DM-CNN: Dynamic Multi-scale Convolutional Neural Network with uncertainty quantification for medical image classification.

Convolutional neural network (CNN) has promoted the development of diagnosis technology of medical images. However, the performance of CNN is limited by insufficient feature information and inaccurate attention weight. Previous works have improved the accuracy and speed of CNN but ignored the uncertainty of the prediction, that is to say, uncertainty of CNN has not received enough attention. Therefore, it is still a great challenge for extracting effective features and uncertainty quantification of medical deep learning models In order to solve the above problems, this paper proposes a novel convolutional neural network model named DM-CNN, which mainly contains the four proposed sub-modules : dynamic multi-scale feature fusion module (DMFF), hierarchical dynamic uncertainty quantifies attention (HDUQ-Attention) and multi-scale fusion pooling method (MF Pooling) and multi-objective loss (MO loss). DMFF select different convolution kernels according to the feature maps at different levels, extract different-scale feature information, and make the feature information of each layer have stronger representation ability for information fusion HDUQ-Attention includes a tuning block that adjust the attention weight according to the different information of each layer, and a Monte-Carlo (MC) dropout structure for quantifying uncertainty MF Pooling is a pooling method designed for multi-scale models, which can speed up the calculation and prevent overfitting while retaining the main important information Because the number of parameters in the backbone part of DM-CNN is different from other modules, MO loss is proposed, which has a fast optimization speed and good classification effect DM-CNN conducts experiments on publicly available datasets in four areas of medicine (Dermatology, Histopathology, Respirology, Ophthalmology), achieving state-of-the-art classification performance on all datasets. DM-CNN can not only maintain excellent performance, but also solve the problem of quantification of uncertainty, which is a very important task for the medical field. The code is available: https://github.com/QIANXIN22/DM-CNN.

Direct visualization of spatially correlated displacive short-range ordering in Nb0.8CoSb.

Whether the atomic arrangement has a long-range order bifurcates solid-state matter into two major categories: crystalline and amorphous, between which lies a short-range order, a frontier research topic of fundamental and application implications. To date, it is still challenging to extract the details of short-range order from the corresponding diffuse diffraction pattern due to the phase problem. Here, we employed the high-angle annular dark field (HAADF) imaging technique to pinpoint the short-range order encoded in the one-of-a-kind diffuse the diffraction bands of defective half-Heusler Nb0.8CoSb. Utilizing a protocol based on two limiting cases, we found that the native Nb vacancies up to 20% are dominantly displacive short-range ordered yet spatially correlated. To the best of our knowledge, this is the first time that a dominantly displacive short-range order is reported at the atomic scale. These results are vital for an in-depth understanding and engineering of the thermodynamics and transport properties of the materials with abundant native defects, including but not limited to defective half-Heusler compounds.

Tribological and Vibration Properties of Three Different Polymer Materials for Water-Lubricated Bearings.

Water-lubricated bearings usually operate under severe environmental conditions, most likely in the mixed regime, in which surface contact between the drive shaft and the bearing sleeve is often significant. This presents great challenges to bearing design, especially material selection. The Tenmat, Thordon, and Rubber are common water-lubricated bearing composites. In this paper, by using a block-on-ring test apparatus, the Stribeck curve, wear rate, and vibration characteristics of three kinds of polymer materials in water-lubricated bearings (Tenmat, Thordon SXL, and Ben Teng Group (BTG) Rubber) under low speed and heavy load were studied. The experimental results show that, under the same working conditions, BTG rubber has excellent tribological properties and vibration properties. The research method in this paper can provide references for the selection of materials used for friction pair, improvement of working performance and vibration reduction of water-lubricated bearings in the future.