In this paper, channel estimation (CE) for up-link hybrid-field communications involving multiple Internet of Things (IoT) devices assisted by an active intelligent reflecting surface (IRS) is investigated. Firstly, to reduce the complexity of near-field (NF) channel modeling and estimation between IoT devices and active IRS, a sub-blocking strategy for active IRS is proposed. Specifically, the entire active IRS is divided into multiple smaller sub-blocks, so that IoT devices are located in the far-field (FF) region of each sub-block, while also being located in the NF region of the entire active IRS. This strategy significantly simplifies the channel model and reduces the parameter estimation dimension by decoupling the high-dimensional NF channel parameter space into low dimensional FF sub channels. Subsequently, the relationship between channel approximation error and CE error with respect to the number of sub-blocks is derived, and the optimal number of sub-blocks is solved based on the criterion of minimizing the total error. In addition, considering that the amplification capability of active IRS requires power consumption, a closed-form expression for the optimal power allocation factor is derived. To further reduce the pilot overhead, a lightweight CE algorithm based on convolutional autoencoder (CAE) and multi-head attention mechanism, called CAEformer, is designed. The Cramér-Rao lower bound is derived to evaluate the proposed algorithm’s performance. Finally, simulation results demonstrate the proposed CAEformer network significantly outperforms the conventional least square and minimum mean square error scheme in terms of estimation accuracy.

Correspondence pruning aims to identify inliers from an initial set of correspondences with a low inlier ratio. Current Graph Neural Networks (GNNs) based correspondence pruning approaches suffer from feature over-smoothing during information propagation, making it difficult to distinguish inliers from outliers. In addition, Transformer-based methods can model long-range dependencies, but their quadratic complexity limits computational efficiency. To address these issues, we propose MatchMamba, a dual-view correspondence pruning network based on a selective state space model, Mamba. MatchMamba combines the strengths of GNNs and Mamba, enhancing local feature extraction while modeling global context with appropriate complexity. Specifically, to overcome Mamba’s limitations in correspondence pruning, such as the lack of local context and unidirectional modeling, we introduce the Cluster Sampling Spatial Mamba (CSSM) block and Correspondence Flip Bidirectional Mamba (CFBM) block. CSSM captures fine-grained local context through the implicit soft assignment and mitigates GNN’s over-smoothing using Mamba’s selective mechanism. CFBM block leverages Mamba’s efficient long-sequence modeling by constructing a pseudo-sequential structure through clustering. It applies forward and backward scanning to enable each correspondence to fully capture contextual information from others, achieving global context modeling with appropriate computational cost. Extensive experiments demonstrate that MatchMamba outperforms current state-of-the-art methods on several challenging tasks. The code is available at https://github.com/Mrwyb/MatchMamba.

The accuracy and stability of pathology image segmentation have become critical factors in clinical applications such as cancer screening and tumor grading. However, the presence of complex local structures, uncertain regions, and subtle morphological variations in pathological images continues to pose significant challenges. Most existing feature fusion approaches rely on the simplistic aggregation of extracted features, neglecting the unique characteristics and relative importance of distinct feature representations, which ultimately limits their potential to enhance model performance. To address these issues, we propose a Gestalt-Inspired Feature Integration Network (GeNet), a novel architecture inspired by Gestalt theory that mirrors the human visual system's ability to derive holistic understanding from partial information. Embracing the principle that 'the whole is greater than the sum of its parts,' GeNet introduces a mechanism to synergistically leverage multi-scale information, which assesses the similarity between features to achieve a more meaningful fusion of global context and local detail. Given the variability in target appearance within pathological images, we use information entropy to quantify feature uncertainty, allowing the model to prioritize uncertain regions and reduce the occurrence of ambiguous results. To explicitly eliminate multi-feature redundancy and misalignment, the refinement block utilizes parallel convolutional recalibration to fully leverage the advantages of various features. Extensive experiments on multiple pathological image segmentation datasets, including GlaS, GCaSeg, and EBHI-Seg, demonstrate that GeNet achieves high accuracy and strong robustness, offering a new perspective for joint modeling of global and local features in medical image analysis.

Whole slide image (WSI) classification is a critical task in computational pathology and is aimed at providing automated diagnostic support through high-resolution tissue image analysis. In weakly supervised WSI classification scenarios, the main challenge concerns the traditional multiple instance learning (MIL) methods, which rely on instance-level embeddings aggregated by an attention-based pooling mechanism. These methods often depend on data-driven statistical correlations, leading to misalignments between their attention allocation schemes and histopathological diagnostic regions and reducing the resulting prediction reliability. To address this, we propose frequency-aware causal regularized multiple instance learning (FC-MIL), an innovative framework combining that combines frequency-aware attention (FAA) and causal regularization (CR). FAA extracts more granular, fine-grained histological textures by jointly modeling spatial- and frequency- domain features, whereas CR introduces feature-level counterfactual perturbations as an intervention-inspired regularizer in the latent space, encouraging the model to rely less on spurious correlations and more on invariant pathological cues. Experimental results obtained on four WSI datasets show that FC-MIL outperforms the state-of-the-art MIL methods in terms of both accuracy and interpretability. Our source code is available at https://github.com/7FFDW/FCMIL.

Establishing reliable correspondences is a fundamental task in computer vision. Constructing neighbor graphs in feature space with position information to mine correspondence consistency has become a common strategy for recognizing correct correspondences (inliers). However, these neighbors may include a high ratio of incorrect correspondences (outliers), only using the correspondence consistency from feature space will probably be difficult to guarantee the matching accuracy. To address this issue, we propose a novel motion consistent space to find consistent neighbors that are independent of the correspondence's position and have a larger search range. On top of that, we build two neighbor graphs according to the feature space and motion consistent space separately, and expand a shift annular convolution to retain rich neighbor graph structure information and fully exploit the neighborhood context. Then, we design a dynamic feature fusion block to dynamically fuse these dual-neighbor graphs to flexibly cope with various complex scenarios. Finally, we develop a Dual-Neighborhoods Dynamic Fusion Network (DDFNet) for accurately identifying inliers and retrieving camera poses. Experimental results demonstrate that our proposed DDFNet outperforms the state-of-the-art methods. Source code:https://github.com/1211193023/DDFNet.

