Search

Resolving the intricate details of biological phenomena at the molecular level is fundamentally limited by both length- and time scales that can be probed experimentally. Molecular dynamics (MD) simulations at various scales are powerful tools frequently employed to offer valuable biological insights beyond experimental resolution. However, while it is relatively simple to observe long-lived, stable configurations of, for example, proteins, at the required spatial resolution, simulating the more interesting rare transitions between such states often takes orders of magnitude longer than what is feasible even on the largest supercomputers available today. One common aspect of this challenge is pathway discovery, where the start and end states of a scientific phenomenon are known or can be approximated, but the mechanistic details in between are unknown. Here, we propose a representation-learning-based solution that uses interpolation and extrapolation in an abstract representation space to synthesize potential transition states, which are automatically validated using MD simulations. The new simulations of the synthesized transition states are subsequently incorporated into the representation learning, leading to an iterative framework for targeted path sampling. Our approach is demonstrated by recovering the transition of a RAS-RAF protein domain (CRD) from membrane-free to interacting with the membrane using coarse-grain MD simulations.

Traditional methods for identifying "hit" molecules from a large collection of potential drug-like candidates rely on biophysical theory to compute approximations to the Gibbs free energy of the binding interaction between the drug and its protein target. These approaches have a significant limitation in that they require exceptional computing capabilities for even relatively small collections of molecules. Increasingly large and complex state-of-the-art deep learning approaches have gained popularity with the promise to improve the productivity of drug design, notorious for its numerous failures. However, as deep learning models increase in their size and complexity, their acceleration at the hardware level becomes more challenging. Hyperdimensional Computing (HDC) has recently gained attention in the computer hardware community due to its algorithmic simplicity relative to deep learning approaches. The HDC learning paradigm, which represents data with high-dimension binary vectors, allows the use of low-precision binary vector arithmetic to create models of the data that can be learned without the need for the gradient-based optimization required in many conventional machine learning and deep learning methods. This algorithmic simplicity allows for acceleration in hardware that has been previously demonstrated in a range of application areas (computer vision, bioinformatics, mass spectrometery, remote sensing, edge devices, etc.). To the best of our knowledge, our work is the first to consider HDC for the task of fast and efficient screening of modern drug-like compound libraries. We also propose the first HDC graph-based encoding methods for molecular data, demonstrating consistent and substantial improvement over previous work. We compare our approaches to alternative approaches on the well-studied MoleculeNet dataset and the recently proposed LIT-PCBA dataset derived from high quality PubChem assays. We demonstrate our methods on multiple target hardware platforms, including Graphics Processing Units (GPUs) and Field Programmable Gate Arrays (FPGAs), showing at least an order of magnitude improvement in energy efficiency versus even our smallest neural network baseline model with a single hidden layer. Our work thus motivates further investigation into molecular representation learning to develop ultra-efficient pre-screening tools. We make our code publicly available at https://github.com/LLNL/hdbind. [ABSTRACT FROM AUTHOR]

Cermet has broad applications in electronics, but achieving stable ceramic‐metal contact has always been a challenge, particularly at hot temperature and large deformation conditions, due to the significant differences in thermal expansion coefficient and stiffness of ceramics and metals. Here, stress matching and strong interphase bonding at the heterogenous ceramic‐metal contact are realized by using flexible ceramics, leading to stable applications in flexible fire‐resistant pressure tactile sensors. Cu/Au nanolayers are deposited first onto the toughened flexible SiO2 nanofibers with a chemical plating method to form sensitive interdigital electrode sensors, then use an in situ thermal reaction strategy to form conformal and interlocked Au3Cu and CuSiO3 interphases, which enhance the mechanical thermal stability of the ceramic‐metal contact. With deep learning technique, the as‐fabricated intelligent pressure tactile gloves can accurately recognize the human body parts in low‐visible burning environments and show a long‐term stability over 1000 cycles with a high sensitivity of 112.18 kPa−1, which is important for developing intelligent firefighting. [ABSTRACT FROM AUTHOR]

Hyperspectral Unmixing (HU), which involves decomposing mixed pixels in hyperspectral images into endmembers and abundance fractions, plays a critical role in spectral analysis. Recent advancements in deep learning methods have shown successful applications in hyperspectral analysis. This paper proposes an end-to-end network structure that combines a Convolutional Neural Network (CNN) and a Multilayer Perceptron (MLP). The 3D-CNN extracts high-level features from both spatial and spectral neighbourhoods of hyperspectral image patches, while the MLP maps these abstracted features to abundance fractions. Considering the challenge of acquiring manual labels, we adopt a Semi-Supervised learning approach that leverages unlabelled data to enhance training. We divide our training data into labelled and unlabelled subsets, defining distinct loss functions for each. Additionally, we introduce a neighbourhood similarity constraint to fully exploit spatial context information. To address scenarios where no labelled data is available, we employ Generative Adversarial Networks (GANs) to generate synthetic labelled samples. Experimental evaluations conducted on both synthetic and real datasets validate the effectiveness of our proposed method, which outperforms several commonly used and state-of-the-art HU methods. [ABSTRACT FROM AUTHOR]

