Abstract: A method and a system for medical image interpretation are provided. A medical image is provided to a convolutional neural network model. The convolutional neural network model includes a feature extraction part, a first classifier, and N second classifiers. N feature maps are generated by using the last layer of the feature extraction part of the convolutional neural network model. N symptom interpretation results of N symptoms of a disease are obtained based on the N feature maps through the N second classifiers. A disease interpretation result of the disease is obtained based on the N feature maps through the first classifier.

Abstract: An electronic device is provided, including a main body and a camera module. The camera module has a frame, a lens unit disposed in the frame, a guiding member, and a hinge. The guiding member is affixed to the main body and has a rail and a spring sheet. The hinge pivotally connects to the frame and the guiding member. When the camera module is in the retracted position, the camera module is hidden in a recess of the main body. When the camera module slides out of the recess from the retracted position along the rail into the operational position, the spring sheet is pressed by the hinge to increase the friction between the hinge and the guiding member.

Abstract: The disclosure provides an augmented reality (AR) device, a notebook, and smart glasses. The AR device includes a laser source, a spatial light modulator (SLM), and a hologram optical element (HOE). The laser source provides a coherent laser ray. The SLM provides a diffraction pattern solely corresponding to the coherent laser ray. When the SLM receives the coherent laser ray, the diffraction pattern diffracts the coherent laser ray as a hologram in response to the coherent laser ray. The HOE provides a concave mirror effect merely in response to a wavelength of the coherent laser ray, wherein the HOE receives the hologram and magnifies the hologram as a stereoscopic virtual image.

Abstract: The disclosure is directed to a method of handling conditional handover with a candidate secondary cell group (SCG), a source master node, and a user equipment, which may be used to solve the above technical problems. The method includes: determining, by the source MN, a first execution condition of a first candidate primary cell (PCell); and receiving, by the source MN from a first candidate MN, a parameter of a second execution condition of a first candidate primary SCG cell (PSCell).

Abstract: A display apparatus including a display panel, a camera module, and a diffraction suppression device is provided. The display panel is provided with multiple signal lines and multiple display pixels. The signal lines and the display pixels are alternately arranged along at least one direction. The camera module has a light receiving surface facing the display panel. The light receiving surface is overlapped with the display panel. The diffraction suppression device is disposed between the display panel and the camera module, and has multiple first light-transmitting regions and multiple second light-transmitting regions alternately arranged along the at least one direction. The first light-transmitting regions are respectively overlapped with the display pixels. The second light-transmitting regions are respectively overlapped with the signal lines.

Abstract: Disclosed are an image display method and a 3d display system. The method is adapted to the 3d display system including a 3d display device and includes the following steps. A first image and a second image are obtained by splitting an input image according to a 3d image format. Whether the input image is a 3D format image complying with the 3D image format is determined through a stereo matching processing performed on the first image and the second image. An image interweaving process is enabled to be performed on the input image to generate an interweaving image in response to determining that the input image is the 3D format image complying with the 3D image format, and the interweaving image is displayed via the 3D display device.

Abstract: A computer system and a processing method thereof of sound signal are provided. The computer system includes a platform path controller (PCH), a high-definition audio (HDA) codec, and a digital microphone. The HDA codec is coupled to the PCH. The digital microphone is coupled to the PCH and the HDA codec. The digital microphone is used to generate sound signal. The HDA codec processes the sound signal from the digital microphone. Accordingly, the audio recording with high quality could be provided.

Abstract: A foldable electronic device having multiple screens is provided. The foldable electronic device includes a first screen, a worm rod, a moving member, at least one second screen, and at least one linking rod. The worm rod is rotatably disposed on the first screen. The moving member is coupled to the worm rod to move along the worm rod when the worm rod rotates. The second screen is movably disposed on the first screen. The linking rod is pivotally connected between the moving member and the second screen. When the moving part moves along the worm rod, the second screen is driven to move away from or closed to the worm rod by the linking rod, so that the second screen moves out of the first screen or is accommodated behind the first screen.

Abstract: A device and method for generating article markup information are provided. The method for generating article markup information includes the following. Segmentation processing is performed on an article to generate a segmentation result. Name entity recognition is performed on the segmentation result to generate a first recognition result. Whether the segmentation result includes any word in an expansion list is determined. Expanded entity classification conversion is performed on the first recognition result to generate a second recognition result. The second recognition result and the segmentation result are used as markup information.

