Since the outbreak of the COVID-19 epidemic, it has posed a great crisis to the health and economy of the world. The objective is to provide a simple deep-learning approach for predicting, modelling, and evaluating the time evolutions of the COVID-19 epidemic. The Dove Swarm Search (DSS) algorithm is integrated with the echo state network (ESN) to optimize the weight. The ESN-DSS model is constructed to predict the evolution of the COVID-19 time series. Specifically, the self-driven ESN-DSS is created to form a closed feedback loop by replacing the input with the output. The prediction results, which involve COVID-19 temporal evolutions of multiple countries worldwide, indicate the excellent prediction performances of our model compared with several artificial intelligence prediction methods from the literature (e.g., recurrent neural network, long short-term memory, gated recurrent units, variational auto encoder) at the same time scale. Moreover, the model parameters of the self-driven ESN-DSS are determined which acts as a significant impact on the prediction performance. As a result, the network parameters are adjusted to improve the prediction accuracy. The prediction results can be used as proposals to help governments and medical institutions formulate pertinent precautionary measures to prevent further spread. In addition, this study is not only limited to COVID-19 time series forecasting but also applicable to other nonlinear time series prediction problems.

We propose a neural network architecture and a training procedure to estimate blurring operators and deblur images from a single degraded image. Our key assumption is that the forward operators can be parameterized by a low-dimensional vector. The models we consider include a description of the point spread function with Zernike polynomials in the pupil plane or product-convolution expansions, which incorporate space-varying operators. Numerical experiments show that the proposed method can accurately and robustly recover the blur parameters even for large noise levels. For a convolution model, the average signal-to-noise ratio of the recovered point spread function ranges from 13 dB in the noiseless regime to 8 dB in the high-noise regime. In comparison, the tested alternatives yield negative values. This operator estimate can then be used as an input for an unrolled neural network to deblur the image. Quantitative experiments on synthetic data demonstrate that this method outperforms other commonly used methods both perceptually and in terms of SSIM. The algorithm can process a 512 $ \times $ 512 image under a second on a consumer graphics card and does not require any human interaction once the operator parameterization has been set up.1

In this work, we propose a novel approach for tomato pollination that utilizes visual servo control. The objective is to meet the growing demand for automated robotic pollinators to overcome the decline in bee populations. Our approach focuses on addressing this challenge by leveraging visual servo control to guide the pollination process. The proposed method leverages deep learning to estimate the orientations and depth of detected flower, incorporating CAD-based synthetic images to ensure dataset diversity. By utilizing a 3D camera, the system accurately estimates flower depth information for visual servoing. The robustness of the approach is validated through experiments conducted in a laboratory environment with a 3D printed tomato flower plant. The results demonstrate a high detection rate, with a mean average precision of 91.2 %. Furthermore, the average depth error for accurately localizing the pollination target is impressively minimal, measuring only 1.1 cm. This research presents a promising solution for tomato pollination, showcasing the effectiveness of visual-guided servo control and its potential to address the challenges posed by diminishing bee populations in greenhouses.

The axisymmetric nozzle mechanism is the core part for thrust vectoring of aero engine, which contains complex rigid-flexible coupled multibody system with joints clearance and significantly reduces the efficiency in modeling and calculation, therefore the kinematics and dynamics analysis of axisymmetric vectoring nozzle mechanism based on deep neural network is proposed. The deep neural network model of the axisymmetric vector nozzle is established according to the limited training data from the physical dynamic model and then used to predict the kinematics and dynamics response of the axisymmetric vector nozzle. This study analyses the effects of joint clearance on the kinematics and dynamics of the axisymmetric vector nozzle mechanism by a data-driven model. It is found that the angular acceleration of the expanding blade and the driving force are mostly affected by joint clearance followed by the angle, angular velocity and position of the expanding blade. Larger joint clearance results in more pronounced fluctuations of the dynamic response of the mechanism, which is due to the greater relative velocity and contact force between the bushing and the pin. Since axisymmetric vector nozzles are highly complex nonlinear systems, traditional numerical methods of dynamics are extremely time-consuming. Our work indicates that the data-driven approach greatly reduces the computational cost while maintaining accuracy, and can be used for rapid evaluation and iterative computation of complex multibody dynamics of engine nozzle mechanism.

