The anatomical information obtained from medical image segmentation will provide a crucial decision-making basis for clinical diagnosis and treatment. Deep networks with encoder-decoder architecture proposed recently have achieved impressive results. However, these existing deep networks have some inherent flaws, e.g., network depth and downsampling operators jointly determine the loss of spatial detail information of deep features. We find that it is the lack of targeted solutions to these inherent flaws that make it difficult to further improve the segmentation performance. Therefore, based on these findings, we propose an end-to-end collaborative refinement method (CoRe). Specifically, we first design to generate an Error-Prone Region (EPR) by predicting uncertainty map and foreground boundary map to simulate the error region, and after locating pixels with high error proneness, we propose a feature refinement module (FRM) based on neighborhood-aware features and foreground-boundary-enhanced features to refine the upsampling features of the decoder, so as to better reconstruct the lost spatial detail information. In addition, a segmentation refinement module (SRM) is proposed to refine coarse segmentation prediction by establishing highly representative global class centers that comprehensively contain the intrinsic properties of each segmentation target. Finally, we conduct extensive experiments on five datasets with different modalities and segmentation targets. The results show that our method achieves significant improvements and competes favorably with current state-of-the-art methods.

With the increasing integration level of flow-based microfluidics, fully programmable valve arrays (FPVAs) have emerged as the next generation of flow-based microfluidic devices. Microvalves in an FPVA are typically managed by a control logic, where valves are connected to a core input via control channels to receive control signals that guide their state switchings. When executing bioassays using an FPVA, however, some valves need to be switched synchronously at different time points, so that both fluid transportation and biochemical operations can be executed correctly. Consequently, the channel lengths from the core input to these valves must be equal, which poses a big challenge to the channel routing of the control logic. To solve this problem, we propose a deep reinforcement learning-based adaptive routing flow for the control logic of FPVAs. With the proposed routing flow, an efficient control-channel network can be automatically constructed to realize accurate control signal propagation. Meanwhile, timing skews among synchronized valves and the total length of control channels are minimized simultaneously, thus generating an optimized control logic with excellent timing performance. Furthermore, by introducing backups of identified critical valves and flexible routing of backup paths without restrictions on control valve locations, a novel fault-tolerant design method considering length matching is implemented to efficiently improve the reliability of the control logic. Simulation results on multiple benchmarks demonstrate that the proposed routing flow leads to control logics with accurate valve synchronization, low cost, and high reliability.

Multi-view learning methods leverage multiple data sources to enhance perception by mining correlations across views, typically relying on predefined categories. However, deploying these models in real-world scenarios presents two primary openness challenges. 1) Lack of Interpretability: The integration mechanisms of multi-view data in existing black-box models remain poorly explained; 2) Insufficient Generalization: Most models are not adapted to multi-view scenarios involving unknown categories. To address these challenges, we propose OpenViewer, an openness-aware multi-view learning framework with theoretical support. This framework begins with a Pseudo-Unknown Sample Generation Mechanism to efficiently simulate open multi-view environments and previously adapt to potential unknown samples. Subsequently, we introduce an Expression-Enhanced Deep Unfolding Network to intuitively promote interpretability by systematically constructing functional prior-mapping modules and effectively providing a more transparent integration mechanism for multi-view data. Additionally, we establish a Perception-Augmented Open-Set Training Regime to significantly enhance generalization by precisely boosting confidences for known categories and carefully suppressing inappropriate confidences for unknown ones. Experimental results demonstrate that OpenViewer effectively addresses openness challenges while ensuring recognition performance for both known and unknown samples.

The fair and objective assessment of performances and competitions is a common pursuit and challenge in human society. The application of computer vision technology offers hope for this purpose, but it still faces obstacles such as occlusion and motion blur. To address these hindrances, our DanceFix proposes a bidirectional spatial-temporal context optical flow correction (BOFC) method. This approach leverages the consistency and complementarity of motion information between two modalities: optical flow, which excels at pixel capture, and lightweight skeleton data. It enables the extraction of pixel-level motion changes and the correction of abnormal skeleton data. Furthermore, we propose a part-level dance dataset (Dancer Parts) and part-level motion feature extraction based on task decoupling (PETD). This aims to decouple complex whole-body parts tracking into fine-grained limb-level motion extraction, enhancing the confidence of temporal information and the accuracy of correction for abnormal data. Finally, we present the DNV dataset, which simulates fully neat group dance scenes and provides reliable labels and validation methods for the newly introduced group dance neatness assessment (GDNA). To the best of our knowledge, this is the first work to develop quantitative criteria for assessing limb and joint neatness in group dance. We conduct experiments on DNV and video-based public JHMDB datasets. Our method effectively corrects abnormal skeleton points, flexibly embeds, and improves the accuracy of existing pose estimation algorithms.

Long-term sports assessment is a challenging task in video understanding since it requires judging complex movement variations and action-music coordination. However, there is no direct correlation between the diverse background music and movements in sporting events. Previous works require a large number of model parameters to learn potential associations between actions and music. To address this issue, we propose a language-guided audio-visual learning (MLAVL) framework that models "audio-action-visual" correlations guided by low-cost language modality. In our framework, multidimensional domain-based actions form action knowledge graphs, motivating audio-visual modalities to focus on task-relevant actions. We further design a shared-specific context encoder to integrate deep multimodal semantics, and an audio-visual cross-modal fusion module to evaluate action-music consistency. To match the sport’s rules, we then propose a dual-branch prompt-guided grading module to weigh both visual and audio-visual performance. Extensive experiments demonstrate that our approach achieves state-of-the-art on four public long-term sports benchmarks while maintaining low parameters.1

The track assignment has been introduced between global routing and detail routing. Based on the independence and divisibility of track assignment, we propose a GPU-accelerated parallel track assignment algorithm. To estimate routability more accurately, the proposed algorithm simultaneously considers global and local nets, and incorporates several strategies for optimization. Moreover, an asynchronous parallelism strategy is proposed to divide the computation of routing resources and the track assignment into fine-grained tasks. Experimental results show that, compared to related work, our algorithm achieves a significant speedup with a better routability estimation.

Label distribution learning quantifies the label space for each instance and has broad applicability in various fields. However, most existing works primarily focus on label correlation, but they have a deficiency in capturing instance correlation. Meanwhile, traditional label distribution learning operates on individual labels sequentially, which restricts the potential application of common features. Therefore, in this paper, we propose a novel approach for label distribution learning with correlation information, i.e. , instance correlation and label correlation. Specifically, the instance correlation and label correlation are identified by an optimization function and Pearson correlation coefficient, respectively. Besides, we conduct ℓ 2 , 1 regularization to exploit common features. Comprehensive experiments conducted on twelve publicly datasets demonstrate the effectiveness of our proposed approach against other well-established label distribution learning algorithms.

As a new generation of flow-based microfluidics, Fully Programmable Valve Array (FPVA) biochips have gained widespread adoption as a biochemical experimental platform, thanks to their enhanced programmability and flexibility. Environmental and human factors, however, often introduce physical faults during the manufacturing process such as channel blockage and leakage, which, undoubtedly, can affect the results of bioassays and even cause execution failure. In this paper, we focus on the fault-tolerant co-design of flow and control layers in FPVA biochips for the first time. For the flow layer, three dynamic fault-tolerant techniques, i.e., a cell function conversion method, a bidirectional redundancy scheme, and a fault mapping method, are presented and integrated into the device placement and flow routing stages. As a consequence, we further realize an efficient and effective fault-tolerance-oriented physical design method, thus ensuring the robustness of chip architecture and correctness of assay outcomes. For the control layer, we design another three fault-tolerant techniques including a series duplication scheme of leakage valves, allocation and merging rules of backup valves, and a logic conflict-aware adjustment strategy of redundant architecture. Based on these techniques, we construct a fault-tolerant control system to realize dynamic recovery of control signals. Experimental results on multiple test cases demonstrate that the proposed method can produce optimized fault-tolerant FPVA architectures with low fabrication cost, high execution efficiency, and high fault-tolerance success rate.