For lung surgery robots, the precise segmentation of pulmonary fissures is very important. Damaging the inter-lobar fissures during surgery can have serious consequences. Accurately segmenting weak and abnormal fissures commonly found in clinical CT scans remains a challenging task. To solve the above problem, we aimed to develop a novel Convolution Transformer for accurate fissure segmentation (SC-Former). The proposed SC-Former adopts an encoder, attention block, and decoder structure. First, we designed an encoder with a hybrid CNNs-transformer block that ingeniously amalgamates coordinate convolution and coordinate transformer to effectively capture both local and global feature information. Second, we introduced the long skip connections of our designed attention block at layers of the decoder-encoder structure to emphasize the field of view for fissures. Third, we added the distance map strategy to alleviate the challenge of training the network to segment the false positives from the complex textures in the lung. Fourth, we developed a multi-scale supervision strategy for independent prediction at various decoder levels, effectively integrating multi-scale semantic information to facilitate the segmentation of weak and abnormal fissures. Because of the lack of open-source inter-pulmonary fissure datasets, we collected 3D CT scans from 400 participants in the clinical trial and created a new high-quality dataset: BMI dataset. Extensive experiments on this dataset revealed the great superiority of our method over several state-of-the-art competitors. The ablation study also validated the effectiveness and robustness of each part of SC-Former.

The accurate identification of high-quality correspondences is a prerequisite task in feature-based point cloud registration. However, it is extremely challenging to handle the fusion of local and global features due to feature redundancy and complex spatial relationships. Given that Gestalt principles provide key advantages in analyzing local and global relationships, we propose a novel Gestalt-guided Parallel Interaction Network via orthogonal geometric consistency (GPI-Net) in this paper. It utilizes Gestalt principles to facilitate complementary communication between local and global information. Specifically, we introduce an orthogonal integration strategy to optimally reduce redundant information and generate a more compact global structure for high-quality correspondences. To capture geometric features in correspondences, we leverage a Gestalt Feature Attention (GFA) block through a hybrid utilization of self-attention and cross-attention mechanisms. Furthermore, to facilitate the integration of local detail information into the global structure, we design an innovative Dual-path Multi-Granularity parallel interaction aggregation (DMG) block to promote information exchange across different granularities. Extensive experiments on various challenging tasks demonstrate the superior performance of our proposed GPI-Net in comparison to existing methods. The code will be released at https://github.com/XXX/GPI-Net.

In extremely low signal-to-noise ratio (SNR) region, the useful features of the signal are weakened by higher-power noise, making it difficult for conventional direction-of-arrival (DOA) estimation methods to adequately exploit and extract the low-SNR signal features. Thus, a generative adversarial network (GAN) is presented to learn the underlying features and complex distributions of high-SNR covariance matrices. The introduced GAN establishes a mapping between low-SNR and high-SNR covariance matrices, thereby generating first-rate high-SNR covariance matrices that closely resemble real high-SNR matrices. Also, it effectively captures signal features that are overwhelmed by excessive noise power. Additionally, to improve the performance of convolutional neural network (CNN)-based DOA estimation models in medium-to-high SNR ranges, a deep residual attention network (DRANet) is designed to significantly enhance DOA estimation accuracy in such SNR region. By integrating residual and attention modules, the network effectively filters key features. This enhances feature learning and adaptability, allowing it to capture DOA-related features more proficiently. The experimental results indicate that the developed GAN-DRANet approach can approach the CRLB in the extremely low SNR range and improves the estimation resolution limits of the other two DL-based methods, DNN and CNN, in medium to high SNR conditions.

In future networks, the integrated sensing, communication and computation (ISCC) has gradually become a research hotspot. In this paper, we investigate a novel computation resource allocation scheme for reconfigurable intelligent surfaces (RIS) backscatter communication (BackCom)-aided ISCC system. We consider the joint design of transmit beamforming at BS and the reflecting coefficients at RIS as well as the computation resource allocation of each user. The optimization problem for the max-min computation efficiency (CE) under the constraints of power consumption, the Cramér-Rao bound (CRB) for angles estimation and communication requirement of each user is formulated. To deal with the intractable optimization problem, the block coordinate descent (BCD) algorithm is utilized to tackle the joint optimization problem. We propose the penalty function-based successive convex approximation (SCA) method to optimize the reflecting coefficients and the majorization-minimization (MM) framework to design the transmit beamforming, respectively. In addition, considering the high complexity of the proposed SCA based algorithm, we design a low-complexity beamforming and reflection coefficient scheme for a special case of single target scenario. Simulation results show that the introduction of RIS-BackCom can improve the efficiency of computing and maintain the tradeoff between CE and sensing performance.

Cognitive Internet of Vehicles (CIoV) adds the cognitive engine based on traditional Internet of Vehicles (IoV), which can improve spectrum utilization. However, spectrum sensing data falsification (SSDF) attacks pose a threat to CIoV network security. To ensure the full utilization of spectrum resources and protect primary users transmission, this article combines blockchain with CIoV to defend against SSDF attacks in the presence of vehicle users (VUs) entering and leaving the network. Specifically, this article introduces a virtual currency called Sencoins serve as credential for VUs to purchase transmission shares. And this article proposes a reward and punishment mechanism and a hybrid Proof-of-Stake (PoS) and Proof-of-Work (PoW) mining model to thwart the motivation of the VUs to launch SSDF attacks. On this basis, this article investigates the dynamics of SSDF attack strategy choice of VUs, and uses the largest Lyapunov exponent (LLE) to determine the critical value of Sencoins that avoids the system to exhibit chaotic behavior. To describe the uncertainty of the population proportion of VUs that choose different attack strategies due to high-speed movement and the VUs entering and leaving the CIoV network, this article introduces Gaussian white noise into the replication dynamics equation and builds the Itô stochastic evolutionary game model, and solves it according to the stability judgment theorem of stochastic differential equations and stochastic Taylor expansion. Finally, simulation results verify that the proposed method can quickly and effectively thwart SSDF attacks in the CIoV network. And compared with traditional methods, the proposed method can improve the efficiency of defending against SSDF attacks by 567% and the average throughput by 25%.