Classical approaches for flood prediction apply numerical methods for the solution of partial differential equations that capture the physics of inundation processes (e.g., the 2D Shallow Water equations). However, traditional inundation models are still unable to satisfy the requirements of many relevant applications, including early-warning systems, high-resolution (or large spatial domain) simulations, and robust inference over distributions of inputs (e.g., rainfall events). Machine learning (ML) approaches are a promising alternative to physics-based models due to their ability to efficiently capture correlations between relevant inputs and outputs in a data-driven fashion. In particular, once trained, ML models can be tested/deployed much more efficiently than classical approaches. Yet, few ML-based solutions for spatio-temporal flood prediction have been developed, and their reliability/accuracy is poorly understood. In this paper, we propose FloodGNN-GRU, a spatio-temporal flood prediction model that combines a graph neural network (GNN) and a gated recurrent unit (GRU) architecture. Compared to existing approaches, FloodGNN-GRU (i) employs a graph-based model (GNN); (ii) operates on both spatial and temporal dimensions; and (iii) processes the water flow velocities as vector features, instead of scalar features. We evaluate FloodGNN-GRU using a LISFLOOD-FP simulation of Hurricane Harvey (2017) in Houston, Texas. Our results, based on several metrics, show that FloodGNN-GRU outperforms several data-driven alternatives in terms of accuracy. Moreover, our approach can be trained 100x faster and tested 1000x faster than the time required to run a comparable simulation. These findings illustrate the potential of ML-based methods to efficiently emulate physics-based inundation models, especially for short-term predictions.

New advancements in radio data post-processing are underway within the Square Kilometre Array (SKA) precursor community, aiming to facilitate the extraction of scientific results from survey images through a semi-automated approach. Several of these developments leverage deep learning methodologies for diverse tasks, including source detection, object or morphology classification, and anomaly detection. Despite substantial progress, the full potential of these methods often remains untapped due to challenges associated with training large supervised models, particularly in the presence of small and class-unbalanced labelled datasets.

Self-supervised learning has recently established itself as a powerful methodology to deal with some of the aforementioned challenges, by directly learning a lower-dimensional representation from large samples of unlabelled data. The resulting model and data representation can then be used for data inspection and various downstream tasks if a small subset of labelled data is available.

In this work, we explored contrastive learning methods to learn suitable radio data representations by training the SimCLR model on large collections of unlabelled radio images taken from the ASKAP EMU and SARAO MeerKAT GPS surveys. The resulting models were fine-tuned over smaller labelled datasets, including annotated images from various radio surveys, and evaluated on radio source detection and classification tasks. Additionally, we employed the trained self-supervised models to extract features from radio images, which were used in an unsupervised search for objects with peculiar morphology in the ASKAP EMU pilot survey data. For all considered downstream tasks, we reported the model performance metrics and discussed the benefits brought by self-supervised pre-training, paving the way for building radio foundational models in the SKA era.

Using convolutional neural networks (CNNs) for image recognition is effective for early weed detection. However, the impact of training data curation, specifically concerning morphological changes during the early growth phases of weeds, on recognition robustness remains unclear. We focused on four weed species (giant ragweed [Ambrosia trifida L.], red morningglory [Ipomoea coccinea L.], pitted morningglory [Ipomoea lacunosa L.], and burcucumber [Sicyos angulatus L.]) with varying cotyledon and true leaf shapes. Creating 16 models in total, we employed four dataset patterns with different growth stage combinations, two image recognition algorithms (object detection: You Look Only Once [YOLO] v5 and image classification: Visual Geometry Group [VGG] 19), and two conditions regarding the number of species treated (four and two species). We evaluated the effects of growth stage training on weed recognition success using two datasets. One evaluation revealed superior results with a single class/species training dataset, achieving >90% average precision for detection and classification accuracy under most conditions. The other dataset revealed that merging different growth stages with different shapes as a class effectively prevented misrecognition among different species when using YOLOv5. Both results suggest that integrating different shapes in a plant species as a single class is effective for maintaining robust recognition success amid temporal morphological changes during the early growth stage. This finding not only enhances early detection of weed seedlings but also bolsters the robustness of general plant species identification.

