Abstract: A protective case of a folding screen mobile phone includes a front protective case, a rear protective case, a soft connecting mechanism and a hinge protector. The front protective case is provided with a transparent window or a hollow-out window. One end of the soft connecting mechanism is fixedly connected to the rear protective case, another end of the soft connecting mechanism is connected to one side of the hinge protector, and a hinge positioning mechanism is provided between another side of the hinge protector and the front protective case; or, one end of the soft connecting mechanism is fixedly connected to the front protective case, another end of the soft connecting mechanism is connected to one side of the hinge protector, and a hinge positioning mechanism is provided between another side of the hinge protector and the rear protective case.

Abstract: Provided is a brassiere allowing for selecting a plurality of types of pads. A brassiere (1) includes a first pocket (70) that holds a pad (90 to 95) inside a cup portion (2), and further includes a second pocket (80) inside the cup portion (2). The first pocket (70) includes a first pocket opening (72) through which the pad (90 to 95) is taken in and out, and a first opening portion (73) communicating with the first pocket opening (72). The first pocket opening (72) is covered with the second pocket (80). The second pocket (80) includes a second pocket opening (82) through which the pad (90 to 95) is taken in and out, and a second opening portion (83) communicating with the first pocket opening (72).

Abstract: Disclosed is a method for establishing a prediction model based on a multidimensional texture of brain nuclear magnetic resonance images. Images are segmented using a region growing method, a contourlet transform method is used to extract an edge texture feature parameter of ROIs, a multidimensional database is established, and a prediction model is established using various data mining methods, comprising a Gaussian process, a support vector machine, a random forest, a Lasso regression and a semi-supervised support vector machine. The ROIs comprise a hippocampus region and an entorhinal cortex region.

Abstract: Disclosed is a method for establishing a prediction model based on a multidimensional texture of brain nuclear magnetic resonance images. Images are segmented using a region growing method, a contourlet transform method is used to extract an edge texture feature parameter of ROIs, a multidimensional database is established, and a prediction model is established using various data mining methods, comprising a Gaussian process, a support vector machine, a random forest, a Lasso regression and a semi-supervised support vector machine. The ROIs comprise a hippocampus region and an entorhinal cortex region.