Object detection in scenes captured by unmanned aerial vehicles (UAV) is an active research area. However, the performance and efficiency of current small object detection models for UAV images are far from reaching the desired level. The inherent limitations of the features of the small objects themselves and the inconsistency of the contextual information in the feature maps lead to a degradation of the final detection performance. In this letter, to improve the performance of UAV image small object detection, we propose a multi-scale feature optimization network, named MFO-Net. We have designed three crucial modules: feature optimization fusion (FOF) module, multi-scale localized feature aggregation (MLFA) module, and feature enhancement (FE) module. FOF module enhances the fusion of features with inconsistent contexts at different levels by learning pixel-wise displacement, facilitating more effective feature fusion, which further helps focus on and capture critical information about small objects. MLFA module aggregates richer contextual information through multi-branch stripe convolution blocks, while the FE module extracts richer gradient flow information, suppresses incompatible information, and enhances feature representation capability. We conduct extensive experiments on the challenging VisDrone2019 dataset and compare the results against those obtained from the state-of-the-art methods. The experimental results show that MFO-Net performs better than other detectors. Specifically, MFO-Net achieves the best performance with 22.3% AP, 38.9% AP50, and 22.5% AP75on VisDrone2019. Code: https://github.com/Lanziyang121/MFO-Net.

Feature matching is an essential computer vision task that requires the establishment of high-quality correspondences between two images. Constructing sparse dynamic graphs and extracting contextual information by searching for neighbors in feature space is a prevalent strategy in numerous previous works. Nonetheless, these works often neglect the potential connections between dynamic graphs from different layers, leading to underutilization of available information. To tackle this issue, we introduce a Sparse Dynamic Graph Interaction block for feature matching. This innovation facilitates the implicit establishment of dependencies by enabling interaction and aggregation among dynamic graphs across various layers. In addition, we design a novel Multiple Sparse Transformer to enhance the capture of the global context from the sparse graph. This block selectively mines significant global contextual information along spatial and channel dimensions, respectively. Ultimately, we present the Multi-layer Sparse Graph Attention Network (MSGA-Net), a framework designed to predict probabilities of correspondences as inliers and to recover camera poses. Experimental results demonstrate that our proposed MSGA-Net surpasses state-of-the-art methods on challenging indoor and outdoor datasets. Code will be available at https://github.com/gongzhepeng/MSGA-Net.

Accurately identifying correct correspondences (inliers) in two-view images is a fundamental task in computer vision. Recent studies usually adopt Graph Neural Networks or stack local graphs into global ones to establish neighborhood relations. However, the smoothing properties of Graph Convolutional Neural network (GCN) cause the model to fall into local extreme, which leads to the issue of indistinguishability between inliers and outliers. Especially when the initial correspondences contain a large number of incorrect correspondences (outliers), these studies suffer from severe performance degradation. To address the above issues and refocus perspective information on distinct features, we design a Consistency Guided ResFormer Network (CGR-Net) that uses consistent correspondences to guide model perspective focusing, thereby avoiding the negative impact of outliers. Specifically, we design an efficient Graph Score Calculation module, which aims to compute global graph scores by enhancing the representation of important features and comprehensively capturing the contextual relationships between correspondences. Then, we propose a Consistency Guided Correspondences Selection module to dynamically fuse global graph scores and consistency graphs and construct a novel consistency matrix to accurately recognize inliers. Extensive experiments on various challenging tasks demonstrate that our CGR-Net outperforms state-of-the-art methods. Our code is released athttps://github.com/XiaojieLi11/CGR-Net.

Multi-objective segmentation (MOS) in medical images is to simultaneously extract multiple regions of interest in the medical images. Due to the unbalanced distribution of samples and the similarity and significant differences between features in medical images, current methods still struggle to achieve satisfactory results. In this context, we propose a novel Morphological Guided Causal Constrain segmentation network (MCCSeg) for medical image multi-object segmentation. We introduced a Causal Constrain Module (CCM) for feature decorrelation by sample reweighting. The morphological guidance module (MG) is designed to extract the boundary features as the prior shape information for enhancing feature representation. Our experiments demonstrate that MCCSeg outperforms other state-of-the-art methods, obtaining up 3.76% and 5.41% improvements in DICE and HD95 scores on Synapse dataset, respectively.

Simultaneous wireless information and power transfer (SWIPT) is a remarkable technology to support both the data and the energy transfer in the era of Internet of Things (IoT). In this article, we proposed a long-range optical wireless information and power transfer system utilizing retro-reflectors, a gain medium, a telescope internal modulator to form the resonant beam, achieving high-power and high-rate SWIPT. We adopt the transfer matrix, which can depict the beam modulated, resonator stability, transmission loss, and beam distribution. Then, we provide a model for energy harvesting and data receiving, which can evaluate the SWIPT performance. Numerical results illustrate that the proposed system can simultaneously supply 0–9 W electrical power and 18-bit/s/Hz spectral efficiency over 20-m distance.

