Abstract: In some aspects, the described systems and methods provide for a method for training a statistical model to predict tissue characteristics for a pathology image. The method includes accessing annotated pathology images. Each of the images includes an annotation describing a tissue characteristic category for a portion of the image. A set of training patches and a corresponding set of annotations are defined using an annotated pathology image. Each of the training patches in the set includes values obtained from a respective subset of pixels in the annotated pathology image and is associated with a corresponding patch annotation determined based on an annotation associated with the respective subset of pixels. The statistical model is trained based on the set of training patches and the corresponding set of patch annotations. The trained statistical model is stored on at least one storage device.

Abstract: A method includes executing a calibration operation on a set of qubits, in a first iteration, to produce a set of parameters, a first subset of the set of parameters corresponding to a first qubit of the set of qubits, and a second subset of the set of parameters corresponding to a second qubit of the set of qubits. In an embodiment, the method includes selecting the first qubit, responsive to a parameter of the first subset meeting an acceptability criterion. In an embodiment, the method includes forming a quantum gate, responsive to a second parameter of the second subset failing to meet a second acceptability criterion, using the first qubit and a third qubit.

Abstract: A method at a computing device for classifying elements within an input, the method including breaking the input into a plurality of patches; for each patch: creating a vector output; applying a characterization map to select a classification bin from a plurality of classification bins; and utilizing the selected classification bin to classify the vector output to create a classified output; and compiling the classified output from each patch.

Abstract: A score explanation method for explaining a score includes at least steps of: a1) providing a first score associated with a first vector containing the first values of the parameters; b) generating a first set of lists, each list including a second number of indicators; c) generating, from a list, of at least a third vector wherein each parameter has a third value; the third value being equal to the corresponding first value when the list does not include an indicator of the corresponding parameter, and different from the corresponding first value otherwise; d) calculating the score of at least one third vector; e) evaluating, from the scores calculated for each of the third vectors, an indicator of significance of each parameter; f) elaborating, from the evaluated indicators of significance, an explanation of the first score.

Abstract: Disclosed is an electronic device. The electronic device according to an embodiment includes a memory and a processor electrically connected with the memory, wherein the processor is configured to obtain an identification of a portion of the media data and a sequence of heart rate (HR) data of a user of the electronic device while the portion of media data is output, and store, in the memory, the identification of the portion of the media data when the HR data sequence satisfies a specified condition.

Abstract: A method, system, and program product for selecting software is provided. The method includes retrieving audio data during a call with a subject matter expert (SME). The audio data is converted into a data training set and documents of the SME are converted into a document training set. Canonical documents generated by authors are analyzed and specified code is extracted from the text data training set and document training set. Attributes of individuals are detected. The attributes are compared with specified data and the canonical documents and it is determined that the individuals are requesting information associated with the text data. The information is provided to the individuals via the canonical documents or the documents of the SME and it is determined if a matched set of data exists between the attributes, the specified data, and the canonical documents. A digital action associated with results of the determination is executed.

Abstract: Mechanisms are provided that generate a knowledge data structure for a medical condition. The mechanisms parse a natural language positional statement data structure representing a natural language positional statement corresponding to a medical condition, where the natural language positional statement specifies guidance information and patient attributes indicative of patients for which an action may be performed for the medical condition. The mechanisms extract the patient attributes and a grading value associated with the natural language positional statement. The mechanisms generate at least one weight value associated with each of the patient attributes based on the grading value.

Abstract: Features are disclosed for sharing network connections among client devices. A client device may connect to an intermediary system and request content from content provider. The intermediary system may, in addition to opening a connection with the content provider and receiving the content on behalf of the client, create a request profile for the client device regarding likely future content requests. The request profile may be used to assign the client device to network comparing components that have available open network connections to one or more content providers from which the client device is likely to request content. In some cases, a gateway network computing component may route content requests to other network computing components which have available open network connections to content providers hosting requested content. Additionally, the number of active network computing components may be adjusted to increase connection sharing and reuse opportunities.

