Search

The rapid pace of urbanization underscores the importance of waste monitoring and management in urban planning and environmental conservation. Remote sensing technology enables the aerial observation of terrestrial and marine features, with high-resolution images revealing diverse objects. Deep learning techniques have gained prominence for enhancing waste monitoring precision and efficiency. This article surveys deep learning approaches for waste monitoring in remote sensing images, focusing on relevant datasets. It reviews existing remote sensing datasets, including those from uncrewed aerial vehicles and satellites, for monitoring solid waste and marine debris. Nine publicly available datasets are described in detail, highlighting their origins and applications. The monitoring methods include two kinds of methods: 1) semantic segmentation; and 2) object detection. Semantic segmentation focuses on pixel-level classification and boundary delineation, while object detection targets object-level localization and shape. Representative methods within these categories are explored, and benchmark results from recent studies are summarized to evaluate the performance of various techniques. The discussion addresses current limitations and suggests future research directions, aiming to assist researchers and professionals in environmental monitoring.

Convolutional neural networks (CNNs) have been successfully applied to motor imagery (MI)-based brain–computer interface (BCI). Nevertheless, single-scale CNN fail to extract abundant information over a wide spectrum from EEG signals, while typical multi-scale CNNs cannot effectively fuse information from different scales with concatenation-based methods. To overcome these challenges, we propose a new scheme equipped with attention-based dual-scale fusion convolutional neural network (ADFCNN), which jointly extracts and fuses EEG spectral and spatial information at different scales. This scheme also provides novel insight through self-attention for effective information fusion from different scales. Specifically, temporal convolutions with two different kernel sizes identify EEG $\boldsymbol{\mu }$ and $\boldsymbol{\beta }$ rhythms, while spatial convolutions at two different scales generate global and detailed spatial information, respectively, and the self-attention mechanism performs feature fusion based on the internal similarity of the concatenated features extracted by the dual-scale CNN. The proposed scheme achieves the superior performance compared with state-of-the-art methods in subject-specific motor imagery recognition on BCI Competition IV dataset 2a, 2b and OpenBMI dataset, with the cross-session average classification accuracies of 79.39% and significant improvements of 9.14% on BCI-IV2a, 87.81% and 7.66% on BCI-IV2b, 65.26% and 7.2% on OpenBMI dataset, and the within-session average classification accuracies of 86.87% and significant improvements of 10.89% on BCI-IV2a, 87.26% and 8.07% on BCI-IV2b, 84.29% and 5.17% on OpenBMI dataset, respectively. What is more, ablation experiments are conducted to investigate the mechanism and demonstrate the effectiveness of the dual-scale joint temporal-spatial CNN and self-attention modules. Visualization is also used to reveal the learning process and feature distribution of the model.

The rapid development and widespread application of Unmanned Aerial Vehicles (UAV) have raised significant concerns about safety and privacy, thus requiring powerful anti-UAV systems. This survey provides an overview of anti-UAV detection and tracking methods in recent years. Firstly, we emphasize the key challenges of existing anti-UAV and delve into various detection and tracking methods. It is noteworthy that our study emphasizes the shift toward deep learning to enhance detection accuracy and tracking performance. Secondly, the survey organizes some public datasets, provides effective links, and discusses the characteristics and limitations of each dataset. Next, by analyzing current research trends, we have identified key areas of innovation, including the progress of deep learning techniques in real-time detection and tracking, multi-sensor fusion systems, and the automatic switching mechanisms that adapt to different conditions. Finally, this survey discusses the limitations and future research directions. This paper aims to deepen the understanding of innovations in anti-UAV detection and tracking methods. Hopefully our work can offer a valuable resource for researchers and practitioners involved in anti-UAV research.

Abstract Target tracking has a wide range of applications in intelligent transportation, real‐time monitoring, human‐computer interaction and other aspects. However, in the tracking process, the target is prone to deformation, occlusion, loss, scale variation, background clutter, illumination variation, etc., which bring great challenges to realize accurate and real‐time tracking. Tracking based on Siamese networks promotes the application of deep learning in the field of target tracking, ensuring both accuracy and real‐time performance. However, due to its offline training, it is difficult to deal with the fast motion, serious occlusion, loss and deformation of the target during tracking. Therefore, it is very helpful to improve the performance of the Siamese networks by learning new features of the target quickly and updating the target position in time online. The broad learning system (BLS) has a simple network structure, high learning efficiency, and strong feature learning ability. Aiming at the problems of Siamese networks and the characteristics of BLS, a target tracking method based on BLS is proposed. The method combines offline training with fast online learning of new features, which not only adopts the powerful feature representation ability of deep learning, but also skillfully uses the BLS for re‐learning and re‐detection. The broad re‐learning information is used for re‐detection when the target tracking appears serious occlusion and so on, so as to change the selection of the Siamese networks search area, solve the problem that the search range cannot meet the fast motion of the target, and improve the adaptability. Experimental results show that the proposed method achieves good results on three challenging datasets and improves the performance of the basic algorithm in difficult scenarios.

