We present Flow-Induced Diagonal Gaussian Processes (FiD-GP), a compression framework that incorporates a compact inducing weight matrix to project a neural network’s weight uncertainty into a lower-dimensional subspace. Critically, FiD-GP relies on normalising flow variational posterior and spectral regularisations to augment its expressiveness and align the inducing subspace with feature-gradient geometry through a numerically stable projection mechanism objective. Furthermore, we demonstrate how the prediction framework in FiD-GP can help to design a single pass projection for Out-of-Distribution (OoD) detection. Our analysis shows that FiD-GP improves uncertainty estimation ability on various tasks compared with SVGP-based baselines, satisfies tight spectral residual bounds with theoretically guaranteed OoD detection, and significantly compresses the neural network’s storage requirements at the cost of increased inference computation dependent on the number of inducing weights employed. Specifically, in a comprehensive empirical study spanning regression, image classification, semantic segmentation, and Out-of-Distribution detection benchmarks, it significantly cuts Bayesian training cost, compresses parameters by roughly 51%, reduces model size by about 75%, and matches state-of-the-art accuracy and uncertainty estimation.

With the advent of the Industry 4.0 era, Federated Learning (FL) provides robust data privacy protection for smart manufacturing and supply chain optimization, while facilitating collaborative intelligent optimization across enterprises and devices. However, the complex and overparameterized deep neural networks used in FL result in significant computational overhead for Industrial Internet of Things (IIoT) devices, leading to low energy efficiency and hindering the practical deployment of FL on IIoT devices. Moreover, the widespread data and device heterogeneity in the IIoT exacerbates the decrease in energy efficiency caused by inconsistent computational efficiency across nodes. This article proposes an energy-efficient dynamic model pruning method for FL, named EDPrune-FL, to address the aforementioned challenges. Compared to existing methods, this approach offers greater flexibility and efficiency by utilizing a dynamic pruning rate allocation mechanism. This mechanism updates the pruning rate for each participating client in every communication round, allowing the pruning upper bound to adapt to the varying importance of different learning stages in FL. EDPrune-FL ensures the global model’s performance while reducing the training energy consumption of clients in heterogeneous environments. To guarantee that dynamic pruning maintains the stability and effectiveness of the model in heterogeneous environments, we also demonstrated the convergence of EDPrune-FL and discussed the relationship between pruning rates and convergence, providing a qualitative analysis. Experimental results demonstrate that our method outperforms the state-of-the-art technique across four real-world datasets. With tests conducted on 100 clients, our approach reduces energy consumption by 10% while maintaining comparable accuracy.

While offering a principled framework for uncertainty quantification in deep learning, the employment of Bayesian Neural Networks (BNNs) is still constrained by their increased computational requirements and the convergence difficulties when training very deep, state-of-the-art architectures. In this work, We reinterpret weight-sharing quantization techniques from a stochastic perspective in the context of training and inference with Bayesian Neural Networks (BNNs). Specifically, we leverage 2D-adaptive Gaussian distributions, Wasserstein distance estimations, and alpha-blending to encode the stochastic behavior of a BNN in a lower-dimensional, soft Gaussian representation. Through extensive empirical investigation, we demonstrate that our approach significantly reduces the computational overhead inherent in Bayesian learning by several orders of magnitude, enabling efficient Bayesian training of large-scale models, such as ResNet-101 and Vision Transformer (VIT). On various computer vision benchmarks—including CIFAR-10, CIFAR-100, and ImageNet1k—our approach compresses model parameters by approximately 50$\times$ and reduces model size by 75% while achieving accuracy and uncertainty estimations comparable to state-of-the-art.

Federated learning (FL) has emerged as a pivotal collaborative machine learning framework, enabling privacy-preserving analytics for smart city applications using distributed data from Internet of Things (IoT) devices. However, the inherent data heterogeneity that arises from diverse geographical and environmental factors poses significant challenges to the effectiveness of FL-based models. To address these challenges, this paper introduces a novel Prototype-Based FL framework for cross-domain object extraction in heterogeneous remote sensing images. The proposed framework employs multiple vectors to represent class prototypes for capturing the intricate intra-class variations and mitigating the adverse effects of non-identically distributed (non-IID) data across clients. Furthermore, we adopt a distance-based classification method to reduce classification errors. Additionally, we propose a Prototype-Anchored Metric Learning approach to minimize intra-class variance and enhance inter-class separability, which can facilitate the alignment of feature representations across heterogeneous datasets. The proposed method improves the coherence and stability of feature spaces in federated settings and enhances the global model’s generalization capabilities for complex urban monitoring tasks. Extensive experiments on three distinct remote sensing datasets(including infrastructure and disaster) demonstrate that the proposed method significantly outperforms state-of-the-art FL-based approaches in urban monitoring accuracy and robustness. The code is available at

