Abstract: Methods and systems to provide a form of probabilistic labeling to associate an outage with a disturbance, which could itself be either known based on the available data or unknown. In the latter case, labeling is especially challenging, as it necessitates the discovery of the disturbance. One approach incorporates a statistical change-point analysis to time-series events that correspond to service tickets in the relevant geographic sub-regions. The method is calibrated to separate the regular periods from the environmental disturbance periods, under the assumption that disturbances significantly increase the rate of loss-causing events. To obtain the probability that a given loss-causing event is related to an environmental disturbance, the method leverages the difference between the rate of events expected in the absence of any disturbances (baseline) and the rate of actually observed events. In the analysis, the local disturbances are identified and estimators of their duration and magnitude are provided.

Abstract: Disclosed embodiments provide techniques for estimating imputation algorithm performance. Multiple imputer algorithms are selected, and an evaluation of how well each of the imputer algorithms can estimate the missing data is performed. Disclosed embodiments obtain an imputer candidate dataset (ICD). The imputer candidate dataset is compared to the incomplete data range, and a similarity metric is determined between the data range and the ICD. When the similarity metric exceeds a predetermined threshold, an imputer evaluation dataset (IED) is created from the ICD by removing one or more data points from the ICD. Each imputer algorithm is evaluated by applying the IED to it, and computing an imputer evaluation metric based on its performance. The multiple imputer algorithms are ranked based on the imputer evaluation metric. The best ranked imputer algorithm can then be selected for use on the incomplete data range within the measurement dataset.

Abstract: An approach for generating an artificial intelligence system configurable for use with assets. In this approach, a model recipe is selected for generating the artificial intelligence system for use with assets. Recipe parameters specified in the model recipe are identified. A training dataset is created using the model recipe and input data. A set of artificial intelligence models is trained using the training dataset, the recipe parameters, and the model recipe. The training creates artifact models. The artifact models resulting from training are evaluated. The evaluation is used to select a set of the artifact models in the artifacts that form the artificial intelligence system that is configurable for use in assets.

Abstract: A computer implemented method for estimating environmental impact for industrial assets is provided. A number of processor units receive data for an industrial asset. The data for the industrial asset includes a number of variables associated with sustainability of the industrial asset. The sustainability of the industrial asset includes energy consumption, leakage, and energy loss associated with operations for the industrial asset. The number of processor units determines a relationship between environmental impact for the industrial asset and the number of variables according to the data. The number of processor units forecast energy consumption, leakage, and energy loss over a period of time for the industrial asset based on the data. The number of processor units estimate environmental impact for the industrial asset over the period of time based on the forecasted energy consumption, the forecasted energy loss, forecasted leakage, and the relationship.

Abstract: A computer implemented federated learning method of predicting failure of assets includes generating a local model at a local site for each of the cohorts and training the local model on local data for each of the cohorts for each failure type. The local model is shared with a central database. A global model is created based on an aggregation of a plurality of the local models from a plurality of the local sites. At each of the plurality of local sites, one of the global model and the local model is chosen for each of the cohorts. The chosen model operates on local data to predict failure of the assets. The utilized features include partitioning features of the assets into static features, semi-static features, and dynamic features, and forming cohorts of the assets based on the static features and the semi-static features.

Abstract: Machine learning (ML) pipeline selection includes performing cross-validation runs for dataset-pipeline combinations and building a matrix of first accuracy scores, factoring the matrix of accuracy scores into pipeline latent factors and dataset latent factors, augmenting the matrix of accuracy scores by selecting a subset of ML pipelines of a plurality of ML pipelines, then, for a new dataset, running the subset of ML pipelines with the new dataset to build and test respective ML models, obtain second accuracy scores, and augment the matrix of accuracy scores with the second accuracy scores to produce an augmented matrix of accuracy scores, factoring the augmented matrix of accuracy scores into refined pipeline latent factors and refined dataset latent factors, and identifying, based on the refined pipeline latent factors and the refined dataset latent factors, ML pipeline(s), of the plurality of ML pipelines, as most optimal for model building based on the new dataset.