Abstract Promoting cooperation in the network has always been a focus of evolutionary game dynamics research. In this paper, a three-strategy local decision model is designed to promote cooperative behavior between agents. The hide right is introduced to accurately describe the agents which tend to choose conservative strategy to achieve stable payoffs. Agents only consider their own and non-defective neighbors’ payoffs information to make their decisions for next move. According to the adaptive dynamics, the equilibrium states under different conditions have been studied. It is found that the introduction of hide strategy helps to reduce the occurrence of defection. The conclusion of this paper will provide a reference for the cooperation promotion mechanism of selfish agents that are closer to the actual situation.

With the rapid increase of economic globalization, the significant expansion of shipping volume has resulted in shipping route congestion, causing the necessity of trajectory prediction for effective service and efficient management. While trajectory prediction can achieve a relatively high level of accuracy, the performance and generalization of prediction models remain critical bottlenecks. Therefore, this article proposes a dual-attention (DA) based end-to-end (E2E) neural network (DAE2ENet) for trajectory prediction. In the E2E structure, long short-term memory (LSTM) units are included for the task of pursuing sequential trajectory data from the encoder layer to the decoder layer. In DA mechanisms, global attention is introduced between the encoder and decoder layers to facilitate interactions between input and output trajectory sequences, and multi-head self-attention is utilized to extract sequential features from the input trajectory. In experiments, we use a ro-ro ship with a fixed navigation route as a case study. Compared with baseline models and benchmark neural networks, DAE2ENet can obtain higher performance on trajectory prediction, and better validation of environmental factors on ship navigation.

Summary: Metabolic syndrome (MetS) as a multifactorial disease is highly prevalent in countries and individuals. Monitoring the conventional risk factors (CRFs) would be a cost-effective strategy to target the increasing prevalence of MetS and the potential of noninvasive CRF for precisely detection of MetS in the early stage remains to be explored. From large-scale multicenter MetS clinical dataset, we discover 15 non-invasive CRFs which have strong relevance with MetS and first propose a broad learning-based approach named Genetic Programming Collaborative-competitive Broad Learning System (GP-CCBLS) with noninvasive CRF for early detection of MetS. The proposed GP-CCBLS model can significantly boost the detection performance and achieve the accuracy of 80.54%. This study supports the potential clinical validity of noninvasive CRF to complement general diagnostic criteria for early detecting the MetS and also illustrates possible strength of broad learning in disease diagnosis comparing with other machine learning approaches.

Fusing structural-functional images of the brain has shown great potential to analyze the deterioration of Alzheimer’s disease (AD). However, it is a big challenge to effectively fuse the correlated and complementary information from multimodal neuroimages. In this work, a novel model termed cross-modal transformer generative adversarial network (CT-GAN) is proposed to effectively fuse the functional and structural information contained in functional magnetic resonance imaging (fMRI) and diffusion tensor imaging (DTI). The CT-GAN can learn topological features and generate multimodal connectivity from multimodal imaging data in an efficient end-to-end manner. Moreover, the swapping bi-attention mechanism is designed to gradually align common features and effectively enhance the complementary features between modalities. By analyzing the generated connectivity features, the proposed model can identify AD-related brain connections. Evaluations on the public ADNI dataset show that the proposed CT-GAN can dramatically improve prediction performance and detect AD-related brain regions effectively. The proposed model also provides new insights into detecting AD-related abnormal neural circuits.

IntroductionAlzheimer's disease (AD) is a chronic neurodegenerative disease of the brain that has attracted wide attention in the world. The diagnosis of Alzheimer's disease is faced with the difficulties of insufficient manpower and great difficulty. With the intervention of artificial intelligence, deep learning methods are widely used to assist clinicians in the early recognition of Alzheimer's disease. And a series of methods based on data input with different dimensions have been proposed. However, traditional deep learning models rely on expensive hardware resources and consume a lot of training time, and may fall into the dilemma of local optima.MethodsIn recent years, broad learning system (BLS) has provided researchers with new research ideas. Based on the three-dimensional residual convolution module and BLS, a novel broad-deep ensemble model based on BLS is proposed for the early detection of Alzheimer's disease. The Alzheimer's Disease Neuroimaging Initiative (ADNI) MRI image dataset is used to train the model and then we compare the performance of proposed model with previous work and clinicians' diagnosis.ResultsThe result of experiments demonstrate that the broad-deep ensemble model is superior to previously proposed related works, including 3D-ResNet and VoxCNN, in accuracy, sensitivity, specificity and F1.DiscussionThe proposed broad-deep ensemble model is effective for early detection of Alzheimer's disease. In addition, the proposed model does not need the pre-training process of its depth module, which greatly reduces the training time and hardware dependence.

Alzheimer's disease (AD) is a progressive neurodegenerative disease, and the development of AD is irreversible. However, preventive measures in the presymptomatic stage of AD can effectively slow down deterioration. Fluorodeoxyglucose positron emission tomography (FDG-PET) can detect the metabolism of glucose in patients' brains, which can help to identify changes related to AD before brain damage occurs. Machine learning is useful for early diagnosis of patients with AD using FDG-PET, but it requires a sufficiently large dataset, and it is easy for overfitting to occur in small datasets. Previous studies using machine learning for early diagnosis with FDG-PET have either involved the extraction of elaborately handcrafted features or validation on a small dataset, and few studies have explored the refined classification of early mild cognitive impairment (EMCI) and late mild cognitive impairment (LMCI). This article presents a broad network-based model for early diagnosis of AD (BLADNet) through PET imaging of the brain; this method employs a novel broad neural network to enhance the features of FDG-PET extracted via 2D CNN. BLADNet can search for information over a broad space through the addition of new BLS blocks without retraining of the whole network, thus improving the accuracy of AD classification. Experiments conducted on a dataset containing 2,298 FDG-PET images of 1,045 subjects from the ADNI database demonstrate that our methods are superior to those used in previous studies on early diagnosis of AD with FDG-PET. In particular, our methods achieved state-of-the-art results in EMCI and LMCI classification with FDG-PET.