Abstract Net primary productivity (NPP) is essential for sustainable resource management and conservation, and it serves as a primary monitoring target in smart forestry systems. The predominant method for NPP inversion involves data collection through terrestrial and satellite sensing systems, followed by parameter estimation using models such as the Carnegie‐Ames‐Stanford Approach (CASA). While this method benefits from low costs and extensive monitoring capabilities, the data derived from multisource sensing systems display varied spatial scale characteristics, and the NPP inversion models cannot detect the impact of data heterogeneity on the outcomes sensitively, reducing the accuracy of fine‐grained NPP inversion. Therefore, this paper proposes a modular system for fine‐grained data processing and NPP inversion. Regarding data processing, a two‐stage spatial‐spectral fusion model based on non‐negative matrix factorization (NMF) is proposed to enhance the spatial resolution of remote sensing data. A spatial interpolation model based on stacking generalization with residual correction is introduced to get raster meteorological data compatible with remote sensing images. Furthermore, we optimize the CASA model with the kernel method to enhance model sensitivity and enrich the spatial details of the inversion results with high resolution. Through validation using real datasets, the proposed fusion and interpolation models have significant advantages over mainstream methods. Furthermore, the correlation coefficient () between the estimated NPP using our improved inversion model and the field‐measured NPP is 0.69, demonstrating the feasibility of this platform in detailed forest NPP monitoring tasks.

While transformers are powerful neural network architectures for feature learning, current Transformer-based approaches for semantic segmentation of high-resolution remote sensing images (HRRSIs) struggle with the extraction of local semantic features. To address this issue, we incorporate a hypergraph into the Transformer. Hypergraph-based methods are proficient at discovering high-order correlations within limited-scale data, extracting pertinent representations to enhance the Transformer’s learning capabilities. We also propose dual pooling and feature aggregation modules (FAMs), inspired by the adaptive pooling’s potent local modeling capabilities, to additionally extract fine-grained features from HRRSIs. In particular, we conceive a hypergraph BiFormer (HGBT) based on these three proposed modules along with a BiFormer backbone. HGBT has the potential to learn general latent features as well as generate high-order representations of HRRSIs by modeling correlations of multiscale features and local topology within an entirely nonlinear space, leading to the aggregation of features in a compact and localized manner, enhancing the model’s ability to capture detailed variations within small areas. We validate our approach through extensive experiments on ISPRS Vaihingen and Potsdam datasets, where HGBT attains mean intersection over union (mIoU) of 83.71% and 87.88%, respectively. Both quantitative and qualitative assessments underscore the dominance of HGBT. Our code will be accessible at:https://github.com/ZhangIceNight/HGBFormer.

Accurate extraction of building vector boundaries holds paramount importance within the domains of urban planning and Geographic Information Systems (GIS), providing indispensable support for urban construction endeavors and resource management initiatives. CNNs, while proficient in local feature extraction, often falter in capturing holistic, global image characteristics. Transformers excel in contextual feature comprehension but demand substantial computational resources and parameterization, impeding practical deployment. To address these challenges, this paper introduces an innovative computational operator known as G-Swap, which integrates Gaussian-distance-based feature correlation considerations, thereby significantly augmenting contextual comprehension within the computational framework. Additionally, a universal architecture for boundary vector extraction is proposed in this paper, comprising three primary components: 1) an Enhanced Backbone, integrating the G-Swap operator to enhance the backbone while bolstering model expressiveness; 2) a Decoder module, tasked with discriminating corner and edge features; and 3) a Two-branch Detection Head. Empirical experiments conducted on the Vectorizing World Building Dataset (VWB) underscore the model’s superior performance. Our G-Swap achieved F1 scores of 91.2% for vertices and 80.1% for edges, surpassing the previous state-of-the-art by 2.1% and 2.0% respectively.

