Abstract: This disclosure relates to ultrasound imaging with reduced speckle. Ultrasound imaging with frequency compounding and angle compounding is disclosed. Techniques are disclosed to make ultrasound imaging with frequency and angle compounding more robust. One such technique is non-rigid image registration to align ultrasound images for angle compounding. Another disclosed technique includes selecting a subset of ultrasound images for non-rigid ultrasound image registration.

Abstract: A high voltage battery cluster, and an overcurrent protection circuit and a switch box of the high voltage battery cluster are provided. The overcurrent protection circuit includes a first fusing module and a second fusing module. Since a withstand current-time curve of the first fusing module is different from a withstand current-time curve of the second fusing module, in a case that an overcurrent fault occurs in a high voltage battery cluster, one fusing module can cause an open circuit in the high voltage battery cluster prior to another fusing module, thereby preventing the high voltage battery cluster from being broken by a large current when an overcurrent fault occurs in the high voltage battery cluster, thus ensuring an electrical safety of the high voltage battery cluster.

Abstract: The disclosed systems can regulate access to an online mode for a dynamic transportation matching system. For example, based on a provider efficiency parameter associated with the dynamic transportation matching system, the disclosed systems can prevent a transportation provider device from switching to the online mode within a geographic area. In addition, the disclosed systems can detect a pattern of behavior and, based on a comparison between the pattern of behavior and a behavioral threshold, cause a transportation provider device to switch from the online mode to an offline mode. Further, the disclosed systems can provide a map interface that indicates where a transportation provider device can switch from the offline mode to the online mode. Additionally, the disclosed systems can determine priorities associated with transportation provider devices and, based on the prioritization, selectively allow the transportation provider devices to switch from the offline mode to the online mode.

Abstract: The disclosed systems can regulate access to an online mode for a dynamic transportation matching system. For example, based on a provider efficiency parameter associated with the dynamic transportation matching system, the disclosed systems can prevent a transportation provider device from switching to the online mode within a geographic area. In addition, the disclosed systems can detect a pattern of behavior and, based on a comparison between the pattern of behavior and a behavioral threshold, cause a transportation provider device to switch from the online mode to an offline mode. Further, the disclosed systems can provide a map interface that indicates where a transportation provider device can switch from the offline mode to the online mode. Additionally, the disclosed systems can determine priorities associated with transportation provider devices and, based on the prioritization, selectively allow the transportation provider devices to switch from the offline mode to the online mode.

Abstract: A method for capturing a scene in a virtual environment for an immersive reality application running in a headset is provided. The method includes determining initiation of an auto-capture session in a headset by a user, the headset running an immersive reality application hosted by a remote server, executing a gaze model based on the initiation, detecting through the gaze model a gaze of the user, tracking the gaze of the user, capturing a scene in a virtual environment based on the gaze of the user, and storing the scene as a media file in storage. A headset and a memory storing instructions to cause the headset and a remote server to perform the above method are also provided.

Abstract: The disclosed systems can regulate access to an online mode for a dynamic transportation matching system. For example, based on a provider efficiency parameter associated with the dynamic transportation matching system, the disclosed systems can prevent a transportation provider device from switching to the online mode within a geographic area. In addition, the disclosed systems can detect a pattern of behavior and, based on a comparison between the pattern of behavior and a behavioral threshold, cause a transportation provider device to switch from the online mode to an offline mode. Further, the disclosed systems can provide a map interface that indicates where a transportation provider device can switch from the offline mode to the online mode. Additionally, the disclosed systems can determine priorities associated with transportation provider devices and, based on the prioritization, selectively allow the transportation provider devices to switch from the offline mode to the online mode.

Abstract: A method for using cameras in an augmented reality headset is provided. The method includes receiving a signal from a sensor mounted on a headset worn by a user, the signal being indicative of a user intention for capturing an image. The method also includes identifying the user intention for capturing the image, based on a model to classify the signal from the sensor according to the user intention, selecting a first image capturing device in the headset based on a specification of the first image capturing device and the user intention for capturing the image, and capturing the image with the first image capturing device. An augmented reality headset, a memory storing instructions, and a processor to execute the instructions to cause the augmented reality headset as above are also provided.

