Abstract: A method includes, based on a fitness function, selecting a subset of models from a plurality of models. The plurality of models is generated based on a genetic algorithm and corresponds to a first epoch of the genetic algorithm. Each of the plurality of models includes data representative of a neural network. The method also includes performing at least one genetic operation of the genetic algorithm with respect to at least one model of the subset to generate a trainable model and sending the trainable model to an optimization trainer. The method includes adding a trained model received from the optimization trainer as input to a second epoch of the genetic algorithm that is subsequent to the first epoch.

Abstract: A data processor system for monitoring a complex system, the processor system configured to receive a plurality of pieces of state information and to merge at least the pieces of state information into a piece of failure information, at least one of the pieces of state information being associated with a confidence flag, and the piece of failure information also being associated with a confidence flag. The system performs the merging by implementing a fuzzy logic technique to produce the piece of failure information while taking account of the respective confidence flag of the pieces of state information and to produce the confidence flag associated with the failure information.

Abstract: A computer-implemented method of determining search intent, comprises: receiving a search query; searching content across a plurality of content classes using the search query, so as to obtain a plurality of search results; deriving summary data from the search results; applying the summary data to a trained machine learning model; and determining from the machine learning model a selected one of the content classes corresponding to the search intent of the search query.

Abstract: Disclosed is a method and Geographic Information System (GIS) for creating a user's proximity model in accordance with a user's feedback. The GIS creates the user's proximity model using a Dempster-Shafer technique. The GIS initializes the user's proximity model upon initializing a fuzzy set with a fuzzy membership function. The fuzzy set includes a plurality of points scattered around a reference point. The GIS creates an intermediate model using the user's proximity model by selecting a group of points from the plurality of points. The GIS receives a user feedback on the intermediate model. The GIS adapts the fuzzy membership function based on the user feedback. The GIS then updates the user's proximity model based on the fuzzy membership function which is adapted on basis of the user feedback.

Abstract: Predictive modeling is an important class of data analytics with applications in numerous fields. Once a predictive model is built, validated, and applied on a set of objects, by a data analytics system (or even by manual modeling), consumers of the model information need assistance to navigate through the results. This is because both regression and classification models that output continuous values (eg, probability of belonging to a class) are often used to rank objects and then a thresholding of the ranked scores needs to be used to separate objects into a “positive” and a “negative” class. The choice of threshold greatly affects the true positive, false positive, true negative, and false negative results of the model's application. An ideal data analytics system should allow the user to understand the tradeoffs of different threshold values for different thresholds.

Abstract: Methods and systems for pharmacy modeling are described. The risk adjusted pharmacy predictive model is created from member data, claims data, and population data. This model can be used to compare the actual pharmacy performance to an expected actual pharmacy performance value, which can be used to identify pharmacies at risk or not performing to an acceptable level. The model can be used for adherence and generic drug utilization ratings of pharmacies. The pharmacy can be judged on a therapy class by therapy class basis with factors that reflect the demographic, socio-economic, location, benefits attributes, etc. that actually affect the performance of the pharmacy and may assist in determining the quality of care by a pharmacy.

Abstract: There is provided a system for providing information. The system includes a data classifying device configured to receive original data and classify the original data as real time data or general data; a real time data analyzing device configured to receive the real time data from the data classifying device and generate condensed information including only a part that satisfies predefined conditions among attribute information of the real time data; and a distributed parallel processing device configured to receive the general data from the data classifying device, perform a predetermined distributed parallel computation process on the general data, and generate analysis information.

Abstract: Devices, methods, and programs for monitoring electrical devices. A method for monitoring an electrical device may include obtaining data representing a sum of electrical signals of electrical devices; processing the data with a Factorial Hidden Markov Model (FHMM) to produce an estimate of an electrical signal of a first of the electrical devices; and outputting the estimate of the electrical signal of the first electrical device. The FHMM may have a factor corresponding to the first electrical device. The factor may have three or more states.

Abstract: The subject matter discloses a method for generating a new dynamic function embedded within a chip, wherein the chip comprises a plurality of a building blocks, a first function, and a specification defining the new dynamic function; the method comprising the steps of: within the chip, performing the first function in accordance with the specification and/or analysis; and within the chip, generating the new dynamic function upon the performing the first function.

Abstract: A computer-implemented method of classifying a search query in a network comprises: classifying a plurality of search queries into categories, comprising: applying predetermined rules to each of the plurality of search queries, wherein the predetermined rules are indicative of the categories and each of the plurality of search queries is associated with search results in the network; determining, for each of the plurality of search queries, similarity values indicating similarity to each of the categories based on the applied predetermined rules; and training a machine learning module, comprising: applying the machine learning module to a plurality of training sets to a plurality of training sets, wherein each of the plurality of training sets is based on one of the plurality of classified search queries and at least one of the respective one or more similarity values, a corresponding system, computing device and non-transitory computer-readable storage medium.