Hyperspectral images capture numerous narrow spectral bands to provide detailed information to identify and locate targets, making them highly suitable for anomaly detection tasks. In recent years, deep learning techniques have demonstrated impressive capabilities and prospects in hyperspectral anomaly detection (HAD), primarily relying on multilayer perceptrons (MLPs) and convolutional neural networks (CNNs) to extract and represent nonlinear features. However, MLPs and CNNs often require deeper network architectures when dealing with complex high-dimensional data, resulting in a constrained generalization and limited representation of features. To address this issue, and inspired by the recent Kolmogorov-Arnold network (KAN), this article introduces a novel asymmetric convolutional autoencoder (AE) network by integrating KAN and CNN, namedKACNet. Specifically, we design a spectral KAN block in the convolutional encoder and a spatial KAN block in the convolutional decoder, to simultaneously enhance the feature extraction and characterization capabilities of the network. Furthermore, to effectively utilize the limited prior information, a weight initialization mechanism based on hierarchical density-based spatial clustering of applications with noise (HDBSCAN) is developed to boost the background recovery. By combining KAN, CNN, and HDBSCAN, the proposed integration enhances the interpretability and reliability of HAD. Extensive experiments are conducted on six public datasets, demonstrating that the KAN poses remarkable performance on background reconstruction, particularly, the proposedKACNetsignificantly outperforms the other state-of-the-art methods.

Effective forest tree species (TS) classification is critical for various application domains such as forest management, biodiversity conservation, and ecological research. However, existing studies on TS classification predominantly rely on high-cost and processing-intensive hyperspectral data, which limits practical applications on large scales. In this work, we focus on investigating the potential of cost-effective unmanned aerial vehicle (UAV) RGB images for TS classification in heterogeneous forests and propose a method that fully leverages the rich spatial, semantic, and visible spectral information of UAV RGB images. We propose an RSVMamba model, which incorporates improved visual state-space (VSS) blocks and an AutoDownsampling module to enhance accuracy and stability while paying particular attention to small objects in sparse spatial locations. The model achieves linear computational complexity while retaining the global receptive field, making it particularly suitable for processing high spatial-resolution images. Additionally, we collected UAV RGB images covering$40~\text {km}^{2}$of subtropical forest in southern China. A meticulous evaluation of this data shows that our method achieves an overall accuracy (OA) of 84.28% for eight TS, dead trees, and other broadleaves. We verify the superiority of our method through a series of comparative experiments on the collected and benchmark datasets. Our results affirm the usefulness of single-temporal UAV RGB images for TS classification in heterogeneous forest environments. Furthermore, the proposed method bridges the gap between data accessibility and precision in TS classification, broadening the boundaries of single-temporal UAV RGB images for practical forestry applications and providing a more cost-effective and time-flexible solution for this problem.

Hyperspectral imaging is a valuable technique for accurately classifying materials because of the abundance of spectral information and high resolution it provides. However, the characteristics of Hyperspectral Imaging, such as high-dimensional features and information redundancy, pose significant challenges to data processing. Traditional dimensionality reduction methods often have information loss, high computational complexity, and easy to ignore the strong correlation between HSI bands when dealing with the HSI data. Although other methods can achieve satisfactory classification performance, they do not consider the dimensionality reduction of HSI, and they focus on the model performance, which limits further improvement in classification performance. This article proposes a transformer-based framework called “SpectrumRecombineFormer” (SRF), which is composed of two key modules, namely “Spatial–Spectral Recombination” (SSRC) and “Cross-Layer Fusion” (CF). The SSRC is capable of utilizing both adjacent and non-adjacent spectrums to generate the spatial-sequential perceptive representations, which alleviate the effect of the strong correlation between HSI bands. The CF can avoid the loss of information during the feed-forward procedure among layers. Extensive experiments on five existing datasets (widely adopted Indian Pines, Houston2013, Pavia University, Salinas, and KSC) demonstrate the capability of our proposed method to address the above-mentioned challenges. Both quantitative and qualitative experimental ablation studies, including visualization results, reveal that the proposed SRF method can successfully and efficiently classify HSIs and surpass the other state-of-the-art methods. For access to the source code, please visit https://github.com/kangpeilun/SRF-HSI-Classification-master .