Abstract: A driving device and a driving method for an electric assisted bicycle are provided. The driving device includes a motor, a rotation speed sensor, a torque sensor and a controller. The rotation speed sensor senses a rotation speed value of a crank or a chainring of the electric assisted bicycle. The torque sensor obtains an average torque value applied by the crank to the chainring of the electric assisted bicycle. The controller controls an output of the motor in response to the rotation speed value and the average torque value.

Abstract: An identifying method of a sound watermark and a sound watermark identifying apparatus are provided. The method includes the following. A synthesized sound signal is received through a network. Noise interference transferred through the network in the synthesized sound signal is determined according to a reflection-cancelling sound signal. A coding threshold is determined according to the noise interference. A sound watermark signal in the synthesized sound signal is identified according to the coding threshold.

Abstract: A cycling heat dissipation module suited for dissipating heat generated from a heat source is provided. The cycling heat dissipation module includes an evaporator, a condenser, and a micro/nano-structure. The evaporator is thermal contacted with the heat source to absorb heat generated therefrom. The condenser is connected to the evaporator to form a loop, and a working fluid is filled in the loop. The working fluid in liquid state is transformed to vapor state by absorbing heat in the evaporator, and the working fluid in vapor state is transformed to liquid state by dissipating heat in the condenser. The micro/nano-structure is disposed in the condenser to destroy a boundary layer of the working fluid while passing through the condenser.

Abstract: A method and a system for mental index prediction are provided. The method includes the following steps. A plurality of images of a subject person are obtained. A plurality of emotion tags of the subject person in the images are analyzed. A plurality of integrated emotion tags in a plurality of predetermined time periods are calculated according to the emotion tags respectively corresponding to the images. A plurality of preferred features are determined according to the integrated emotion tags. A mental index prediction model is established according to the preferred features to predict a mental index according to the emotional index prediction model.

Abstract: A cabling structure of a foldable electronic device includes a first body, a second body, a hinge module connecting the first body and the second body, a sliding member movably disposed in the second body, a flexible electrical connecting member connected to the first body, the second body, and the sliding member and being driven when the first body and the second body are rotated relatively, and a restoring module disposed in the second body and providing a force to the sliding member. The first body and the second body are rotated relatively to each other through the hinge module. When being rotated relatively to each other, the first body and the second body drive the flexible electrical connecting member and the sliding member. The restoring module restores the sliding member and the flexible electrical connecting member via the force.

Abstract: An electronic device including a body and a receptacle connector is provided. The body has a side wall surface, a receptacle slot located at the side wall surface, a waterproof protrusion protruding from the side wall surface, and two gutters located at the side wall surface, where the waterproof protrusion is located above the receptacle slot, and the two gutters are respectively located at two opposite sides of the receptacle slot. The receptacle connector is disposed in the receptacle slot.

Abstract: A method for handling a multi-cell scheduling and a user equipment is provided. In the method, downlink control information (DCI) from a first serving cell is received. A first number of multiple scheduled cells according to the DCI is determined. The DCI is configured to schedule at least one communication on the scheduled cells. Th communication is performed on at least one of the first number of the scheduled cells according to the DCI. The DCI includes at least one single DCI field, at least one separate DCI field and at least one configurable DCI field.

Abstract: A foldable electronic device is provided, including a first body, a second body, a supporting member, a first hinge connecting the first body and the supporting member, a second hinge connecting the supporting member and the second body, and a gravity-type latch movably disposed in the supporting member. The first body and the supporting member are rotated relatively to be folded or unfolded via the first hinge, and the second body and the supporting member are rotated relatively to be folded or unfolded via the second hinge. In a transforming process of the first body folding to the supporting member and together unfolding relative to the second body, the gravity-type latch is latched onto the first body once the unfolding angle is less than a predetermined value, and the gravity-type latch is de-latched from the first body once the unfolding angle is equal to or greater than the predetermined value.

Abstract: A manufacturing method of housing structure of electronic device is provided. The manufacturing method includes stacking a first structural layer, a painting layer, and a second structural layer, wherein the painting layer is located between the first and the second structural layers. The layer stacked after the painting layer washes and squeezes at least a portion of the flowing painting layer to form a random texture pattern.