Abstract: Systems and methods are described for a scalable approach to build a knowledge database of clinical trial data by extracting, aligning, and synthesizing information from a variety of sources including clinical trial registries, abstracts of papers, and full-text medical journal articles, as well as external gazetteers, dictionaries, and lexicons. For examples, a system may implement a flexible and repeatable workflow that extracts both structured and semi-structured elements from unstructured data such as journal articles using a ‘back off strategy’ in which specialized rules are used to extract structured, clinical trial design parameters as well as information retrieval techniques that exploit regularities in language used in the medical literature to discover semi-structured trial outcomes.

Abstract: Methods, systems, and computer program products for cognitive disambiguation of problem-solving tasks involving a power grid are provided herein. A computer-implemented method includes capturing user feedback pertaining to relevance of remote terminal unit measurements related to a grid event through user interface interactions carried out by the user, wherein the user interface is communicatively linked to at least one computing device; automatically inferring rules related to the grid event to curate remote terminal unit measurements across iterations of analysis by recognizing irrelevant data and/or distractions in a visual display associated with the user interface, wherein said automatically inferring comprises implementing machine learning via the at least one computing device based on the user feedback; and outputting candidate solutions to a problem-solving task involving the grid based on the inferred rules, wherein said outputting is carried out by the at least one computing device.

Abstract: Methods, systems, and computer program products for cognitive disambiguation of problem-solving tasks involving a power grid are provided herein. A computer-implemented method includes capturing user feedback pertaining to relevance of remote terminal unit measurements related to a grid event through user interface interactions carried out by the user, wherein the user interface is communicatively linked to at least one computing device; automatically inferring rules related to the grid event to curate remote terminal unit measurements across iterations of analysis by recognizing irrelevant data and/or distractions in a visual display associated with the user interface, wherein said automatically inferring comprises implementing machine learning via the at least one computing device based on the user feedback; and outputting candidate solutions to a problem-solving task involving the grid based on the inferred rules, wherein said outputting is carried out by the at least one computing device.

Abstract: Methods and arrangements for computing disruptive current in a transformer. Transformer current is measured, and disruptive current is predicted. Based on the active transformer current and predicted disruptive current, a predicted reactive power and predicted neutral current are determined. At least one corrective action, to be taken with respect to the transformer, is thereupon identified. Other variants and embodiments are broadly contemplated herein.

Abstract: A method of receiving a substorm activity data log from one or more remote sensors, where substorm activity is due to solar activity. The method also includes receiving a harmonic distortion data stream from one or more remote observatories monitoring disturbances on a power grid, where the distortion is due to geomagnetically induced currents. The method also includes applying a mathematical model to the harmonic distortion data stream to create a derived harmonic distortion data log, and comparing phase-to-phase similarity of the three phases from the derived harmonic distortion data log. The method also includes predicting future adverse events due to geomagnetically-induced currents on the power grid based at least in part on the comparison and the substorm activity data log, and creating a warning based on the prediction.

Abstract: A subset of mobile devices is selected from a set of mobile devices located in a local area. From a mobile device in the subset, a magnetic measurement value obtained by performing a magnetic measurement is received. The magnetic measurement value comprises a change in a magnetic property of an immediate surrounding ambient environment of the mobile device. When the magnetic measurement corresponds to a deviation in a network condition in a portion of a network, the portion being located in the local area, a conclusion is output that the deviation is caused by an electromagnetic disturbance (EMD), where an effect of the EMD causes the magnetic measurement value. A notification including an indication of the EMD and an identification of the local area is generated.

Abstract: Systems and methods for cognitive alarm management in a power grid are described. In one embodiment, sensor measurements are transformed to determine the state of a power grid. Given current state information relating to the power grid, various analyses of the alarms may be conducted to produce various rankings of the alarms (e.g., by severity, graph analyses, etc.). In an embodiment, using power flow analysis, an optimal ranking is identified from the rankings in which a causal alarm is prioritized for resolution. Given the resolution of the causal alarm, remaining alarms (either all or a sub-set) may be resolved without further action. Thus, an embodiment provides an appropriate ranking of alarm conditions in a power grid such that the optimal resolution of alarms may be achieved. Other variants and embodiments are broadly contemplated herein.

Abstract: A method of receiving a substorm activity data log from one or more remote sensors, where substorm activity is due to solar activity. The method also includes receiving a harmonic distortion data stream from one or more remote observatories monitoring disturbances on a power grid, where the distortion is due to geomagnetically induced currents. The method also includes applying a mathematical model to the harmonic distortion data stream to create a derived harmonic distortion data log, and comparing phase-to-phase similarity of the three phases from the derived harmonic distortion data log. The method also includes predicting future adverse events due to geomagnetically-induced currents on the power grid based at least in part on the comparison and the substorm activity data log, and creating a warning based on the prediction.

Abstract: A subset of mobile devices is selected from a set of mobile devices located in a local area. From a mobile device in the subset, a magnetic measurement value obtained by performing a magnetic measurement is received. The magnetic measurement value comprises a change in a magnetic property of an immediate surrounding ambient environment of the mobile device. When the magnetic measurement corresponds to a deviation in a network condition in a portion of a network, the portion being located in the local area, a conclusion is output that the deviation is caused by an electromagnetic disturbance (EMD), where an effect of the EMD causes the magnetic measurement value. A notification including an indication of the EMD and an identification of the local area is generated.