Abstract: Detecting and mitigating anomalous system behavior by providing a machine learning model comprising a knowledge graph depicting system entity relationships, and modeling behavioral correlations among system entities according to historical time-series data, receiving real-time time-series data for the system, detecting an anomalous system behavior in a system locale, according to the real-time time-series data, according to the machine learning model and multivariate sensor metrics, diagnosing the anomalous system behavior according to an upstream portion of the knowledge graph and a statistical behavior model for the system locale, and mitigating the anomalous behavior by deriving a recommended action according to the anomalous behavior and generating a work order to implement the recommended action.

Abstract: A computer-implemented method for developing a hierarchical machine-learning pipeline can include receiving a hierarchy specification, a set of estimators for the root node, and one or more transformer options for each of the transformer nodes. The hierarchy specification provides a configuration of the root node, transformer nodes, and edges interconnecting the root and transformer nodes. A rank can be obtained for each estimator in the root node. A hierarchy pipeline traverser can then traverse a first child layer of the transformer nodes connected to the root node via one of the edges. A first ranked list of pathways can be determined with respect to the one or more transformer options selected for the first child layer and at least one selected estimator of the root node.

Abstract: A computing device includes a processor and a storage device. A vehicle asset modeling module is stored in the storage device and is executed by the processor to configure the computing device to perform acts of identifying and clustering a plurality of assets based on static properties of a vehicle asset using a first module of the vehicle asset modeling module. The clustered plurality of assets is determined based on dynamic properties of the vehicle asset using a second module. Event prediction is performed by converting a numeric data of the clustered plurality of assets to a natural language processing (NLP) domain by a third module. One or more sequence-to-sequence methods are performed to predict a malfunction of a component of the vehicle asset and/or an event based on past patterns. Prediction information is stored in the storage device.

Abstract: Various systems and methods are presented regarding code-based pattern extraction (Code-PE) and the application of Code-PE to a named entity recognition pipeline. Patterns can be generated from named entities, wherein the entities have an assigned type. Codes are identified within the entities, subsequently vectorized and clustered based upon the presence of the identified codes. Patterns are identified for the respective clusters. The patterns can be applied to an untyped entity, in the event of the pattern matching, the entity can be typed with the type assigned to the pattern. The typed entity can be used to recursively update knowledge regarding typed- and untyped-entities. In the event a pattern incorrectly types an entity, the pattern can be retrained with the updated knowledge.

Abstract: A computing device, method, and system are provided of improving data quality to conserve computational resources. The computing device receives a raw dataset. One or more data quality metric goals corresponding to the received raw dataset are received. A schema of the dataset is determined. An initial set of validation nodes is identified based on the schema of the dataset. The initial set of validation nodes are executed. A next set of validation nodes are iteratively expanded and executed based on the schema of the dataset until a termination criterion is reached. A corrected dataset of the raw dataset is provided based on the iterative execution of the initial and next set of validation nodes.

Abstract: An embodiment for identifying influential disturbances is provided. The embodiment may automatically receive a set of service records including disturbance-related probability values corresponding to the disturbance-revealing events, and wherein one or more service records are mislabeled or have no label relating to an associated disturbance. The embodiment may generate baselines for a series of relevant sub-regions associated with the service records, and normalize daily summaries of disturbance probabilities for each of the relevant sub-regions. The embodiment may automatically identify subsets of service records corresponding to a series of newly-discovered disturbances by using the disturbance-related probability values and a series of associated features to identify deviations from normal non-disturbance event distributions.

Abstract: Systems and methods for optimizing and training machine learning (ML) models are provided. In embodiments, a computer implemented method includes: performing, by a processor set, a group execution of ML pipelines using a first subset of a training data set as input data for the ML pipelines, thereby generating a trained ML model for each of the ML pipelines, wherein data transformations that are common between the ML pipelines are implemented only once to generate an output, and the output is shared between the ML pipelines during the group execution of the ML pipelines; generating, by the processor set, performance metrics for each of the trained ML models based on validation data; ranking, by the processor set, the trained ML models based on the performance metrics, thereby generating a list of ranked ML models; and outputting, by the processor set, the list of ranked ML models to a user.