Abstract: Disclosed herein includes a system, a method, and a device for improving power efficiency of a neural network implemented in an AI chip. In a neural network, large amounts of computations for multiply and accumulate can result in frequent toggles or transitions in states of logic circuits in the AI chip. Such frequent toggles or transitions of states of logic circuits can cause a large overall power consumption. In one aspect, to minimize the number of toggles, a sequence or order of computations can be rearranged. In one approach, total hamming distances for weights or input strings in different arrangements or sequences can be identified, and an arrangement or a sequence of weights or input strings with a reduced or minimum total hamming distance can be identified. An arrangement or a sequence of weights that render a reduced total hamming distance can be identified.

Abstract: In one embodiment, a method includes accessing from a client system associated with a first user sensor signals captured by sensors of the client system, wherein the client system comprises a plurality of sensors, and wherein the sensors signals are accessed from the sensors based on cascading model policies, wherein each cascading model policy utilizes one or more of a respective cost or relevance associated with each sensor, detecting a change in a context of the first user associated with an activity of the first user based on machine-learning models and the sensor signals, wherein the change in the context of the first user satisfies a trigger condition associated with the activity, and responsive to the detected change in the context of the first user automatically capturing visual data by cameras of the client system.

Abstract: Nonlinear ultrasound imaging systems and methods are disclose. In one aspect, a nonlinear ultrasound imaging system includes a first transducer configured to transmit a first ultrasound signal along a scan line, a second transducer configured to sweep a second ultrasound signal along the scan line such that the first and second ultrasound signals intersect at a plurality of voxels, and a third transducer configured to receive echoes associated with interactions of the first and second ultrasound signals at the plurality of voxels. The nonlinear ultrasound imaging system further includes a processor configured to generate an ultrasound image based on the echoes.

Abstract: In one embodiment, a method includes receiving an input for a machine-learning model configured to detect a plurality of predetermined features, the machine-learning model including at least a first neural network configured to detect a first subset of the plurality of predetermined features and a second neural network configured to detect a second subset of the plurality of predetermined features, generating a detection result by processing the input using the first neural network, determining that the input includes a feature in the first subset of the plurality of predetermined features based on the detection result and one or more detection criteria, and outputting the detection result as an output of the machine-learning model without using the second neural network to process the input in response to the determination.

Abstract: Ultrasound imaging systems and methods with frequency (spectral) compounding for speckle reduction are disclosed. In one aspect, an ultrasound imaging system includes a transducer probe with interleaved transmit and receive arrays. The system may utilize ultrasound pulses having an optimized time-bandwidth product. In one aspect, a transducer probe with separate transmit and receive elements can enable transmission and reception of multiple ultrasound pulses, each centered at a different frequency, during the time of one A-scan. Thus, such a system can capture multiple independent speckle images without reducing overall B-mode framerate. In another aspect, the system may transmit a broadband pulse and may obtain separate speckle images by filtering the received echo using multiple spectral filters. The system may compound multiple images captured at different frequencies to provide speckle reduction.

Abstract: A multiplier for calculating a multiplication of a first fixed point number and a second fixed point number comprises a converter and a restoration circuit. The converter is configured to convert the first fixed point number to a sign, a mantissa, and an exponent. At least one of a bit width of the sign, a bit width of the mantissa, and a bit width of the exponent is dynamically configured based on a position of a layer associated with the first fixed point number in a neural network, a position of a pixel in an input feature map associated with the first fixed point number, and/or a channel associated with the first fixed point number. The restoration circuit is configured to calculate the multiplication based on the sign, the mantissa, the exponent, and the second fixed point number.

Abstract: This disclosure relates to ultrasound imaging with reduced speckle. Ultrasound imaging with frequency compounding and angle compounding is disclosed. Techniques are disclosed to make ultrasound imaging with frequency and angle compounding more robust. One such technique is non-rigid image registration to align ultrasound images for angle compounding. Another disclosed technique includes selecting a subset of ultrasound images for non-rigid ultrasound image registration.

