Background: Fine-grained classification deals with data with a large degree of similarity, such as cat or bird species, and similarly, knee osteoarthritis severity classification [Kellgren-Lawrence (KL) grading] is one such fine-grained classification task. Recently, a plug-in module (PIM) that can be integrated into convolutional neural-network-based or transformer-based networks has been shown to provide strong discriminative regions for fine-grained classification, with results that outperformed the previous deep learning models. PIM utilizes each pixel of an image as an independent feature and can subsequently better classify images with minor differences.
View Article and Find Full Text PDFIonic polymer-metal composites (IPMCs) have been proposed as biomimetic actuators that are operable at low applied voltages. However, the bending strain and generating force of the IPMC actuators have generally exhibited a trade-off relationship, whereas simultaneous enhancement of both the qualities is required for their practical applications. Herein, a significant improvement in both the strain and force of the IPMC actuators is achieved by a facile approach, exploiting thickness-controlled ion-exchange membranes and nanodispersed metal electrodes.
View Article and Find Full Text PDFACS Appl Mater Interfaces
August 2015
On purpose to enhance the generating force of ionic polymer-metal composite (IPMC) actuators, the thickness of the ion-exchange membrane is manipulated in two different ways. One is grafting poly(styrenesulfonic acid) onto poly(vinylidene fluoride-co-hexafluoropropylene) films with varying thickness, and the other is stacking pre-extruded Nafion films to thicker films by pressing at high temperatures. For both groups of the membranes, ionic properties including ion-exchange capacity and ionic conductivity are maintained similarly inside the groups regardless of the thickness.
View Article and Find Full Text PDF