Camera-based stereo 3D object detection estimates 3D properties of objects with binocular images only, which is a cost-effective solution for autonomous driving. The state-of-the-art methods mainly improve the detection accuracy of general objects by designing ingenious stereo matching algorithms or complex pipeline modules. Moreover, additional fine-grained annotations, such as masks or LiDAR point clouds, are often introduced to deal with the occlusion problems, which brings in high manual costs for this task. To address the detection bottleneck caused by occlusion in a more cost-effective manner, we develop a novel stereo 3D object detection method named DSC3D, which achieves significant improvements for occluded objects without introducing additional supervision. Specifically, we first report the ambiguity in feature sampling, which refers to the presence of noisy features in the sampling for occluded objects. Then, we propose the Epipolar Constraint Deform-Attention (ECDA) module to address the unreliable left-right correspondence computation in stereo matching caused by occlusion, which reweights epipolar features by adaptively aggregating local neighbor information. Furthermore, to ensure that 3D property estimation is based on robust object features, we propose visible regions guided constraint to explicitly guide the offset learning for feature sampling. Extensive experiments conducted on the KITTI benchmark have demonstrated the proposed DSC3D outperforms the state-of-the-art camera-based methods.

Multimodal prompt learning has emerged as an effective strategy for adapting vision-language models such as CLIP to downstream tasks. However, conventional approaches typically operate at the input level, forcing learned prompts to propagate through a sequence of frozen Transformer layers. This indirect adaptation introduces cumulative geometric distortions, a limitation that we formalize as the indirect learning dilemma (ILD), leading to overfitting of the base class and reduced generalization to novel classes. To overcome this challenge, we propose the Multimodal Self-Attention Prompt (MSP) framework, which shifts adaptation into the semantic core of the model by injecting learnable prompts directly into the key and value sequences of attention blocks. This direct modulation preserves the pretrained embedding geometry while enabling more precise downstream adaptation. MSP further incorporates distance-aware optimization to maintain semantic consistency with CLIP's original representation space, and partial prompt learning via stochastic dimension masking to improve robustness and prevent over-specialization. Extensive evaluations across 11 benchmarks demonstrate the effectiveness of MSP. It achieves a state-of-the-art harmonic mean accuracy of 80.67%, with 77.32% accuracy on novel classes-representing a 2.18% absolute improvement over prior methods-while requiring only 0.11M learnable parameters. Notably, MSP surpasses CLIP's zero-shot performance on 10 out of 11 datasets, establishing a new paradigm for efficient and generalizable prompt-based adaptation. Our implementation is available at https://github.com/laixinyi023/Multimodal-Self-Attention-Prompt.

Although Graph Neural Networks (GNNs) have exhibited the powerful ability to gather graph-structured information from neighborhood nodes via various message-passing mechanisms, the performance of GNNs is limited by poor generalization and fragile robustness caused by noisy and redundant graph data. As a prominent solution, Graph Augmentation Learning (GAL) has recently received increasing attention in the literature. Among the existing GAL approaches, edge-dropping methods that randomly remove edges from a graph during training are effective techniques to improve the robustness of GNNs. However, randomly dropping edges often results in bypassing critical edges. Consequently, the effectiveness of message passing is weakened. In this paper, we propose a novel adversarial edge-dropping method (ADEdgeDrop) that leverages an adversarial edge predictor guiding the removal of edges, which can be flexibly incorporated into diverse GNN backbones. Employing an adversarial training framework, the edge predictor utilizes the line graph transformed from the original graph to estimate the edges to be dropped, which improves the interpretability of the edge-dropping method. The proposed ADEdgeDrop is optimized alternately by stochastic gradient descent and projected gradient descent. Comprehensive experiments on eight graph benchmark datasets demonstrate that the proposed ADEdgeDrop outperforms state-of-the-art baselines across various GNN backbones, demonstrating improved generalization and robustness.

Long-term action quality assessment poses a challenging visual task since it requires assessing technical actions at different skill levels in a long video. Recent state-of-the-art methods incorporate additional modality information to aid in understanding action semantics, which incurs extra annotation costs and imposes higher constraints on action scenes and datasets. To address this issue, we propose a Quality-Guided Vision-Language Learning (QGVL) method to map visual features into appropriate fine-grained intervals of quality scores. Specifically, we use a set of quality-related textual prompts as quality prototypes to guide the discrimination and aggregation of specific visual actions. To avoid fuzzy rule mapping, we further propose a progressive semantic learning strategy with a Granularity-Adaptive Semantic Learning Module (GSLM) that refines accurate score intervals from coarse to fine at clip, grade, and score levels. The quality-related semantics we designed are universal to all types of action scenarios without any additional annotations. Extensive experiments show that our approach outperforms previous work by a significant margin and establishes new state-of-the-art on four public AQA benchmarks: Rhythmic Gymnastics, Fis-V, FS1000, and FineFS.

As interconnect delay increasingly becomes the primary source of chip delay, timing analysis in the very large-scale integration (VLSI) routing process is becoming more crucial. Concurrently, to maintain computational synchronization in the chip, the bounded-skew constraint must be introduced. Additionally, the issue of obstacle-avoiding has gained attention due to the presence of routing obstacles on the chip. Furthermore, the introduction of X-architecture enables more efficient utilization of routing resources. In this article, we propose an obstacle-avoiding X-architecture bounded-skew tree (BST) algorithm under timing slack constraints, which, for the first time, simultaneously considers timing slack, bounded-skew, obstacle-avoidance, and X-architecture in a unified framework. First, an effective preprocessing strategy is presented to support fast information retrieval for the subsequent strategies. Second, a BST construction strategy is developed to ensure compliance with skew constraints by consulting and updating a dedicated skew table. Third, a local worst negative slack (WNS) optimization strategy is designed to improve the WNS of critical paths by balancing wirelength (WL) and radius. Fourth, an obstacle-avoiding strategy is implemented to navigate around routing obstacles while minimizing unnecessary WL overhead. Finally, a path refinement strategy is designed to select routing structures with maximal edge sharing to replace the initial structure, thereby further optimizing WL. Experimental results demonstrate that the proposed algorithm significantly improves both WL and the key timing metric WNS, while satisfying obstacle-avoidance and bounded-skew constraints.

Image hiding aims to conceal one or more secret images within a cover image of the same resolution. Due to strict capacity requirements, image hiding is commonly called large-capacity steganography. In this paper, we propose StegFormer, a novel autoencoder-based image-hiding model. StegFormer can conceal one or multiple secret images within a cover image of the same resolution while preserving the high visual quality of the stego image. In addition, to mitigate the limitations of current steganographic models in real-world scenarios, we propose a normalizing training strategy and a restrict loss to improve the reliability of the steganographic models under realistic conditions. Furthermore, we propose an efficient steganographic capacity expansion method to increase the capacity of steganography and enhance the efficiency of secret communication. Through this approach, we can increase the relative payload of StegFormer to 96 bits per pixel without any training strategy modifications. Experiments demonstrate that our StegFormer outperforms existing state-of-the-art (SOTA) models. In the case of single-image steganography, there is an improvement of more than 3 dB and 5 dB in PSNR for secret/recovery image pairs and cover/stego image pairs.