The use of a reconfigurable intelligent surface (RIS) in the enhancement of the rate performance is considered to involve the limitation of the RIS being a passive reflector. To address this issue, we propose a RIS-aided amplify-and-forward (AF) relay network in this paper. By jointly optimizing the beamforming matrix at AF relay and the phase-shift matrices at RIS, two schemes are put forward to address a maximizing signal-to-noise ratio (SNR) problem. First, aiming at achieving a high rate, a high-performance alternating optimization (AO) method based on Charnes–Cooper transformation and semidefinite programming (CCT-SDP) is proposed, where the optimization problem is decomposed into three subproblems solved using CCT-SDP, and rank-one solutions can be recovered using Gaussian randomization. However, the optimization variables in the CCT-SDP method are matrices, leading to extremely high complexity. To reduce the complexity, a low-complexity AO scheme based on Dinkelbachs transformation and successive convex approximation (DT-SCA) is proposed, where the variables are represented in vector form, and the three decoupling subproblems are solved using DT-SCA. Simulation results verify that compared to three benchmarks (i.e., a RIS-assisted AF relay network with random phase, an AF relay network without RIS, and a RIS-aided network without AF relay), the proposed CCT-SDP and DT-SCA schemes can harvest better rate performance. Furthermore, it is revealed that the rate of the low-complexity DT-SCA method is close to that of the CCT-SDP method.

Building high-quality correspondences is critical in the feature-based point cloud registration pipelines. However, existing single-sequence learning frameworks are difficult to accurately and adequately capture contextual information, leaving a large proportion of outliers between two low-overlap scenes. In this paper, we present a progressive guidance network (PG-Net) to gather rich contextual information and exclude outliers. Specifically, we design a novel iterative structure that exploits the inlier probabilities of correspondences to guide the classification of initial correspondences progressively. This structure can mitigate outlier effects with robust contextual information to obtain more accurate model estimation. In addition, to sufficiently capture contextual information, we propose a grouped dense fusion attention feature embedding module to enhance the representation of inliers and significant channel-spatial. Meanwhile, we propose a two-stage neural spectral matching module to compute the inlier probability of each correspondence and estimate a 3D transformation model in a coarse-to-fine manner. Experiments results on indoor and outdoor datasets using distinct 3D local descriptors demonstrate that our PG-Net surpasses state-of-the-art outlier removal methods. Especially compared to the recent outlier removal network PointDSC, our PG-Net improves the registration recall by 4.06% on the indoor dataset with the FPFH descriptor. Source code: https://github.com/changcaiyang/PG-Net.

Accurate correspondence selection between two images is of great importance for numerous feature matching based vision tasks. The initial correspondences established by off-the-shelf feature extraction methods usually contain a large number of outliers, and this often leads to the difficulty in accurately and sufficiently capturing contextual information for the correspondence learning task. In this paper, we propose a Preference-Guided Filtering Network (PGFNet) to address this problem. The proposed PGFNet is able to effectively select correct correspondences and simultaneously recover the accurate camera pose of matching images. Specifically, we first design a novel iterative filtering structure to learn the preference scores of correspondences for guiding the correspondence filtering strategy. This structure explicitly alleviates the negative effects of outliers so that our network is able to capture more reliable contextual information encoded by the inliers for network learning. Then, to enhance the reliability of preference scores, we present a simple yet effective Grouped Residual Attention block as our network backbone, by designing a feature grouping strategy, a feature grouping manner, a hierarchical residual-like manner and two grouped attention operations. We evaluate PGFNet by extensive ablation studies and comparative experiments on the tasks of outlier removal and camera pose estimation. The results demonstrate outstanding performance gains over the existing state-of-the-art methods on different challenging scenes. The code is available at https://github.com/guobaoxiao/PGFNet.

Seeking reliable correspondences then recovering camera poses from a set of putative correspondences extracted from two images of the same scene is a fundamental problem in computer vision. Recent advances have demonstrated that this problem can be effectively solved by using a deep architecture based on the multi-layer perceptron, where the context normalization is designed to make the network permutation-equivariant and embed global information in the sparse point data. However, the context normalization simply normalizes the feature maps according to their distribution and treats each correspondence equally, leading to difficulties in adequately capturing scene geometry encoded by the inliers, especially in case of severe outliers. To address this issue, this paper designs a context-sensitive network based on the self-attention mechanism, termed as correspondence attention transformer (CAT), to enhance the consistent geometry information of inliers and simultaneously suppress outliers during embedding global information. In particular, we design an attention-style structure to aggregate features from all correspondences, i.e., a spatial attention namely CAT-S, which provides each correspondence with information exchange from others in the putative set. To capture the contextual information in a more comprehensive and robust way, we also introduce a multi-head mechanism in our structure to exploit the geometrical context from different aspects. Moreover, considering the high memory request in spatial attention, we propose a covariance normalized channel attention CAT-C in our framework, which can largely reduce the memory consumption and parameter scale, but it asks for eigenvalue decomposition in each attention block thus resulting in more runtime. Anyway, these two attention mechanisms can realize information exchange from the spatial or channel aspect, which both contribute to constructing the geometrical context between inliers and encourage the network to pay more attention to the feature subset about potential inliers. Extensive experiments have been conducted over both indoor and outdoor datasets on the tasks of camera pose estimation, outlier removal, and image registration, which demonstrate the superiority of our method that realizes a large performance improvement compared with the current state-of-the-art approaches.

