Abstract: An anomaly detection system and method is provided. The system comprising: a hardware processor; and a memory storing instructions to configure the hardware processor, wherein the hardware processor receives a first time-series data comprising a first set of points and a second time-series data comprising a second set of points, computes a first set of error vectors for each point of the first set, and a second set of error vectors for each point of the second set, each set of error vectors comprising one or more prediction errors; estimates parameters based on the first set of error vectors comprising; applies (or uses) the parameters on the second set of error vectors; and detects an anomaly in the second time-series data when the parameters are applied on the second set of error vectors.

Abstract: This disclosure relates generally to health monitoring of systems, and more particularly to monitor health of a system for fault signature identification. The system estimates Health Index (HI) of the system as time series data. By analyzing data corresponding to the estimated HI, the system identifies one or more time windows in which majority of the estimated HI values are low as a low HI window, and one or more time windows in which majority of the estimated HI values are high as a high HI window. Upon identifying a low HI window, which indicates an abnormal behavior of the system being monitored, based on a local Bayesian Network generated for the system being monitored, an Explainability Index (EI) for each sensor is generated, wherein the EI quantifies contribution of the sensor to the low HI. Further, associated component(s) is identified as contributing to abnormal/faulty behavior of the system.

Abstract: A method and a system to enable customer behavior prediction are disclosed. Temporal and aggregate features with respect to purchases made by a customer are extracted from purchase history of customers. Further, temporal and aggregate models are generated corresponding to the features extracted, wherein the temporal and aggregate models are data of a first type and data of a second type respectively. Further, a Mixture of Experts (ME) is used to process the temporal and aggregate models that are of different types of data, to build a combined model, and purchase behavior of the customer is identified based on the combined model.

Abstract: This disclosure relates generally to data processing, and more particularly to a system and a method for mapping heterogeneous data sources. For a product being sold globally, there might be one global database listing characteristics of the product, and from various System and method for mapping attributes of entities are disclosed. In an embodiment, the system uses a combination of Supervised Bayesian Model (SBM) and an Unsupervised Textual Similarity (UTS) model for data analysis. A weighted ensemble of the SBM and the UTS is used, wherein the ensemble is weighted based on a confidence measure. The system, by performing data processing, identifies data match between different data sources (a local databases and a corresponding global database) being compared, and based on matching data found, performs mapping between the local databases and the global database.

Abstract: This disclosure relates generally to multi-sensor visual analytics, and more particularly to method and system for multi-sensor visual analytics using machine-learning models. In one embodiment, a method for multi-sensor visual analytics includes acquiring sensor data associated with a plurality of sensors for a plurality of days of operation. A plurality of multi-dimensional histograms, having operational profiles of the plurality of sensors are computed from the sensor data. The plurality of multi-dimensional histograms are monitored, and a plurality of multi-sensor patterns are obtained from the plurality of multi-dimensional histograms. The plurality of multi-sensor patterns are indicative of one or more properties of a plurality of sensor-clusters of the plurality of sensors. One or more visual analytical tasks are performed by processing the plurality of multi-sensor patterns using at least one machine-learning model.

Abstract: Methods and systems for searching logical patterns in voluminous multi sensor data from the industrial internet is provided. The method retrieves instances of patterns in time-series data where patterns are specified logically, using a sequence of symbols. The logical symbols used are a subset of the qualitative abstractions specifically, the concepts of steady, increasing, decreasing. Patterns can include symbol-sequences for multiple sensors, approximate duration as well as slope values for each symbol. To facilitate efficient querying, each sensor time-series is pre-processed into a sequence of logical symbols. Each position in the resulting compressed sequence is registered across a TRIE-based index structure corresponding to the multiple logical patterns it may belong to. Logical multi-sensor patterns are efficiently retrieved and ranked using such a structure. This method of indexing and searching provides an efficient mechanism for exploratory analysis of voluminous multi-sensor data.

Abstract: System and method for training inductive logic programming enhanced deep belief network models for discrete optimization are disclosed. The system initializes (i) a dataset comprising values and (ii) a pre-defined threshold, partitions the values into a first set and a second set based on the pre-defined threshold. Using Inductive Logic Programming (ILP) engine and a domain knowledge associated with the dataset, a machine learning model is constructed on the first set and the second set to obtain Boolean features, and using the Boolean features that are being appended to the dataset, a deep belief network (DBN) model is trained to identify an optimal set of values between the first set and the second set. Using the trained DBN model, the optimal set of values are sampled to generate samples. The pre-defined threshold is adjusted based on the generated samples, and the steps are repeated to obtain optimal samples.