Abstract: According to a computer-implemented method, an available amount of each of multiple computing resources is determined by machine logic over a period of time at a computing device. The machine logic also determines an expected usage of each computing resource to execute each workflow in a queue. The machine logic also determines a time of execution of each workflow in the queue based on the available amount of each of the multiple computing resources over time and the expected usage of each computing resource to execute each workflow in the queue.

Abstract: A data management system enables users to contact support agents with questions about the data management system. For each support case, the support agents access one or more assistance documents to assist the users. The data management system tracks, for each support case, the assistance documents that were accessed in the support case. The data management system generates a matrix representing the support cases and the assistance documents accessed in the support cases. The data management system generates groups of similar support cases by performing clustering processes on the matrix.

Abstract: In implementations of higher-order graph clustering and embedding, a computing device receives a heterogeneous graph representing a network. The heterogeneous graph includes nodes that each represent a network entity and edges that each represent an association between two of the nodes in the heterogeneous graph. To preserve node-type and edge-type information, a typed graphlet is implemented to capture a connectivity pattern and the types of the nodes and edges. The computing device determines a frequency of the typed graphlet in the graph and derives a weighted typed graphlet matrix to sort graph nodes. Sorted nodes are subsequently analyzed to identify node clusters having a minimum typed graphlet conductance score. The computing device is further implemented to determine a higher-order network embedding for each of the nodes in the graph using the typed graphlet matrix, which can then be concatenated into a matrix representation of the network.

Abstract: A non-transitory computer-readable storage medium storing a program that causes a computer to execute a process, the process including receiving a search query, obtaining a first document containing a word included in the received search query from a storage device that stores a plurality of documents, extracting a plurality of words included in the first document, selecting one or more words from the plurality of extracted words, the one or more words having lower similarity to the word included in the received search query being specified in the specifying, obtaining a second document containing the selected one or more words, and outputting information corresponding to the second document.

Abstract: A computer-implemented method for providing contextual outputs based on varying coordinates related to a target event is provided. The method is implemented by a processor. The processor receives the target event based on a user input and the varying coordinates. The processor then executes a semantic analysis and relationships building operation on the varying coordinates and the target event to generate proposals and provides the contextual outputs based on the proposals. Note that the semantic analysis and relationships building operation reduces recommendation errors by and increases a computing efficiency of the processor with regard to providing the contextual outputs.

Abstract: A system, method, and computer program product are provided for generating intelligent automated adaptive decisions. In operation, a system receives a request to generate a prediction associated with a business problem for a customer. The system identifies a customer segment from a plurality of customer segments to which the new customer is most closely associated. Additionally, the system identifies a statistical model associated with the customer segment. Moreover, the system selects a best prediction from a competing set of machine learning models and the statistical model, utilizing a multi arm bandit arbitrator applying a multi arm bandit technique to solve the business problem.

Abstract: Automated fault correction in a network environment comprises identifying a pattern in a set of network events and generating a set of substantiating data for the identified patterns. The method can also identify an occurrence probability value for each network event and generate root cause data based on a ranking for the network events using a set of parameters including the occurrence probability. The method can also be directed to performing a regression of the root cause data against a set of historic data and selecting the root cause with a predefined accuracy as an acceptable candidate. The acceptable candidate is then provided for assisted learning for automated fault correction.

Abstract: A system is configured to receive first training data, train a first neural network (NN) based on the first training data, receive second training data, train a second NN based on the second training data, receive a first plain English phrase, provide the first plain English phrase to the first NN, generate, via the first NN, one or more first legal clauses based on the first plain English phrase, receive a second plain English phrase, provide the second plain English phrase to the first NN, generate, via the first NN, one or more second legal clauses based on the second plain English phrase, provide the one or more first legal clauses and the one or more second legal clauses to the second NN, and generate, via the second NN, a legal document based on the one or more first legal clauses and the one or more second legal clauses.

Abstract: Methods and apparatus to determine reach with time dependent weights are disclosed. An example method disclosed herein includes determining a first subset of panelists exposed to media at a first time; determining a second subset of the panelists exposed to the media at a second time; applying a first plurality of weights to the first subset of panelists to generate first weighted exposures; applying a second plurality of weights to the second subset of the panelists to generate second weighted exposures; for a first panelist in the first and second subsets, determining a first cumulative weighted exposure by determining which of the first and second weighted exposures is largest for each of the first panelist; for a second panelist in one of the first and second subsets, determining a second cumulative weighted exposure by based on the weight applied to the second panelist; and determining a reach of the media for the first and second times by combining the first and second cumulative weighted exposures.

