Abstract: Systems and methods for authenticating material samples are provided. Digital images of the samples are processed to extract computer-vision features, which are used to train a classification algorithm along with location and optional time information. The extracted features/information of a test sample are evaluated by the trained classification algorithm to identify the test sample. The results of the evaluation are used to track and locate counterfeits or authentic products.

Abstract: Systems and methods for detecting/identifying novel material samples are provided. A test sample image is processed with a trained transformation function to obtain a transformed matrix. A measure of similarity of the test image based on the transformed matrix is compared to a threshold to determine whether the test sample is novel to a batch of material samples that are provided to train the transformation function.

Abstract: The disclosure describes techniques for detecting a crack or defect in a material. The technique may include applying an electrical signal to a first electrode pair electrically coupled to the material. The technique also may include, while applying the electrical signal to the first electrode pair, determining a measured voltage between a second, different electrode pair. At least one electrode of the second, different electrode pair is electrically coupled to the material. The technique may further include determining a corrected measured voltage by suppressing a thermally induced voltage from the measured voltage and determining whether the material includes a crack or other defect based on the corrected measured voltage.

Abstract: A technique may include applying a first electrical signal to a first pair of drive electrodes, and, while applying the first electrical signal to the first pair of drive electrodes, determining a first measured voltage using a first measurement electrode. The technique further may include applying a second electrical signal to a second pair of drive electrodes, and, while applying the second electrical signal to the second pair of drive electrodes, determining a second measured voltage using a second, different measurement electrode. The first pair of drive electrodes, the second pair of drive electrodes, the first measurement electrode, and the second, different measurement electrode may from a set of N electrodes electrically coupled to the material. The technique also may include determining whether the material includes a crack or other defect based on a comparison between the first measured voltage and the second measured voltage.

Abstract: Systems and methods for authenticating material samples are provided. Digital images of the samples are processed to extract computer-vision features, which are used to train a classification algorithm. The computer-vision features of a test sample are evaluated by the trained classification algorithm to identify the test sample.

Abstract: A method and system for monitoring impairment indicators. The method comprises, during a first time window, measuring a first movement signal related to movement of a person with a movement sensor associated with the person, and measuring a first environmental signal with an environmental sensor. The method further comprises electronically storing at least one numerical descriptor derived from the first movement signal and the first environmental signal as reference data for the person. The method further includes, during a second time window, measuring a second movement signal related to movement of the person with the movement sensor and measuring a second environmental signal with the environmental sensor; and comparing at least one numerical descriptor derived from the second movement signal and the second environmental signal to the reference data to identify an impairment indicator.

Abstract: Systems and methods are provided for optimally determining sensor or infrastructure placement in a fluid network, for determining an anomaly of interest in the fluid network, and for determining sensor coverage in a fluid network, which are based on a model of the fluid network represented by a directed graph.

Abstract: Systems and methods are provided for optimally determining sensor or infrastructure placement in a fluid network, for determining an anomaly of interest in the fluid network, and for determining sensor coverage in a fluid network, which are based on a model of the fluid network represented by a directed graph.

Abstract: Systems and methods for detecting a crack or defect in a material are described. An example method may include determining, by a computing device, for each respective adjacent pair of electrodes of a plurality of electrodes electrically coupled to the material, a respective electrode pair voltage. The method also may include determining, by the computing device, for each respective adjacent pair of electrodes, a respective temperature-corrected electrode pair value based on the respective electrode pair voltage and at least one of a respective control voltage associated with the respective adjacent pair of electrodes or a temperature correction factor. The method may further include determining, by the computing device, whether the material includes a crack or defect based on the plurality of respective temperature-corrected electrode pair values.

Abstract: Systems and methods for detecting/identifying novel material samples are provided. A test sample image is processed with a trained transformation function to obtain a transformed matrix. A measure of similarity of the test image based on the transformed matrix is compared to a threshold to determine whether the test sample is novel to a batch of material samples that are provided to train the transformation function.

Abstract: A measurement system may include an electrical signal source; a plurality of electrical contacts electrically coupled to a tested material; a respective resistor associated with each electrical contact; a common node to which the respective resistors are electrically connected; and a control module. The control module may cause the electrical signal source to be electrically connected to a selected electrical contact as an input electrical contact. The remaining electrical contacts are electrically connected to a return node of the electrical signal source as extraction electrical contacts. The control module also may cause the electrical signal source to output an electrical signal to an input electrical contact; cause a respective electrical signal parameter to be determined at the respective resistor associated with each respective extraction electrical contact; and determine whether the tested material includes a crack or other defect based on the respective electrical signal parameters.

