Abstract: A system is disclosed in which a plurality of in-vitro diagnostic (IVD) devices each include a network communication device for connecting to a publicly accessible data network. For example, IVD devices are provided with a cellular modem for connecting to a public cellular network. These IVD devices connect to the data network upon completion of a diagnostic test, and upload results of the test, as well as other appropriate data, to a remote device which is also on the network. The IVD devices also download appropriate data from remote network elements. The remote network element may be a network element such as a Hospital Information System (HIS) or Laboratory Information System (LIS) database. Alternatively, the remote device may be a remote server or another IVD device. This connectivity enables the system to accumulate diagnostic test data, and to analyze, report, and/or update the IVD devices based on the accumulated data.

Abstract: A system and a computer-implemented method of evaluating a formation. The system includes a plurality of acoustic transmitters and acoustic receivers and a processor. Acoustic data is obtained from the formation using the plurality of acoustic transmitters and acoustic receivers. The acoustic data is projected into a plurality of image planes and a feature in one of the image planes is selected. The plurality image planes are scrolled through in order to determine the three-dimensional structure of the feature. The formation is drilled based on the three-dimensional structure of the feature.

Abstract: A diagnostic system may utilize telemetry from a monitored system to infer information about the operation of various components systems within the monitored system. In embodiments, inferences may be drawn from a comparison of various component systems using a system of implication and exoneration. Exoneration is utilized to isolate faulty components from functioning components by comparing information between the systems, which may run in parallel. A dynamic grouping algorithm may eventually isolate faulty components and suggest the root cause as well as multiple distinct faults.

Abstract: The present disclosure describes methods and systems for interpreting geological features in a seismic volume based on mono-frequency filtering of the seismic volume. One computer-implemented method includes receiving a seismic data volume, decomposing the seismic data volume into multiple sub-volumes, generating one or more seismic horizons on each sub-volume, analyzing the generated seismic horizons for the multiple sub-volumes including determining a first sub-volume and a second sub-volume from the multiple sub-volumes, and subtracting the generated one or more seismic horizons for the first sub-volume from the generated one or more seismic horizons for the second sub-volume.

Abstract: An interactive media system enables creation, editing, and presentation of voice-driven interactive media content. The interactive media content may include prompts for user input via voice, manual input, or gestures. In the case of an audio input, the interactive media player application obtains a text string representing the spoken phrases and matches the text string against a set of expected values corresponding to different predefined responses and each associated with a different possible action. Based on the matching of the phrase to an expected value, the interactive media player application dynamically selects and performs the action associated with the matching response. The action may comprise, for example, transitioning to playback of a different media object (e.g., a second video segment) and/or causing some other functionality programmatically accessible by the interactive media player application to occur.

Abstract: A method, computing system, and non-transitory computer-readable medium, of which the method includes receiving offset well data collected while drilling one or more offset wells, generating a machine learning model configured to predict drilling risks from drilling measurements or inferences, based on the offset well data, receiving drilling parameters for a new well, determining that the drilling parameters are within an engineering design window, generating a drilling risk profile for the new well using the machine learning model, and adjusting one or more of the drilling parameters for the new well, after determining the drilling parameters are within the engineering design window, and after determining the drilling risk profile, based on the drilling risk profile.

Abstract: The present technology relates to an information processing device, an information processing method, and an information processing system that are capable of establish smooth and natural conversation with a person who has difficulty in hearing. The information processing device includes a sound acquisition unit that acquires sound information of a first user that is input to a sound input device and a display control unit that controls display of text information on a display device for a second user, the text information corresponding to the acquired sound information. The display control unit performs control related to display amount of the text information on the display device on the basis of at least one of the display amount of the text information on the display device or input amount of the sound information input through the sound input device.

Abstract: A method for filtering a sound signal acquired by a voice recognition system is proposed wherein the filter used to delete the unwanted sound signal is based on a noise model created from a history of preceding acquisitions of the sound signal. The method is based on the history for predicting the characteristics of the signal in the course of acquisition and relies on this prediction to establish the noise model used by the filtering function.

Abstract: A method and a data processing device are disclosed for at least partially automatically transferring a word sequence composed in a source language into a word sequence in a target language with corresponding substantive content. By analyzing the word sequence and identifying terms with lexical ambiguity in the word sequence by comparing with a terminology database comprising terms with lexical ambiguity in the source language which are assigned a plurality of term identifiers depending on their number of meanings, an unambiguous term definition is provided for translating the word sequence into the target language by assigning a term identifier to the term with lexical ambiguity in the source language. This may render a machine translation less susceptible to errors.

Abstract: A system processes audio data to detect when it includes a representation of a wakeword or of an acoustic event. The system may receive or determine acoustic features for the audio data, such as log-filterbank energy (LFBE). The acoustic features may be used by a first, wakeword-detection model to detect the wakeword; the output of this model may be further processed using a softmax function, to smooth it, and to detect spikes. The same acoustic features may be also be used by a second, acoustic-event-detection model to detect the acoustic event; the output of this model may be further processed using a sigmoid function and a classifier. Another model may be used to extract additional features from the LFBE data; these additional features may be used by the other models.