With the increasing integration level of flow-based microfluidics, fully programmable valve arrays (FPVAs) have emerged as the next generation of microfluidic devices. Mi-crovalves in an FPVA are typically managed by a control logic, where valves are connected to a core input via control channels to receive control signals that guide states switching. The critical valves that suffer from asynchronous actuation leading to chip malfunctions, however, need to be switched simultaneously in a specific bioassay. As a result, the channel lengths from the core input to these valves are required to be equal or similar, which poses a challenge to the channel routing of the control logic. To solve this problem, we propose a deep reinforcement learning-based adaptive routing flow for the control logic of FPVAs. With the proposed routing flow, an efficient control channel network can be automatically constructed to realize accurate control signals propagation. Meanwhile, the timing skews among synchronized valves and the total length of control channels can be minimized, thus generating an optimized control logic with excellent timing behavior. Simulation results on multiple benchmarks demonstrate the effectiveness of the proposed routing flow.

Fully Programmable Valve Array (FPVA) biochips have attracted much attention as a new generation of continuous-flow microfluidic platform for biochemical experiments automation. With the increasing density of microvalves in FPVA biochips, the control system for managing the open/close of these valves has become more and more complex. To improve the scalability of biochips and reduce the number of control pins, a highly efficient control system using multiplexer and boolean logic has been introduced in FPVA biochips. In the manufacturing and using of such systems, however, various faults such as channel blockage, channel leakage, and reliability issues caused by frequent valve switching can occur in the multiplexers. Accordingly, in this paper, we propose the first automated fault test method for the multiplexer of FPVA control systems. The proposed method includes the following key techniques: 1) an automated test pattern generation algorithm based on integer linear programming and 2) an automated fault test strategy based on image recognition technology. Experiment results on multiple benchmarks have shown that the proposed method can generate fewer test patterns, while achiving 100% fault coverage.

The sparse interactions between users and items have aggravated the difficulty of their representations in recommender systems. Existing methods leverage tags to alleviate the sparsity problem but ignore prevalent logical relations among items and tags (e.g., membership, hierarchy, and exclusion), which can be leveraged to enhance the accuracy of modeling user preferences and conducting recommendations. To this end, we propose to extract logical relations among item tags from existing tag taxonomies and exploit the individual strengths of the Poincaré and the Lorentz models in hyperbolic space for logical relation modeling towards enhanced recommendations. Moreover, we find that the logical relations directly extracted from existing tag taxonomies can be inaccurate and coarse. Therefore, we further devise innovative consistency-based and granularity- based weighting mechanisms based on user behavior patterns for data-driven logical relation mining that can be jointly optimized along with recommendations in an end-to-end fashion. Extensive experiments on four real-world benchmark datasets show drastic performance gains brought by our proposed framework, which constantly achieves an average of 8.25% improvement over state-of-the-art competitors regarding both Recall and NDCG metrics. Insightful case studies further demonstrate that our automatically refined logical relations are highly accurate and interpretable.

Graph anomaly detection (GAD) aims to identify anomalous graphs that significantly deviate from other ones, which has raised growing attention due to the broad existence and complexity of graph-structured data in many real-world scenarios. However, existing GAD methods usually execute with centralized training, which may lead to privacy leakage risk in some sensitive cases, thereby impeding collaboration among organizations seeking to collectively develop robust GAD models. Although federated learning offers a promising solution, the prevalent non-IID problems and high communication costs present significant challenges, particularly pronounced in collaborations with graph data distributed among different participants. To tackle these challenges, we propose an effective federated graph anomaly detection framework (FGAD). We first introduce an anomaly generator to perturb the normal graphs to be anomalous and train a powerful anomaly detector by distinguishing generated anomalous graphs from normal ones. We subsequently leverage a student model to distill knowledge from the trained anomaly detector (teacher model), which aims to maintain the personality of local models and alleviate the adverse impact of non-IID problems. Additionally, we design an effective collaborative learning mechanism that facilitates the personalization preservation of local models and significantly reduces communication costs among clients. Empirical results of diverse GAD tasks demonstrate the superiority and efficiency of FGAD.

Few-shot font generation (FFG) aims to learn the target style from a limited number of reference glyphs and generate the remaining glyphs in the target font. Previous works focus on disentangling the content and style features of glyphs, combining the content features of the source glyph with the style features of the reference glyph to generate new glyphs. However, the disentanglement is challenging due to the complexity of glyphs, often resulting in glyphs that are influenced by the style of the source glyph and prone to artifacts. We propose IF-Font, a novel paradigm which incorporates Ideographic Description Sequence (IDS) instead of the source glyph to control the semantics of generated glyphs. To achieve this, we quantize the reference glyphs into tokens, and model the token distribution of target glyphs using corresponding IDS and reference tokens. The proposed method excels in synthesizing glyphs with neat and correct strokes, and enables the creation of new glyphs based on provided IDS. Extensive experiments demonstrate that our method greatly outperforms state-of-the-art methods in both one-shot and few-shot settings, particularly when the target styles differ significantly from the training font styles. The code is available at [https://github.com/Stareven233/IF-Font](https://github.com/Stareven233/IF-Font).

Summary In label distribution learning (LDL), an instance is involved with many labels in different importance degrees, and the feature space of instances is accompanied with thousands of redundant and/or irrelevant features. Therefore, the main characteristic of feature selection in LDL is to evaluate the ability of each feature. Motivated by neighborhood rough set (NRS), which can be used to measure the dependency degree of feature via constructing neighborhood relations on feature space and label space, respectively, this article proposes a novel label distribution feature selection method. In this article, the neighborhood class of instance in label distribution space is defined, which is beneficial to recognize the logical class of target instance. Then, a new NRS model for LDL is proposed. Specially, the dependency degree of feature combining label weight is defined. Finally, a label distribution feature selection based on NRS is presented. Extensive experiments on 12 data sets show the effectiveness of the proposed algorithm.

Research on knowledge graph embedding (KGE) has emerged as an active field in which most existing KGE approaches mainly focus on static structural data and ignore the influence of temporal variation involved in time-aware triples. In order to deal with this issue, several temporal knowledge graph embedding (TKGE) approaches have been proposed to integrate temporal and structural information. However, these methods only employ a uniformly random sampling to construct negative facts. As a consequence, the corrupted samples are often too simplistic for training an effective model. In this paper, we propose a new temporal knowledge graph embedding framework by introducing adversarial learning to further refine the performance of traditional TKGE models. In our framework, a generator is utilized to construct high-quality plausible quadruples and a discriminator learns to obtain the embeddings of entities and relations based on both positive and negative samples. Meanwhile, we also apply a Gumbel-Softmax relaxation and the Wasserstein distance to prevent vanishing gradient problems on discrete data; an inherent flaw in traditional generative adversarial networks . Through comprehensive experimentation on temporal datasets, the results indicate that our proposed framework can attain significant improvements based on benchmark models and also demonstrate the effectiveness and applicability of our framework.