With the spread of distributed renewable energy, residents are shifting from being mere consumers to being energy producers and consumers. This role shift poses challenges to the electricity trading mechanism that connects distributed renewable energy sources to the grid. In this paper, a new efficient and secure blockchain-based distributed community energy trading mechanism is proposed, called CE-SDT. Our system is proved to be stable and scalable. It can also help shift loads and power peaks and reduce customer costs by 60%. As a result, our proposed blockchain-based trading mechanism, as compared to the centralized trading mechanism, is applied to microgrids formed by distributed renewable energy sources, not only obtaining greater economic benefits but also reducing the carbon footprint of residents, and furthermore, it promotes low or zero-carbon configurations of the power system, thereby achieving certain environmental benefits.

Abstract In this paper, a variable projection approach based on the BFGS (Broyden–Fletcher–Goldfarb–Shanno) method for image reconstruction problems is proposed, which is an alternative to the common alternating minimisation scheme. The image restoration is expressed as a nonlinear least‐squares problem with reduced parameter space. To improve the efficiency of the algorithm, the BFGS method is proposed to be used to optimise the reduced objective function. The large‐scale problem considered in this paper is projected on to a small Krylov subspace using Lanczos bidiagonalisation. The regularisation parameter is selected by a weighted generalised cross validation criterion. Numerical examples demonstrate the efficiency and effectiveness of the proposed algorithm.

With the rapid growth of shipping volumes, ship navigation and path planning have attracted increased attention. To design navigation routes and avoid ship collisions, accurate ship trajectory prediction based on automatic identification system data is required. Therefore, this study developed an encoder–decoder learning model for ship trajectory prediction, to avoid ship collisions. The proposed model includes long short-term memory units and an attention mechanism. Long short-term memory can extract relationships between the historical trajectory of a ship and the current state of encountered ships. Simultaneously, the global attention mechanism in the proposed model can identify interactions between the output and input trajectory sequences, and a multi-head self-attention mechanism in the proposed model is used to learn the feature fusion representation between the input trajectory sequences. Six case studies of trajectory prediction for ship collision avoidance from the Yangtze River of China and the eastern coast of the U.S. were investigated and compared. The results showed that the average mean absolute errors of our model were much lower than those of the classical neural networks and other state-of-the-art models that included attention mechanisms.

Epilepsy is a chronic brain disease that causes persistent and severe damage to the physical and mental health of patients. Daily effective prediction of epileptic seizures is crucial for epilepsy patients especially those with refractory epilepsy. At present, a large number of deep learning algorithms such as Convolutional Neural Networks and Recurrent Neural Networks have been used to predict epileptic seizures and have obtained better performance than traditional machine learning methods. However, these methods usually transform the Electroencephalogram (EEG) signal into a Euclidean grid structure. The conversion suffers from loss of adjacent spatial information, which results in deep learning models requiring more storage and computational consumption in the process of information fusion after information extraction. This study proposes a general Graph Convolutional Networks (GCN) model architecture for predicting seizures to solve the problem of oversized seizure prediction models based on exploring the graph structure of EEG signals. As a graph classification task, the network architecture includes graph convolution layers that extract node features with one-hop neighbors, pooling layers that summarize abstract node features; and fully connected layers that implement classification, resulting in superior prediction performance and smaller network size. The experiment shows that the model has an average sensitivity of 96.51%, an average AUC of 0.92, and a model size of 15.5 k on 18 patients in the CHB-MIT scalp EEG dataset. Compared with traditional deep learning methods, which require a large number of parameters and computational effort and are demanding in terms of storage space and energy consumption, this method is more suitable for implementation on compact, low-power wearable devices as a standard process for building a generic low-consumption graph network model on similar biomedical signals. Furthermore, the edge features of graphs can be used to make a preliminary determination of locations and types of discharge, making it more clinically interpretable.

Hyperspectral image (HSI) classification has attracted much attention in the field of remote sensing. However, the lack of sufficient labeled training samples is a huge challenge for HSI classification. To face this challenge, we propose a semisupervised HSI classification method based on graph convolutional broad network (GCBN). First, to avoid the underfitting problem caused by the insufficient linear sparse feature representation ability of broad learning system (BLS), graph convolution operation is applied to extract nonlinear and discriminative spectral-spatial features from the original HSI to replace the linear mapping features in the traditional BLS. Second, to solve the problem of insufficient model classification ability caused by limited labeled samples, the combinatorial average method (CAM) is proposed to use valuable paired samples to generate sample expansion set for GCBN model training. Third, BLS is used to perform broad expansion on spectral-spatial features extracted by GCN and extended by CAM, which further enhances the feature representation ability. Finally, the output weights can be easily calculated by the ridge regression theory. Experimental results on three real HSI datasets demonstrate the effectiveness of our proposed GCBN.

