Abstract: A system for quantifying viewer engagement with a video playing on a display includes at least one camera to acquire image data of a viewing area in front of the display. A microphone acquires audio data emitted by a speaker coupled to the display. The system also includes a memory to store processor-executable instructions and a processor. Upon execution of the processor-executable instructions, the processor receives the image data and the audio data and determines an identity of the video displayed on the display based on the audio data. The processor also estimates a first number of people present in the viewing area and a second number of people engaged with the video. The processor further quantifies the viewer engagement of the video based on the first number of people and the second number of people.

Abstract: A system for forecasting leaks in a fluid-delivery pipeline network. The system identifies a subsystem in the pipeline network that comprises a plurality of topologically connected stations. The system accesses historical temporal sensor measurements of a plurality of variables of the stations that are directly connected and generates a temporal causal dependency model for a first control variable at the first station in the subsystem, based on the plurality of time series of sensor measurements of a second variable of the first station, and temporal delay characteristics of the plurality of time series of sensor measurements of the second variable at the stations directly connected to the first station. The system automatically calculates a normal operating value of the first control variable at the first station and the deviations between actual measured values and the normal operating value and determines a threshold deviation that indicates a leak event.

Abstract: A method, system, and computer program product for resource management are described. The method includes selecting trouble regions within the service area, generating clustered regions, and training a trouble forecast model for the trouble regions for each type of damage, the training for each trouble region using training data from every trouble region within the clustered region associated with the trouble region. The method also includes applying the trouble forecast model for each trouble region within the service area for each type of damage, determining a trouble forecast for the service area for each type of damage based on the trouble forecast for each of the trouble regions within the service area, and determining a job forecast for the service area based on the trouble forecast for the service area, wherein the managing resources is based on the job forecast for the service area.

Abstract: Systems and techniques for measuring process characteristics including electrolyte distribution in a battery cell. A non-destructive method for analyzing a battery cell includes determining acoustic features at two or more locations of the battery cell, the acoustic features based on one or more of acoustic signals travelling through at least one or more portions of the battery cell during one or more points in time or responses to the acoustic signals obtained during one or more points in time, wherein the one or more points in time correspond to one or more stages of electrolyte distribution in the battery cell. One or more characteristics of the battery cell are determined based on the acoustic features at the two or more locations of the battery cell.

Abstract: Provided is a process, including: obtaining geographic regions and geolocations that are places of interest within those geographic regions; obtaining first data about at least some of the plurality of geolocations, wherein the first data is not pathogen specific; obtaining second data about at least some of the plurality of geolocations, wherein the second data is pathogen-specific; determining geolocation-pathogen-risk scores of the geographic regions based on both the first data and the second data; determining geolocation-pathogen-risk scores of the places of interest with a machine learning model trained to allocate risk of geographic regions to places of interest based on at least some of the first data.

Abstract: Mapping anonymous Internet entities to known accounts. In an embodiment, events, representing online activity and comprising IP addresses, are received from a plurality of sources. Subsets of the events are aggregated into mappings that associate the IP address, shared by the subset, with an account. Each mapping is associated with statistics regarding the events. A confidence value is calculated for each mapping based on the statistics, and a final subset of the mappings is selected based on the confidence values. Subsequently, when a request with an IP address is received, the final subset of mappings is searched for the requested IP address, and an indication of the account associated with the requested IP address is returned in response to the request.

Abstract: Disclosed herein is a method for making hydrogen with carbon sequestration. The method may comprise using a biomass hydroconverter product to fuel a steam reformer that converts a hydrocarbon fuel stream into a gas mixture that contains at least hydrogen and carbon dioxide. The gas stream is separated to form a hydrogen-enriched gas stream and at least one hydrogen-depleted stream. The hydrogen-depleted stream may be stored or further processed to sequester the carbon contained therein. Additionally, or alternatively, the solid residue from the biomass hydroconverter also may be stored for further sequester carbon generated by the method.

Abstract: A system and method of managing a network that includes assets are described. The method includes modeling the network as a directed graph with each of the assets represented as a node and determining alternative paths to each node from each available corresponding source of the node. The method also includes computing upstream robustness of each node, computing upstream robustness of the network, and computing downstream criticality of each node. Managing the network and each asset of the network is based on the upstream robustness and the downstream criticality of each node.

Abstract: A large-scale radio frequency signal collection and processing system comprising a plurality of sensor systems mounted on a plurality of collection platforms that integrates a plurality of overlapping datasets with differing characteristics (e.g., different resolutions, different view angles, different heights, different time periods, unrelated types of data) to generate an enriched dataset or datasets using a variety of processing techniques (e.g., statistical analysis, signal processing, image processing) that allows for more comprehensive analysis of the radio frequency signal landscape than would be possible using any of the datasets individually, or in combination but without such integration.

Abstract: A large-scale radio frequency signal information processing and analysis system that provides advanced signal analysis for telecommunication applications, including band capacity and geographical density determinations and detection, classification, identification, and geolocation of signals across a wide range of frequencies and across broad geographical areas. The system may utilize a range of novel algorithms for bin-wise processing, Rayleigh distribution analysis, telecommunication signal classification, receiver anomaly detection, transmitter density estimation, transmitter detection and location, geolocation analysis, telecommunication activity estimation, telecommunication utilization estimation, frequency utilization estimation, and data interpolation.