Single Image Super-Resolution (SISR) aims to reconstruct a high-resolution image from its corresponding low-resolution input. A common technique to enhance the reconstruction quality is Non-Local Attention (NLA), which leverages self-similar texture patterns in images. However, we have made a novel finding that challenges the prevailing wisdom. Our research reveals that NLA can be detrimental to SISR and even produce severely distorted textures. For example, when dealing with severely degrade textures, NLA may generate unrealistic results due to the inconsistency of non-local texture patterns. This problem is overlooked by existing works, which only measure the average reconstruction quality of the whole image, without considering the potential risks of using NLA. To address this issue, we propose a new perspective for evaluating the reconstruction quality of NLA, by focusing on the sub-pixel level that matches the pixel-wise fusion manner of NLA. From this perspective, we provide the approximate reconstruction performance upper bound of NLA, which guides us to design a concise yet effective Texture-Fidelity Strategy (TFS) to mitigate the degradation caused by NLA. Moreover, the proposed TFS can be conveniently integrated into existing NLA-based SISR models as a general building block. Based on the TFS, we develop a Deep Texture-Fidelity Network (DTFN), which achieves state-of-the-art performance for SISR. Our code and a pre-trained DTFN are available on GitHub†for verification.

Fully programmable valve array (FPVA) biochips have emerged as a promising alternative for traditional application-specific microfluidic platforms thanks to their advantages in terms of flexibility and reconfigurability. By regularly deploying microvalves along vertical and horizontal flow channels, microfluidic modules with different sizes and shapes can be constructed dynamically on the chip, thereby enabling the automatic execution of various assay procedures in biology and biochemistry. The above advantages, however, result largely from the large-scale integration of valves as well as accurate control of their switchings, leading to very complicated control-logic design of such chips. In this article, we propose an reinforcement learning (RL)-based synthesis flow for the control-logic design of fully programmable valve array (FPVA) biochips, taking multichannel switching and control-cost minimization into consideration simultaneously. By employing a double deep$Q$-network (DDQN) and two Boolean-logic simplification techniques, control logics with both high-switching efficiency and low-fabrication cost can be constructed automatically. Furthermore, the solution space of multichannel-switching combinations is reduced to improve the search efficiency of the proposed method. Experimental results on multiple benchmarks demonstrate that the proposed synthesis flow leads to better-design solutions compared with the state-of-the-art techniques.

Few-shot object detection achieves rapid detection of novel-class objects by training detectors with a minimal number of novel-class annotated instances. Transfer learning-based few-shot object detection methods have shown better performance compared to other methods such as meta-learning. However, when training with base-class data, the model may gradually bias towards learning the characteristics of each category in the base-class data, which could result in a decrease in learning ability during fine-tuning on novel classes, and further overfitting due to data scarcity. In this paper, we first find that the generalization performance of the base-class model has a significant impact on novel class detection performance and proposes a generalization feature extraction network framework to address this issue. This framework perturbs the base model during training to encourage it to learn generalization features and solves the impact of changes in object shape and size on overall detection performance, improving the generalization performance of the base model. Additionally, we propose a feature-level data augmentation method based on self-distillation to further enhance the overall generalization ability of the model. Our method achieves state-of-the-art results on both the COCO and PASCAL VOC datasets, with a 6.94% improvement on the PASCAL VOC 10-shot dataset.

Blind super-resolution (BlindSR) has recently attracted attention in the field of remote sensing. Due to the lack of paired data, most works assume that the acquired remote sensing images are high-resolution (HR) and use predefined degradation models to synthesize low-resolution (LR) images for training and evaluation. However, these acquired remote sensing images are often degraded by various factors, which still require super-resolution reconstruction to meet practical needs. Using them as ground truth images will limit the model’s ability to restore fine details, resulting in blurry and noisy reconstructions. To overcome these limitations, we propose an unsupervised degradation-aware network which transforms natural images into the degraded domain as real-world remote sensing images. It uses natural images containing rich texture information as a reference for fine-grained restoration of the network, enabling the network to produce clearer reconstructions. Furthermore, we discovered the remarkable capability of patch-wise discriminator to perceive the degradation type of different regions within the acquired remote sensing image. Inspired by this finding, we design a novel degradation representation module (DRM) that can estimate the degradation information from LR images and guide the network to perform adaptive restoration. Comprehensive experimental results demonstrate that our proposed unsupervised blind super-resolution framework (UDASR) achieves state-of-the-art restoration performance. Our code and pre-trained models have been uploaded to GitHub† for validation.

Recent developments in the field of non-local attention (NLA) have led to a renewed interest in self-similarity-based single image super-resolution (SISR). Researchers usually use the NLA to explore non-local self-similarity (NSS) in SISR and achieve satisfactory reconstruction results. However, a surprising phenomenon that the reconstruction performance of the standard NLA is similar to that of the NLA with randomly selected regions prompted us to revisit NLA. In this paper, we first analyzed the attention map of the standard NLA from different perspectives and discovered that the resulting probability distribution always has full support for every local feature, which implies a statistical waste of assigning values to irrelevant non-local features, especially for SISR which needs to model long-range dependence with a large number of redundant non-local features. Based on these findings, we introduced a concise yet effective soft thresholding operation to obtain high-similarity-pass attention (HSPA), which is beneficial for generating a more compact and interpretable distribution. Furthermore, we derived some key properties of the soft thresholding operation that enable training our HSPA in an end-to-end manner. The HSPA can be integrated into existing deep SISR models as an efficient general building block. In addition, to demonstrate the effectiveness of the HSPA, we constructed a deep high-similarity-pass attention network (HSPAN) by integrating a few HSPAs in a simple backbone. Extensive experimental results demonstrate that HSPAN outperforms state-of-the-art approaches on both quantitative and qualitative evaluations. Our code and a pre-trained model were uploaded to GitHub (https://github.com/laoyangui/HSPAN) for validation.

Multi-view data containing complementary and consensus information can facilitate representation learning by exploiting the intact integration of multi-view features. Because most objects in the real world often have underlying connections, organizing multi-view data as heterogeneous graphs is beneficial to extracting latent information among different objects. Due to the powerful capability to gather information of neighborhood nodes, in this article, we apply Graph Convolutional Network (GCN) to cope with heterogeneous graph data originating from multi-view data, which is still under-explored in the field of GCN. In order to improve the quality of network topology and alleviate the interference of noises yielded by graph fusion, some methods undertake sorting operations before the graph convolution procedure. These GCN-based methods generally sort and select the most confident neighborhood nodes for each vertex, such as picking the top- k nodes according to pre-defined confidence values. Nonetheless, this is problematic due to the non-differentiable sorting operators and inflexible graph embedding learning, which may result in blocked gradient computations and undesired performance. To cope with these issues, we propose a joint framework dubbed Multi-view Graph Convolutional Network with Differentiable Node Selection (MGCN-DNS), which is constituted of an adaptive graph fusion layer, a graph learning module, and a differentiable node selection schema. MGCN-DNS accepts multi-channel graph-structural data as inputs and aims to learn more robust graph fusion through a differentiable neural network. The effectiveness of the proposed method is verified by rigorous comparisons with considerable state-of-the-art approaches in terms of multi-view semi-supervised classification tasks, and the experimental results indicate that MGCN-DNS achieves pleasurable performance on several benchmark multi-view datasets.

Sparse crowdsensing collects data from a subset of the sensing area and infers data for unsensed areas, reducing data collection costs. Previous works have primarily focused on independently collecting and inferring single types of data. However, real-world scenarios often involve multiple types of data that can complement each other by providing missing spatiotemporal distribution information. In this paper, we fully consider both intra-data correlations among data of the same type and inter-data correlations among data of different types, enabling collaborative execution of various tasks. In addition, we enhance the adaptability in practical application scenarios by utilizing real-time collected sparse data to guide task execution. For this purpose, we propose a multi-task adaptive budgeting framework for online sparse crowdsensing, called MTAB-SC. This framework consists of three parts: training data updating, data inference, and data collection. Firstly, we propose a multi-task data updating method to keep models up-to-date. Secondly, we design a data inference network for multi-task data joint inference. Finally, to allocate suitable budgets for each task and facilitate collaborative data collection across multiple tasks, we propose an Adaptive Budgeting for Collaborative Data Collection model (AB-CoDC). The effectiveness of our proposals is demonstrated through extensive experiments on two real-world datasets.