For multimodal medical image fusion problems, most of the existing fusion approaches are based on pixel-level. However, the pixel-based fusion method tends to lose local and spatial information as the relationships between pixels are not considered appropriately, which has much influence on the quality of the fusion results. To address this issue, a region-based multimodal medical image fusion framework is proposed based on superpixel segmentation and a post-processing optimization method in this paper. In this framework, the average image of the source medical images is firstly obtained by a weighted averaging method. To effectively obtain homogeneous regions and preserve the complete information of image details, the fast linear spectral clustering(LSC) superpixel algorithm is carried out to segment the average image and get superpixel labels. For each region of the medical images, log-gabor filter(LGF) and sum modified laplacian(SML) are adopted to extract texture feature and contrast feature for the measurement of region importance. The most important regions are selected and the decision map is generated by comparison. Moreover, to get a more accurate decision map, a new post-processing optimized method based on genetic algorithm(GA) is given. A weighted strategy is applied to the extracted features and the weighting factor can be adaptively adjusted by GA. The effectiveness of the proposed fusion method is validated by conducting experiments on eight pairs of medical images from diverse modalities. In addition, seven other mainstream medical image fusion methods are adopted for comparing the performance of fusion. Experimental results in terms of qualitative and quantitative evaluation demonstrate that the proposed method can achieve state-of-the-art performance for multimodal medical image fusion problems.

This paper addresses the decentralized control issue for the fractional-order (FO) nonlinear large-scale strict-feedback systems with unmodeled dynamics. The unknown nonlinear functions are identified by fuzzy logic systems (FLSs) and the FO dynamic signals are introduced to dominate the unmodeled dynamics. Additionally, the fractional-order dynamic surface control (FODSC) design technique is introduced into the adaptive backstepping control algorithm to avoid the issue of “explosion of complexity”. Then, an adaptive fuzzy decentralized control scheme is developed via the FO Lyapunov stability criterion. It is proved that the controlled FO systems are stable and the tracking errors can converge to a small neighborhood of zero. The simulation example is provided to confirm the validity of the put forward control scheme.

In this paper, we propose an efficient algorithm to accelerate the existing Broad Learning System (BLS) algorithm for new added nodes. The existing BLS algorithm computes the output weights from the pseudoinverse with the ridge regression approximation, and updates the pseudoinverse iteratively. As a comparison, the proposed BLS algorithm computes the output weights from the inverse Cholesky factor of the Hermitian matrix in the calculation of the pseudoinverse, and updates the inverse Cholesky factor efficiently. Since the Hermitian matrix in the definition of the pseudoinverse is smaller than the pseudoinverse, the proposed BLS algorithm can reduce the computational complexity, and usually requires less than $\frac {2}{3}$ of complexities with respect to the existing BLS algorithm. Our experiments on the Modified National Institute of Standards and Technology (MNIST) dataset show that the speedups in accumulative training time and each additional training time of the proposed BLS over the existing BLS are 24.81%~ 37.99% and 36.45%~ 58.96%, respectively, and the speedup in total training time is 37.99%. In our experiments, the proposed BLS and the existing BLS both achieve the same testing accuracy when the tiny differences (≤ 0.05%) caused by the numerical errors are neglected, and the above-mentioned tiny differences and numerical errors become zeroes and ignorable, respectively, when the ridge parameter is not too small.

Recently, collaborative representation based classifiers (CRC) have shown outstanding performances in recognition tasks. The key to success of most CRC algorithms states that the testing samples can be coded well by a suitable dictionary globally, while the local knowledge between samples has not been fully considered. We observe that the representations of similar samples have a high degree of similarity. In order to take advantage of this important similarity information, this paper proposes a new local knowledge-based collaborative representation model for image classification. Specifically, certain adjacent training samples of the testing image should be determined firstly, and then the representations of these neighborhoods can be applied to guide the coefficients of the testing samples to be more discriminative. Further, we derive a robust version of the proposed method to treat the face recognition with occlusions or corruptions. Extensive experiments are carried out to show the superiority of the proposed method over other state-of-the-art classifiers on various image recognition tasks.

Recently, the robust continuous clustering (RCC) has been proposed for unsupervised data classification. The RCC algorithm integrates representation learning and clustering by seeking the balance of the distance of data between intra-cluster and inter-cluster. But the inter-cluster distance in RCC highly depend on the pairwise graph of neighbors, which are constructed by the less-expressive original data. This hampers the performance of RCC on complex epically high-dimensional data. Encouraged by the hybrid feature learning and universal approximation capabilities of the broad learning system (BLS), we first propose a broad graph-based robust continuous clustering algorithm to upgrade RCC. The proposed algorithm measures the distance of the pairwise data with the feature learned from the BLS when constructing the graph. Then to further enhance the clustering performance of the RCC on high-dimensional data, we embed the non-negative matrix factorization (NMF) into the broad graph-based RCC algorithm. By resolving the original data into the basis matrix and coefficient matrix and performing the broad graph-based RCC on the coefficient matrix, the proposed approach takes full advantages of the abundant representation from the BLS and the sparsity and interpretability of NMF coefficients. We verified the proposed algorithms on the synthetic dataset, the UCI dataset and some real-world high dimension datasets. All the empirical results show the proposed algorithms outperform the baselines and improve the clustering performance of RCC effectively.