Establishing superior-quality correspondences in an image pair is pivotal to many subsequent computer vision tasks. Using Euclidean distance between correspondences to find neighbors and extract local information is a common strategy in previous works. However, most such works ignore similar sparse semantics information between two given images and cannot capture local topology among correspondences well. Therefore, to deal with the above problems, Multiple Sparse Semantics Dynamic Graph Network (MS2DG-Net) is proposed, in this paper, to predict probabilities of correspondences as inliers and recover camera poses. MS2 DG-Net dynamically builds sparse semantics graphs based on sparse semantics similarity between two given images, to capture local topology among correspondences, while maintaining permutation-equivariant. Extensive experiments prove that MS2 DG-Net outperforms state-of-the-art methods in outlier removal and camera pose estimation tasks on the public datasets with heavy outliers. Source code:https://github.com/changcaiyang/MS2DG-Net

In this letter, we propose a remote sensing image matching method that is simple yet efficient to deal with different deformations. Inspired by the region growing strategy used in image segmentation, we integrate the motion consistency into the general region growing pipeline from a novel perspective. Specifically, we first obtain a subset with a high ratio inlier as the seed correspondence set. Then, to find more reliable correspondences, we formulate the motion consistency into the correspondence growing criterion, which is general to be suitable to many remote sensing applications. Extensive experimental results on the public available remote sensing data set show that our method achieves the best performance compared with state-of-the-art methods.

Summary For the dataset with different sample contributions and different feature importance, it is difficult to acquire a proper cluster structure that covers the entire features of the sample set. To improve the clustering result, a novel weighted fuzzy clustering algorithm based on both samples and generalized entropy features, called SGEF‐WFCM, is proposed in this article, among which a new objective function is developed on the basis of feature‐weighted generalized entropy regularization with a double‐weighting strategy of samples and features, the weighted coefficients of the features to each cluster, as well as the importance of the samples to the cluster are calculated dynamically, to obtain a better clustering result. Finally, experiments on both synthetic datasets and real‐world datasets from UCI are employed to verify the performance of the proposed SGEF‐WFCM algorithm. The results show that SGEF‐WFCM is superior to the conventional FCM algorithm in both the effectiveness and the usefulness during practices.

Summary This article focuses on how to design an efficient GPU‐based chicken swarm optimization (CSO) algorithm (GCSO), so as to improve diversity and speed up convergence by running a large number of populations in parallel. GCSO mainly improves the sequential CSO in three aspects: (i) GCSO modifies the location updating equation of the rooster and proposes a parallel iterative strategy to transform the sequential iteration process into a parallel iterative process, thereby achieving fine‐grained parallelism and improving the convergence speed. (ii) A multirange search strategy is proposed to build different neighborhoods for each flock on the graphic process units (GPU), so that each flock searched in their respective neighborhoods, thus increasing the density and diversity of the search, and making it not easy to fall into a local optimum. (iii) A new column storage structure is designed to meet the requirement of coalescent access on GPU. Twelve benchmark functions are selected to compare GCSO algorithm with some sequential intelligence optimization algorithms and the GPU‐based particle swarm algorithm. The results show that the GCSO is able to obtain a speedup up to 163.09× compared with the CSO and achieve better optimization results in terms of both optimization accuracy and convergence speed than some intelligence optimization algorithms.

Evaluating startup companies is an important management process for technology business incubators and it is also a typical multicriteria decision-making (MCDM) problem. There exist various methods that have proposed to solve MCDM problems, but these methods heavily depend on the exact criteria weight values. The decision results of these methods are unstable. Moreover, they cannot provide the improvement suggestions for the nonoptimal startup companies. To overcome these two drawbacks, we propose a novel hesitant fuzzy linguistic decision-making method to solve the problem of evaluating startup companies. To this end, a novel semantic comparison method based on the experts' psychology and the ratio of score value to deviation degree is proposed to compare the hesitant fuzzy linguistic term sets. Then, a novel definition of hesitant fuzzy linguistic information envelopment efficiency (HFLIEE) is proposed, based on which, a novel hesitant fuzzy linguistic information envelopment analysis (HFLIEA) model and a novel preference model are proposed. By solving these models, all the alternatives can be ranked and nonoptimal alternatives can be improved. Finally, the numerical analysis is given to illustrate the applicability of the proposed models and the robustness analyses of the proposed models are provided. At the same time, they are compared with the previous hesitant fuzzy linguistic decision-making methods.

This work considers unmanned aerial vehicle (UAV) networks for collecting data covertly from ground users. The full-duplex (FD) UAV intends to gather critical information from a scheduled user (SU) through wireless communication and generate artificial noise (AN) with random transmit power in order to ensure a negligible probability of the SU’s transmission being detected by the unscheduled users (USUs). To enhance the system performance, we jointly design the UAV’s trajectory and its maximum AN transmit power together with the user scheduling strategy subject to practical constraints, e.g., a covertness constraint, which is explicitly determined by analyzing each USU’s detection performance, and a binary constraint induced by user scheduling. The formulated design problem is a mixed-integer non-convex optimization problem, which is challenging to solve directly, but tackled by our developed penalty successive convex approximation (P-SCA) scheme. An efficient UAV trajectory initialization is also presented based on the successive hover-and-fly (SHAF) trajectory, which also serves as a benchmark scheme. Our examination shows the developed P-SCA scheme significantly outperforms the benchmark scheme in terms of achieving a higher max-min average transmission rate (ATR) from all the SUs to the UAV.

This letter proposes a polarization mapping (PM) for polar coded modulation with physical network coding (PM-PNC) over two-way relay channels (TWRC). The achievable information rates (AIRs) of the mapped bits within a XOR symbol from bit-wise XOR of two user symbols are significantly different, since the users adopt non-uniform PAM modulation to avoid mapping ambiguity. In the polar-coded PM-PNC, the original channels associated with the split information bit channel are mapped to the XOR bit stream with a larger AIR. In this way, the achieved rate of the split information channels can be maximized and is illustrated in distribution of split bit channel AIRs. Simulation results show that the proposed PM-PNC can achieve significant performance gains of more than 0.5 dB as compared to the bit-interleaved coded modulation (BICM) and multilevel coded (MLC) PNC systems over Gaussian and block fading channels.

