It is a common fact that data(features,characteristics or variables)are collected at different sampling frequencies in some fields such as economic and industry.The existing methods usually either ignore the differenc...It is a common fact that data(features,characteristics or variables)are collected at different sampling frequencies in some fields such as economic and industry.The existing methods usually either ignore the difference from the different sampling frequencies or hardly take notice of the inherent temporal characteristics in mixed frequency data.The authors propose an innovative dual attention-based neural network for mixed frequency data(MID-DualAtt),in order to utilize the inherent temporal characteristics and select the input characteristics reasonably without losing information.According to the authors’knowledge,this is the first study to use the attention mechanism to process mixed fre-quency data.The MID-DualAtt model uses the frequency alignment method to trans-form the high--frequency variables into observation vectors at low frequency,and more critical input characteristics are selected for the current prediction index by attention mechanism.The temporal characteristics are explored by the encoder-decoder with attention based on long-short-term memory networks(LSTM).The proposed MID-DualAtt has been tested in practical application,and the experimental results show that it has better prediction ability than the compared models.展开更多
Magnetorheological fluid(MRF)has shown its great potential in the development of large mechanical devices,such as dampers,shock absorbers,rotary brakes,clutches,and prosthetic joints.Recently,more research focus has b...Magnetorheological fluid(MRF)has shown its great potential in the development of large mechanical devices,such as dampers,shock absorbers,rotary brakes,clutches,and prosthetic joints.Recently,more research focus has been invested on using MRF to develop soft,stretchable,and miniaturized devices with variable stiffness for realizing functionalities that cannot be achieved using solid smart materials.Here,based on liquid metal magnetoactive slurries(LMMS),a variable stiffness wire with excellent electrical conductivity is demonstrated.Without exposure to a magnetic field,the LMMS wire has an extremely low stiffness,and can be easily stretched while maintaining an excellent electrical conductivity.When applying a magnetic field,the wire becomes much stiffer and can retain its shape even under a load.The combination of properties of flexibility,high electrical conductivity,and variable stiffness of the wire is harnessed to make a flexible gripper that can grasp objects of various shapes.Moreover,by using gallium instead of its liquid metal alloys,the tunable stiffness range of the LMMS wire is signifi-cantly enhanced and can be controlled using both external magnetic fields and temperature-induced phase change.The presented LMMS wire has the potential to be applied in flexible electronics,soft robotics and so on.展开更多
基金This work was supported in part by the National Natural Science Foundation of China under Grant Nos.61876027,61533020 and 61751312the key T&A program of Chongqing under grant No.cstc2019jscx-mbdxX0048.
文摘It is a common fact that data(features,characteristics or variables)are collected at different sampling frequencies in some fields such as economic and industry.The existing methods usually either ignore the difference from the different sampling frequencies or hardly take notice of the inherent temporal characteristics in mixed frequency data.The authors propose an innovative dual attention-based neural network for mixed frequency data(MID-DualAtt),in order to utilize the inherent temporal characteristics and select the input characteristics reasonably without losing information.According to the authors’knowledge,this is the first study to use the attention mechanism to process mixed fre-quency data.The MID-DualAtt model uses the frequency alignment method to trans-form the high--frequency variables into observation vectors at low frequency,and more critical input characteristics are selected for the current prediction index by attention mechanism.The temporal characteristics are explored by the encoder-decoder with attention based on long-short-term memory networks(LSTM).The proposed MID-DualAtt has been tested in practical application,and the experimental results show that it has better prediction ability than the compared models.
基金This research was partially supported by the National Natural Science Foundation of China(nos.51975550,U1713206,and 51828503).
文摘Magnetorheological fluid(MRF)has shown its great potential in the development of large mechanical devices,such as dampers,shock absorbers,rotary brakes,clutches,and prosthetic joints.Recently,more research focus has been invested on using MRF to develop soft,stretchable,and miniaturized devices with variable stiffness for realizing functionalities that cannot be achieved using solid smart materials.Here,based on liquid metal magnetoactive slurries(LMMS),a variable stiffness wire with excellent electrical conductivity is demonstrated.Without exposure to a magnetic field,the LMMS wire has an extremely low stiffness,and can be easily stretched while maintaining an excellent electrical conductivity.When applying a magnetic field,the wire becomes much stiffer and can retain its shape even under a load.The combination of properties of flexibility,high electrical conductivity,and variable stiffness of the wire is harnessed to make a flexible gripper that can grasp objects of various shapes.Moreover,by using gallium instead of its liquid metal alloys,the tunable stiffness range of the LMMS wire is signifi-cantly enhanced and can be controlled using both external magnetic fields and temperature-induced phase change.The presented LMMS wire has the potential to be applied in flexible electronics,soft robotics and so on.