The classification of high-dimensional data is a challenge in machine learning. Traditional classifier ensemble methods improve the diversity of classifiers through either dimensionality reduction or sample selection for high-dimensional data classification. However, these methods have several limitations: 1) dimensionality reduction methods easily cause information loss, which leads to a decrease in accuracy; 2) sample selection methods are susceptible to noise and redundant features. To address the above limitations, we propose a novel hybrid dimensionality reduction forest (HDRF) to increase the diversity of an integrated system from feature space and sample space. First, a tree-based feature selection algorithm is employed to partition effective features. Then the Bagging method is applied to obtain diverse training subsets. To fully retain and mine the important information of the unselected samples, a sample-feature based transformation process (SFTP) is proposed to generate the extended features. Since PCA can effectively reduce dimension and remove noise features, it is applied to compress the unselected features and the extended features into the new features which are compact and compensatory. Further, a novel classifier ensemble pruning framework (HDRFPF) based on HDRF is designed to remove redundant and invalid classifiers. Experimental results on 23 high-dimensional data sets verify that our method outperforms mainstream classifier ensemble methods, and the better results are obtained on 19 out of 23 datasets.

Although semi-supervised clustering ensemble methods have achieved satisfactory performance, they fail to effectively utilize the constrained knowledge such as cannot-link and must-link when generating diverse ensemble members. In addition, they ignore negative effects brought about by redundancies and noisy data. To address the above shortcomings, in this paper we propose an approach to combine multiple semi-supervised clustering solutions via adaptively regularizing the weights of clustering ensemble members, which is referred to as ARSCE. First, we generate a series of feature subspaces by randomly selecting feature without replacement to avoid the scenario where there are two identical feature subspaces. Second, we conduct feature transformation on the above obtained feature subspaces while considering the pairwise constraints to find new clustering-friendly spaces, where clustering methods are exploited to generate various clustering solutions. Finally, we design a novel fusion strategy to integrate multiple clustering solutions into a unified clustering partition, where weights are designated for each clustering ensemble member. Extensive experiments are conducted on multiple real-world benchmarks, and experimental results demonstrate the effectiveness and superiority of our proposed method ARSCE over other counterparts.

Event cameras are bio-inspired vision sensors measuring brightness changes (referred to as an `event') for each pixel independently, instead of capturing brightness images at a fixed rate using conventional cameras. Asynchronous event data mixed with noise information is challenging for event-based vision tasks. In this paper, we propose a broad learning network for object detection using the event data. The broad learning network consists of two distinct layers, a feature-node layer and an enhancement-node layer. Different to convolutional neural networks, the broad learning network can be extended by adding nodes into layers during training. We design a gradient descent algorithm to train network parameters, which creates an event-based broad learning network in an end-to-end manner. Our model outperforms state-of-the-art models, specifically, because of the small scale and increased speed displayed by our model during training. This demonstrates the superiority of event cameras towards online training and inference.

Broad learning system (BLS) is proposed as a competitor to deep neural network, which is constructed using only single hidden layer instead of multilayered structure. It also manages incremental learning with intelligible mathematical derivation by pseudoinverse. Despite its empirical success, the limitations of BLS cannot be overlooked, especially for its sensibility to the number of feature nodes. For this reason, large model is required in training, which may easily cause overfitting. In this paper, a probabilistic model called sparse Bayesian broad learning system (SBBLS) is proposed to dispose of this defect by linearly-weighting a small group of basis functions from an enormous number of candidates within Bayesian framework. Outstanding sparsity and generalization can be observed in SBBLS. More distinctively, SBBLS is capable of outputting probabilistic estimation of prediction for further decision analysis while maintaining inherent properties of BLS simultaneously. Experimental results demonstrate that the proposed SBBLS model could achieve comparable performance to BLS both in regression and classification with probabilistic interpretability.

Alzheimer's disease (AD) is a serious chronic health problem that causes great pain and loss to patients and their families. Its early and accurate diagnosis would achieve significant progress on the prevention and treatment of the disease. Magnetic Resonance Imaging (MRI) is a commonly used technique in nuclear medical diagnostics. However, it is still a challenging problem to diagnose AD, Control Normal (CN), and Mild Cognitive Impairment (MCI) because of the complex structures of MRI. In this paper, diagnosing models for MRI images are proposed to identify the various stages of AD based on the Broad Learning Systems (BLS), as well as its convolutional variants. To verify the validity of the proposed models, experiments on MRI images collected from the ADNI website are tested and evaluated. The results show that our algorithms outperform the other state-of-the-art algorithms for various tasks with better accuracy and less training times. Finally, the cross-domain learning ability of the proposed algorithms is verified on an independent AD dataset.