Abstract: This disclosure relates to combined frequency and angle compounding for speckle reduction in ultrasound imaging Such combined frequency and angle compounding can result in a multiplicative speckle reduction compared to using either frequency compounding or angle compounding alone. Compounding methods of this disclosure can make use of the full aperture of the ultrasound probe when acquiring individual images, hence there can be no compromise in resolution. In disclosed embodiments, ultrasound images can be obtained while an ultrasound probe is moving and the relative position and orientation of the ultrasound images can be determined from a measurement of the position and orientation of the ultrasound probe. Certain embodiments can correct for the movement and distortion of an object being imaged during the image acquisition.

Abstract: Ultrasound imaging systems and methods with frequency (spectral) compounding for speckle reduction are disclosed. In one aspect, an ultrasound imaging system includes a transducer probe with interleaved transmit and receive arrays. The system may utilize ultrasound pulses having an optimized time-bandwidth product. In one aspect, a transducer probe with separate transmit and receive elements can enable transmission and reception of multiple ultrasound pulses, each centered at a different frequency, during the time of one A-scan. Thus, such a system can capture multiple independent speckle images without reducing overall B-mode framerate. In another aspect, the system may transmit a broadband pulse and may obtain separate speckle images by filtering the received echo using multiple spectral filters. The system may compound multiple images captured at different frequencies to provide speckle reduction.

Abstract: The disclosed systems can regulate access to an online mode for a dynamic transportation matching system. For example, based on a provider efficiency parameter associated with the dynamic transportation matching system, the disclosed systems can prevent a transportation provider device from switching to the online mode within a geographic area. In addition, the disclosed systems can detect a pattern of behavior and, based on a comparison between the pattern of behavior and a behavioral threshold, cause a transportation provider device to switch from the online mode to an offline mode. Further, the disclosed systems can provide a map interface that indicates where a transportation provider device can switch from the offline mode to the online mode. Additionally, the disclosed systems can determine priorities associated with transportation provider devices and, based on the prioritization, selectively allow the transportation provider devices to switch from the offline mode to the online mode.

Abstract: The disclosed systems can regulate access to an online mode for a dynamic transportation matching system. For example, based on a provider efficiency parameter associated with the dynamic transportation matching system, the disclosed systems can prevent a transportation provider device from switching to the online mode within a geographic area. In addition, the disclosed systems can detect a pattern of behavior and, based on a comparison between the pattern of behavior and a behavioral threshold, cause a transportation provider device to switch from the online mode to an offline mode. Further, the disclosed systems can provide a map interface that indicates where a transportation provider device can switch from the offline mode to the online mode. Additionally, the disclosed systems can determine priorities associated with transportation provider devices and, based on the prioritization, selectively allow the transportation provider devices to switch from the offline mode to the online mode.

Abstract: The disclosed systems can regulate access to an online mode for a dynamic transportation matching system. For example, based on a provider efficiency parameter associated with the dynamic transportation matching system, the disclosed systems can prevent a transportation provider device from switching to the online mode within a geographic area. In addition, the disclosed systems can detect a pattern of behavior and, based on a comparison between the pattern of behavior and a behavioral threshold, cause a transportation provider device to switch from the online mode to an offline mode. Further, the disclosed systems can provide a map interface that indicates where a transportation provider device can switch from the offline mode to the online mode. Additionally, the disclosed systems can determine priorities associated with transportation provider devices and, based on the prioritization, selectively allow the transportation provider devices to switch from the offline mode to the online mode.

Abstract: The disclosed systems can regulate access to an online mode for a dynamic transportation matching system. For example, based on a provider efficiency parameter associated with the dynamic transportation matching system, the disclosed systems can prevent a transportation provider device from switching to the online mode within a geographic area. In addition, the disclosed systems can detect a pattern of behavior and, based on a comparison between the pattern of behavior and a behavioral threshold, cause a transportation provider device to switch from the online mode to an offline mode. Further, the disclosed systems can provide a map interface that indicates where a transportation provider device can switch from the offline mode to the online mode. Additionally, the disclosed systems can determine priorities associated with transportation provider devices and, based on the prioritization, selectively allow the transportation provider devices to switch from the offline mode to the online mode.