Abstract The connectivity of a graph is a classic measure for fault tolerance of the network. Restricted connectivity measure is a crucial subject for a multiprocessor system’s ability to tolerate fault processors, and improves the connectivity measurement accuracy. Furthermore, if a network possesses a restricted connectivity property, it is more reliable with a lower vertex failure rate compared with other networks. The $\left (n,k\right )$-dimensional enhanced hypercube, denoted by $Q_{n,k}$, a variant of hypercube, which is a well-known interconnection network. In this paper, we analyze the fault tolerant properties for $\left (n,k\right )$-enhanced hypercube, and establish the $1$-restricted connectivity of $Q_{n,k} (n\ge k+1)$ and $\{2,3\}$-restricted connectivity of $(n,k)$-enhanced hypercube $Q_{n,k} (n=k+1)$. Furthermore, we propose the tight upper bound of $\{2,3\}$-restricted connectivity of $Q_{n,k} (n> k+1)$. Moreover, we show many figures to better illustrate the process of the proofs.

Evaluating the Internet-of-Things (IoT) platforms is a crucial step in the development and deployment process of IoT applications. It is still an open issue. In this article, evaluating the IoT platforms is formulated to be a multicriteria decision-making (MCDM) problem since it involves multiple considerations and a novel integrated MCDM method is put forward for handling this problem. To this end, an evaluation criteria system is established to characterize these considerations for evaluating IoT platforms, and then the concept of probabilistic linguistic term sets (PLTSs) is introduced to express the group preference information of IoT platforms with respect to the criteria. Then, a novel probabilistic linguistic best-worst (PLBW) method based on the score value is put forward for calculating and analyzing the importance degrees of criteria. Based on the PLBW method, two-tuple distance measure, and two-level possibility degree, a novel integrated probabilistic linguistic MCDM model based on the TODIM method is proposed to rank IoT platforms. Finally, a practical case is provided to show the procedure of evaluating IoT platforms and the comparative analysis is performed to verify the advantages of the probabilistic linguistic TODIM method.

In this paper, a new robust model fitting method is proposed to efficiently segment multistructure data even when they are heavily contaminated by outliers. The proposed method is composed of three steps: first, a conventional greedy search strategy is employed to generate (initial) model hypotheses based on the sequential "fit-and-remove" procedure because of its computational efficiency. Second, to efficiently generate accurate model hypotheses close to the true models, a novel global greedy search strategy initially samples from the inliers of the obtained model hypotheses and samples subsequent data subsets from the whole input data. Third, mutual information theory is applied to fuse the model hypotheses of the same model instance. The conventional greedy search strategy is used to generate model hypotheses for the remaining model instances, if the number of retained model hypotheses is less than that of the true model instances after fusion. The second and the third steps are performed iteratively until an adequate solution is obtained. Experimental results demonstrate the effectiveness and efficiency of the proposed method for model fitting.

Color and depth information provided simultaneously in RGB-D images can be used to segment scenes into disjoint regions. In this paper, a graph-based segmentation method for RGB-D image is proposed, in which an adaptive data-driven combination of color- and normal-variation is presented to construct dissimilarity between two adjacent pixels and a novel region merging threshold exploiting normal information in adjacent regions is proposed to control the proceeding of the region merging. We evaluate our method on the NYU-v2 depth database and compare it with several published RGB-D partition methods. The experimental results show that our method is comparable with the state-of-the-art methods and provides more details of structures in the scene.

The h-extra node-connectivity of a graph G is the size of a minimal node-set, whose removal will disconnect G, but each remaining component has no fewer h + 1 nodes. Based on h-extra node-connectivity, the h-extra conditional fault-diagnosability of networks has been proposed for a better, more realistic measure of networks' fault-tolerability. It is the maximal x such that G is h-extra conditionally x-fault-diagnosable. This paper will establish a relationship between the h-extra node-connectivity and h-extra conditional fault-diagnosability for a regular graph G, under the classic PMC diagnostic model. We will apply the newly found relationship to a variety of well-known regular networks, to directly obtain their h-extra conditional fault-diagnosability. The significance of the paper's work is that it relates the notions of h-extra node-connectivity and h-extra conditional fault-diagnosability, so that a regular network's h-extra conditional fault-diagnosability may be known once its h-extra node-connectivity is known.

In this paper, a practical wireless transmission scheme is proposed to transmit confidential messages to the desired user securely and precisely by the joint use of multiple techniques, including artificial noise (AN) projection, phase alignment/beamforming, and random subcarrier selection (RSCS) based on orthogonal frequency division multiplexing (OFDM), and directional modulation (DM), namely RSCS-OFDM-DM. This RSCS-OFDM-DM scheme provides an extremely low-complexity structure for the desired receiver and makes the secure and precise wireless transmission realizable in practice. For illegal eavesdroppers, the receive power of confidential messages is so weak that their receivers cannot intercept these confidential messages successfully once it is corrupted by AN. In such a scheme, the design of phase alignment/beamforming vector and AN projection matrix depends intimately on the desired direction angle and distance. It is particularly noted that the use of RSCS leads to a significant outcome that the receive power of confidential messages mainly concentrates on the small neighboring region around the desired receiver and only small fraction of its power leaks out to the remaining large broad regions. This concept is called secure precise transmission. The probability density function of real-time receive signal-to-interference-and-noise ratio (SINR) is derived. Also, the average SINR and its tight upper bound are attained. The approximate closed-form expression for average secrecy rate is derived by analyzing the first-null positions of the SINR and clarifying the wiretap region. Simulation and analysis show that the proposed scheme actually can achieve a secure and precise wireless transmission of confidential messages in line-of-propagation channel, and the derived theoretical formula of average secrecy rate is verified to coincide with the exact results well for medium and large scale transmit antenna array or in the low and medium SNR regions.

The g-restricted connectivity (g-RC) is the minimum vertex-set size of a network, whose deletion disconnects the network such that each remaining vertex has at least g neighbors in its respective component. The g-RC is a deterministic indicator of tolerability of a network with failing processors. The g-good-neighbor fault diagnosability (g-GNFD) is the largest set size of correctly identified faulty vertices in a network such that any good vertex has no fewer g good neighbors. This paper establishes the relationship between g-RC and g-GNFD of general regular networks, first under the PMC model and second under the MM* model. Moreover, this paper directly gives the g-GNFD of some well-known special networks by their g-RC and our proposed relationship.