Deep learning-based clustering methods, especially those incorporating deep generative models, have recently shown noticeable improvement on many multimedia benchmark datasets. However, existing generative models still suffer from unstable training, and the gradient vanishes, which results in the inability to learn desirable embedded features for clustering. In this paper, we aim to tackle this problem by exploring the capability of Wasserstein embedding in learning representative embedded features and introducing a new clustering module for jointly optimizing embedding learning and clustering. To this end, we propose Wasserstein embedding clustering (WEC), which integrates robust generative models with clustering. By directly minimizing the discrepancy between the prior and marginal distribution, we transform the optimization problem of Wasserstein distance from the original data space into embedding space, which differs from other generative approaches that optimize in the original data space. Consequently, it naturally allows us to construct a joint optimization framework with the designed clustering module in the embedding layer. Due to the substitutability of the penalty term in Wasserstein embedding, we further propose two types of deep clustering models by selecting different penalty terms. Comparative experiments conducted on nine publicly available multimedia datasets with several state-of-the-art methods demonstrate the effectiveness of our method.

Capturing images at night are susceptible to inadequate illumination conditions and motion blurring. Given the typical coupling of these two forms of degradation, a pioneer work takes a compact approach of brightening followed by deblurring. However, this sequential approach may compromise informative features and elevate the likelihood of generating unintended artifacts. In this paper, we observe that the co-existing low light and blurs intuitively impair multiple perceptions, making it difficult to produce visually appealing results. To meet these challenges, we propose perceptual decoupling with heterogeneous auxiliary tasks (PDHAT) for joint low-light image enhancement and deblurring. Based on the crucial perceptual properties of the two degradations, we construct two individual auxiliary tasks: coarse preview prediction (CPP) and high-frequency reconstruction (HFR), so that the perception of color, brightness, edges, and details are decoupled into heterogeneous auxiliary tasks to obtain task-specific representations for parallel assisting the main task: joint low-light enhancement and deblurring (LLE-Deblur). Furthermore, we develop dedicated modules to build the network blocks in each branch based on the exclusive properties of each task. Comprehensive experiments are conducted on LOL-Blur and Real-LOL-Blur datasets, showing that our method outperforms existing methods on quantitative metrics and qualitative results.

Graph convolutional network (GCN) with the powerful capacity to explore graph-structural data has gained noticeable success in recent years. Nonetheless, most of the existing GCN-based models suffer from the notorious over-smoothing issue, owing to which shallow networks are extensively adopted. This may be problematic for complex graph datasets because a deeper GCN should be beneficial to propagating information across remote neighbors. Recent works have devoted effort to addressing over-smoothing problems, including establishing residual connection structure or fusing predictions from multilayer models. Because of the indistinguishable embeddings from deep layers, it is reasonable to generate more reliable predictions before conducting the combination of outputs from various layers. In light of this, we propose an alternating graph-regularized neural network (AGNN) composed of graph convolutional layer (GCL) and graph embedding layer (GEL). GEL is derived from the graph-regularized optimization containing Laplacian embedding term, which can alleviate the over-smoothing problem by periodic projection from the low-order feature space onto the high-order space. With more distinguishable features of distinct layers, an improved Adaboost strategy is utilized to aggregate outputs from each layer, which explores integrated embeddings of multi-hop neighbors. The proposed model is evaluated via a large number of experiments including performance comparison with some multilayer or multi-order graph neural networks, which reveals the superior performance improvement of AGNN compared with the state-of-the-art models.

Continuous-flow microfluidic biochips are gaining increasing attention with promising applications for automatically executing various laboratory procedures in biology and biochemistry. Biochips with distributed channel-storage architectures enable each channel to switch between the roles of transportation and storage. Consequently, fluid transportation, caching, and fetch can occur concurrently through different flow paths. When two dissimilar types of fluidic flows occur through the same channels in a time-interleaved manner, it may cause contamination to the latter as some residues of the former flow may be stuck at the channel wall during transportation. To remove the residues, wash operations are introduced as an essential step to avoid incorrect assay outcomes. However, existing work has been considered that the washing capacity of a buffer fluid is unlimited. In the actual scenario, a fixed-volume buffer fluid irrefutably possesses a limited washing capacity, which can be successively consumed while washing away residues from the channels. Hence, capacity-aware wash scheme is a basic requirement to fulfil the dynamic fluid scheduling and channel storage. In this paper, we formulate a practical wash optimization problem for microfluidic biochips, which considers the requirements of dynamic fluid scheduling, channel storage, as well as washing capacity constraints of buffer fluids simultaneously, and present an efficient design flow to solve this problem systematically. Given the high-level synthesis result of a biochemical application and the corresponding component placement solution, our goal is to complete a contamination-aware flow-path planning with short flow-channel length. Meanwhile, the biochemical application can be executed efficiently and correctly with an optimized capacity-aware wash scheme. Experimental results show that compared to a state-of-the-art washing method, the proposed method achieves an average reduction of 26.1%, 43.1%, and 34.1% across all the benchmarks with respect to the total channel length, total wash time, and execution time of bioassays, respectively.

Mobile Crowdsensing (MCS) is a sensing paradigm that enables large-scale smart city applications, such as environmental sensing and traffic monitoring. However, traditional MCS often suffers from performance degradation due to the limited spatiotemporal coverage of collected data. In this context, Sparse MCS has been proposed, which utilizes data inference algorithms to recover full data from sparse data collected by users. However, existing Sparse MCS approaches often overlook spatiotemporal fractures, where no data is observed either for a sensing subarea across all sensing time slots (temporal fracture), or for a sensing time slot in all sensing subarea (spatial fracture). Such spatiotemporal fractures pose great challenges to the data inference algorithms, as it is difficult to capture the complex spatiotemporal correlations of the sensing data from very limited observations. To address this issue, we propose a Graph-and Attention-based Matrix Completion (GAMC) method for the spatiotemporal fracture data inference problem in Sparse MCS. Specifically, we first pre-fill the general missing values using the classical Matrix Factorization (MF) technique. Then, we propose a neural network architecture based on Graph Attention Networks (GAT) and Transformer to capture complex spatiotemporal dependencies in the sensing data. Finally, we recover the complete data with a projection layer. We conduct extensive experiments on three real-world urban sensing datasets. The experimental results show the effectiveness of the proposed method.

Global routing is an extremely important stage of very large scale integration (VLSI) physical design. With the rise of nano-scale integrated circuit design, the multilayer global routing problem has attracted considerable research interest during the past few years. In this article, a multilayer X-architecture global routing (ML-XGR) system based on particle swarm optimization (PSO), called FZU-Router, is proposed to solve the ML-XGR problem for the first time. FZU-Router contains a multilayer X-architecture integer linear programming (MX-ILP) model and a multilayer X-architecture PSO (MX-PSO) algorithm, which are presented to formulate and solve the ML-XGR problem, respectively. Moreover, four effective strategies are designed to enhance the efficiency of FZU-Router: 1) a strategy for generating new routing modes is proposed to strengthen the robustness of encoding strategy of MX-PSO; 2) a strategy for combining MX-PSO with maze routing is proposed to improve the routability; 3) a strategy for reducing the channel capacity is proposed to make better use of optimization ability of MX-PSO; and 4) a strategy for dynamic resource assignment is proposed to make better use of routing resources and shorten the running time. Experimental results on multiple benchmarks confirm that the proposed FZU-Router leads to fewer total overflow and shorter total wirelength compared with the state-of-the-art routers.

