Abstract: A live flaw detection system for a multi-bundled conductor splicing sleeve and an application method thereof are disclosed. The system includes an upper apparatus and a lower apparatus, where the upper apparatus includes an unmanned aerial vehicle and an industrial X-ray machine, and a laser sensor, and the lower apparatus includes a press plate frame apparatus, vertical screw slide table modules, a horizontal screw slide table module, a projection imager, and a linear retractable apparatus. The unmanned aerial vehicle functions as a power apparatus that controls the system to be online or offline, the industrial X-ray machine is configured to perform ray flaw detection on each splicing sleeve, the laser sensor is configured to guide the unmanned aerial vehicle to land the lower apparatus on splicing sleeves accurately, and the press plate frame apparatus is configured to fixedly clamp the splicing sleeves.

Abstract: Methods and systems for budgeted and simplified training of deep neural networks (DNNs) are disclosed. In one example, a trainer is to train a DNN using a plurality of training sub-images derived from a down-sampled training image. A tester is to test the trained DNN using a plurality of testing sub-images derived from a down-sampled testing image. In another example, in a recurrent deep Q-network (RDQN) having a local attention mechanism located between a convolutional neural network (CNN) and a long-short time memory (LSTM), a plurality of feature maps are generated by the CNN from an input image. Hard-attention is applied by the local attention mechanism to the generated plurality of feature maps by selecting a subset of the generated feature maps. Soft attention is applied by the local attention mechanism to the selected subset of generated feature maps by providing weights to the selected subset of generated feature maps in obtaining weighted feature maps.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for driver detection are described. One example method includes monitoring data provided by an accelerometer associated with a client device. It is determined whether the data indicates a particular event associated with a vehicle. In response to determining that the data indicates the particular event associated with the vehicle, one or more micro-activities associated with the vehicle are determined based on data from at least one of the accelerometer and one or more other sensors associated with the client device. Results from each of the one or more micro-activities are provided to a trained model associated with the client device. In response to providing the results to the trained model, one or more vehicular events in a time sequence are identified based on the one or more micro-activities associated with the vehicle.

Abstract: The present disclosure relates to methods and devices for indoor-outdoor detection. One example computer-implemented method for indoor-outdoor detection by an electronic device includes receiving, from an ambient light sensor in the electronic device, light intensity data. The electronic device determines an indoor-outdoor feature indicator based on the light intensity data. The electronic device determines whether the electronic device is in an indoor environment or an outdoor environment based on the indoor-outdoor feature indicator.

Abstract: A live flaw detection system for a multi-bundled conductor splicing sleeve and an application method thereof are disclosed. The system includes an upper apparatus and a lower apparatus, where the upper apparatus includes an unmanned aerial vehicle and an industrial X-ray machine, and a laser sensor, and the lower apparatus includes a press plate frame apparatus, vertical screw slide table modules, a horizontal screw slide table module, a projection imager, and a linear retractable apparatus. The unmanned aerial vehicle functions as a power apparatus that controls the system to be online or offline, the industrial X-ray machine is configured to perform ray flaw detection on each splicing sleeve, the laser sensor is configured to guide the unmanned aerial vehicle to land the lower apparatus on splicing sleeves accurately, and the press plate frame apparatus is configured to fixedly clamp the splicing sleeves.

Abstract: A mobile device such as a smart phone, tablet computer, Internet of things (IoT) device, and/or wearable device includes a sensor module coupled to multiple corresponding sensors. The multiple corresponding sensors include multiple instances of the same type of motion sensor in different physical locations on the mobile device. The sensor module includes a software architecture/algorithm that can configure the multiple corresponding sensors to provide sensor measurements having a higher sampling frequency and/or an improved accuracy. In addition, the sensor module may provide sensor measurements having additional degrees of freedom and/or lower power consumption than can be provided by existing sensor modules.

Abstract: A computer-implemented method for indoor-outdoor detection by an electronic device includes: receiving, from an ambient light sensor in the electronic device, light intensity data. The electronic device determines an indoor-outdoor feature indicator based on the light intensity data. The electronic device determines whether the electronic device is in an indoor environment or an outdoor environment based on the indoor-outdoor feature indicator.

