Abstract: The present disclosure is directed towards systems and methods that leverage machine-learned models to decrease the rate at which abnormal sites are missed during a gastroenterological procedure. In particular, the system and methods of the present disclosure can use machine-learning techniques to determine the coverage rate achieved during a gastroenterological procedure. Measuring the coverage rate of the gastroenterological procedure can allow medical professionals to be alerted when the coverage output is deficient and thus allow an additional coverage to be achieved and as a result increase in the detection rate for abnormal sites (e.g., adenoma, polyp, lesion, tumor, etc.) during the gastroenterological procedure.

Abstract: A charge voltage calibration system comprising a power supply, a plurality of light sources coupled in series, and a driver coupled to the power supply and to the plurality of light sources. The driver includes a capacitor, a switch, and a sense resistor. The switch, the sense resistor, and the plurality of light sources are coupled in series to form a discharge path. The discharge path is coupled in parallel with the capacitor. The charge voltage calibration system also comprises a controller configured to cause the power supply to supply a first charge voltage to the driver and to cause the switch to transition from an off state to an on state to discharge at least a portion of a first stored energy in the capacitor through the plurality of light sources.

Abstract: A charge voltage calibration system comprises a power supply, a light string, a driver, and a calibration circuit. The driver comprises a capacitor, a switch, and a sense resistor. The switch, sense resistor, and light string are coupled in series to form a discharge path coupled in parallel with the capacitor. The calibration circuit comprises a controller, a DAC, a comparator, a memory device. The controller is configured to control the DAC to provide a reference voltage to the comparator, cause the power converter to supply a first charge voltage to the driver, cause the switch to transition from an off state to an on state to discharge stored energy in the capacitor through the discharge path, and store a value of the first charge voltage in the memory device in response to detection of voltage generated across the sense resistor being greater than or equal to the reference voltage.

Abstract: A charge voltage calibration system comprises a power supply, a light string, a driver, and a calibration circuit. The driver comprises a capacitor, a switch, and a sense resistor. The switch, sense resistor, and light string are coupled in series to form a discharge path coupled in parallel with the capacitor. The calibration circuit comprises a controller, a DAC, a comparator, a memory device. The controller is configured to control the DAC to provide a reference voltage to the comparator, cause the power converter to supply a first charge voltage to the driver, cause the switch to transition from an off state to an on state to discharge stored energy in the capacitor through the discharge path, and store a value of the first charge voltage in the memory device in response to detection of voltage generated across the sense resistor being greater than or equal to the reference voltage.

Abstract: Embodiments of a system, a machine-accessible storage medium, and a computer-implemented method are described in which operations are performed. The operations comprising receiving a plurality of image frames associated with a video of an endoscopy procedure, generating a probability estimate for one or more image frames included in the plurality of image frames, and identifying a transition in the video when the endoscopy procedure transitions from a first phase to a second phase based, at least in part, on the probability estimate for the one or more image frames. The probability estimate includes a first probability that one or more image frames are associated with a first phase of the endoscopy procedure.

Abstract: The present disclosure is directed towards systems and methods that leverage machine-learned models to decrease the rate at which abnormal sites are missed during a gastroenterological procedure. In particular, the system and methods of the present disclosure can use machine-learning techniques to determine the coverage rate achieved during a gastroenterological procedure. Measuring the coverage rate of the gastroenterological procedure can allow medical professionals to be alerted when the coverage output is deficient and thus allow an additional coverage to be achieved and as a result increase in the detection rate for abnormal sites (e.g., adenoma, polyp, lesion, tumor, etc.) during the gastroenterological procedure.

Abstract: Regulating an AC voltage. The device includes a magnetic core, multiple windings around the core, and multiple switch arrays connectable between an AC power source and respective windings. The switch arrays including multiple switches controllable to connect the AC power source to the windings in a first polarity or in a second polarity. The first polarity and second polarity are different polarities, e.g. phase shifted by 180 degrees. An electrical conductor is disposed around or through the core. The electrical conductor is series-connectable to a power line. AC voltage of the power line is regulated by adding an AC voltage of the electrical conductor responsive to selection of the switches of the switch arrays.