SMT is an optimized model for solving the routing problem of a multipin net in very large-scale integrated circuits. As the appearance of various obstacles on chips, the obstacle-avoiding problem has attracted much attention in recent years. Meanwhile, since interconnect delay plays a major role in chip delay, timing analysis is another critical problem worthy of consideration when constructing an Steiner minimum tree (SMT). Furthermore, the introduction of theX-architecture allows for better utilization of routing resources. In this article, a timing-driven obstacle-avoiding X-architecture Steiner minimum tree algorithm with slack constraints (TD-OAXSMT-SC) is proposed to consider obstacle-avoiding, timing slack constraints, andX-architecture simultaneously for the first time. The TD-OAXSMT-SC algorithm consists of four major stages: 1) in the routing tree initialization stage, this article constructs anX-architecture Prim–Dijkstra spanning tree as the initial routing tree with minimum total delay; 2) in the particle swarm optimization (PSO)-based routing tree iteration stage, a novel discrete PSO algorithm based on genetic operators is proposed to obtain a high-quality routing tree; 3) in the routing tree standardization stage, two effective standardization strategies are proposed to obtain a routing tree that satisfies both obstacle-avoiding and timing slack constraints; and 4) in the routing tree optimization stage, the connection of interconnected wires is optimized in a global manner, thus obtaining an optimized routing tree. Experimental results show that the proposed TD-OAXSMT-SC algorithm outperforms the state-of-the-art methods in routing quality with slack constraints.

Due to the powerful capability to gather the information of neighborhood nodes, Graph Convolutional Network (GCN) has become a widely explored hotspot in recent years. As a well-established extension, Graph AutoEncoder (GAE) succeeds in mining underlying node representations via evaluating the quality of adjacency matrix reconstruction from learned features. However, limited works on GAE were devoted to leveraging both semantic and topological graphs, and they only indirectly extracted the relationships between graphs via weights shared by features. To better capture the connections between nodes from these two types of graphs, this paper proposes a graph neural network dubbed Dual Low-Rank Graph AutoEncoder (DLR-GAE), which takes both semantic and topological homophily into consideration. Differing from prior works that share common weights between GCNs, the presented DLR-GAE conducts sustained exploration of low-rank information between two distinct graphs, and reconstructs adjacency matrices from learned latent factors and embeddings. In order to obtain valid adjacency matrices that meet certain conditions, we design some surrogates and projections to restrict the learned factor matrix. We compare the proposed model with state-of-the-art methods on several datasets, which demonstrates the superior accuracy of DLR-GAE in semi-supervised classification.

As a new generation of flow-based microfluidics, the Fully Programmable Valve Array (FPVA) biochips have become a popular biochemical experimental platform that provide higher flexibility and programmability. Due to environmental and human factors, however, there are usually some physical faults in the manufacturing process such as channel blockage and leakage, which, undoubtedly, can affect the results of bioassays and even cause execution failure. Accordingly, we focus on the fault-tolerant design of FPVA biochips for the first time in this paper, and present three dynamic fault-tolerant techniques including a cell function conversion method, a bidirectional redundancy scheme, and a fault mapping method. By integrating these techniques into the component placement and channel routing stages, we further realize an efficient and effective fault-tolerance-oriented physical design approach for FPVA biochips, thus ensuring the robustness of chip architecture and correctness of assay outcomes. Experimental results on multiple benchmarks confirm that the proposed approach can generate fault-tolerant FPVA architectures with both high execution efficiency and low fabrication cost.

Transferability of adversarial examples is of critical importance to launch black-box adversarial attacks, where attackers are only allowed to access the output of the target model. However, under such a challenging but practical setting, the crafted adversarial examples are always prone to overfitting to the proxy model employed, presenting poor transferability. In this paper, we suggest alleviating the overfitting issue from a novel perspective, i.e., designing a fitted model architecture. Specifically, delving the bottom of the cause of poor transferability, we arguably decompose and reconstruct the existing model architecture into an effective model architecture, namely multi-track model architecture (MMA). The adversarial examples crafted on the MMA can maximumly relieve the effect of model-specified features to it and toward the vulnerable directions adopted by diverse architectures. Extensive experimental evaluation demonstrates that the transferability of adversarial examples based on the MMA significantly surpass other state-of-the-art model architectures by up to 40% with comparable overhead.

Point clouds semantic labeling is an important task in 3D computer vision. Current major researches focus on fully supervised learning. However, point-by-point manual annotations are expensive and time-consuming. To this end, we propose a general point clouds deep active learning framework to ease the annotation burden for researchers. In this work, we propose a conditional random field (CRF) based pseudo labels generation to provide more supervised information for deep neural network (DNN) and employ Golden Loss Correction (GLC) to correct pseudo labeled data training loss. Finally, we propose the Modified Margin acquisition function which can select the most valuable points for labeling. We demonstrate the improvements provided by our proposed method on the S3DIS benchmark.

Graph neural networks (GNNs) have been applied successfully in many machine learning tasks due to their advantages in utilizing neighboring information. Recently, with the global enactment of privacy protection regulations, federated GNNs have gained increasing attention in academia and industry. However, the graphs owned by different participants could be non-independently-and-identically distributed (non-IID), leading to the deterioration of federated GNNs' accuracy. In this paper, we propose a globally consistent federated graph autoencoder (GCFGAE) to overcome the non-IID problem in unsupervised federated graph learning via three innovations. First, by integrating federated learning with split learning, we train a unique global model instead of FedAvg-styled global and local models, yielding results consistent with that of the centralized GAE. Second, we design a collaborative computation mechanism considering overlapping vertices to reduce communication overhead during forward propagation. Third, we develop a layer-wise and block-wise gradient computation strategy to reduce the space and communication complexity during backward propagation. Experiments on real-world datasets demonstrate that GCFGAE achieves not only higher accuracy but also around 500 times lower communication overhead and 1000 times smaller space overhead than existing federated GNN models.

As researchers strive to narrow the gap between machine intelligence and human through the development of artificial intelligence multimedia technologies, it is imperative that we recognize the critical importance of trustworthiness in open-world, which has become ubiquitous in all aspects of daily life for everyone. However, several challenges may create a crisis of trust in current open-world artificial multimedia systems that need to be bridged: 1) Insufficient explanation of predictive results; 2) Inadequate generalization for learning models; 3) Poor adaptability to uncertain environments. Consequently, we explore a neural program to bridge trustworthiness and open-world learning, extending from single-modal to multi-modal scenarios for readers.1) To enhance design-level interpretability, we first customize trustworthy networks with specific physical meanings; 2) We then design environmental well-being task-interfaces via flexible learning regularizers for improving the generalization of trustworthy learning; 3) We propose to increase the robustness of trustworthy learning by integrating open-world recognition losses with agent mechanisms. Eventually, we enhance various trustworthy properties through the establishment of design-level explainability, environmental well-being task-interfaces and open-world recognition programs. As a result, these designed open-world protocols are applicable across a wide range of surroundings, under open-world multimedia recognition scenarios with significant performance improvements observed.