Abstract: A platform for implementing a method of aggregating and contextualizing metrics relevant to developing, launching and marketing a target therapeutic or related therapy. The method of processing the metrics includes retrieving data related to the target from one or more data sources and synthesizing the retrieved target data in a contextual manner and creating synthesized target data by converting unstructured data into structured data including an event, wherein an event comprises a corpus of data from a single source on a single date. The synthesized target data is stored in a target specific database and a user may query the database regarding the target, where the query includes at least one search parameter. The user query is processed against the synthesized target data in the target specific database and the results are presented to the user.

Abstract: Aspects of the invention include detecting and predicting application performance. A non-limiting example computer-implemented method includes receiving source code and generating a first model of the source code by labeling a word of the source code. The computer implemented method optimizes the first model of the source code by assembling the first model of the source code with a plurality of models generated by a model generation module into a second model of the source code and extracts at least two basic features from the second model of the source code. The computer-implemented method provides an estimated performance of the source code based on historical data of the basic features extracted from the second model of the source code.

Abstract: Examples provide a metric definition component for creating and defining key performance indicators. A metric definition component connects to a set of data sources using database credentials to onboard the data tables. An extraction component automatically extracts data structures associated with the set of data sources. An analysis component analyzes the extracted set of data structures and a set of predefined performance metrics using a set of algorithms. The set of algorithms can include an entity classification algorithm, an entity search algorithm and/or an entity relational mapping algorithm. The metric definition component defines a set of KPIs based on the analysis of the extracted data. A visualization component generates a set of visualizations representing the set of KPIs.

Abstract: Quantum annealers as analog or quantum processors can find paths in problem graphs embedded in a hardware graph of the processor, for example finding valid paths, shortest paths or longest paths. A set of input, for example nucleic acid reads, can be used to set up a graph with edges between nodes denoting overlap (i.e., common base pairs) between the reads with constraints applied to perform sequence alignment or sequencing of a nucleic acid (e.g., DNA) strand or sequence, finding a solution that has a ground state energy. At least a portion of the described approaches can be applied to other problems, for instance resource allocations problems, e.g., job scheduling problems, traveling salesperson problems, and other NP-complete problems.

Abstract: A message sorting systems includes: an extraction block configured to extract some of a plurality of posted messages on the basis of a rule with respect to message posting person, reply destination, or contents; and a sorting block configured to sort the extracted messages through a machine-learning sorting device. A message sorting method includes: extracting some of a plurality of posted messages on the basis of a rule with respect to message posting person, reply destination, or contents; and sorting the extracted messages through a machine-learning sorting device.

Abstract: A content server generates media playlists for social events. The content server receives a seed value describing desired characteristics of media to present during a social event, and event parameters describing conditions for selecting media items to generate a media playlist for the social event. The content server selects media items based on the event parameters and the seed value, and uses the selected media items to generate the media playlist for the social event. The media items in the playlist are retrieved from a media database and provided to a media player for presentation at the social event.

Abstract: A method for evaluating a state of health (SOH) of an electric battery of an electric vehicle, said method comprising a step of: performing on said electric battery, under given conditions, a test, called proxy test, said proxy test including a partial charge and/or discharge action of the battery, comparing the results of the proxy test with data stored in a dataset, and estimating the SOH in function of the comparison result.

Abstract: A system configured to determine that a trigger condition has occurred that is related to an operation performed on a memory device of the system. Responsive to determining that the trigger condition has occurred, reordering error handling mechanisms of an error handling sequence based upon an error handling mechanism performance metric. Each error handling mechanism specifies operations to be performed to recover an error in the operation on the memory device.