Abstract: System and method for visual Bayesian data fusion are disclosed. In an example, a plurality of datasets associated with a topic are obtained from a data lake. Each of the plurality of datasets include information corresponding to various attributes of the topic. Further, the plurality of datasets are joined to obtain a joined dataset. Furthermore, distribution associated with a target attribute is predicted using Bayesian modeling by selecting a plurality of attributes (k) based on mutual information with the target attribute in the joined dataset, learning a minimum spanning tree based Bayesian structure using the selected attributes and the target attribute, learning conditional probabilistic tables at each node of the minimum spanning tree based Bayesian structure; and predicting the distribution associated with the target attribute by querying the conditional probabilistic tables, thereby facilitating visual Bayesian data fusion.

Abstract: A method for performing email analytics is described. The method includes extracting emails from the configured email repository. The emails are then grouped into mail groups based on identification of content similarity of the emails. A network graph is then constructed for each of the mail group to identify an association of emails in the mail group based on header-level analysis of emails. Thereafter, email analytics is performed on the mail groups by clustering the mail groups into mail clusters based on temporal progression of emails in the mail groups. Key phrases are then determined based on a content analysis of emails in the mail groups in the mail clusters. The key phrases are then associated with the network graphs of the mail groups.

Abstract: This disclosure relates generally to multi-sensor visual analytics, and more particularly to method and system for multi-sensor visual analytics using machine-learning models. In one embodiment, a method for multi-sensor visual analytics includes acquiring sensor data associated with a plurality of sensors for a plurality of days of operation. A plurality of multi-dimensional histograms, having operational profiles of the plurality of sensors are computed from the sensor data. The plurality of multi-dimensional histograms are monitored, and a plurality of multi-sensor patterns are obtained from the plurality of multi-dimensional histograms. The plurality of multi-sensor patterns are indicative of one or more properties of a plurality of sensor-clusters of the plurality of sensors. One or more visual analytical tasks are performed by processing the plurality of multi-sensor patterns using at least one machine-learning model.

Abstract: The present subject matter relates to analysis of time-series data based on world events derived from unstructured content. According to one embodiment, a method comprises obtaining event information corresponding to at least one world event from unstructured content obtained from a plurality of data sources. The event information includes at least time of occurrence of the world event, time of termination of the world event, and at least one entity associated with the world event. Further, the method comprises retrieving time-series data pertaining to the entity associated with the world event from a time-series data repository. Based on the event information and the time-series data, the world event is aligned and correlated with at least one time-series event to identify at least one pattern indicative of cause-effect relationship amongst the world event and the time-series event.

Abstract: This disclosure relates generally to multi-sensor data, and more particularly to summarizing multi-sensor data. In one embodiment, the method includes computing plurality of histograms from sensor data associated with a plurality of sensors. The respective histograms of each sensor are clustered into a first plurality of sensor-clusters, and a first set of rules is extracted therefrom. First set of rules defines patterns of histograms of a set of sensors occurring frequently over a time-period. Two or more sensor-clusters from amongst the first plurality of sensor-clusters are merged selectively to obtain a second plurality of sensor-clusters. Second set of rules are extracted from the second plurality of sensor-clusters, and a set of correlated sensors are identified therefrom based on the second set of rules. Third set of rules are extracted from the set of correlated sensors, the third set of rules summarizes the multi-sensor data to represent prominent co-occurring sensor behaviors.

Abstract: Systems and methods for predictive reliability mining are provided that enable predicting of unexpected emerging failures in future without waiting for actual failures to start occurring in significant numbers. Sets of discriminative Diagnostic Trouble Codes (DTCs) from connected machines in a population are identified before failure of the associated parts. A temporal conditional dependence model based on the temporal dependence between the failure of the parts from past failure data and the identified sets of discriminative DTCs is generated. Future failures are predicted based on the generated temporal conditional dependence and root cause analysis of the predicted future failures is performed for predictive reliability mining. The probability of failure is computed based on both occurrence and non-occurrence of DTCs. The root cause analysis enables identifying a subset of the population when an early warning is generated and also when an early warning is not generated.