Community detection is an important research direction in complex network analysis that can help us discover valuable network structures. The community detection algorithms based on multiobjective particle swarm optimization encode community membership of nodes in particles and employ evolutionary strategies to search for the optimal community division. Existing algorithms face two challenges: (1) they are inapplicable to large networks because the evolution process is time-consuming; (2) they are easy to fall into local optima. In this paper, we propose a novel algorithm that combines a label-propagation-based multiobjective particle swarm optimization algorithm with a graph attention variational autoencoder to realize community detection. On the one hand, the label propagation strategy is involved in the update of a swarm's particles to speed up its evolution. The optimal solutions found by the particle swarm optimization algorithm are embedded into the objective of the autoencoder to improve the embedding vectors’ quality. On the other hand, the embedding vectors are used to improve the solutions of the particle swarm optimization algorithm to avoid its early convergence. The experiments on artificial and real-world networks demonstrate the feasibility and effectiveness of our algorithm compared with some state-of-the-art algorithms.

Unsupervised clustering is a crucial issue in data mining and pattern recognition. Based on deep learning paradigms, deep clustering algorithms have been studied extensively and obtained superior performance in various applications. However, most of previous methods did not use helpful information from neighborhood relations to form group-separated space, and the feature embedding is usually distorted during the training process. To tackle the former limitation, we develop a graph convolution based unsupervised learning algorithm named Stacked Graph Autoencoder (SGAE). Specifically, SGAE utilizes the message passing mechanism to aggregate information from neighbors and obtain a meaningful and separated latent representation. Since the adjacency matrix is unavailable in clustering tasks, a graph construction approach with two pruning strategies is introduced to generate a transition matrix. To reduce the distortion caused by the multi-layered network training process, we further propose a topological structure preservation mechanism. It uses the constructed adjacency graph as supervised information, to maintain the relationship between nodes in the original space. Experiments on several popular benchmark datasets show that SGAE achieves significant improvements compared to unsupervised and semi-supervised deep clustering methods.

Owing to the high complexity of chip architecture and assay protocol, considerable effort has been directed toward the design automation of continuous-flow microfluidics over the past decade. Existing methods, however, perform the corresponding design tasks, including binding, scheduling, placement, and routing separately, leading to serious gaps between different steps and potentially even cause design failure. To overcome these drawbacks, in this article, we propose a one-pass design paradigm for continuous-flow microfluidic lab-on-a-chip systems, integrating all the design steps into an “organic whole,” which has never been considered in prior work. With the proposed paradigm, all the design tasks can be synchronized seamlessly and performed in a combined manner, thereby eliminating the gaps between design steps. Consequently, optimized biochip architectures can be generated without any design adjustments and modifications. The experimental results demonstrate the effectiveness of the proposed automation flows.

In this article, we proposedualtraceabledistributedattributebasedencryption withsubsetkeywordsearch system (DT-DABE-SKS, abbreviated as$\mathcal {DT}$) to simultaneously realize data source trace (secure provenance) and user trace (traitor trace) and flexible subset keyword search from polynomial interpolation. Leveraging non-interactive zero-knowledge proof technology,$\mathcal {DT}$preserves privacy for both data providers and users in normal circumstances, but a trusted authority can disclose their real identities if necessary, such as the providers deceitfully uploading false data or users maliciously leaking secret attribute key. Next, we introduce the new conception of updatable and transferable message-lock encryption (UT-MLE) for block-level dynamic encrypted file update, where the owner does not have to download the whole ciphertext, decrypt, re-encrypt and upload for minor document modifications. In addition, the owner is permitted to transfer file ownership to other system customers with efficient computation in an authenticated manner. A nontrivial integration of$\mathcal {DT}$and UT-MLE lead to the distributed ABSE with ownership transfer system ($\mathcal {DTOT}$) to enjoy the above merits. We formally define$\mathcal {DT}$, UT-MLE, and their security model. Then, the instantiations of$\mathcal {DT}$and UT-MLE, and the formal security proof are presented. Comprehensive comparison and experimental analysis based on real dataset affirm their feasibility.

Community detection is a fundamental problem in complex network analysis that aims to find closely related groups of nodes. Recently, network embedding techniques have been integrated into community detection in two manners to capture the intricate relationships between nodes. The two-staged manner generates node embedding vectors and obtains communities by running a clustering algorithm on them. The single-staged manner simultaneously obtains node embedding vectors and communities by optimizing a hybrid objective concerning with node–community relationships. The general-purpose network embedding algorithms used in the first manner do not emphasize retaining node–community relationships. The second manner ignores the influence of a node’s location in a community (at the center or boundary) and its attributes on community generation. In this article, we propose a biased-random-walk-based community detection (BRWCD) algorithm to tackle the issues. First, a topology-weighted degree is designed to enhance the random walk at the boundary of and inside a community to extract communities precisely. Second, we design an attribute-to-node influence index and an attribute-weighted degree to distinguish different attributes’ influence on node transition to obtain communities with high internal cohesion. Comprehensive experiments on the real-world and synthetic networks demonstrate that BRWCD achieves nearly 10% higher accuracy at most than the state-of-the-art algorithms.

Taking photos of digital screens often produces color-distorting moire patterns caused by inconsistency between the color filter array of cameras and the sub-pixel layout of screens, which severely degrades the quality of photos. Most existing demoireing methods employ multi-stream network architecture to simultaneously process the same moire image with different resolutions, but they neglect the complementarity among different resolutions. In this paper, we propose a novel moire removal model to address this issue. Unlike the existing multi-stream based approaches, in this model, we present a progressive texture complementation block to exploit the complementary information from different resolutions in order to progressively remove moire textures and restore image content. Additionally, we propose a residual moire removal block, in which the depthwise separable convolution is utilized to remove moire from image while reducing computation overhead. This block also includes a local color correction structure, which is used to correct color shifts presented in the moire images. Experimental results on two public datasets show that our method outperforms state-of-the-art methods. Besides, the quantity of parameters and FLOPs of our model are tens of times fewer than the off-the-shelf models. Furthermore, our network framework can adapt well to another low-level vision task, rain removal, in which our model also achieves state-of-the-art performance.

Community structure is a typical characteristic of complex networks. Finding communities in complex networks has many important applications, such as the advertisement and recommendation based on social networks and the discovery of new protein molecules in biological networks, which make it a hot topic in the field of complex network analysis. With the increasing concerns about the leakage of personal privacy, discovering communities spread across the local networks owned by multiple participants accurately while preserving each participant’s privacy has become an emerging challenge in distributed community detection. In this article, we propose a general federated graph learning model for privacy-preserving distributed graph learning and develop two federated clique percolation algorithms (CPAs) based on it to discover overlapping communities distributed across multiple participants’ local networks without disclosing any participant’s network privacy. Homomorphic encryption and hash operation are used in combination to protect the privacy of the vertices and edges of each local network. Furthermore, vertex attributes are involved in the calculation of clique similarity and clique percolation when dealing with attributed networks. The experimental results on real-world and artificial datasets demonstrate that the proposed algorithms achieve identical results to those of their stand-alone counterparts and more than 200% higher accuracy than the simple distributed CPAs without federating learning.

Recently, with the development of deep learning, Automatic License Plate Recognition (ALPR) has made great progress, However, there are still many challenges to accomplish license plate (LP) recognition under various traffic scenarios. One of them is the detection speed and recognition speed, and the other is the difficulty to recognize the low resolution and highly tilted LP images. In this paper, we present a two-stage ALPR framework to achieve efficient LP detection and recognition in unconstrained scenarios. Our LP detector is based on improved Yolov3-tiny, and we also propose a lightweight recognition network MRNet based on multi-scale features. In order to improve the inference speed, we abandoned the rectification of LP images, and RNNs that are difficult to compute in parallel. Additionally, we also propose a license plate data augmentation method, which achieves more effective augmentation and improves the generalization ability of the network through secondary random and hyperparametric search. As an additional contribution, we provide a challenging dataset collected from real-world driving recorders. The dataset is for multiple LPs in a single image, which makes up for the lack of public datasets in multiple LP scenarios. We evaluated the results on five datasets and showed that we achieved the best performance on almost all test sets, achieving 99.8% accuracy on CCPD with more than 180,000 license plate test sets. In terms of speed, the inference speed for detecting license plates reaches 751 FPS, and the fastest inference time for recognizing a single license plate takes only 2.9 ms.