Abstract: Control of grid voltage in a power grid. A power transformer converts alternating current (AC) electrical power at a higher voltage on the primary leads to AC electrical power at a lower grid voltage on the secondary leads. An auxiliary AC/AC power converter converts input AC electrical power at the input conductors to output AC electrical power at the output conductors, The auxiliary AC/AC power converter converts substantially less electrical power than the AC electrical power converted by the power transformer. The secondary leads of the power transformer are series-connected to the output conductors of the auxiliary AC/AC power converter. Input conductors of the auxiliary AC/AC power converter are parallel-connected to either (i) the primary leads of the power transformer, or (ii) the secondary leads of the power transformer. The output alternating voltage of the auxiliary AC/AC power converter adds to the output alternating voltage of the power transformer to control the grid voltage in the power grid.

Abstract: Control of grid voltage in a power grid. A power transformer converts alternating current (AC) electrical power at a higher voltage on the primary leads to AC electrical power at a lower grid voltage on the secondary leads. An auxiliary AC/AC power converter converts input AC electrical power at the input conductors to output AC electrical power at the output conductors, The auxiliary AC/AC power converter converts substantially less electrical power than the AC electrical power converted by the power transformer. The secondary leads of the power transformer are series-connected to the output conductors of the auxiliary AC/AC power converter. Input conductors of the auxiliary AC/AC power converter are parallel-connected to either (i) the primary leads of the power transformer, or (ii) the secondary leads of the power transformer. The output alternating voltage of the auxiliary AC/AC power converter adds to the output alternating voltage of the power transformer to control the grid voltage in the power grid.

Abstract: A monitoring devices and electrically insulated elongated member for installing a monitoring device on a utility asset while maintaining a safe approach distance during operation of the power equipment. The monitoring device includes: a housing having a receptacle member adapted for detachably mating with a distal end of the electrically insulated elongated member and a permanent magnet mounted on the housing. The magnet magnetically attaches the device to the power equipment.

Abstract: Control of grid voltage in a power grid. A power transformer converts alternating current (AC) electrical power at a higher voltage on the primary leads to AC electrical power at a lower grid voltage on the secondary leads. An auxiliary AC/AC power converter converts input AC electrical power at the input conductors to output AC electrical power at the output conductors, The auxiliary AC/AC power converter converts substantially less electrical power than the AC electrical power converted by the power transformer. The secondary leads of the power transformer are series-connected to the output conductors of the auxiliary AC/AC power converter. Input conductors of the auxiliary AC/AC power converter are parallel-connected to either (i) the primary leads of the power transformer, or (ii) the secondary leads of the power transformer. The output alternating voltage of the auxiliary AC/AC power converter adds to the output alternating voltage of the power transformer to control the grid voltage in the power grid.

Abstract: Control of grid voltage in a power grid. A power transformer converts alternating current (AC) electrical power at a higher voltage on the primary leads to AC electrical power at a lower grid voltage on the secondary leads. An auxiliary AC/AC power converter converts input AC electrical power at the input conductors to output AC electrical power at the output conductors, The auxiliary AC/AC power converter converts substantially less electrical power than the AC electrical power converted by the power transformer. The secondary leads of the power transformer are series-connected to the output conductors of the auxiliary AC/AC power converter. Input conductors of the auxiliary AC/AC power converter are parallel-connected to either (i) the primary leads of the power transformer, or (ii) the secondary leads of the power transformer. The output alternating voltage of the auxiliary AC/AC power converter adds to the output alternating voltage of the power transformer to control the grid voltage in the power grid.