Unmanned merchant ships are ships that carry goods and engage in commercial activities without manual operations on board. In contrast to traditional merchant ships, unmanned merchant ships have great advantages in economy, society, and safety. However, we observe that commercial applications of unmanned ships are still at an exploratory stage. We believe that unmanned merchant ships will be widely adopted and popular in the near future. There is a need to have a good survey of current technologies, foundation, and obstacles of implementation of future unmanned merchant ships. Such a survey is beneficial to ship builders, researchers, owners, and students. Therefore, in this paper, we present a comprehensive survey of ship structure and technology, navigation, automation, algorithms, communication, Internet of Things (IOT), etc. We introduce traditional ships and analyze the role of crew and navigation operations on board. We summarize classifications, benefits, and core technologies of unmanned merchant ships. We review architecture, communication standards, security, essential technologies of IOT for unmanned merchant ships. Moreover, we introduce intelligent awareness, data fusion, applications, and E-navigation for unmanned merchant ships. We also present several future research directions at the end.

Hyperspectral images (HSI) are widely applied in numerous fields for their rich spatial and spectral information. However, in these applications, we always face the situation that the available labeled samples are limited or absent. Therefore, we propose an HSI classification method based on domain adaptation broad learning (DABL). First, according to the importance of the marginal and conditional distributions, the maximum mean discrepancy is used in mapped features to adapt these distributions between source and target domains. Meanwhile the manifold regularization is added to maintain the manifold structure of the input HSI data. Second, to further reduce the distribution difference and maintain manifold structure, the domain adaptation and manifold regularization are added to the output layer of DABL. Finally, the output weights can be easily calculated by the ridge regression theory. Experimental results on three real HSI datasets demonstrate the effectiveness of our proposed DABL.

This paper investigates a fault-tolerant control problem for the dynamic positioning of unmanned marine vehicles based on a Takagi–Sugeno (T-S) fuzzy model using an integral sliding mode scheme. First, the T-S fuzzy model of an unmanned marine vehicle is established by taking the yaw angle variable range into account. An integral sliding mode control scheme combined with the H∞ performance index is then developed to attenuate the initial influence of thruster faults and ocean disturbances. The unknown nonlinear function is approximated using a fuzzy logic system based on a representation of marine data, which provides a good tradeoff between resolution of the unknown nonlinear term approximation and computational complexity for marine engineering by adjusting the number of fuzzy logic system rules. In addition, the fault estimation information is utilized to design the sliding mode surface on the basis of an adaptive mechanism and a matrix full rank decomposition technique, which reduces conservatism. The validity of the proposed approach is finally demonstrated by an analysis of simulation results using a typical floating production vessel model.

Water surface object detection is one of the most significant tasks in autonomous driving and water surface vision applications. To date, existing public large-scale datasets collected from websites do not focus on specific scenarios. As a characteristic of these datasets, the quantity of the images and instances is also still at a low level. To accelerate the development of water surface autonomous driving, this paper proposes a large-scale, high-quality annotated benchmark dataset, named Water Surface Object Detection Dataset (WSODD), to benchmark different water surface object detection algorithms. The proposed dataset consists of 7,467 water surface images in different water environments, climate conditions, and shooting times. In addition, the dataset comprises a total of 14 common object categories and 21,911 instances. Simultaneously, more specific scenarios are focused on in WSODD. In order to find a straightforward architecture to provide good performance on WSODD, a new object detector, named CRB-Net, is proposed to serve as a baseline. In experiments, CRB-Net was compared with 16 state-of-the-art object detection methods and outperformed all of them in terms of detection precision. In this paper, we further discuss the effect of the dataset diversity (e.g., instance size, lighting conditions), training set size, and dataset details (e.g., method of categorization). Cross-dataset validation shows that WSODD significantly outperforms other relevant datasets and that the adaptability of CRB-Net is excellent.

This paper presents a novel leader-follower formation control for autonomous surface vehicles (ASVs). The dynamic model of ASV and the traditional methods of trajectory tracking are analyzed. Previous research about ASVs' formation focuses on the way of realizing trajectory tracking under conditions, such as time-delays, finite-time, and non-holonomic system. However, principles of constructing a suitable ASVs formation are often neglected. We present a novel leader-follower relation-invariable persistent formation (RIPF) control for ASVs, from which a persistent formation can be generated in any position. Obtained by using RIPF control potential function, the outputs of RIPF control are data points, which should be smoothened using broad learning system (BLS). The global leader navigates the mission trajectory, and each follower follows the RIPF trajectory to satisfy the RIPF potential function. The neural network-based adaptive dynamic surface control is introduced to solve the mission trajectory tracking problems. Environmental disturbances exist in ASV model, and BLS also can be used to approximate the disturbances. The simulation results show that the proposed generative method and control law are effective to realize the desired formation.

Although kernel fuzzy clustering can handle non-spherical clusters by mapping data to a more separable feature space, its performance is highly determined by the setting of kernels. So, the multiple kernel fuzzy clustering (MKFC) is proposed to obtain the flexibility in designing an optimal kernel from a large set of candidates. In MKFC, many predefined general kernels like Gaussian and polynomial ones are linearly aggregated and the weights of kernels are adjusted automatically. However, the performance of MKFC is greatly hampered by two noticeable problems. First, MKFC only uses predefined general kernels and pays less attention to the inherent structure of specific data. This leads to the trouble of selecting proper base kernels for different data. The second problem is the ignorance of correlations between kernels in MKFC. It results in redundant kernels being used to define the feature space. This paper solves the two problems simultaneously by introducing a new MKFC model. Based on unsupervised random forests (RFs), some data-dependent kernels are generated and combined with others to build a more representative feature space. The correlations between kernels are also calculated and inserted into the objective function of fuzzy clustering as a matrix-induced regularization to encourage the diversity in kernels. We name the new model as MKFC with unsupervised RFs kernel and matrix-induced regularization. The optimization algorithm for the new model is derived, and the experiments on benchmark datasets demonstrate its superiority over other MKFC approaches.