Abstract: A medical imaging system for detecting ionizing radiation. The system includes one or more pixilated imagers positioned to acquire patient image data and one or more position sensors positioned to acquire patient position data. Once the patient image data and patient position data are acquired, one or more processors operably connected to each of the one or more pixilated imagers and one or more position sensors calculate a three-dimensional mass distribution based on patient image data and patient position data.

Abstract: Methods, systems, and computer program products for dynamic pricing of energy consumed from a shared battery using real-time consumption data are provided herein. A computer-implemented method includes calculating wear cost arising from a battery shared by multiple users, wherein the wear cost is based on usage data of the battery; calculating a proportionality factor for each of the multiple users for the calculated wear cost, wherein the proportionality factor is based on individual usage of the battery; apportioning the calculated wear cost to each of the multiple users based on the user's proportionality factor; and determining a dynamic price for energy used by the battery for each of the multiple users, based on said apportioning.

Abstract: A system accesses a plurality of ratio values for similar AOIs, each ratio value indicating a ratio between a count of device users at a similar AOI and a count of vehicles of the similar AOI. The similar AOIs are AOIs that have measurable characteristics within a range of similarity with those of the target AOI. The count of vehicles of the similar AOI is generated using aerial imagery received for the similar AOI. The count of device users at the similar AOI is extracted from third party data for the similar AOI. The system accesses a count of a number of reported device users at the target AOI, and generates an estimate of the vehicle count for the target AOI using the count of the number of reported device users at the target AOI and a combination of the plurality of ratio values for similar AOIs.

Abstract: A large-scale radio frequency signal information processing and analysis system that provides advanced signal analysis for telecommunication applications, including band capacity and geographical density determinations and detection, classification, identification, and geolocation of signals across a wide range of frequencies and across broad geographical areas. The system may utilize a range of novel algorithms for bin-wise processing, Rayleigh distribution analysis, telecommunication signal classification, receiver anomaly detection, transmitter density estimation, transmitter detection and location, geolocation analysis, telecommunication activity estimation, telecommunication utilization estimation, frequency utilization estimation, and data interpolation.

Abstract: A method for operating a power generating facility connected to a power distribution grid having an uncertain power generation condition includes predicting a probabilistic power flow forecast in a transmission line of the power distribution grid for a period of time, wherein the transmission line is electrically coupled to the power generating facility, predicting, using the probabilistic power flow forecast, a probability of congestion over the transmission line of the power distribution grid during the period of time, generating a mitigation plan, including a load adjustment on the transmission line, using the probability of congestion predicted over the transmission line and a thermal limit constraint of the transmission line, wherein the mitigation plan balances load adjustment and an overlimit line capacity on the transmission line, and controlling the power generating facility, using the mitigation plan, to achieve load modification and mitigate the probability of congestion predicted in the transmissi

Abstract: A system and method are disclosed for receiving a request to track data of an area of interest (AOI). The system receives a plurality of geolocation data records corresponding to a plurality of mobile devices. The system determines which mobile devices of the plurality of mobile devices have visited the AOI. For each mobile device determined to have visited the AOI, the system determines a path of the mobile device. The path including a prior location of the mobile device and a next location of the mobile device. The system transmits for display by a client device, a report including the path for each mobile device determined to have visited the AOI. The path indicating an identification of additional AOIs based on the prior location and the next location.

Abstract: A method comprises receiving an area of interest (AOI) selection. The method further comprises accessing an AOI device location data for the AOI, the AOI device location data indicating locations of devices over time received within the AOI. The AOI device location data is filtered to only include the device location data that match one or more characteristics. A proximity zone is determined for the for the AOI that includes the area of the AOI. A zone device location data for the proximity zone is determined, which indicates locations of devices over time reported within the proximity zone. The method further comprises normalizing the filtered AOI device location data by computing a ratio of the filtered AOI device location data and the zone device location data to generate an AOI user estimate, and transmitting the AOI user estimate to a client device of a requestor.

Abstract: An example method comprises receiving historical wind turbine failure data and asset data from SCADA systems, receiving first historical sensor data, determining healthy assets of the renewable energy assets by comparing signals to known healthy operating signals, training at least one machine learning model to indicate assets that may potentially fail and to a second set of assets that are operating within a healthy threshold, receiving first current sensor data of a second time period, applying a machine learning model to the current sensor data to generate a first failure prediction a failure and generate a list of assets that are operating within a healthy threshold, comparing the first failure prediction to a trigger criteria, generating and transmitting a first alert if comparing the first failure prediction to the trigger criteria indicates a failure prediction, and updating a list of assets to perform surveillance if within a healthy threshold.

Abstract: An example method comprises receiving historical sensor data of a renewable energy asset for a first time period, identifying historical log data in one or more log sources, retrieving dates of the identified historical log data, retrieving sequences of historical sensor data using the dates, training hidden Markov models using the sequences of historical sensor data to identify probability of shifting states of one or more components of the renewable energy asset, receiving current sensor data of a second time period, identifying current log data in the one or more log sources, retrieving dates of the identified current log data, retrieving sequences of current sensor data using the dates, applying the hidden Markov models to the sequences of the current sensor data to assess likelihood of the one or more faults, creating a prediction of a future fault, and generating a report including the prediction of the future fault.