Abstract: Disclosed embodiments provide techniques for estimating imputation algorithm performance. Multiple imputer algorithms are selected, and an evaluation of how well each of the imputer algorithms can estimate the missing data is performed. Disclosed embodiments obtain an imputer candidate dataset (ICD). The imputer candidate dataset is compared to the incomplete data range, and a similarity metric is determined between the data range and the ICD. When the similarity metric exceeds a predetermined threshold, an imputer evaluation dataset (IED) is created from the ICD by removing one or more data points from the ICD. Each imputer algorithm is evaluated by applying the IED to it, and computing an imputer evaluation metric based on its performance. The multiple imputer algorithms are ranked based on the imputer evaluation metric. The best ranked imputer algorithm can then be selected for use on the incomplete data range within the measurement dataset.

Abstract: Embodiments of the invention are directed to a computer-implemented method. A non-limiting example of the computer-implemented method includes accessing, using a processor system, a process-step sequence that includes a plurality process-steps and a plurality of queue-times. A process-step sequence mining operation is applied to the process-step sequence, wherein the process-step sequence mining operation is operable to make a prediction of an impact of a portion of the process-step sequence on a characteristic of a product generated by the process-step sequence.

Abstract: A computer-implemented method in accordance with one embodiment includes, in response to a submission of an input dataset to an artificially intelligent application, receiving an explanation from each module of the application. The modules are configured within the application in a serial sequence in which each module, upon receiving the input dataset and any input generated by an immediately preceding module of the serial sequence, generates output that is forwarded as input to a next module, if any, in the sequence. A determination is made that at least two of the received explanations are semantically inconsistent.

Abstract: A computer implemented method of administering a complex system includes receiving multivariate data from a plurality of sensors of the system in an ambient state. Event sequences in the received multivariate data are identified. The multivariate event sequences are projected to a lower stochastic latent embedding. A temporal structure of the sequences is learned in a lower latent space. A probabilistic prediction in the lower latent space is provided. The probabilistic prediction in the lower stochastic latent space is decoded to an event prediction in the ambient state.

Abstract: Embodiments of the present invention provide a computer system, a computer program product, and a method that comprises ingesting tabular data from at least one modality of a plurality of modalities; simultaneously extracting data and generating a prediction model for a task of a computing device from the extracted data from at least two modalities in the plurality of modalities; generating a data signature based on the generated prediction model from the at least two modalities by leveraging the generated prediction model for ingested tabular data and extracted data; comparing the generated data signature to identified data signatures stored in at least one modality in the plurality of modalities; and performing a task based on the generated data signature and a validation of the comparison of identified data signatures.

Abstract: Temporal and spatially integrated forecast modeling includes generating a plurality of forecast models for a plurality of short-term to long-term time periods for a plurality of locations. Temporally integrating the plurality of forecast models sequentially over the plurality of time periods for the plurality of locations and spatially integrating the temporally integrated plurality of forecast models for each location hierarchically over the geographic areas. The forecast models are autoregressive distributed lag models with different explanatory variables for the short-term and long-term forecast models. The temporally integrating includes recursively integrating the plurality of forecast models over the time periods from the short-term to the long-term time periods and the spatially integrating includes recursively integrating the temporally integrated plurality of forecast models hierarchically from larger size geographic areas to smaller size geographic areas.

Abstract: A computing device includes a processor and a storage device. A wafer asset modeling module is stored in the storage device and is executed by the processor to configure the computing device to perform acts identifying and clustering a plurality of assets based on static properties of a wafer asset using a first module of the wafer asset modeling module. The clustered plurality of assets is determined based on dynamic properties of the wafer asset using a second module of the wafer asset modeling module. Event prediction is performed by converting a numeric data of the clustered plurality of assets to a natural language processing (NLP) domain by a third module of the wafer asset modeling module. One or more sequence-to-sequence methods are performed to predict a malfunction of a component of the wafer asset and/or an event based on past patterns. Prediction information is stored in the storage device.