Unsupervised hashing methods have gained wide-spread popularity for remote sensing (RS) image retrieval due to their high efficiency. Existing methods heavily rely on similarity matrix generated by pre-trained models as supervised signals. However, such pre-trained models obtained from natural images fail to comprehensively extract features in RS images, yielding unreliable similarity relationships. Considering complex features in RS images, we propose a novel adaptive global-local fusion network based deep unsupervised hashing (AFDUH) method. The advantages of AFDUH lie in the use of large kernel convolution and bi-level routing attention mechanism for learning local and global features simultaneously. AFDUH fuses these features under different resolutions in an interactive fashion to deduce high-quality similarity matrix based on contrastive learning. Besides, we embed a sample selection strategy in AFDUH, which can filter out unreliable supervised signals to further improve retrieval accuracy. Extensive experiments on two RS datasets demonstrate that AFDUH outperforms the state-of-the-art baselines.

Previous studies have demonstrated the importance of combining infrared defect detection methods with UAV inspection to promote the development of solar energy. The defect detection frequently encounters difficulties such as small objects, easy confusion between defects and environment, and uneven sample number, resulting in a low detection accuracy. To solve these problems, this paper proposed a model BT-YOLO to detect infrared photovoltaic images captured by UAV based on the YOLOv5 network. Firstly, BiFormer is a visual transformer structure embedded into the backbone network of the model, better preserving fine-grained details. Secondly, to achieve more accurate classification and finer localization, the feature encoding of classification and localization is decoded separately in the detection head. Finally, the regression loss is calculated using Wise-IoU instead of GIoU, thereby allowing the model to note the loss of ordinary-quality anchor boxes. The results demonstrate that the improved model improves the mAP performance by 5.1%.

Abstract Lesion segmentation is a fundamental task in medical image processing, often facing the challenge of subtle lesions. It is important to detect these lesions, even though they can be difficult to identify. Convolutional neural networks, an effective method in medical image processing, often ignore the relationship between lesions, leading to topological errors during training. To tackle topological errors, move is made from pixel‐level to hypergraph representations. Hypergraphs can model lesions as vertices connected by hyperedges, capturing the topology between lesions. This paper introduces a novel dynamic hypergraph learning strategy called DHLS. DHLS allows for the dynamic construction of hypergraphs contingent upon input vertex variations. A hypergraph global‐aware segmentation network, termed HGSNet, is further proposed. HGSNet can capture the key high‐order structure information, which is able to enhance global topology expression. Additionally, a composite loss function is introduced. The function emphasizes the global aspect and the boundary of segmentation regions. The experimental setup compared HGSNet with other advanced models on medical image datasets from various organs. The results demonstrate that HGSNet outperforms other models and achieves state‐of‐the‐art performance on three public datasets.

The building planar graph reconstruction, a.k.a. footprint reconstruction, which lies in the domain of computer vision and geoinformatics, has been long afflicted with the challenge of redundant parameters in conventional convolutional models. Therefore, in this letter, we proposed an advanced and adaptive shift architecture, the “Switch” operator, which incorporates nonexponential growth parameters while retaining analogous functionalities to integrate local feature spatial information, resembling a high-dimensional convolution operation. The “Switch” operator, cross-channel operation, architecture implements the XOR operation to exchange adjacent or diagonal features alternately and then blends alternating channels through a$1 \times 1$convolution operation to consolidate information from different channels. The SwitchNN architecture, on the other hand, incorporates a group-based parameter-sharing mechanism inspired by the convolutional neural network (CNN) process, thereby significantly reducing the number of parameters. We validated our proposed approach through experiments on the SpaceNet corpus. Our method achieves 82.9% precision, 79.8% F1 score, 83.7% recall, and an MAE of 0.018 with the FLOPs of 24.83 G, outperforming existing state-of-the-art methods, such as Roof-Former and HEAT. These results demonstrate the effectiveness of this innovative architecture in building planar graph reconstruction from 2-D building images.

Cloud data centers (CDCs) have been used as the basic platforms for data storage in industrial scenarios such as smart manufacturing. However, a lack of effective data storage schemes exacerbates reading latency and replicas' inconsistency in the machine tools of smart factories. In this article, we propose a full-replicas scheme (FRS) to attain the low-latency reading and high data consistency required in smart manufacturing. First, inspired by the susceptible–infectious–recovered epidemic model, the network bandwidth usage generated by the FRS is adjusted by the targeted immunization principle. Then, the final breakout rate is derived as a function of the immunization rate, which can reduce the complexity of target immunization implementation in scale-free networks. Finally, the experimental results confirm our theoretical analysis and show that the FRS provides strong consistency with lower client-side reading latency.