Abstract: The present disclosure relates to business data processing and facilitates fusing business data spanning disparate sources for processing distributional queries for enterprise business intelligence application. Particularly, the method comprises defining a Bayesian network based on one or more attributes associated with raw data spanning a plurality of disparate sources; pre-processing the raw data based on the Bayesian network to compute conditional probabilities therein as parameters; joining the one or more attributes in the raw data using the conditional probabilities; and executing probabilistic inference from a database of the parameters by employing an SQL engine. The Bayesian Network may be validated based on estimation error computed by comparing results of processing a set of validation queries on the raw data and the Bayesian Network.

Abstract: Methods and systems for searching logical patterns in voluminous multi sensor data from the industrial internet is provided. The method retrieves instances of patterns in time-series data where patterns are specified logically, using a sequence of symbols. The logical symbols used are a subset of the qualitative abstractions specifically, the concepts of steady, increasing, decreasing. Patterns can include symbol-sequences for multiple sensors, approximate duration as well as slope values for each symbol. To facilitate efficient querying, each sensor time-series is pre-processed into a sequence of logical symbols. Each position in the resulting compressed sequence is registered across a TRIE-based index structure corresponding to the multiple logical patterns it may belong to. Logical multi-sensor patterns are efficiently retrieved and ranked using such a structure. This method of indexing and searching provides an efficient mechanism for exploratory analysis of voluminous multi-sensor data.

Abstract: An anomaly detection system and method is provided. The system comprising: a hardware processor; and a memory storing instructions to configure the hardware processor, wherein the hardware processor receives a first time-series data comprising a first set of points and a second time-series data comprising a second set of points, computes a first set of error vectors for each point of the first set, and a second set of error vectors for each point of the second set, each set of error vectors comprising one or more prediction errors; estimates parameters based on the first set of error vectors comprising; applies (or uses) the parameters on the second set of error vectors; and detects an anomaly in the second time-series data when the parameters are applied on the second set of error vectors.

Abstract: The invention facilitates asynchronous interaction between a geographically separated facilitator and at least one user. The said invention provides asynchronous interaction between rural classrooms (teacher-student community) and expert teachers to increase the outreach of the expert teachers much beyond that is permitted with the teachings of the prior art.

Abstract: A method and a system for interpreting a dataset comprising a plurality of items is described herein. The method may include computing a rule set pertaining to the dataset, generating a rule cover, calculating a plurality of distances between the plurality of rule pairs in the rule cover and generating a distance matrix based on the calculated plurality of distances between the plurality of rule pairs, storing the calculated plurality of distances between the plurality of rule pairs, clustering the overlapping rules within the rule cover using the distance matrix; selecting a representative rule from each cluster, determining at least one exception for each representative rule in the rule cover selected from each cluster and interpreting the dataset using the representative rules and the at least one exception determined for each representative rule in the rule set.

Abstract: Estimating warranty cost of products having multiple parts is described. In an implementation, part-failure data indicative of number of cycles at which each part fails in and after a first predefined time period is determined Sensor data and service records data are obtained to determine DTC occurrence data and DTC observance data. The DTC occurrence data and the DTC observance data are indicative of number of cycles at which each DTC associated with each part occurs and is observed for first time in the first predefined time period, respectively. Dependency parameters between the part-failure data, the DTC occurrence data and the DTC observance data are identified based on Bayesian Network that represents probabilistic relationships between the part-failure data, the DTC occurrence data and the DTC observance data. Number of failures of products in a second predefined time period is computed based on the dependency parameters for estimating the warranty cost.

Abstract: The present subject matter discloses system and method for executing prescriptive analytics. Simulation is performed from an input data (xinput) and simulation parameters (?) to generate simulating data (D). Further, forecast data may be predicted by processing the simulating data (D) using predictive model (M). Further, prescriptive value (x?) may be determined based on the forecast data by using optimization model. The prescriptive value (x?) may be determined such that an objective function associated with the optimization model is optimized, whereby the optimization of the objective function indicates business objective being achieved. Further, the steps of simulating, predicting and determining may be iteratively performed until the objective function is not further optimized, satisfying predefined condition.