The global increase in observed forest dieback, characterized by the death of tree foliage, heralds widespread decline in forest ecosystems. This degradation causes significant changes to ecosystem services and functions, including habitat provision and carbon sequestration, which can be difficult to detect using traditional monitoring techniques, highlighting the need for large-scale and high-frequency monitoring. Contemporary developments in the instruments and methods to gather and process data at large scales mean this monitoring is now possible. In particular, the advancement of low-cost drone technology and deep learning on consumer-level hardware provide new opportunities. Here, we use an approach based on deep learning and vegetation indices to assess crown dieback from RGB aerial data without the need for expensive instrumentation such as LiDAR. We use an iterative approach to match crown footprints predicted by deep learning with field-based inventory data from a Mediterranean ecosystem exhibiting drought-induced dieback, and compare expert field-based crown dieback estimation with vegetation index-based estimates. We obtain high overall segmentation accuracy (mAP: 0.519) without the need for additional technical development of the underlying Mask R-CNN model, underscoring the potential of these approaches for non-expert use and proving their applicability to real-world conservation. We also find that color-coordinate based estimates of dieback correlate well with expert field-based estimation. Substituting ground truth for Mask R-CNN model predictions showed negligible impact on dieback estimates, indicating robustness. Our findings demonstrate the potential of automated data collection and processing, including the application of deep learning, to improve the coverage, speed, and cost of forest dieback monitoring.

In spite of the superior performance deep neural networks have proven in thousands of applications in the past few years, addressing the over-sensitivity of these models to noise and/or intentional slight perturbations is still an active area of research. In the computer vision domain, perturbations can be directly applied to the input images. The task in the natural language processing domain is quite harder due to the discrete nature of natural languages. There has been a considerable amount of effort put to address this problem in high-resource languages like English. However, there is still an apparent lack of such studies in the Arabic language, and we aim to be the first to conduct such a study in this work. In this study, we start by training seven different models on a sentiment analysis task. Then, we propose a method to attack our models by means of the worst synonym replacement where the synonyms are automatically selected via the gradients of the input representations. After proving the effectiveness of the proposed adversarial attack, we aim to design a framework that enables the development of models robust to attacks. Three different frameworks are proposed in this work and a thorough comparison between the performance of these frameworks is presented. The three scenarios revolve around training the proposed models either on adversarial samples only or also including clean samples beside the adversarial ones, and whether or not to include weight perturbation during training.

There has been a steep rise in user-generated content on the Web and social media platforms during the last few years. While the ease of content creation allows anyone to create content, at the same time it is difficult to monitor and control the spread of detrimental content. Recent research in natural language processing and machine learning has shown some hope for the purpose. Approaches and methods are now being developed for the automatic flagging of problematic textual content, namely hate speech, cyberbullying, or fake news, though mostly for English language texts. This paper presents an algorithmic approach based on deep learning models for the detection of violent incidents from tweets in the Spanish language (binary classification) and categorizes them further into five classes – accident, homicide, theft, kidnapping, and none (multi-label classification). The performance is evaluated on the recently shared benchmark dataset, and it is found that the proposed approach outperforms the various deep learning models, with a weighted average precision, recall, and F1-score of 0.82, 0.81, and 0.80, respectively, for the binary classification. Similarly, for the multi-label classification, the proposed model reports weighted average precision, recall, and F1-score of 0.54, 0.79, and 0.64, respectively, which is also superior to the existing results reported in the literature. The study, thus, presents meaningful contribution to detection of violent incidents in Spanish language social media posts.

This manuscript introduces deep learning models that simultaneously describe the dynamics of several yield curves. We aim to learn the dependence structure among the different yield curves induced by the globalization of financial markets and exploit it to produce more accurate forecasts. By combining the self-attention mechanism and nonparametric quantile regression, our model generates both point and interval forecasts of future yields. The architecture is designed to avoid quantile crossing issues affecting multiple quantile regression models. Numerical experiments conducted on two different datasets confirm the effectiveness of our approach. Finally, we explore potential extensions and enhancements by incorporating deep ensemble methods and transfer learning mechanisms.

Deep learning (DL) has been widely used in bearing fault diagnosis. In particular, convolutional neural networks (CNNs) improve diagnosis accuracy by extracting excellent fault features. However, CNN lacks an explicit learning mechanism to distinguish between different fault characteristics in the input signal to the diagnosis results. This article presents a new end-to-end depth framework called multi-head self-attention convolution neural network (MSA-CNN) for bearing fault diagnosis. Firstly, we adopt a data pre-processing method that directly converts one-dimensional (1D) original signals into two-dimensional (2D) grayscale images, which is simple to implement and preserves the complete information of the original signal. Secondly, multi-head self-attention (MSA) is first constructed to aggregate the global information and adaptively assign weights to the input signal's features. Thirdly, the CNN with small-scale kernels extracted detailed local features. Finally, the learned high-level representations are fed into the full connect (FC) layer for fault diagnosis. The performance of the MSA-CNN is validated on different datasets. The results show that the proposed MSA-CNN can significantly improve fault diagnosis accuracy compared with the other state-of-the-art methods and has excellent noise immunity performance.