Abstract: Example apparatus and methods transform a non-metric latent space produced by a matrix factorization process to a higher dimension metric space by applying an order preserving transformation to the latent space. The transformation preserves the order of the results of an inner product operation defined for the latent space. The higher dimension metric space may be queried for the results to different requests. Example apparatus and methods may assign every user i a vector ui in a latent space, and may assign every item j a vector vj in the latent space. The dot product ui·vj represents the score between the user i and the item j. The score represents the strength of the relationship between the user i and the item j. Example apparatus and methods may then apply ranking methodologies (e.g., LSH, K-D trees) to problems including recommendation, targeting, matchmaking, or item to item.

Abstract: Example apparatus and methods transform a non-metric latent space produced by a matrix factorization process to a higher dimension metric space by applying an order preserving transformation to the latent space. The transformation preserves the order of the results of an inner product operation defined for the latent space. The higher dimension metric space may be queried for the results to different requests. Example apparatus and methods may assign every user i a vector ui in a latent space, and may assign every item j a vector vj in the latent space. The dot product ui·vj represents the score between the user i and the item j. The score represents the strength of the relationship between the user i and the item j. Example apparatus and methods may then apply ranking methodologies (e.g., LSH, K-D trees) to problems including recommendation, targeting, matchmaking, or item to item.

Abstract: Example apparatus and methods transform a non-metric latent space produced by a matrix factorization process to a higher dimension metric space by applying an order preserving transformation to the latent space. The transformation preserves the order of the results of an inner product operation defined for the latent space. The higher dimension metric space may be queried for the results to different requests. Example apparatus and methods may assign every user i a vector ui in a latent space, and may assign every item j a vector vj in the latent space. The dot product ui·vj represents the score between the user i and the item j. The score represents the strength of the relationship between the user i and the item j. Example apparatus and methods may then apply ranking methodologies (e.g., LSH, K-D trees) to problems including recommendation, targeting, matchmaking, or item to item.

Abstract: Example apparatus and methods transform a non-metric latent space produced by a matrix factorization process to a higher dimension metric space by applying an order preserving transformation to the latent space. The transformation preserves the order of the results of an inner product operation defined for the latent space. The higher dimension metric space may be queried for the results to different requests. Example apparatus and methods may assign every user i a vector ui in a latent space, and may assign every item j a vector vj in the latent space. The dot product ui·vj represents the score between the user i and the item j. The score represents the strength of the relationship between the user i and the item j. Example apparatus and methods may then apply ranking methodologies (e.g., LSH, K-D trees) to problems including recommendation, targeting, matchmaking, or item to item.

Abstract: A system and method for assigning one or more tags to an image file. In one aspect, a server computer receives an image file captured by a client device. In one embodiment, the image file includes an audio component embedded therein by the client device, where the audio component was spoken by a user of the client device as a tag of the image file. The server computer determines metadata associated with the image file and identifies a dictionary of potential textual tags from the metadata. The server computer determines a textual tag from the audio component and from the dictionary of potential textual tags. The server computer then associates the textual tag with the image file as additional metadata.

Abstract: A system and method for assigning one or more tags to an image file. In one aspect, a server computer receives an image file captured by a client device. In one embodiment, the image file includes an audio component embedded therein by the client device, where the audio component was spoken by a user of the client device as a tag of the image file. The server computer determines metadata associated with the image file and identifies a dictionary of potential textual tags from the metadata. The server computer determines a textual tag from the audio component and from the dictionary of potential textual tags. The server computer then associates the textual tag with the image file as additional metadata.

Abstract: A method in a computerized system including a microprocessor adapted to run a previously installed firmware code. The computerized system is adapted to receive power from an alternating current (AC) power supply. The AC power supply may include either an AC generator or an AC output of direct current (DC) to AC inverter. The frequency is monitored for a frequency variation pattern of the AC power supply. Optionally, the frequency is monitored upon receiving a request to update the firmware code. Upon recognizing the frequency variation pattern, a firmware update of the firmware code is enabled.