Abstract: The present subject matter enables early or real-time detection of anomalies in electric networks. In various applications, the system detects anomalies, such as electricity theft, electricity surge, etc. It solves the difficult-to-detect problems in an electrical network, where anomalies like electricity theft or electrical surge may not be found until it has raised numerous concerns or complaints, or has created a significant impact on infrastructure functionality, service quality, or cost. In addition, the present subject matter decreases the requirement for large number of sensors and provides more cost effective and scalable solutions. The present subject matter provides a method for determining where a detected anomaly is occurring within an electrical network. Variations of the present subject matter include anomaly identification systems for addressing anomalies in large networks.

Abstract: The disclosure describes techniques for detecting a crack or defect in a material. The technique may include applying an electrical signal to a first electrode pair electrically coupled to the material. The technique also may include, while applying the electrical signal to the first electrode pair, determining a measured voltage between a second, different electrode pair. At least one electrode of the second, different electrode pair is electrically coupled to the material. The technique may further include determining a corrected measured voltage by suppressing a thermally induced voltage from the measured voltage and determining whether the material includes a crack or other defect based on the corrected measured voltage.

Abstract: The disclosure describes techniques for detecting a crack or defect in a material. The technique may include applying an electrical signal to a first electrode pair electrically coupled to the material. The technique also may include, while applying the electrical signal to the first electrode pair, determining a measured voltage between a second, different electrode pair. At least one electrode of the second, different electrode pair is electrically coupled to the material. The technique may further include determining a corrected measured voltage by suppressing a thermally induced voltage from the measured voltage and determining whether the material includes a crack or other defect based on the corrected measured voltage.

Abstract: A technique may include applying a first electrical signal to a first pair of drive electrodes, and, while applying the first electrical signal to the first pair of drive electrodes, determining a first measured voltage using a first measurement electrode. The technique further may include applying a second electrical signal to a second pair of drive electrodes, and, while applying the second electrical signal to the second pair of drive electrodes, determining a second measured voltage using a second, different measurement electrode. The first pair of drive electrodes, the second pair of drive electrodes, the first measurement electrode, and the second, different measurement electrode may from a set of N electrodes electrically coupled to the material. The technique also may include determining whether the material includes a crack or other defect based on a comparison between the first measured voltage and the second measured voltage.

Abstract: Systems and methods are provided for determining sensor or infrastructure placement in a fluid network, for determining an anomaly of interest in the fluid network, and for optimally determining sensor coverage in a fluid network, which are based on a model of the fluid network represented by a directed graph.

Abstract: A technique may include applying a first electrical signal to a first pair of drive electrodes, and, while applying the first electrical signal to the first pair of drive electrodes, determining a first measured voltage using a first measurement electrode. The technique further may include applying a second electrical signal to a second pair of drive electrodes, and, while applying the second electrical signal to the second pair of drive electrodes, determining a second measured voltage using a second, different measurement electrode. The first pair of drive electrodes, the second pair of drive electrodes, the first measurement electrode, and the second, different measurement electrode may from a set of N electrodes electrically coupled to the material. The technique also may include determining whether the material includes a crack or other defect based on a comparison between the first measured voltage and the second measured voltage.

Abstract: A device for recognizing activity of an object. The device comprises a housing configured to be attached to the object and a processing unit disposed in the housing comprising a processor and a movement sensor. The movement sensor measures a signal related to movement of the object during a time window. The processor assigns at least one preliminary activity label to the time window based on at least one numerical descriptor computed from the signal. The processor then determines whether to perform additional analysis dependent upon at least the preliminary activity label. The processor then assigns a final activity label to the time window.

Abstract: A device for recognizing activity of an object. The device has a housing configured to be attached to the object and a processing unit disposed in the housing has a processor and a movement sensor. The movement sensor measures a signal related to the movement of the object during a time window. The processor assigns at least one preliminary activity label to the time window based on at least one numerical descriptor computed from the signal. The processor then determines whether to perform additional analysis dependent upon at least the preliminary activity label. The processor then assigns a final activity label to the time window.

Abstract: Systems and methods for authenticating material samples are provided. Digital images of the samples are processed to extract computer-vision features, which are used to train a classification algorithm along with location and optional time information. The extracted features/information of a test sample are evaluated by the trained classification algorithm to identify the test sample. The results of the evaluation are used to track and locate counterfeits or authentic products.