Abstract: The present disclosure relates to a medical silicon rubber having high mechanical property and a preparation method thereof. The medical silicon rubber comprises the following raw materials in parts by weight: 50˜90 parts of silicon rubber, 10˜50 parts of polyurethane, 10˜50 parts of fillers, 2˜6 parts of hydrogen-containing silicon oil and 2˜5 parts of a vulcanizing agent. The preparation method comprises: evenly mixing a part of fillers with silicon rubber in an internal mixer, and evenly mixing the other part of fillers with polyurethane in the internal mixer; and mixing the mixed polyurethane on an open type rubber refining machine, then successively adding hydrogen-containing silicon oil, the evenly mixed silicon rubber and the vulcanizing agent into the open type rubber refining machine many times by small portions, and finally vulcanizing the mixed rubber on a plate rubber vulcanizing machine for 5˜15 min at 150˜190° C.

Abstract: The present disclosure provides an image classification method for maximizing mutual information, device, medium and system, the method including: acquiring a training image; maximizing the mutual information between the training image and a neural network architecture, and automatically determining the network architecture and parameter of the neural network; and processing image data to be classified using the obtained neural network to obtain an image classification result. According to the present disclosure, the network architecture and parameter of the neutral network are automatically designed and determined by maximizing the mutual information based on given image data without burdensome manual design and saving human and computational resource consumption. The present disclosure can automatically design and obtain a neural network-based image classification method in a very short time, and at the same time can achieve higher image classification accuracy.

Abstract: A switched capacitor converter includes a first energy storage branch, a second energy storage branch, a third energy storage branch comprising a third capacitor, a seventh switch, an eighth switch, a ninth switch and a tenth switch, and a control branch connected to a first terminal of each switch in the first energy storage branch, the second energy storage branch and the third energy storage branch respectively, wherein the control branch is configured to control each switch to alternately turn on and off periodically in two phases, so that a ratio of a voltage at the input terminal to a voltage at an output terminal is 2N:1, wherein in each operating cycle, the tenth switch is turned on later than at least one switch in the third energy storage branch, and wherein the at least one switch and the tenth switch are in a same phase.

Abstract: The present disclosure provides an image classification method for maximizing mutual information, device, medium and system, the method including: acquiring a training image; maximizing the mutual information between the training image and a neural network architecture, and automatically determining the network architecture and parameter of the neural network; and processing image data to be classified using the obtained neural network to obtain an image classification result. According to the present disclosure, the network architecture and parameter of the neutral network are automatically designed and determined by maximizing the mutual information based on given image data without burdensome manual design and saving human and computational resource consumption. The present disclosure can automatically design and obtain a neural network-based image classification method in a very short time, and at the same time can achieve higher image classification accuracy.

Abstract: A fatigue measurement method includes obtaining a face video of a target object, processing the facial video to obtain a plurality of quasi-heart rates and a plurality of quasi-vibration frequencies, selecting a target heart rate from the plurality of quasi-heart rates and a target vibration frequency from the plurality of quasi-vibration frequencies, detecting the target heart rate and the target vibration frequency, and determining, according to the detection result, that the target object is in a fatigue state. The quasi-heart is obtained through one or more of a region of interest (ROI) between eyebrows and an ROI of chin, and the quasi-vibration frequency obtained through one or more of an ROI of eyes and an ROI of mouth.

Abstract: An array substrate, a display panel, a display device, and a manufacturing method for an array substrate are provided. The array substrate includes a pixel unit group which includes a first pixel and a second pixel; the first pixel includes a first pixel electrode, a first switching element, and a first connection portion extending and protruding from the first pixel electrode; the second pixel includes a second pixel electrode, a second switching element, and a second connection portion extending and protruding from the second pixel electrode; the first pixel electrode and the first switching element are electrically connected to each other via the first connection portion; the second pixel electrode and the second switching element are electrically connected to each other via the second connection portion; and an extension length of the first connection portion is not equal to an extension length of the second connection portion.

Abstract: An array substrate, a display panel, a display device, and a manufacturing method for an array substrate are provided. The array substrate includes a pixel unit group which includes a first pixel and a second pixel; the first pixel includes a first pixel electrode, a first switching element, and a first connection portion extending and protruding from the first pixel electrode; the second pixel includes a second pixel electrode, a second switching element, and a second connection portion extending and protruding from the second pixel electrode; the first pixel electrode and the first switching element are electrically connected to each other via the first connection portion; the second pixel electrode and the second switching element are electrically connected to each other via the second connection portion; and an extension length of the first connection portion is not equal to an extension length of the second connection portion.

Abstract: A thin film reeling device is provided. The device comprises a rotating shaft and a rotating bowl. The rotating shaft is nested into the rotating bowl for reeling a thin film, and two ends of the rotating shaft are provided with a first baffle plate and a second baffle plate for reeling the thin film regularly, respectively.