In this paper, the containment control problem of the second-order multi-agent systems (MASs) with general noise over directed topology is investigated. General noise, which may be the mixture of colored and white noise, is introduced to model the perturbation of MASs. Since constructing an anti-perturbed distributed controller for concerned MASs is difficult, we attend to use the perturbation tolerant character of the convex hull spanned by multiple leaders in the containment control problems of MASs. To this end, the hierarchical topology structure of MASs is used, which can largely reduce the communication loads and computational complexity. It is shown that the MASs are noise-to-state stable and the state of the MASs has an asymptotic gain in the mean square based on random differential equations (RDEs) theorem framework. Moreover, the relative hierarchical topology reconfiguration algorithm is given based on which the system can withstand stronger noise and all followers gradually converge to the convex hull formed by the leaders of the respective level. Finally, the numerical simulation is carried out to substantiate the feasibility of the proposed control theory.

Construction projects always deal with different types of risks such as financial problems, legal factors, availability of resources and other issues during the project lifecycle. According to the type, size and complexity of the project, the number and intensity of risks could be different and many projects cannot reach the project goals due to exposure to multiple risks. This study aims to propose a hybrid DEMATEL-ANP model for risk prioritization in construction projects and the originality of the work comes from its ability to consider interdependencies between risk factors. The first stage of model applied Delphi method to use experts' judgments for risk identification. The second stage used Decision-Making Trial and Evaluation Laboratory (DEMATEL) method to define the interdependencies' relative intensity among the risks. Afterwards, Analytic Network Process (ANP) method is used in the third stage to assess the relative importance of the risk factors to define risk priorities in project. A case study of oil pipeline project is reported to indicate efficiency and performance of the proposed model. The results indicated that the proposed methodology could successfully reveal the important risk factors and define the interdependencies between them in the case study. On the whole, the proposed methodology can be considered as an efficient approach for risk assessment in construction projects.

Zhouqu County is located at the intersection of two active structural belts in the east of the Qinghai-Tibet Plateau, which is a rare, high-incidence area of landslides, debris flow, and earthquakes on a global scale. The complex regional geological background, the fragile ecological environment, and the significant tectonic activities have caused great difficulties for the dynamic susceptibility assessment and prediction of landslides in the study area. Specifically, Zhouqu is a typical alpine-canyon region in geomorphology; currently there is still a lack of a landslide susceptibility assessment study for this particular type of area. Therefore, the development of landslide susceptibility mapping (LSM) in this area is of great significance for quickly grasping the regional landslide situation and formulating disaster reduction strategies. In this article, we propose a graph-represented learning algorithm named GBLS within a broad framework in order to better extract the spatially relevant characteristics of the geographical data and to quickly obtain the change pattern of landslide susceptibility according to the frequent variation (increase or decrease) of the data. Based on the broad structure, we construct a group of graph feature nodes through graph-represented learning to make better use of geometric correlation of data to upgrade the precision. The proposed method maintains the efficiency and effectiveness due to its broad structure, and even better, it is able to take advantage of incremental data to complete fast learning methodology without repeated calculation, thus avoiding time waste and massive computation consumption. Empirical results verify the excellent performance with high efficiency and generalization of GBLS on the 407 landslides in the study area inventoried by remote sensing interpretation and field investigation. Then, the landslide susceptibility map is drawn to visualize the landslide susceptibility assessment according to the result of GBLS with the highest AUC (0.982). The four most influential factors were ranked out as rainfall, NDVI, aspect, and Terrain Ruggedness Index. Our research provides a selection criterion that can be referenced for future research where GBLS is of great significance in LSM of the alpine-canyon region. It plays an important role in demonstrating and popularizing the research in the same type of landform environment. The LSM would help the government better prevent and confine the risk of landslide hazards in the alpine-canyon region of Zhouqu.

Variable-length license plate segmentation and recognition has always been a challenging barrier in the application of intelligent transportation systems. Previous approaches mainly concern fixed-length license plates, lacking adaptability for variable-length license plates. Although objection detection methods can be used to address the issue, they face a series of difficulties: cross class problem, missing detections, and recognition errors between letters and digits. To solve these problems, we propose a machine learning method that regards each character as a region of interest. It covers three parts. Firstly, we explore a transfer learning algorithm based on Faster-RCNN with InceptionV2 structure to generate candidate character regions. Secondly, a strategy of cross-class removal of character is proposed to reject the overlapped results. A mechanism of template matching and position predicting is designed to eliminate missing detections. Moreover, a twofold broad learning system is designed to identify letters and digits separately. Experiments performed on Macau license plates demonstrate that our method achieves an average 99.68% of segmentation accuracy and an average 99.19% of recognition rate, outperforming some conventional and deep learning approaches. The adaptability is expected to transfer the developed algorithm to other countries or regions.

