Methods and systems for detecting false alarms. Methods and systems described herein may receive data associated with an alarm signal using an interface, extract at least one artifact feature from the received data, and then receive a classification of the alarm signal as a true positive or false positive based on the at least one extracted artifact feature. The classifier may be configured to execute an ensemble of decision trees.

A system and method of 3-D image segmentation of brain images includes obtaining a 3-D MRI image, an employee phase including performing search cycles of generating solutions in a neighborhood, taking into account (a) movement of a bee's current location toward a mean value of a positive direction of a global best location and a positive direction of its own best location, (b) movement of the bee's current location toward the mean value of the positive direction of its own best location and a negative direction of the global best location, and (c) a random number, calculating a fitness value for the solutions based on membership values of pixels and distances between the pixels to cluster centers of pixels until search ends. Image segmentation of the image is performed using centers of clusters.

One or more computer processors create a binary cluster of events by bootstrapping a set of ground truths contained with a rule engine applied to a set of high-dimensional datapoints, wherein the binary cluster contains two clusters each containing a plurality of high-dimensional datapoints; determine one or more peer groups for a set of unknown high-dimensional datapoints utilizing a trained multiclass classifier, wherein the high-dimensional datapoints are assigned to one or more peer groups by the trained multiclass classifier using an incremental learning algorithm in order to reduce system resources; create an activity distribution for each unknown high-dimensional datapoint associated with a user in the set of unknown high-dimensional datapoints and each peer group; calculate a deviation percentage between the activity distribution of the user and each peer group associated with the user; and responsive to exceeding a deviation threshold, classify the user or associated high-dimensional datapoints as risky.

Aspects of the present disclosure involve systems, methods, devices, and the like for presenting a recommendation. In one embodiment, a system is introduced that includes a plurality of models for obtaining a recommendation score. The recommendation score may be obtained using one or more models which can include supervised and unsupervised learning as well as a combination of user information and transactions. In another embodiment, the system is introduced that can provide a total recommendation score and recommendation generated by an ensemble model whose input can include the one or more recommendation scores previously obtained.

A computer-implemented method for learning unknown concepts during natural language processing is disclosed, including identifying a sentence associated with an unknown concept, selecting a first sequential set of sentences from a first document, including the sentence associated with the unknown concept, one sentence prior, and subsequent to the sentence associated with the unknown concept, selecting a second sequential set of sentences from a second document, including a sentence associated with a known concept, and one sentence prior and subsequent to the sentence associated with the known concept, comparing concepts associated with the first sequential set of sentences and second sequential set of sentences, determining whether an inference can be made between the unknown concept associated with the sentence from the first document and the sentence associated with the known concept associated with the sentence from the second document, and tagging the unknown concept associated with the known concept.

An approach for determining a veracity of a reported event is provided. In an embodiment, a set of predictor variables is retrieved from a selected use case. Each of these predictor values is a condition that indicates the veracity of the reported event. In addition, a set of hidden predictor variables is generated from a set of unstructured documents related to the reported event using a hidden Markov model that is based on the predictor variables using a cognitive system. These hidden predictor variables are combined with the set of predictor variables to generate a set of updated predictor variables. These updated predictor variables are used by the cognitive system to return a determination of the veracity of the reported event.

Methods and systems are provided to determine suitable hyperparameters for a machine learning model and/or feature engineering process. A suitable machine learning model and associated hyperparameters are determined by analyzing a dataset. Suitable hyperparameter values for compatible machine learning models having one or more hyperparameters in common and a compatible dataset schema are identified. Hyperparameters may be ranked according to each of their respective influences on a model performance metrics, and hyperparameter values identified as having greater influence may be more aggressively searched.

The present invention belongs to the field of information technology, involving the techniques of fuzzy modeling, reinforcement learning, parallel computing, etc. It is a method combining granular computing and reinforcement learning for construction of long-term prediction interval and determination of its structure. Adopting real industrial data, the present invention constructs multi-layer structure for assigning information granularity in unequal length and establishes corresponding optimization model at first. Then considering the importance of the structure on prediction accuracy, Monte-Carlo method is deployed to learn the structural parameters. Based on the optimal multi-layer granular computing structure along with implementing parallel computing strategy, the long-term prediction intervals of gaseous generation and consumption are finally obtained. The proposed method exhibits superiority on accuracy and computing efficiency which satisfies the demand of real-world application. It can be also generalized to apply on other energy systems in steel industry.

A set of partial words is received. At least one partial word in the set of partial words is completed. The set of partial words with the at least one completed partial word is run through a trained deep neural network, the trained deep neural network inferring a word embedding associated with an unfinished word in the set of partial words. An inferred word is determined based on the inferred word embedding associated with the unfinished word. A sentence may be output, which includes at least the completed partial word and the inferred word.

An approach is provided in which the approach trains a machine learning model using reference entries included in a reference dataset. During the training, the machine learning model learns a first set of unidirectional associations between the reference entries. The approach inputs a user dataset into the trained machine learning model and generates a second set of unidirectional associations between user dataset entries included in the user dataset. The approach builds a hierarchical relationship of the user dataset based on the second set of unidirectional associations and manages the user dataset based on the hierarchical relationship.