As the volume of data and technical complexity of large-scale analysis increases, many domain experts can no longer be seated in the data exploration and analysis workflow. What is desired is a computational powerful but still familiar analysis interface for domain experts to fully participate in the analysis workflow by just focusing on individual datasets, leaving the large-scale computation to the system. Towards this goal, we present VisRden, a research prototype that combines user friendly visual programming and scalable computing backend for large-scale 3D reconstruction in carious lesion research. VisRden uses R as the analysis language, making a set of core functions available to the users by hiding the computational complexity behind a visual interface, and allowing advanced users to provide custom R scripts and variables to be fully embedded into the final analysis script. Using R as the analysis language allows cariologists to continue explore data and propose new analysis methods in the way they are already familiar with. VisRden conquers large-scale image processing and 3D reconstruction in a MapReduce-like framework using R and SGE (Sun Grid Engine) array jobs. Image-based operations and result aggregation are scheduled as array jobs in a parallel means to accelerate the knowledge discovery process. All these combine to provide a new analytics workflow for performing similar large-scale analysis loops that need expert users to closely supervise, provide feedback, and refine the subtasks.

Summary The paper illustrates a parallel and distributed scheme for computing a planar Delaunay triangulation using a divide‐and‐conquer strategy in Cloud environment, which combines the incremental insertion algorithm and the divide‐and‐conquer method. The proposed hybrid algorithm for Delaunay triangulation construction is easy to be parallelized due to the dynamic pruned characteristic of the binary tree model used. Moreover, the Cloud platform decreases the communication overhead and improves data locality by making use of a data partitioning and integrating scheme offered by the map‐reduce architecture. The implementation of the parallel and distributed version of the algorithm relied on a robust data structure called quad‐edge, which implies the geometric relationship among the edges and vertexes adjacent. More importantly, the data are serialized easily and transmitted efficiently between different Cloud nodes; the algorithm is executed conveniently on PC clusters. We tested the parallel version of the algorithm on GeoKSCloud, a geographical knowledge service Cloud developed by our research team. Experimental results show that the proposed hybrid algorithm is efficient and competitive; it can be easily migrated and deployed in distributed and parallel computing environment, such as grid and Cloud. The parallel implementation of the hybrid algorithm has a good speed‐up, while data communication is the crucial factor for the efficiency of the parallel version. Overall, the parallel version outperforms both the sequential divide‐and‐conquer algorithm and the sequential incremental insertion algorithm.

Summary The problem of distributed cooperative control for networked multiagent systems is investigated in this paper. Each agent is modeled as an uncertain nonlinear high‐order system incorporating with model uncertainty, unknown external disturbance, and actuator fault. The communication network between followers can be an undirected or a directed graph, and only some of the follower agents can obtain the commands from the leader. To develop the distributed cooperative control algorithm, a prefilter is designed, which can derive the state‐space representation to a newly constructed plant. Then, a set of distributed adaptive neural network controllers are designed by making certain modifications on traditional backstepping techniques with the aid of adaptive control, neural network control, and a second‐order sliding mode estimator. Rigorous proving procedures are provided, which show that uniform ultimate boundedness of all the tracking errors can be achieved in a networked multiagent system. Finally, a numerical simulation is carried out to evaluate the theoretical results.

Exemplar learning is a kind of inductive learning, and it is a very important component in the research of machine learning. But the explosion problem of calculation which caused by it is a big trouble in use. Finding key feature of concept can solve this problem well. Time complexity analysis shows that the Exemplar learning problem can be translated into the problem that is independent of the number of instances by using the Key Feature Variable Based Learning Model for Exemplar learning, which can reduce the size of the search space, and this model is of practical significance to improve the efficiency of Exemplar learning and the stability of the system, while the risk didn't raise at all.

In the paper, a city educational resources assignment problem (CERAP) is raised. The combination of big data, multi-agent model and cellular automata (CA) methodologies are argued and developed. Then, the agent-based computational framework is discussed to the educational social science control (assignment) system. The proposed methodologies provides a powerful way to address nonlinearities, humanities, and especially interdisciplinary control problem. Agent-based modeling offers powerful new forms of hybrid theoretical-computational work. The agent-based approach invites the interpretation of society as a distributed computational network, and in turn the interpretation of social dynamics as a type of computation. Then, the simulation tools are mentioned. Finally, a short discussion and conclusion end this paper.

With the completion of the Human Genome Project, proteomics research has become one of the most important topics in the fields of life science and natural science. The project determined that proteins participate in life activities mainly in the form of complexes. At present, research on protein-protein interaction networks (PPINs) have mainly focused on detecting protein complexes or function modules. This problem has been transformed into a recognizable dense subgraph problem in a PPIN diagram.The situation in PPIN research in recent years is introduced in this study, including commonly used databases, traditional detection algorithms, recent solutions, and the application of the swarm intelligence algorithms in this field. We then propose a detection scheme based on particle swarm optimization (PSO) and gene ontology knowledge. This scheme combines PSO and biological gene ontology knowledge to identify complexes from PPINs. Simultaneously, network topology knowledge improves the detection accuracy of the protein module.

In this paper, we present two methods using Neural networks to mine virtual machine usage data. For the one-for-all training method, we use the trained model to predict the whole weeks' data. For the separated model, we cut the testing set into seven smaller sets of each day, then use the corresponding model to predict that particular day's data. A whole weeks' data are used as testing set. The final results show that our method can predict network usage with only around 20% of errors.