With the rapid development of the Internet of Things (IoT), massive terminals and emerging applications bring a large amount of data. As an essential prerequisite for mining potential value from these data, data sharing is crucial and getting more and more attention. However, security and privacy concerns, and the lack of effective incentive mechanisms in the decentralized environment hinder the data owners from sharing their data. In this article, we propose a federated learning (FL) and blockchain-based privacy-preserving data sharing system, which solve the privacy leakage problem of FL and the scalability problem of blockchain by their technical complementarity. Considering the resource shortage and the heterogeneity of terminals, we first design a cross-layer architecture by exploiting the cloud–edge–terminal collaboration, and innovatively propose differential data sharing by dividing the providers into origin data providers and model providers. Then, we design a targeted incentive mechanism to maximize the utility of requesters and two types of data providers by formulating it into a two-stage Stackelberg game. Finally, a gradient-based algorithm is designed to get the optimal solution. Theoretical analysis and numerical simulations show that the proposed data-sharing system could eliminate privacy concerns and motivate more participants to share data. With 500 nodes, the differentiated data sharing scheme (DASC) is 1.72 s faster than the shared model scheme (SMC) and 2.59 s faster than SDC. In terms of utility of the requester, DASC is$2.0 \times {10^{3}}$higher than SDC, and 9.27 higher than SMC in average utility of providers.

Numerous web services with the same function but different service qualities are constantly emerging on the network. Optimizing web service composition based on multiple candidate services sets an urgent problem in the service composition neighborhood. This paper modifies the traditional Firefly algorithm and adds exchange and mutation mechanisms to optimize the Web service composition efficiently in multiple candidate service sets. Meanwhile, it discretizes the continuous space of its solution set and better adapts to the service composition optimization problem. Experimental results show that compared with the GA, IA, SA, ACO, FACO, and EFACO algorithms, this algorithm has better optimization performance, faster speed, and higher energy efficiency for solving service composition optimization problems in the case of large-scale data. The higher the combined complexity of the solution, the stronger the performance compared to other algorithms. It can better deal with the increasingly complex situation of Web service composition problems.

Remote-sensing (RS) images with high spatial and temporal resolutions play a significant role in monitoring periodic landscape changes for earth observation science. To enrich RS images, spatiotemporal fusion (STF) is considered a promising approach. The key challenge in the current STF-based methods is the requirement for large-scale data. In this work, we propose a deep-learning-based method called spatiotemporal fusion multilayer perceptron (StfMLP) to tackle this challenge. First, our method focuses on the given data in the manner of transductive learning. Second, we propose a designed multilayer perceptron (MLP) model to capture the time dependency and consistency among the input images. Consequently, StfMLP is capable of simultaneously achieving more accurate fusion and requiring a small-scale of data. We conduct extensive experiments on two widely adopted public datasets, namely Coleambally irrigation area (CIA) and the lower Gwydir catchment (LGC). The experimental results demonstrate that the proposed method outperforms the state-of-the-art methods effectively. Code, trained model, and cropped images are available online ( https://github.com/luhailaing-max/StfMLP-master ).

The smart city system, which is a type of enterprise management system (EMS), automatically manages cities and schedules resources efficiently based on spatial data generated by devices, such as the Internet of Things and mobile. However, with the increasing deployment of technologies, including sensor and location-based services, their ever-growing spatial data are no longer managed efficiently by traditional EMS. To overcome this issue, we present SeFrame, which is aspatiallyenabledframework for improving the efficiency of smart city EMS based on a distributed architecture. The framework supports a set of spatial queries, including: The range query, k-nearest neighbors query, and spatial join query. It benefits greatly from using the buffer-enabled partition method to eliminate duplicate results. In each partition, the local index based on combination of the quad-tree and grid index (CQG) significantly improves the spatial query efficiency in memory. CQG manages complex spatial objects, including a point, polygon, and polyline. By taking full advantage of the local index, SeFrame accesses skewed spatial data in constant time. In experiments, we demonstrated that the proposed method delivered superior performance in terms of scalability and query efficiency, in most cases.