Abstract: An embodiment of the present invention is directed to quantifying the value of an individual log source sent to the SIEM. Through vendor-agnostic measurement, an algorithmic model utilized by a Log Quality Value (LQV) index enables security engineers and incident response (IR) teams to determine which logs provide the most value for security investigations. An embodiment of the present invention recognizes a positive correlation between the LQV index and critical logs used to investigate the attack. An embodiment of the present invention may be extended to evaluate the LQV algorithms against a more extensive dataset from live production environments and to further measure the tool effectiveness through periodically comparing the LQV index to logs used to detect security incidents.

Abstract: A method, computer system, and a computer program product for determining the reliability of a claim is provided. The present invention may include receiving an input data from a user. The present invention may also include analyzing the claim associated with the received input data to determine a reliability score associated with the input data, wherein the claim is semantically similar to the received input data. The present invention may further include generating, from a prediction model, the reliability score for the claim associated with the received input data. The present invention may also include presenting the reliability score for the claim associated with the received input data to the user.

Abstract: Disclosed are a device and a method for restoring missing operational data. The method for restoring missing operational data includes determining whether missing data is present in a first event defining operational data or a first resource constituting the operational data, extracting candidate data from a missing table, depending on a form in which the first resource is defined by the first event and a location where the missing data is identified, and processing the candidate data to restore the missing data, based on a predetermined restoration scheme.

Abstract: A marketing analytics pipeline that receives transaction-level trend reporting of media IP assets distributed on digital service providers (DSPs), the marketing analytics pipeline including a marketing action analytics hub configured to receive the growth and re-engagement opportunities from an opportunity detection analytics hub or from a marketing platform directly and to identify high growth potential audiences using predictive models of engagement; and a marketing platform configured to interact with the marketing action analytics hub and to create marketing campaigns based around the high growth potential audiences and suggest marketing actions to media IP asset managers and owners to deliver to the high growth potential audiences on appropriate marketing channels via targeted marketing campaigns. The marketing action analytics hub uses a geodemographic and interest-based targeting method of generating descriptions of high growth potential audiences.

Abstract: A system for discovering semantic relationships in computer programs is disclosed. In particular, the system may synergistically identify and validate semantic relationships, concepts, and groupings associated with data elements within a static or dynamic, time varying, source input. The system may utilize feature extractors to extract features from the input and reasoners to develop associations using data from multiple feature set types, and, can thus generate reliable, robust, and complete sets of semantic relationships from the input. The system may generate hypotheses associated with the relationships, concepts, and groupings, and validate the hypotheses by testing an application under evaluation by the system and observing the outputs generated from the testing.

Abstract: Methods and systems for finding and ranking video sequences that contain tactical sequences (e.g., an uninterrupted portion of a sporting event) that are similar to tactical event content in a target video sequence, such as those occurring in sports, include learning and labelling (e.g., through use of metadata and the like) tactically significant sequences in a plurality of video segments, including a plurality of such tactically significant sequences in a single video segment.

Abstract: Techniques and mechanisms for automatically identifying counters/features of a network component that are related to a state change (or event) for the network component or for the network itself. For example, using data obtained from the network component around a time of the state change, delta averages for the features around the time of the state change may be determined. The delta averages may be utilized to determine which counters/features are most descriptive for a particular state change. The counter/features that are the most descriptive for a particular state change is as important as the change detection itself. This is especially true since in a case of an event/state change occurring, a large amount of counters/features may react to the state change or event. Thus, the techniques described herein provide for an approach to distill which counters/features contribute the most to a particular state change from a data driven perspective.

Abstract: A connection can be made to a processing element of a remotely deployed and live streaming application executed by a first data processing system, the processing element containing at least one operator that processes at least one tuple. As the live streaming application is executed, without slowing or modifying data flow of the live streaming application execution to client devices, a copy of the tuple and a memory dump of state data for a state of the operator can be received, and the tuple can be tracked through a call graph. The state data can be loaded into a local instance of the operator loaded into a debugger. At least a portion of the call graph can be presented to a user, and a flow of the tuple through the call graph based on the state data for the operator can be indicated.

Abstract: Techniques for data sharing between a data miner and a data provider are provided. A set of public parameters is downloaded from the data miner. The public parameters are data miner parameters associated with a feature set of training sample data. A set of private parameters in the data provider can be replaced with the set of public parameters. The private parameters are data provider parameters associated with the feature set of training sample data. The private parameters are updated to provide a set of update results. The private parameters are updated based on a model parameter update algorithm associated with the data provider. The update results is uploaded to the data miner.