Cryogenic electron tomography (cryoET) is capable of determining in situ biological structures of molecular complexes at near-atomic resolution by averaging half a million subtomograms. While abundant complexes/particles are often clustered in arrays, precisely locating and seamlessly averaging such particles across many tomograms present major challenges. Here, we developed TomoNet, a software package with a modern graphical user interface to carry out the entire pipeline of cryoET and subtomogram averaging to achieve high resolution. TomoNet features built-in automatic particle picking and three-dimensional (3D) classification functions and integrates commonly used packages to streamline high-resolution subtomogram averaging for structures in 1D, 2D, or 3D arrays. Automatic particle picking is accomplished in two complementary ways: one based on template matching and the other using deep learning. TomoNet’s hierarchical file organization and visual display facilitate efficient data management as required for large cryoET datasets. Applications of TomoNet to three types of datasets demonstrate its capability of efficient and accurate particle picking on flexible and imperfect lattices to obtain high-resolution 3D biological structures: virus-like particles, bacterial surface layers within cellular lamellae, and membranes decorated with nuclear egress protein complexes. These results demonstrate TomoNet’s potential for broad applications to various cryoET projects targeting high-resolution in situ structures.

Visual simultaneous localisation and mapping (vSLAM) has shown considerable promise in positioning and navigating across a variety of indoor and outdoor settings, significantly enhancing the mobility of robots employed in industrial and everyday services. Nonetheless, the prevalent reliance of vSLAM technology on the assumption of static environments has led to suboptimal performance in practical implementations, particularly in unstructured and dynamically noisy environments such as substations. Despite advancements in mitigating the influence of dynamic objects through the integration of geometric and semantic information, existing approaches have struggled to strike an equilibrium between performance and real-time responsiveness. This study introduces a lightweight, multi-modal semantic framework predicated on vSLAM, designed to enable intelligent robots to adeptly navigate the dynamic environments characteristic of substations. The framework notably enhances vSLAM performance by mitigating the impact of dynamic objects through a synergistic combination of object detection and instance segmentation techniques. Initially, an enhanced lightweight instance segmentation network is deployed to ensure both the real-time responsiveness and accuracy of the algorithm. Subsequently, the algorithm’s performance is further refined by amalgamating the outcomes of detection and segmentation processes. With a commitment to maximising performance, the framework also ensures the algorithm’s real-time capability. Assessments conducted on public datasets and through empirical experiments have demonstrated that the proposed method markedly improves both the accuracy and real-time performance of vSLAM in dynamic environments.

Body-worn sensor data is used in monitoring patient activity during rehabilitation and also can be extended to controlling rehabilitation devices based on the activity of the person. The primary focus of research has been on effectively capturing the spatiotemporal dependencies in the data collected by these sensors and efficiently classifying human activities. With the increasing complexity and size of models, there is a growing emphasis on optimizing their efficiency in terms of memory usage and inference time for real-time usage and mobile computers. While hybrid models combining convolutional and recurrent neural networks have shown strong performance compared to traditional approaches, self-attention-based networks have demonstrated even superior results. However, instead of relying on the same transformer architecture, there is an opportunity to develop a novel framework that incorporates recent advancements to enhance speed and memory efficiency, specifically tailored for human activity recognition (HAR) tasks. In line with this approach, we present GLULA, a unique architecture for HAR. GLULA combines gated convolutional networks, branched convolutions, and linear self-attention to achieve efficient and powerful solutions. To enhance the performance of our proposed architecture, we employed manifold mixup as an augmentation variant which proved beneficial in limited data settings. Extensive experiments were conducted on five benchmark datasets: PAMAP2, SKODA, OPPORTUNITY, DAPHNET, and USC-HAD. Our findings demonstrate that GLULA outperforms recent models in the literature on the latter four datasets but also exhibits the lowest parameter count and close to the fastest inference time among state-of-the-art models.