Abstract: Systems and methods for receiving galvanic skin response data from a galvanic skin response sensor that includes multiple electrodes fastened to a hand of a human; monitoring the galvanic skin response data to determine a time for initiating a Blood Pressure (BP) measurement using a blood pressure measurement cuff worn by the human (e.g., in a continuous or on-demand BP measurement mode); at the determined time, initiating the blood pressure measurement using the blood pressure measurement cuff; receiving blood pressure data for the human that results from the blood pressure measurement; and storing a blood pressure value that is based on the blood pressure data.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for driver detection are described. One example method includes monitoring data provided by an accelerometer associated with a client device. It is determined whether the data indicates a particular event associated with a vehicle. In response to determining that the data indicates the particular event associated with the vehicle, one or more micro-activities associated with the vehicle are determined based on data from at least one of the accelerometer and one or more other sensors associated with the client device. Results from each of the one or more micro-activities are provided to a trained model associated with the client device. In response to providing the results to the trained model, one or more vehicular events in a time sequence are identified based on the one or more micro-activities associated with the vehicle.

Abstract: The disclosure discloses an antiemetic control device and a control method thereof, comprising a housing, a MCU single-chip microcontroller provided in the housing, a charging circuit, a discharging circuit and a rechargeable battery for supplying power, a button, a display screen, an alarm device and a plurality of mode indicator lights disposed on the housing, two electrodes and an optical pulse detecting unit disposed on the lower surface of the housing, and two wrist straps disposed on the housing. The disclosure has the characteristics of stable therapeutic effects.

Abstract: Systems, methods, and detection apparatuses, for the detection of body capacitance, such as the capacitance of a human body, are disclosed. A detection apparatus determines an electronic signal characteristic of one or more electrodes. The electronic signal characteristic can be based on a voltage. Responsive to the electronic signal characteristic being within a predetermined electronic signal characteristic range, a charging mode is activated. Responsive to the electronic signal characteristic of the one or more electrodes being outside the predetermined electronic signal characteristic range, a capacitance detection mode is activated. The capacitance detection mode includes: determining a capacitance value of the one or more electrodes in which the capacitance value is based on a frequency of change in a capacitance associated with the one or more electrodes. Responsive to the capacitance of the one or more electrodes exceeding a capacitance threshold, activating a wearable mode.

Abstract: The disclosure discloses an antiemetic control device and a control method thereof, comprising a housing, a MCU single-chip microcontroller provided in the housing, a charging circuit, a discharging circuit and a rechargeable battery for supplying power, a button, a display screen, an alarm device and a plurality of mode indicator lights disposed on the housing, two electrodes and an optical pulse detecting unit disposed on the lower surface of the housing, and two wrist straps disposed on the housing. The disclosure has the characteristics of stable therapeutic effects.

Abstract: A wearable device notification framework includes devices configured to generate and transmit messages. Measurement data and location data generated based on an event can be received by a server device from a wearable device or a connected device configured to receive data from the wearable device and relay the data to the server device. The measurement data can indicate values generated using one or more sensors of the wearable device, and the location data can indicate a geolocation of the wearable device as of the event. An address-based location corresponding to the location data can then be identified by querying a map service for map data based on the location data. The address-based location can correspond to one of an on-road or off-road location of the wearable device. A message can then be generated using the measurement data and the address-based location and transmitted to a recipient device.

Abstract: A wearable device notification framework includes devices configured to generate and transmit messages. Measurement data and location data generated based on an event can be received by a server device from a wearable device or a connected device configured to receive data from the wearable device and relay the data to the server device. The measurement data can indicate values generated using one or more sensors of the wearable device, and the location data can indicate a geolocation of the wearable device as of the event. An address-based location corresponding to the location data can then be identified by querying a map service for map data based on the location data. The address-based location can correspond to one of an on-road or off-road location of the wearable device. A message can then be generated using the measurement data and the address-based location and transmitted to a recipient device.

Abstract: Systems and methods for receiving galvanic skin response data from a galvanic skin response sensor that includes multiple electrodes fastened to a hand of a human; monitoring the galvanic skin response data to determine a time for initiating a Blood Pressure (BP) measurement using a blood pressure measurement cuff worn by the human (e.g., in a continuous or on-demand BP measurement mode); at the determined time, initiating the blood pressure measurement using the blood pressure measurement cuff; receiving blood pressure data for the human that results from the blood pressure measurement; and storing a blood pressure value that is based on the blood pressure data.

Abstract: Systems, methods, and detection apparatuses, for the detection of body capacitance, such as the capacitance of a human body, are disclosed. A detection apparatus determines an electronic signal characteristic of one or more electrodes. The electronic signal characteristic can be based on a voltage. Responsive to the electronic signal characteristic being within a predetermined electronic signal characteristic range, a charging mode is activated. Responsive to the electronic signal characteristic of the one or more electrodes being outside the predetermined electronic signal characteristic range, a capacitance detection mode is activated. The capacitance detection mode includes: determining a capacitance value of the one or more electrodes in which the capacitance value is based on a frequency of change in a capacitance associated with the one or more electrodes. Responsive to the capacitance of the one or more electrodes exceeding a capacitance threshold, activating a wearable mode.