Abstract: According to embodiments of the present invention, an entity may be represented by an unstructured feature vector comprising a plurality of features extracted from unstructured data using semantic analysis and a structural feature vector comprising a plurality of features from chemical structure data. A similarity matrix may be used to compare entities and generate a similarity score, based on both the unstructured feature vector and the structural feature vector for each entity. In some aspects, a user may enter a query (from which a chemical structural feature vector is dynamically generated) to compare against entities having unstructured and/or structural feature vectors, stored in a database.

Abstract: Methods and systems for enhanced natural language processing of clinical documentation are provided. Using natural language processing, a clinical condition is extracted from unstructured data within a current electronic document. A clinical ontology identifying itemsets associated with the clinical condition is retrieved, and indicators of relevant clinical concepts, as identified from the ontology, are searched from within the patient's longitudinal record, which comprises documentation from at least a prior encounter. Based on the whether the clinical concepts are present in the patent's record, a confidence is assigned to the NLP-extracted clinical condition, and one or more actions may be performed.

Abstract: A method of machine learning that teaches a computer to determine likelihood that a medical journal article is classified as high value for an intended system. In some embodiments, the method includes procuring, in a medical articles database on the computer, a training set including medical articles recommended by subject matter experts associated with medical journals that have published the medical articles. The method can also include identifying, by a feature extraction controller of the computer, first features in the medical articles via a remote annotation service and a remote article information service. The method can also include identifying, by intended system services electronically available to the intended system, second features in the medical articles. The method can also include reducing, by the feature extraction controller, the first and second features to form a set of relevant features.

Abstract: A computer-implemented method, system, and/or computer program product controls uploading applications to a mobile device. A server receives a power descriptor from a mobile device, where the power descriptor identifies an amount of power available to the mobile device from a battery on the mobile device. The server receives a set of application downloading rules for the mobile device, where the set of application downloading rules comprises a medium rule, and where the medium rule prioritizes downloading a second application over a first application in response to the amount of power available to the mobile device from the battery being below a predetermined value. The server receives a request to upload the first application and the second application to the mobile device and a rule selection message. The server uploads to the mobile device the first application after uploading the second application based on the selected medium rule.

Abstract: The invention relates to a method for real-time scheduling of multi-energy complementary micro-grids based on a Rollout algorithm, which is technically characterized by comprising the following steps of: Step 1, setting up a moving-horizon Markov decision process model for the real-time scheduling of the multi-energy complementary micro-grids with random new-energy outputs, and establishing constraint conditions for the real-time scheduling; Step 2, establishing a target function of the real-time scheduling; Step 3, dividing a single complete scheduling cycle into a plurality of scheduling intervals, and finding one basic feasible solution meeting the constraint conditions for the real-time scheduling based on a greedy algorithm; and Step 4, finding a solution to the moving-horizon Markov decision process model for the real-time scheduling of the multi-energy complementary micro-grids by using the Rollout algorithm based on the basic feasible solution from Step 3.

Abstract: Embodiments include a system for determining cardiovascular information for a patient. The system may include at least one computer system configured to receive patient-specific data regarding a geometry of the patient's heart, and create a three-dimensional model representing at least a portion of the patient's heart based on the patient-specific data. The at least one computer system may be further configured to create a physics-based model relating to a blood flow characteristic of the patient's heart and determine a fractional flow reserve within the patient's heart based on the three-dimensional model and the physics-based model.

Abstract: Approaches presented herein enable automated cognitive problem management in a systems environment. A first problem component is identified from a problem ticket. In response to the problem ticket, a logical relationship between the problem component and other related components is generated. While applying an automated fix to the problem component, its related components are measured for any deviation. If a deviation exists, a second problem component is identified and a causality relationship among the first and second components is established. An automated fix is applied to the second problem component and then to the first problem component based on the causality relationship. The causality relationship and order of applying the component fixes is stored for resolving future similar problem tickets.