Delaunay triangulation (D-TIN) is an important graphic tool in computational geometry, which is not only widely used in many real applications, but also very significant for many spatial data mining algorithms. However, constructing Delaunay triangulation is time-consuming for most practical applications. Distributed and parallel computing mechanism is becoming a good choice to solve large scale and compute-intensive D-TIN applications. This paper proposes a novel hybrid algorithm (HA) for D-TIN construction in cloud computing environment, which is based on a balanced binary-tree model and an elegant data structure called quad-edge. HA combines the divide & conquer approach and the incremental method. Moreover, a distributed and parallel version of Delaunay triangulation computing service in cloud is designed and implemented. The hybrid algorithm performed in both centralised and in cloud environments are compared. Experimental results showed that the hybrid D-TIN service outperforms both the the divide & conquer one and the incremental one, and it can effectively provide higher data mining services with fundamental D-TIN construction function in cloud.

Various sensors are now widely used for geospatial data acquisition, but due to the limitations of the data structure, most geographic information systems (GIS) cannot manage and analyze the real-time or dynamic observed data. Current Event-driven (E-ST) spatiotemporal data model can use observed events to express causality of space-time changes during the GIS process. But it cannot express the interior factors that causing event changes and relationship between events. An improved E-ST spatiotemporal data model is proposed to better support the complex geographical process simulation and analysis. Its conceptual model is composed of observation, event, object, process and some management mechanism. The monitoring on typical landslide area is taken as case study to test the validity of this model. According to the system discrimination model, synthesized anomaly information can be used to landslide disaster forecast based on spatiotemporal analysis.

Non-rigid point set registration is a fundamental problem for many computer vision technologies. In this paper, we proposed a new non-rigid point set registration method based on coherent spatial mapping (CSM) and local geometrical constraint. Our central idea is to express each point as a weighted sum of several nearest neighbors and the same relation holds after the transformation. The registration problem is solved by minimizing an error function, which combines the the global model and local geometrical constraint. The registration experiments are undertaken on various synthetic and real data. The results demonstrate that the proposed approach is robust and is superior to the state-of-the-art methods.

In this paper, we aim to develop a set of distributed adaptive fuzzy controllers for a group of uncertain nonlinear high-order multi-agent systems in the presence of actuator faults. Firstly, a pre-filter is designed which can derive the state space representation to a newly constructed plant. Design of the control variable will be provided by making certain modifications on traditional backstepping technique with the aid of adaptive control, fuzzy control and a second-order sliding mode estimator. It shows that the effects due to actuator faults, external disturbances and the uncertainties of the model can be compensated with the proposed scheme, and the global boundedness of the tracking errors can also be ensured.

The aim of this article is to investigate the approach for multi-attribute group decision-making, in which the attribute values take the form of multi-granularity multiplicative linguistic information. Firstly, to process multiple sources of decision information assessed in different multiplicative linguistic label sets, a method for transforming multi-granularity multiplicative linguistic information into multiplicative trapezoidal fuzzy numbers is proposed. Then, a formula for ranking multiplicative trapezoidal fuzzy numbers is given based on geometric mean. Furthermore, the concept of similarity degree between two multiplicative trapezoidal fuzzy numbers is defined. The attribute weights are obtained by solving some optimization models. An effective approach for group decision making with multi-granularity multiplicative linguistic information is developed based on the ordered weighted geometric mean operator and proposed formulae. Finally, a practical example is provided to illustrate the practicality and validity of the proposed method.

In this paper, spatial channel pairing (SCP) is introduced to coherent combining at the relay in relay networks. Closed-form solution to optimal coherent combining is derived. Given coherent combining, the approximate SCP solution is presented. Finally, an alternating iterative structure is developed. Simulation results and analysis show that, given the symbol error rate and data rate, the proposed alternating iterative structure achieves signal-to-noise ratio gains over existing schemes in maximum ratio combining (MRC) plus matched filter, MRC plus antenna selection, and distributed space-time block coding due to the use of SCP and iterative structure.

In wideband multi-pair two-way relay networks, the performance of beamforming at a relay station (RS) is intimately related to the accuracy of the channel state information (CSI) available. The accuracy of CSI is determined by Doppler spread, delay between beamforming and channel estimation, and density of pilot symbols, including transmit power of pilot symbols. The coefficient of the Gaussian-Markov CSI error model is modeled as a function of CSI delay, Doppler spread, and signal-to-noise ratio, and can be estimated in real time. In accordance with the real-time estimated coefficients of the error model, an adaptive robust maximum signal-to-interferenceand- noise ratio (Max-SINR) plus maximum signal-to-leakage-and-noise ratio (Max-SLNR) beamformer at an RS is proposed to track the variation of the CSI error. From simulation results and analysis, it is shown that: compared to existing non-adaptive beamformers, the proposed adaptive beamformer is more robust and performs much better in the sense of bit error rate (BER); with increase in the density of transmit pilot symbols, its BER and sum-rate performances tend to those of the beamformer of Max-SINR plus Max-SLNR with ideal CSI.

Dentistry is a particularly complex and sophisticated applied science; many problems have to be solved by analyzing intensive longitudinal data. For example, dynamic carious lesion assessment requires dental researchers to perform knowledge discovery in a situation with multiple specimens across different experimental phases. The technological development and availability of cyberinfrastructure today can enable dental researchers to perform existing procedures far faster and more accurately than ever. This paper uses dynamic carious lesion activity assessment as a case study, to illustrate how visual computing on advanced cyberinfrastructure can expand beyond statistical number crunching and information retrieval to make an imaginative and creative contribution to some aspects of dental science. Our work focuses on the generation of BIG pictures on cyberinfrastructure and the presentation of derived dental structures in an interactive means, which combine to allow researchers to navigate from observation to qualitative discovery and then to quantitative assessment with multiple variables and degrees of freedom. Our work has seen early use by our collaborators in oral health research, where our system has been used to pose and answer domain-specific questions for quantitative assessment of dynamic carious lesion activities.