Abstract: Features are disclosed for identifying and routing items for tagging using a latent feature model, such as a recurrent neural network language model (RNNLM). The model may be trained to identify latent features for catalog items such as movies, books, food items, beverages, and the like. Based on similarities in latent features, tags previous assigned to items may be applied to untagged items. Application may be manual or automatic. In either case, resources need to be balances to ensure efficient tagging of items. The included features help to identify and direct these limited tagging resources.

Abstract: A method and apparatus for predicting based on multi-source heterogeneous data. The method comprises: acquiring, with regard to an event of a set type, at least two types of historical data that can reflect an event result; establishing a joint likelihood model of attribute data of the event of the set type and the historical data; determining an optimal estimation of the attribute data according to a maximum posterior principle; and determining, based on a probability distribution associated with the attribute data in the joint likelihood model, a parameter in the probability distribution as a prediction result of a predicted event of the set type. Some embodiments use a hierarchical model to introduce data of different sources into different data layers, unify heterogeneous data in a joint likelihood model to perform analysis, and obtain a more accurate, instant and stable prediction result through effective fusion.

Abstract: Example embodiments relate to a network-based ontology curation system employed for receiving a request to view a data object, curating an ontology associated with the data object on-the-fly based on attributes of the request that include device and user characteristics.

Abstract: A computer-based detection tool for detecting whether content within a given document is common to content within a plurality of other, existing documents, the detection tool comprising: a character string recognizer for recognizing character strings in the content of the given document; a character string distinguisher for distinguishing main character strings and auxiliary character strings in the recognized character strings by reference to a closed list of main character strings; an encoder for encoding the content of the given document by assigning one or more digits to each main character string and one or more digits to auxiliary character strings; and a matcher for matching a plurality of n-digit streams from within the encoded content with any corresponding n-digit streams within previously-encoded content of the one or more other documents. The character strings may be encoded as a bit-stream.

Abstract: Deep learning is used to identify specific, potential risks to an enterprise (of which litigation is the prime example) while such risks are still internal electronic communications. The system involves mining and using existing classifications of data (e.g., from a litigation database) to train one or more deep learning algorithms, and then examining the internal electronic communications with the trained algorithm, to generate a scored output that will enable enterprise personnel to be alerted to risks and take action in time to prevent the risks from resulting in harm to the enterprise or others.

Abstract: Deep learning is used to identify a potential risk that a contract will be unenforceable due to a drafting error whereby one or more terms or phrases are ambiguous. The system involves mining and using existing classifications of data (e.g., from a litigation database) to train one or more deep learning algorithms, and then examining the internal electronic drafts of contracts with the trained algorithm, to generate a scored output that will enable enterprise personnel to be alerted to the ambiguity risks and take action in time to prevent the risks from resulting in harm to the enterprise.

Abstract: In embodiments of the present invention improved capabilities are described for a computer program product embodied in a computer readable medium that, when executing on one or more computers, helps determine an unknown user's preferences through the use of internet based social interactive graphical representations on a computer facility by performing the steps of (1) ascertaining preferences of a plurality of users who are part of an internet based social interactive construct, wherein the plurality of users become a plurality of known users; (2) determining the internet based social interactive graphical representation for the plurality of known users; and (3) inferring the preferences of an unknown user present in the internet based social interactive graphical representation of the plurality of known users based on the interrelationships between the unknown user and the plurality of known users within the graphical representation.

Abstract: Deep learning is used to identify specific, potential risks of missed diagnosis for a patient and reporting the risk to healthcare provider. The system involves mining and using existing electronic health records for specific medical diagnosis to train one or more deep learning algorithms, and then examining the internal electronic health record of the patient with the trained algorithm, to generate a scored output that will enable a healthcare provider to be alerted to potential risks of a missed diagnosis.

Abstract: Deep learning is used to identify specific, potential financial advantage for an enterprise that are hidden in internal electronic documents. The system involves mining and using existing classifications of data (e.g., from previously sorted documents) to train one or more deep learning algorithms, and then examining internal electronic documents with the trained algorithm, to generate a scored output that will enable enterprise personnel to evaluate the identified documents for a potential financial advantage to the enterprise.

Abstract: Deep learning is used to identify specific, potential entertainment risks to an enterprise while such risks before the enterprise commits large sums of money to a project. The system involves mining and using existing classifications of data (e.g., from a database of previously successful book and film franchises) to train one or more deep learning algorithms, and then examining a proposed entertainment document with the trained algorithm, to generate a scored output that will enable enterprise personnel to be alerted to risks and take action in time to prevent the risks from resulting in harm to the enterprise.