Hyperspectral image classification involves assigning a land cover class to each pixel of a hyperspectral image (HSI). Recently, several classification methods based on deep learning with spatial information from HSI have been proposed. These methods typically demonstrate strong classification capabilities. However, spatial information often comprises complex data, making it challenging to extract valuable information. To address this issue, this paper proposes a novel image preprocessing method for classification based on metric learning. This method aims to reduce the complexity of spatial information to facilitate network learning. First, the method assesses the similarity between the central pixel and other pixels in each image patch using a relation network. It replaces pixels that are dissimilar to the central pixel with pixels that are similar to the central pixel to simplify the image patch. This approach reduces interference information in the image patch, allowing the network to focus more on the central pixel features that represent category information during the classification task. This greatly reduces the complexity of the required network, the difficulty of the network learning, and the number of training samples needed. Experimental results on three popular hyperspectral image datasets demonstrate that the proposed preprocessing method significantly improves classification accuracy compared to the baseline network. The study also compares our method to the state-of-the-art attention mechanism CNN, demonstrating how our method excels at hyperspectral classification in data-smoothing and feature preservation. [ABSTRACT FROM AUTHOR]

Automaticidentification and prevention of leaf diseases and insect pests on fruit crops represent a key trend in the development of smart agriculture. In order to address the limitations of existing models with low identification rates of apple leaf diseases and insect pests, a novel identification model based on an improved ResNet-50 architecture was proposed, which incorporated the coordinate attention (CA) module and weight-adaptive multi-scale feature fusion (WAMFF) to enhance the ResNet-50's image feature extraction capabilities. Transfer learning and online data enhancement are employed to boost the model's generalization ability. The proposed model achieved a top-1 accuracy rate of 98.32% on the basis of AppleLeaf9 datasets, which is 4.58% higher than the value from the original model, and the improved model can effectively improve the localization of lesion features. Furthermore, compared with mainstream deep networks, such as AlexNet, VGG16, DenseNet, MNASNet, and GoogLeNet on the same dataset, the top-1 accuracy rate increased by 7.3%, 3.19%, 4.98%, 6.04% and 3.87%, respectively. The experimental results demonstrate that the improved model is effective in improving the identification accuracy of apple leaf diseases and insect pests and enhancing the model's effective feature extraction capabilities. [ABSTRACT FROM AUTHOR]

Hyperspectral unmixing decomposes the observed mixed spectra into a collection of constituent pure material signatures and the associated fractional abundances. Because of the universal modeling ability of neural networks, deep learning (DL) techniques are gaining prominence in solving hyperspectral analysis tasks. The autoencoder (AE) network has been extensively investigated in linear blind source unmixing. However, the linear mixing model (LMM) may fail to provide good unmixing performance when the nonlinear mixing effects are nonnegligible in complex scenarios. Considering the limitations of LMM, we propose an unsupervised nonlinear spectral unmixing method, based on autoencoder architecture. Firstly, a deep neural network is employed as the encoder to extract the low-dimension feature of the mixed pixel. Then, the generalized bilinear model (GBM) is used to design the decoder, which has a linear mixing part and a nonlinear mixing one. The coefficient of the bilinear mixing part can be adjusted by a set of learnable parameters, which makes the method perform well on both nonlinear and linear data. Finally, some regular terms are imposed on the loss function and an alternating update strategy is utilized to train the network. Experimental results on synthetic and real datasets verify the effectiveness of the proposed model and show very competitive performance compared with several existing algorithms. [ABSTRACT FROM AUTHOR]