Abstract: A computer-implemented method predicting a life span of a battery storage unit by employing a deep neural network is presented. The method includes collecting energy consumption data from one or more electricity meters installed in a structure, analyzing, via a data processing component, the energy consumption data, removing one or more features extracted from the energy consumption data via a feature engineering component, partitioning the energy consumption data via a data partitioning component, and predicting battery capacity of the battery storage unit via a neural network component sequentially executing three machine learning techniques.

Abstract: A method of generating a weather forecast. The method is executable by a server, the server including a processor, the processor configured to execute a Machine Learning Algorithm (MLA). The method comprises: receiving, by the MLA at the given period of time, satellite data for a given geographical region; based on the satellite data, generating by the MLA, a 3D precipitation map for the given geographical region, based on the 3D precipitation map, generating by the MLA the weather forecast for the given period of time for the given geographical region. The MLA is trained based on a prediction of another MLA (based on meteo radar data) and satellite data.

Abstract: Embodiments of the present disclosure set forth a computer-implemented technique for providing a personalized audio signal to a user. The technique includes determining a first mood of the user based on a first set of user parameters, selecting, based on the first mood of the user, a first acoustic profile. The first acoustic profile may include a first set of acoustic parameters, and causing an audio output device to reproduce a first input audio signal based on the first set of acoustic parameters.

Abstract: A natural language processing system for analyzing speech includes a computer processing device configured to receive recorded speech of a person. The computer processing device constructs a baseline speech model of the person, the baseline speech model of the person including a property of speech based on a personal attribute of the person, compares current recorded speech of the person to the baseline speech model of the person to determine a deviation of the property of speech therebetween, and determines if the deviation of the property of speech meets a threshold of the property of speech that is defined for a disorder.

Abstract: In one example, this disclosure describes a method including receiving, at a central controller of an air mattress system, a plurality of air pressure value, determining a plurality of average values using the plurality of the received air pressure values, calculating a difference value between a first one of the plurality of average values and a second one of the plurality of average values, comparing the difference value to a threshold value, determining, based on the comparison, whether a user of the air mattress system moved.

Abstract: A mathematical model of load flow equations for an electrical grid having a chain of busses is embedded in a holomorphic embedding using a first embedding parameter s. The holomorphic embedding is transcribed into software for use in a computer processor. Voltages for each bus are calculated as an algebraic curve parameterized by the first embedding parameter. A second embedding parameter z is defined wherein the first embedding parameter s is a function of the second embedding parameter z. The holomorphic embedding is re-parameterized using the second embedding parameter z, such that the re-parameterized embedding provides an elimination polynomial equation relating parameters s and z. The roots of the elimination polynomial equation are determined by solving the for zero, which roots are used to compute bus voltages for each bus of the chain of busses. The bus voltages are displayed as the solution to the load flow equations.

Abstract: This disclosure relates to attention shifting of a robot in a group conversation with two or more attendees, wherein at least one of them is a speaker. State of the art has dealt with several aspects of Human-Robot Interaction (HRI) including responding to a source of sound at a time, addressing a fixed viewing area or determining who is the speaker based on eye gaze direction. However, attention shifting to make the conversation human-like is a challenge. The present disclosure uses audio-visual perception for speaker localization. Only qualified direction of arrivals (DOAs) are used for the audio perception. Further the audio perception is complimented by visual perception employing real time face detection and lip movement detection. Use of HRI rules, clustering of the DOAs, dynamic adjustment of rotation of the robot and a dynamically updated knowledge repository enriches the robot with intelligence to shift attention with minimum human intervention.

Abstract: A method for performing a Bode measurement on a device under test having a specified working input range and a specified working output range using a measurement system comprising: receiving at least one input boundary parameter of the working input range and at least one output boundary parameter of the output working range; generating a first stimulus signal using a stimulus signal generator of the measurement system based on the at least one input boundary parameter; feeding the first stimulus signal to an input of the device under test; and measuring an output signal of the device under test using a measurement unit of the measurement system in a measurement range based on the at least one output boundary parameter obtaining a measurement result. Further, a measurement setup is shown.

Abstract: An inspection specifying unit specifies a member position that is a point and a type of damage that is a soundness determination target on the basis of building structure information. An inspection data analysis unit acquires the image data from an inspection data acquisition unit, analyzes the image data, and determines from the image data, whether or not there is damage of the type of damage specified as the inspection target, and the degree of damage in a case where there is the damage. A damage influence degree calculation unit calculates the degree of damage influence for each damage. A soundness determination unit determines the soundness of the entire building on the basis of the degree of damage influence for each damage. A soundness output unit outputs the soundness determined in to a display, a printer, or the like.

Abstract: Aspects of the present disclosure relate to identifying spans within unstructured electronic text. Natural language content is received. A part of speech and slot name of each word within the natural language content is identified. A parse tree representation is then generated based on the natural language content, wherein visual characteristics of each node of a plurality of nodes within the parse tree representation depend on the part of speech and slot name of each word. A bounding box identifying a span category is then generated around a set of nodes on the parse tree representation by a machine learning model.