As an effective method to increase the computing capability of vehicles, vehicle-to-vehicle (V2V) assisted vehicular edge computing (VEC) has great potential to reduce infrastructure spending and better adapt to mobility. However, its feasibility depends heavily on the sharing willingness, how to incentive selfish vehicles in such decentralized architecture is a vital problem. In this paper, we jointly consider the pricing strategy and the users’ concerns about security and privacy to incentive more participants. We first construct a P2P resource trading system based on consortium blockchain to build trust between strange vehicles and guarantee transaction security and user privacy without an authority center. To overcome the resource constraint on blockchain deployment and enhance the scalability of blockchain, the proposed system is built on edge-terminal architecture and improves the consistency algorithm. In addition, the V2V trading process is formalized as a two-stage Stackelberg game model to maximize the utility of both requesters and providers. The optimal pricing and trading volume strategy are derived from efficient optimization algorithms. Finally, we conduct a security analysis to show the performance of the trading process in terms of security and privacy. Numerical simulations show the effectiveness of the proposed strategy to motivate more participants.

Abstract Epilepsy is a common mental disorder that affects about 70 million people worldwide. Epileptic electroencephalogram (EEG) signal, an important means to judge epileptic seizure, needs neurologists' prior knowledge to mark manually. This marking method is time‐consuming and laborious. Currently, the existing automated diagnosis methods have achieved good results on one benchmark EEG dataset, most of which can achieve accuracy of more than 0.95. However, the method has limitations on the dataset, and the accuracy of the diagnosis results on another new dataset drops sharply to nearly 0.5. Aiming at the existing EEG signal diagnosis lacks stability and generalization ability, this paper proposed a multilayer‐weighted integrated self‐learning algorithm for different classifiers. For this algorithm, weighted voting was first conducted on the the diagnostic results by different classifiers to obtain a result, which was weighted again to produce the final diagnostic results. This algorithm improves the problem that the traditional self‐learning algorithm is greatly affected by data noise, which shows a strong stability in different data sets and in clinical epileptic EEG signal data detection, so as to reduce the workload of neurologists and provide support and assistance for the diagnosis and treatment of epilepsy. The experiment result shows that the algorithm can improve the stability and reliability of EEG automatic diagnosis of epilepsy. The accuracy and AUC area of its classification in two different public data sets and clinical data can reach 0.80 to 0.95.

Abstract High resolution remote sensing image cloud removal can bring a lot of convenience for human activities. However, the existing cloud removal algorithms have a variety of disadvantages. First of all, they have the disadvantages of long computing time and large consumption of computing resources. Secondly, the effect of recovery needs to be improved. In order to improve the above two points, a near real‐time effective algorithm is proposed, namely MSAR‐Defognet (multiple scale attention residual network using for cloud remove), which consumes less computing power and space and has superior cloud removal effect. On the one hand, several different large‐scale filters are chosen to extract the weak information effectively, while can save the computing power and shorten the image processing time. On the other hand, the fine‐grained convolution residual block with channel attention mechanism is used to enhance the network's ability to extract cloud features. In addition, a data set which is closer to the real cloud shape and has higher richness to train the cloud removal network, so that the parameters obtained by training have stronger robustness and can adaptively remove clouds with different thickness. Experiments show that, compared with other advanced network models, the network not only has the advantage of fast processing speed, but also has better image restoration effect in high‐resolution remote sensing image restoration. It can meet the requirements of many hard real‐time tasks, so that remote sensing images can play a greater value for human activities.

Deep unsupervised hashing methods are gaining attention in the field of remote sensing (RS) image retrieval due to the rapid growth in the volume of unlabeled RS data. Most previous unsupervised hashing research used only natural image-based pre-trained models to generate label matrices; however, this method cannot capture the semantic information of RS images well and limits the accuracy of retrieval. To solve this problem, the authors propose a deep unsupervised weighted hashing (DUWH) model that uses a similarity matrix updating strategy based on a weighted similarity structure to achieve the mutual optimization of the similarity matrix and hash network. The authors devise a novel combinatorial loss function to improve the hash performance that can be used to obtain higher quality hash codes by assigning different weights to the sample pairs with different difficulties. Experiments were conducted on two RS datasets to verify the excellent performance of the proposed method.