Abstract: A subset of mobile devices is selected from a set of mobile devices located in a local area. From a mobile device in the subset, a magnetic measurement value obtained by performing a magnetic measurement is received. The magnetic measurement value comprises a change in a magnetic property of an immediate surrounding ambient environment of the mobile device. When the magnetic measurement corresponds to a deviation in a network condition in a portion of a network, the portion being located in the local area, a conclusion is output that the deviation is caused by an electromagnetic disturbance (EMD), where an effect of the EMD causes the magnetic measurement value. A notification including an indication of the EMD and an identification of the local area is generated.

Abstract: A subset of mobile devices is selected from a set of mobile devices located in a local area. From a mobile device in the subset, a magnetic measurement value obtained by performing a magnetic measurement is received. The magnetic measurement value comprises a change in a magnetic property of an immediate surrounding ambient environment of the mobile device. When the magnetic measurement corresponds to a deviation in a network condition in a portion of a network, the portion being located in the local area, a conclusion is output that the deviation is caused by an electromagnetic disturbance (EMD), where an effect of the EMD causes the magnetic measurement value. A notification including an indication of the EMD and an identification of the local area is generated.

Abstract: Methods and arrangements for localizing an outage in a power grid. An outage is detected in a power grid, the power grid including interconnected nodes. At least one candidate network topology (in the power grid) with respect to the outage is determined, and power consumption information and measured voltages relative to the nodes in the power grid are received. Voltage at a plurality of the nodes in the power grid is estimated based on the received power consumption information and on the at least one candidate network topology, and a location of the outage is estimated, based on the estimated node voltages and measured voltages. Other variants and embodiments are broadly contemplated herein.

Abstract: Methods, systems, and computer program products for cognitive disambiguation of problem-solving tasks involving a power grid are provided herein. A computer-implemented method includes capturing user feedback pertaining to relevance of remote terminal unit measurements related to a grid event through user interface interactions carried out by the user, wherein the user interface is communicatively linked to at least one computing device; automatically inferring rules related to the grid event to curate remote terminal unit measurements across iterations of analysis by recognizing irrelevant data and/or distractions in a visual display associated with the user interface, wherein said automatically inferring comprises implementing machine learning via the at least one computing device based on the user feedback; and outputting candidate solutions to a problem-solving task involving the grid based on the inferred rules, wherein said outputting is carried out by the at least one computing device.

Abstract: Methods, systems, and computer program products for determining severity of a geomagnetic disturbance on a power grid using similarity measures are provided herein. A method includes extracting multiple features of activity associated with geomagnetically induced currents from multiple heterogeneous data streams; comparing the extracted features to historical data related to geomagnetically induced currents to determine a level of similarity between each of the extracted features and the historical data; assigning a level of severity to one or more of the extracted features having a level of similarity with the historical data above a given threshold; and generating a notification comprising (i) a prediction of activity associated with geomagnetically induced currents based on the extracted features having a level of similarity with the historical data above the given threshold, and (ii) the level of severity assigned thereto.

Abstract: Methods, systems, and computer program products for determining severity of a geomagnetic disturbance on a power grid using similarity measures are provided herein. A method includes extracting multiple features of activity associated with geomagnetically induced currents from multiple heterogeneous data streams; comparing the extracted features to historical data related to geomagnetically induced currents to determine a level of similarity between each of the extracted features and the historical data; assigning a level of severity to one or more of the extracted features having a level of similarity with the historical data above a given threshold; and generating a notification comprising (i) a prediction of activity associated with geomagnetically induced currents based on the extracted features having a level of similarity with the historical data above the given threshold, and (ii) the level of severity assigned thereto.

Abstract: Methods and arrangements for computing disruptive current in a transformer. Transformer current is measured, and disruptive current is predicted. Based on the active transformer current and predicted disruptive current, a predicted reactive power and predicted neutral current are determined. At least one corrective action, to be taken with respect to the transformer, is thereupon identified. Other variants and embodiments are broadly contemplated herein.

Abstract: Methods and arrangements for localizing an outage in a power grid. An outage is detected in a power grid, the power grid comprising interconnected nodes. At least one candidate network topology (in the power grid) with respect to the outage is determined, and power consumption information and measured voltages relative to the nodes in the power grid are received. Voltage at a plurality of the nodes in the power grid is estimated based on the received power consumption information and on the at least one candidate network topology, and a location of the outage is estimated, based on the estimated node voltages and measured voltages. Other variants and embodiments are broadly contemplated herein.

Abstract: Systems and methods for cognitive alarm management in a power grid are described. In one embodiment, sensor measurements are transformed to determine the state of a power grid. Given current state information relating to the power grid, various analyses of the alarms may be conducted to produce various rankings of the alarms (e.g., by severity, graph analyses, etc.). In an embodiment, using power flow analysis, an optimal ranking is identified from the rankings in which a causal alarm is prioritized for resolution. Given the resolution of the causal alarm, remaining alarms (either all or a sub-set) may be resolved without further action. Thus, an embodiment provides an appropriate ranking of alarm conditions in a power grid such that the optimal resolution of alarms may be achieved. Other variants and embodiments are broadly contemplated herein.

Abstract: A computer implemented method for retrieving video clips from a database is disclosed. The method may include retrieving in an initial query from a video collection based on a search term; receiving a user selection of at least one video clip from a first set of video clips corresponding to the search term; associating at least one visual attribute of the selected video clip with the search term; receiving the at least one search term from a user in a subsequent query; determining a set of physical concepts based on the at least one search term; mapping the set of physical concepts to a plurality of visual attributes; searching the database for at least one video clip corresponding to the plurality of visual attributes; identifying at least one video clip in the database having the plurality of visual attributes; and returning a second set of video clips having the set of visual attributes to the user, the second set including the at least one video clip.