Feature selection and ensemble learning can be used to improve the accuracy and robustness of epileptic seizure detection and classification. Unfortunately, a few studies have fully utilized feature selection and ensemble learning. In this paper, we present an adaptive hybrid feature selection-based classifier ensemble (AHFSE) for epileptic seizure classification. The AHFSE creates new sample subsets in every bootstrap using adaptive hybrid feature selection. It combines them using rank aggregation to obtain a distinguished subset of features. These new samples' subsets are then fed into a classifier. Finally, majority voting is used to complete the detection and classification tasks. The AHFSE is designed to obtain an optimized subset of features based on the different samples in every bootstrap, which have a tendency to generate different results with respect to rank aggregation. With discrete wavelet transform, the experiments based on binary and multi-class tasks show that the AHFSE performs well on the Bonn data set and improves the specificity, sensitivity, or accuracy of the selected features by combining the subsets of different feature selections to obtain new samples within the bagging process. Furthermore, the adaptive process helps the framework obtain the optimum combination of the feature selection algorithm. The AHFSE also obtains more desirable final results in several perspectives, such as: 1) compared with other feature selection methods; 2) compared with other ensemble methods; and 3) compared with other research that uses discrete wavelet transform as a preprocessing step.

By combining the broad learning and a convolutional neural network (CNN), a block-diagonal constrained multi-stage convolutional broad learning (MSCBL-BD) method is proposed for hyperspectral image (HSI) classification. Firstly, as the linear sparse feature extracted by the conventional broad learning method cannot fully characterize the complex spatial-spectral features of HSIs, we replace the linear sparse features in the mapped feature (MF) with the features extracted by the CNN to achieve more complex nonlinear mapping. Then, in the multi-layer mapping process of the CNN, information loss occurs to a certain degree. To this end, the multi-stage convolutional features (MSCFs) extracted by the CNN are expanded to obtain the multi-stage broad features (MSBFs). MSCFs and MSBFs are further spliced to obtain multi-stage convolutional broad features (MSCBFs). Additionally, in order to enhance the mutual independence between MSCBFs, a block diagonal constraint is introduced, and MSCBFs are mapped by a block diagonal matrix, so that each feature is represented linearly only by features of the same stage. Finally, the output layer weights of MSCBL-BD and the desired block-diagonal matrix are solved by the alternating direction method of multipliers. Experimental results on three popular HSI datasets demonstrate the superiority of MSCBL-BD.

Shadow detection and removal is an important task for digitized document applications. It is hard for many methods to distinguish shadow from printed text due to the high darkness similarity. In this paper, we propose a local water-filling method to remove shadows by mapping a document image into a structure of topographic surface. Firstly, we design a local water-filling approach including a flooding and effusing process to estimate the shading map, which can be used to detect umbra and penumbra. Then, the umbra is enhanced using Retinex Theory. For penumbra, we propose a binarized water-filling strategy to correct illumination distortions. Moreover, we build up a dataset called optical shadow removal (OSR dataset), which includes hundreds of shadow images. Experiments performed on OSR dataset show that our method achieves an average ErrorRatio of 0.685 with a computation time of 0.265 s to process an image size of 960×544 pixels on a desktop. The proposed method can remove the shading artifacts and outperform some state-of-the-art methods, especially for the removal of shadow boundaries.

Adopting a measure is essential in many multimedia applications. Recently, distance learning is becoming an active research problem. In fact, the distance is the natural measure for dissimilarity. Generally, a pairwise relationship between two objects in learning tasks includes two aspects: similarity and dissimilarity. The similarity measure provides different information for pairwise relationships. However, similarity learning has been paid less attention in learning problems. In this work, firstly, we propose a general framework for similarity measure learning (SML). Additionally, we define a generalized type of correlation as a similarity measure. By a set of parameters, generalized correlation provides flexibility for learning tasks. Based on this similarity measure, we present a specific algorithm under the SML framework, called correlation similarity measure learning (CSML), to learn a parameterized similarity measure over input space. A nonlinear extension version of CSML, kernel CSML, is also proposed. Particularly, we give a closed-form solution avoiding iterative search for a local optimal solution in the high-dimensional space as the previous work did. Finally, classification experiments have been performed on face databases and a handwritten digits database to demonstrate the efficiency and reliability of CSML and KCSML.

The global optimization of sensor locations and a sensitivity analysis based on the minimization of interferences due to wireless communications between sensors are studied in the presence of additive white Gaussian noise (AWGN). We used a Gram matrix approach for robust determination of sensor locations by minimizing the interferences (maximizing the signal strength) among sensors for engine health monitoring systems. In order to solve the problem of optimum placement, an iterative algorithm for maximizing the determinant of the Gram matrix is proposed and implemented. The sensitivity criterion proposed in this paper is the spectral number of the Frobenius norm of the Gram matrix associated with sensor readings. We derived the necessary conditions under which the number of sensors and the optimal sensor locations will remain unchanged when the data measured for sensitivity analysis is affected by AWGN. Our theoretical results are verified by simulations providing details concerning numerical implementations.