Compared with traditional images, multispectral images (MSIs) contain more spectral bands and higher data dimensions. The existing MSI classification model has high computational complexity and consumes a lot of computing resources. In this letter, we propose a lightweight multispectral classification method named CABNN based on binary neural networks (BNNs) to effectively have a trade-off between model performance and computational cost. First, we modify and binarize the MobileNetV1 network and add almost computation-free shortcuts to enhance the expressive capability. Secondly, since the BNN is sensitive to the distribution of activation functions, we introduce RPReLU with learnable coefficients to automatically adjust activation distribution at almost no extra cost. Lastly, considering that MSIs have multiple channels, we utilize an efficient channel attention (ECA) module to assign different weights to each channel to concentrate on crucial features and suppress insignificant features. We conduct experiments on four public MSI datasets, including NaSC-TG2, EuroSAT, GID Fine land-cover classification, and UC Merced Land Use. Extensive experiments demonstrate that the proposed CABNN has higher efficiency and better comprehensive performance than the state-of-the-art methods across the board.

Hyperspectral image (HSI) registers hundreds of spectral bands, whose intraclass variability and interclass similarity are resourceful information to be mined. Intraclass variability reflects the nonuniform and redundancy of the spatial and semantic features extracted from HSI. Interclass similarity represents the inherent relationship between adjacent features and snapshots. Existing models extract the superficial correlation representation for HSI to tackle the classification task but fail to embed the interclass and intraclass correlations due to these models’ intrinsic bottlenecks. Confronting the challenges of capturing interrelation for complex data in practice, we propose a Context-Aware Attentional Graph U-Net (CAGU) to improve these two modes of representation, which is more flexible in feature enhancement. In this method, attentional Graph U-Net is capable of extracting the intraclass embeddings within a non-Euclidean space by combining similar distributing feature vertices. The gated recurrent unit (GRU) is another critical component of our model to capture the context-aware dynamic interclass embeddings. Extensive experiments demonstrate that our model can efficiently outperform state-of-the-art methods across-the-board on five wide-adopted public data sets, namely, Pavia University, Indian Pines, Salinas Scene-show, Houston 2013, and Houston 2018, on par with the same scale of model parameters.

Hyperspectral images (HSIs) have significant applications in various domains, since they register numerous semantic and spatial information in the spectral band with spatial variability of spectral signatures. Two critical challenges in identifying pixels of the HSI are, respectively, representing the correlated information among the local and global, as well as the abundant parameters of the model. To tackle this challenge, we propose a multi-scale U-shape multi-layer perceptron (MUMLP) a model consisting of the designed multi-scale channel (MSC) block and the U-shape multi-layer perceptron (UMLP) structure. MSC transforms the channel dimension and mixes spectral band feature to embed the deep-level representation adequately. UMLP is designed by the encoder–decoder structure with multi-layer perceptron layers, which is capable of compressing the large-scale parameters. Extensive experiments are conducted to demonstrate that our model can outperform state-of-the-art methods across the board on three wide-adopted public datasets, namely Pavia University (PaviaU), Houston 2013, and Houston 2018.

The ubiquitous deployment of 5G New Radio (5G NR) stimulates Unmanned Aircraft Systems (UAS) swarm networking to evolve to achieve more imminent progress. The heterogeneous collaboration between UAS swarm enhances the complexity and the efficiency of mission complement that requires robustness, flexibility, and sustainability of throughput in UAS swarm networking. The conventional approaches mainly are based on the hierarchical architectures that are limited to satisfy the challenges of UAS swarm with high dynamics on a large scale. In this paper, we propose an optimal cell wall paradigm to enhance the throughput in heterogeneous UAS swarm networking. With the weight adjustment of each link, we map the optimization into a polyhedron scheduling problem and formula the problem into Max-min Throughput Fair Scheduling (MTFS). Further, we propose a max-min throughput algorithm to optimize the minimum throughput of cell wall paradigm. With the optimal max-min throughput, we optimize the schedule with edge-coloring to achieve global MTFS solving. The normalized MTFS shows our algorithm can achieve over 40% improvement of MTFS globally. In terms of MTFS solving, our algorithms have promising potential to improve the throughput and mitigate the incidents for multiple beams enabling of UAS in cell wall communication. With the throughput enhancement, the advanced aerial mobility of UAS swarm networking can be escalated on a large scale.

