WUYI UNIVERSITY

A compressed ultrafast imaging device based on time stretching, and a method and a storage medium are disclosed. The compressed ultrafast imaging device based on time stretching includes: a laser light generation module, configured to emit laser light; a collimation module, optically connected to the laser light generation module and configured to collimate the laser light; a laser light conversion module, optically connected to the collimation module and configured to convert the collimated laser light into spatial light; an encoding module, optically connected to the laser light conversion module and configured to encode according to the spatial light; an image acquisition module, connected to the encoding module; and a control processing module, communicatively connected to the laser light generation module and the image acquisition module respectively, and configured to obtain a target image sequence frame based on an observed image sent by the image acquisition module.

A two-wire fabric touch panel includes a first wire, a second wire, an upper conductor layer, a middle conductor layer, and a lower conductor layer. The first wire is connected to the upper conductor layer, and the second wire is connected to the lower conductor layer. The middle conductor layer has a conductivity significantly lower than conductivities of the upper conductor layer and the lower conductor layer, and the middle conductor layer has different resistances at various positions in a plane. At least one of the upper conductor layer and the lower conductor layer is isolated from the middle conductor layer when an external force is absent, and a resistance between the upper conductor layer and the lower conductor layer is infinite. The upper conductor layer and the lower conductor layer are connected through the middle conductor layer at the pressure position when subjected to pressure.

A compressed ultrafast imaging device based on time stretching, and a method and a storage medium are disclosed. The compressed ultrafast imaging device based on time stretching includes: a laser light generation module, configured to emit laser light; a collimation module, optically connected to the laser light generation module and configured to collimate the laser light; a laser light conversion module, optically connected to the collimation module and configured to convert the collimated laser light into spatial light; an encoding module, optically connected to the laser light conversion module and configured to encode according to the spatial light; an image acquisition module, connected to the encoding module; and a control processing module, communicatively connected to the laser light generation module and the image acquisition module respectively, and configured to obtain a target image sequence frame based on an observed image sent by the image acquisition module.

An ultrafast diffraction imaging system and method, and a storage medium are disclosed. The ultrafast diffraction imaging system includes: a laser generation module configured to emit laser; a time stretching module optically connected to the laser generation module and configured to stretch the laser into a time data stream; an encoding module optically connected to the time stretching module and configured to perform encoding according to the time data stream to obtain an encoding matrix; an image acquisition module connected to the encoding module and configured to capture the encoding matrix to obtain an observed image; and a control processing module respectively in communicative connection with the laser generation module and the image acquisition module, and configured to perform phase reconstruction according to the observed image transmitted by the image acquisition module to obtain a target phase change sequence frame.

A multi-task facial beauty prediction method and apparatus, device, and medium are disclosed. The method includes: training a multi-task teacher model according to a facial image to obtain a first model; performing regularization on the first model according to a beauty grade label and a noise label to obtain a second model; performing cooperative teaching on a plurality of second models to obtain a target model parameter; substituting the target model parameter into a multi-task student model to obtain the target model; and performing facial beauty prediction processing using the target model to obtain a facial beauty prediction result.

A fabric touch device includes an upper conductor layer and a lower conductor layer. The upper conductor layer includes a first semiconductor and a first good conductor drawn out from the first semiconductor. The lower conductor layer includes a second semiconductor and a second good conductor drawn out from the second semiconductor. The upper conductor layer and the lower conductor layer remain isolated when an external force is absent. When any one of planar positions of the fabric touch device is subjected to pressure, the upper conductor layer and the lower conductor layer are in contact with each other through intersection between the first good conductor and the second good conductor, such that the first semiconductor and the second semiconductor form a conductive path, and a conduction resistance value obtained by conducting the first semiconductor and the second semiconductor uniquely corresponds to a coordinate of the planar position.

A flexible three-dimensional ( 3 D) pressure sensing device includes a force-sensitive component composed of a single piece of flexible and electrically conductive material with piezoresistive properties, a plurality of 3 D transmission components distributed on a surface of the force-sensitive component, and a plurality of electrodes arranged on a periphery of the force-sensitive component. The 3 D transmission components are configured to transmit pressure to the force-sensitive component, causing characteristic corresponding changes in electrical resistance of the force-sensitive component, the pressure including a normal pressure and shear pressure. The plurality of the electrodes are configured to lead out resistance distribution data of the force-sensitive component through wires, so that a backend circuit device calculates 3 D pressure distribution information of the flexible 3 D pressure sensing device at each position on the surface at each time point based on the resistance distribution data.

An intermittent extrusion system and an extrusion device are disclosed. The intermittent extrusion system includes a barrel and an extrusion unit. The extrusion unit includes a first screw and a second screw, both the first screw and the second screw are installed in the barrel and can rotate in the barrel, a screw thread of the first screw can mesh with a screw groove of the second screw, the first screw has at least one thread start, and the second screw has at least one thread start. The first screw rotates at a constant speed, while the second screw rotates intermittently, and a rotating direction of the first screw is opposite to that of the second screw.

Embodiments of the disclosure discloses method and apparatus for facial beauty prediction, device and storage medium. The method includes the steps of classifying a training set into a plurality of first images with noise labels and a plurality of second images with non-noise labels; performing a re-weighting processing on the plurality of the second images; training a first model by using a target training set to obtain a second model; labeling image data by using the second model to obtain first data with labels and second data without labels; generating third data with pseudo labels through a classifier by using the second data; training the classifier according to the first data, the second data and the third data; processing an image to be predicted through a model with a target classifier to obtain a facial beauty prediction result.

A train data transmission system and method, an apparatus, and a medium are disclosed. The method includes: acquiring, by a train data acquisition device, train-related data; receiving the train-related data from an onboard central control device and forwarding the train-related data to a database server by a network address translation (NAT) server; and in response to a web server receiving access information of an access terminal accessing a web service port exposed by a public network, acquiring, by the web server, target data from the train-related data stored in the database server according to the access information; and receiving, by the access terminal, the target data from the web server.