustic device which internally includes a first cavity communicating with the passage via a first through hole formed in the combustion cylinder, a second acoustic device which is located on a radially outer side of the first acoustic device so as to cover the first acoustic device, and internally includes a second cavity communicating with the passage via a second through hole formed in the combustion cylinder, and a first communication passage causing the first cavity and an outer space of the combustion cylinder to communicate with each other without via the first through hole and the second cavity.

Abstract: A computer-implemented method, a computer program product, and a computer system for diagnosing anomalies detected by a black-box machine learning model. A computer determines a local variance of a test sample in a test dataset, where the local variance represents uncertainty of a prediction by the black-box machine learning model. The computer initializes optimal compensations for the test sample, where the optimal compensations are optimal perturbations to test sample values of respective components of a multivariate input variable. The computer determines local gradients for the test sample. Based on the local variance and the local gradients, the computer updates the optimal compensations until convergences of the optimal compensations are reached. Using the optimal compensations, the computer diagnoses the anomalies detected by the black-box machine learning model.

Abstract: A combustor provided with: a nozzle having formed therein an air jet section that causes air to be jetted from a nozzle section; a cylindrical part covering the nozzle from the outer peripheral side thereof and forming an air flow path between the cylindrical part and the nozzle; and a pressure loss section provided to the air flow path. The pressure loss section causes a loss of pressure in the air that flows through the air flow path. The nozzle is provided with: at least one air inlet section that takes in air from an outer peripheral surface that is an upstream side from the pressure loss section; and a flow path-forming section forming a discharge air flow path that guides air that is taken in from the at least one air inlet section to the air jet section.

Abstract: A computer-implemented method, a computer program product, and a computer system for diagnosing anomalies detected by a black-box machine learning model. A computer determines a local variance of a test sample in a test dataset, where the local variance represents uncertainty of a prediction by the black-box machine learning model. The computer initializes optimal compensations for the test sample, where the optimal compensations are optimal perturbations to test sample values of respective components of a multivariate input variable. The computer determines local gradients for the test sample. Based on the local variance and the local gradients, the computer updates the optimal compensations until convergences of the optimal compensations are reached. Using the optimal compensations, the computer diagnoses the anomalies detected by the black-box machine learning model.

Abstract: A method for anomaly alarm consolidation includes detecting a plurality of anomalies in time-series data received from an information technology infrastructure; identifying a plurality of root-cause candidates for each of the anomalies; generating, by a scenario analysis of the anomalies, a plurality of alarms, wherein the scenario analysis predicts a plurality of future expected values of the time-series data over a plurality of historical values of the time-series data using a graphical Granger causal model and generates the alarms based on a difference between the future expected values of the time-series data and actual values of the anomalies in the time-series data; and performing a belief propagation procedure between the root-cause candidates and the alarms to determine a plurality of root-causes that collectively comprise attributed root-causes for the alarms.

Abstract: A method for anomaly alarm consolidation includes detecting a plurality of anomalies in time-series data received from an information technology infrastructure; identifying a plurality of root-cause candidates for each of the anomalies; generating, by a scenario analysis of the anomalies, a plurality of alarms, wherein the scenario analysis predicts a plurality of future expected values of the time-series data over a plurality of historical values of the time-series data using a graphical Granger causal model and generates the alarms based on a difference between the future expected values of the time-series data and actual values of the anomalies in the time-series data; and performing a belief propagation procedure between the root-cause candidates and the alarms to determine a plurality of root-causes that collectively comprise attributed root-causes for the alarms.

Abstract: An image processing apparatus includes an image-data processor, an interface, a power source, and a controller. The controller selects a first mode, a second mode, or a third mode as a power supply mode. In the first mode, electric power is supplied from the power source to the image-data processor and the interface. In the second mode, supply of the electric power from the power source to the image-data processor and the interface is in a stopped state. In the third mode, the electric power is supplied from the power source to the interface, but supply of the electric power to the image-data processor is in a stopped state. The controller switches the power supply mode from the second mode to the third mode in response to receiving a power supply request from an external device via the interface in the second mode.