The lack of labeled samples severely restricts the classification performance of deep learning on hyperspectral image classification. To solve this problem, Generative Adversarial Networks (GAN) are usually used for data augmentation. However, GAN have several problems with this task, such as the poor quality of the generated samples and an unstable training process. Thereby, knowing how to construct a GAN to generate high-quality hyperspectral training samples is meaningful for the small-sample classification task of hyperspectral data. In this paper, an Auxiliary Classifier based Wasserstein GAN with Gradient Penalty (AC-WGAN-GP) was proposed. The framework includes AC-WGAN-GP, an online generation mechanism, and a sample selection algorithm. The proposed method has the following distinctive advantages. First, the input of the generator is guided by prior knowledge and a separate classifier is introduced to the architecture of AC-WGAN-GP to produce reliable labels. Second, an online generation mechanism ensures the diversity of generated samples. Third, generated samples that are similar to real data are selected. Experiments on three public hyperspectral datasets show that the generated samples follow the same distribution as the real samples and have enough diversity, which effectively expands the training set. Compared to other competitive methods, the proposed framework achieved better classification accuracy with a small number of labeled samples. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) classification is one of the main research contents of hyperspectral technology. Existing HSI classification algorithms that are based on deep learning use a large number of labeled samples to train models to ensure excellent classification effects, but when the labeled samples are insufficient, the deep learning model is prone to overfitting. In practice, there are a large number of unlabeled samples that have not been effectively utilized, so it is meaningful to study a semi-supervised method. In this paper, an adversarial representation learning that is based on a generative adversarial networks (ARL-GAN) method is proposed to solve the small samples problem in hyperspectral image classification by applying GAN to the representation learning domain in a semi-supervised manner. The proposed method has the following distinctive advantages. First, we build a hyperspectral image block generator whose input is the feature vector that is extracted from the encoder and use the encoder as a feature extractor to extract more discriminant information. Second, the distance of the class probability output by the discriminator is used to measure the error between the generated image block and the real image instead of the root mean square error (MSE), so that the encoder can extract more useful information for classification. Third, GAN and conditional entropy are used to improve the utilization of unlabeled data and solve the small sample problem in hyperspectral image classification. Experiments on three public datasets show that the method achieved better classification accuracy with a small number of labeled samples compared to other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Supervised machine learning and deep learning methods perform well in hyperspectral image classification. However, hyperspectral images have few labeled samples, which make them difficult to be trained because supervised classification methods rely heavily on sample quantity and quality. Inspired by the idea of self-supervised learning, this article proposes a hyperspectral imagery classification algorithm based on contrast learning, which uses the information of abundant unlabeled samples to alleviate the problem of insufficient label information in hyperspectral data. The algorithm uses a two-stage training strategy. In the first stage, the model is pretrained in the way of self-supervised learning, using a large number of unlabeled samples combined with data enhancement to construct positive and negative sample pairs, and contrastive learning (CL) is carried out. The purpose is to enable the model to make judgments on positive and negative samples. In the second stage, based on the pretrained model, the features of the hyperspectral image are extracted for classification, and a small amount of labeled samples are used to fine-tune the features. Experiments show that the features extracted by self-supervised learning achieved improved results on downstream classification task. [ABSTRACT FROM AUTHOR]

Object detection has played an important role in the remote sensing (RS) image understanding domain, but it still suffers from challenges, including the complexity of the image background, the variety of objects and differences of target scales. Although many studies applying deep learning methods to object detection have been presented, effective methods of multiscale object detection in RS images are still lacking. In this paper, we propose a novel object detection approach based on the Multiscale-SELU-DenseNet (MSE-DenseNet) and the dynamic anchor assignment (DAA) strategy. We fuse a highly modified DenseNet and a feature pyramid network into the MSE-DenseNet to extract multi-level feature descriptions of RS images, and then we use them to detect objects on various scales. To further improve the detection performance, we propose a DAA strategy for assigning prior anchor boxes. The experimental results show that our proposed method outperforms state-of-the-art detection methods on the VHR-10 dataset and maintains a real-time detection speed. [ABSTRACT FROM AUTHOR]

The signal degradation due to the Poisson noise is a common problem in the low‐light imaging field. Recently, deep learning employing the convolution neural network for image denoising has drawn considerable attention owing to its favourable denoising performance. On the basis of the fact that the reconstruction of corrupted pixels can be facilitated by the context information in image denoising, the authors propose a deep multi‐scale cross‐path concatenation residual network (MC2RNet) which incorporates cross‐path concatenation modules for Poisson denoising. Multiple paths are achieved by the cross‐path concatenation operation and the skip connection. As a consequence, multi‐scale context representations of images under different receptive fields can be learnt by MC2RNet. With the residual learning strategy, MC2RNet learns the residual between the noisy image and the latent clean image rather than the direct mapping to facilitate model training. Specially, unlike existing discriminative Poisson denoising algorithms that train a model only for the specific noise level, they aim to train a single model for handling Poisson noise with different levels, i.e. blind Poisson denoising. Quantitative experiments demonstrate that the proposed model is superior over the state‐of‐the‐art Poisson denoising approaches in terms of peak signal‐to‐noise ratio and visual effect. [ABSTRACT FROM AUTHOR]

Abstract Many applications, such as computer-aided design and game rendering, need to reproduce realistic material appearance in complex light environment and different visual conditions. The authenticity of the three-dimensional object or the scene is heavily depended on the representation and rendering of textures, where the Bidirectional Texture Function (BTF) is one of the most widely-used texture models. In this paper, we proposed a neural network to learn the representation of the BTF data for predicting new texture images under novel conditions. The proposed method was tested on a public BTF dataset and was shown to produce satisfactory synthetic results. [ABSTRACT FROM AUTHOR]