Abstract: Systems and methods are provided to automatically respond to questions on websites. An electronic communication comprising words is received over a network. In some embodiments, the electronic communication could comprise a message posted by a user on a social networking website. The words of the electronic communication are matched to words in prior search queries, where the prior search queries are associated with online content. A reply is then returned in response to the electronic communication. The reply comprises a representation of the online content, for example, a URL linking to the online content.

Abstract: A method comprises receiving one or more plan parameters of a first radiation treatment plan for a first patient and one or more passing rate data for the first treatment plan; generating a predictive model for passing rate data from the plan parameters of the first radiation treatment plan and the passing rate data for the first treatment plan; receiving one or more plan parameters of a second radiation treatment plan for a second patient; and applying the predictive model to the plan parameters of the second radiation treatment to generate one or more predicted passing rate data for the plan parameters for the second patient.

Abstract: A selected document from corpus of a cognitive computing system is processed according to its association with a category of documents already contained within the corpus, such as a topical category. Then, the cognitive computing system is engaged automatically to query one or more questions previously-associated with the category to discover discrepancies between the selected document and the other corpus documents. If a discrepancy is found, a confidence factor based upon extracted natural language entities and relationships is assigned to the discrepancy, and it is flagged and reported to a user for reconciliation.

Abstract: Embodiments are directed to managing data correlation over a network. Role success models that correspond to roles and to success criteria may be provided. A student profile that includes skill vectors may be provided based on student information. Role success models may be employed to determine intermediate scores based on the skill vectors and the success criteria. A predictive score for the student that corresponds with a predicted performance of the student in the roles may be generated based on the one or more intermediate scores. Actions for the student may be determined based on a mismatch of the skill vectors and role skill vectors that correspond to the roles. In response to the student performing the actions: updating the one or more skill vectors based on a completion of the actions; and updating the predictive score based on the role success models and the updated skill vectors.

Abstract: A system and computer-implemented method is provided for a neural network for the optimal display of hotels on a graphical user interface. Computation is undertaken on a dataset wherein combinatorial complexity is reduced by obtaining a metric that can be a subset of a larger universe of user displays. A desired result set is obtained that can improve traveller satisfaction, travel agent revenues, and overall utility. This is accomplished by computing a first combination of displays, weighted as appropriate, and obtaining the results of an expression defined by factoring in a probability to sell a hotel based on a selected display on a user interface.

Abstract: The present invention provides a method for identifying trends and correlation of content items characteristics in relation to user emotional reaction. The method comprising the steps of: receiving plurality of rating/votes originated by different users relating one or more content item, wherein the user is required to selection emotion icon from multiple choice emotion icons, analyzing statistics of users selections by identifying characteristics of the news/article item, including at least one of; timing of news item publication, subject of content item, source/writer of the content, context of the content, style of content, key words/image appearing in the content and identifying correlations of content item characteristics in relation user emotion reaction according to the said analysis identifying trends.

Abstract: A disclosed method may include receiving geographic coordinates of a location at which two parties are to rendezvous, generating a human-understandable geospatial descriptor for the request location, and sending the descriptor to respective devices of the two parties for presentation to the two parties. Generating the human-understandable geospatial descriptor may include identifying a human-visible feature in the vicinity of the request location that is labeled within available map data, selecting, based on a descriptor generation model, a reference expression relative to the identified feature, and applying a grammar-based constructor to the label and the selected reference expression to form the human-understandable geospatial descriptor. The model may be tuned using machine learning. The two parties may include a ride requestor and a ride provider in a ridesharing service. The identified feature may be a point of interest, landmark, street name, intersection, marker, or structure.

Abstract: A display method is provided. The method includes: acquiring media data within a collection range of a first acquisition device; determining a target object associated with the media data; determining associated data corresponding to the target object; and outputting the associated data corresponding to the target object to a user.

Abstract: Techniques for using different data sources for a predictive model are described. According to various implementations, techniques described herein enable different data sets to be used to generate a predictive model, while minimizing the risk that individual data points of the data sets will be exposed by the predictive model. This aids in protecting individual privacy (e.g., protecting personally identifying information for individuals), while enabling robust predictive models to be generated using data sets from a variety of different sources.