In the area of geographic information processing, there are few researches on geographic text classification. However, the application of this task in Chinese is relatively rare. In our work, we intend to implement a method to extract text containing geographical entities from a large number of network texts. The geographic information in these texts is of great practical significance to transportation, urban and rural planning, disaster relief, and other fields. We use the method of graph convolutional neural network with attention mechanism to achieve this function. Graph attention networks (GAT) is an improvement of graph convolutional neural networks (GCN). Compared with GCN, the advantage of GAT is that the attention mechanism is proposed to weight the sum of the characteristics of adjacent vertices. In addition, We construct a Chinese dataset containing geographical classification from multiple datasets of Chinese text classification. The Macro-F Score of the geoGAT we used reached 95% on the new Chinese dataset.

Semantic segmentation is a fundamental task extensively used in the analysis of high-resolution aerial images. Due to the objects with various scales widely appearing in high-resolution aerial images, the fixed square receptive field in most existing DCNNs cannot work well and usually leads to unexpected predictions. To alleviate this problem, we propose a light-weight scale-aware module (SWD), which is end-to-end differentiable and can be embedded in most existing networks. In our module, we employ the re-sampling scheme to make each element of convolutional patches adjust its position, which explicitly adjusts the receptive field size to fit different scales of target objects. Further, considering re-sampled feature maps as weighted maps implicitly introduces spatial attention mechanism. As a result, with only 0. 2M additional parameters, the network embedded with our module can automatically adjust its receptive field to better recognize objects in various scales. In the experiment, we evaluate our method on the ISPRS Vaihingen Dataset, especially the analysis of buildings category, which usually in different scales. We further compare it to the spatial attention mechanism and mainstream networks that utilize multi-scale information. The experimental results and comprehensive analysis demonstrate the effectiveness and efficiency of our proposed method.

Summary In the era of edge computing, real‐time data preprocessing on the edge node has the potential to improve computational efficiency and data accuracy. However, a significant challenge is private data disclosure, particularly in the case of location‐based services. To address this challenge, in this paper, by leveraging differential privacy, we propose a privacy‐aware framework for mobile edge computing called MEPA to protect the location privacy in which the edge node is regarded as an anonymous central server. The proposed framework can provide computing services without deploying special infrastructure. To be specific, in order to solve the problem of constrained computing resources in the edge nodes, the algorithm of Quadtree Differential Privacy based on Hilbert curve division (QTDP‐H) two‐dimensional spatial data query transmission is proposed. First, a noise quadtree is established and the privacy budget is divided according to the tree level. Then, the constructed quadtree is represented by quanternary, so that the partition based on Hilbert curve can be established and the two‐dimensional data in the area can be converted into one‐dimensional, which can greatly improve the retrieval efficiency. The effectiveness of the proposed algorithm in terms of time complexity and retrieval accuracy has been verified by extensive experimental results. Compared with traditional methods of (D,ε) − LP, the average runtime can be reduced by 15%‐20%, and the average relative error is reduced by 20%.

The traditional method is used to deal with massive remote sensing data stored in low efficiency and poor scalability. This article presents a parallel processing method based on MapReduce and HBase. The filling of remote sensing images by the Hilbert curve makes the MapReduce method construct pyramids in parallel to reduce network communication between nodes. Then, the authors design a massive remote sensing data storage model composed of metadata storage model, index structure and filter column family. Finally, this article uses MapReduce frameworks to realize pyramid construction, storage and query of remote sensing data. The experimental results show that this method can effectively improve the speed of data writing and querying, and has good scalability.

With the development of network communication, a 1000‐fold increase in traffic demand from 4G to 5G, it is critical to provide efficient and fast spatial data access interface for applications in mobile environment. In view of the low I/O efficiency and high latency of existing methods, this paper presents a memory‐based spatial data query method that uses the distributed memory file system Alluxio to store data and build a two‐level index based on the Alluxio key‐value structure; moreover, it aims to solve the problem of low efficiency of traditional method; according to the characteristics of Spark computing framework, a data input format for spatial data query is proposed, which can selectively read the file data and reduce the data I/O. The comparative experiments show that the memory‐based file system Alluxio has better I/O performance than the disk file system; compared with the traditional distributed query method, the method we proposed reduces the retrieval time greatly.