Semi-supervised learning is a common way that investigates how to improve performance of a visual learning model, while data annotation is far from sufficient. Recent works in semi-supervised deep learning have successfully applied consistency regularization, which encourages a model to maintain consistent predictions for different perturbed versions of an image. However, most of such methods ignore the category correlation of image features, especially when exploiting strong augmentation methods for unlabeled images. To address this problem, we propose PConMatch, a model that leverages a probabilistic contrastive learning framework to separate the features of strongly-augmented versions from different classes. A semi-supervised probabilistic contrastive loss is designed, which takes both labeled and unlabeled samples into account and develops an auxiliary module to generate a probability score to measure the model prediction confidence for each sample. Specifically, PConMatch first generates a pair of weakly-augmented versions for each labeled sample, and produces a weakly-augmented version and a corresponding pair of strongly-augmented versions for each unlabeled sample. Second, a probability score module is proposed to assign pseudo-labeling confidence scores to strongly-augmented unlabeled images. Finally, the probability score of each sample is further passed to the contrastive loss, combining with consistency regularization to enable the model to learn better feature representations. Extensive experiments on four publicly available image classification benchmarks demonstrate that the proposed approach achieves state-of-the-art performance in image classification. Several rigorous ablation studies are conducted to validate the effectiveness of the method.

Continuous-flow microfluidic biochips have emerged as a potential low-cost and fast-responsive lab-on-chip platform. They have attracted much attention due to their capability of performing various biochemical applications concurrently and automatically within a coin-sized chip area. To improve execution efficiency and reduce fabrication cost, a distributed channel-storage architecture can be implemented in which the same channels can be switched between the roles of transportation and storage. Accordingly, fluid transportation, caching, and fetch can be performed simultaneously through different flow paths. Such a flow-path planning needs to be considered carefully in the mapping procedure from a biochemical application to a given biochip architecture. Moreover, all the on-chip valves should be actuated correctly and promptly to temporally block the fluid transportation in unwanted directions and seal the fluids in caching channels. Such an exact control of the valves needs to be considered systematically in control-system design to support the mapping scheme for bioassay execution. In this article, we formulate the practical mapping-control co-design problem for microfluidic biochips with distributed channel storage, considering application mapping, valve synchronization, and control-system design simultaneously, and present an efficient synthesis flow to solve this problem systematically. Given the protocol of a biochemical application and the corresponding chip layout in the flow layer, our goal is to map the biochemical application onto the chip with short execution time. Meanwhile, a practical control system considering the real valve-switching requirements can be constructed efficiently with low fabrication cost. Experimental results on multiple real-life bioassays and synthetic benchmarks demonstrate the effectiveness of the proposed design flow.

Recently deep learning methods have shown significant progress in data clustering tasks. Deep clustering methods (including distance-based methods and subspace-based methods) integrate clustering and feature learning into a unified framework, where there is a mutual promotion between clustering and representation. However, deep subspace clustering methods are usually in the framework of self-expressive model and hence have quadratic time and space complexities, which prevents their applications in large-scale clustering and real-time clustering. In this paper, we propose a new mechanism for deep clustering. We aim to learn the subspace bases from deep representation in an iterative refining manner while the refined subspace bases help learning the representation of the deep neural networks in return. The proposed method is out of the self-expressive framework, scales to the sample size linearly, and is applicable to arbitrarily large datasets and online clustering scenarios. More importantly, the clustering accuracy of the proposed method is much higher than its competitors. Extensive comparison studies with state-of-the-art clustering approaches on benchmark datasets demonstrate the superiority of the proposed method.

As the last stage of VLSI routing, detailed routing should consider complicated design rules in order to meet the manufacturability of chips. With the continuous development of VLSI technology node, the design rules are changing and increasing which makes detailed routing a hard task. In this paper, we present a practical track-assignment-based detailed router to deal with the most representative design rules in modern designs. The proposed router consists of four major stages: (1) a graph-based track assignment algorithm is proposed to optimize the design rule violations of an entire die area; (2) an effective rip-up and reroute method is used to reduce the design rule violations in local regions; (3) a segment migration algorithm is proposed to reduce short violations; and (4) a stack via optimization technique is proposed to reduce minimum area violations. Practical benchmarks from 2019 ISPD contest are used to evaluate the proposed router. Compared with the state-of-the-art detailed router, Dr. CU 2.0, the number of violations can be reduced by up to 35.11 % with an average reduction rate of 10.08 %. The area of short can be reduced by up to 61.49 % with an average reduction rate of 44.80 %.

Adversarial training is believed to be the most robust and effective defense method against adversarial attacks. Gradient-based adversarial attack methods are generally adopted to evaluate the effectiveness of adversarial training. However, in this paper, by diving into the existing adversarial attack literature, we find that adversarial examples generated by these attack methods tend to be less imperceptible, which may lead to an inaccurate estimation for the effectiveness of the adversarial training. The existing adversarial attacks mostly adopt gradient-based optimization methods and such optimization methods have difficulties in searching the most effective adversarial examples (i.e., the global extreme points). On the contrast, in this work, we propose a novel Non-Gradient Attack (NGA) to overcome the above-mentioned problem. Extensive experiments show that NGA significantly outperforms the state-of-the-art adversarial attacks on Attack Success Rate (ASR) by 2% ∼ 7%.

Recently, laser scanning system is widely used to accurately predict forest inventory attributes. In this work, we propose an efficient framework including Feature Extractor Module and Conditional Adversarial Module for object classification in 3D heterogeneous point clouds. The Feature Extractor Module can aggregate features of objects in point clouds. For domain adaptation task, the Conditional Adversarial Module is proposed to minimize the discrepancy of source and target domains. Since there is no common evaluation benchmark for object classification in 3D point cloud, we build a bench-mark of six tasks from three 3D objects datasets. Evaluations on six tasks with four categories have demonstrated the effectiveness of our proposed framework of object classification. The framework can be applied potentially in forest management.

Nowadays, the impressive performance of deep neural networks (DNNs) greatly advances the development of Internet of Things (IoT) in diverse scenarios. However, the exceptional vulnerability of DNNs to adversarial attack leads IoT devices to be exposed to potential security issues. Up to now, since adversarial training empirically remains robust against gradient-based adversarial attacks, it is believed to be the most effective defense method. In this article, we find that adversarial examples generated by gradient-based adversarial attacks tend to be less imperceptible induced by the gradient-based optimization methods (adopted in the attacks) being difficult on searching the most effective adversarial examples (i.e., the global extreme points), which may lead to an inaccurate estimation for the effectiveness of the adversarial training. To overcome the inherent defect of gradient-based adversarial attacks, we propose a novel adversarial attack named nongradient attack (NGA), of which search strategy is effective but no longer depends on gradients to enhance the threat of adversarial examples. In detail, NGA first initializes the adversarial examples outside, rather than inside, of decision boundary to make them misclassified by the model and then, under without violation of misclassified condition, adjusts the adversarial examples toward the crafted direction to close the original examples. Extensive experiments show that NGA significantly outperforms the state-of-the-art adversarial attacks on attack success rate (ASR) by 2%–7%. Moreover, we propose a new evaluation metric, i.e., composite criterion (CC) based on both ASR and accuracy, to better measure the effectiveness of adversarial training. In the experiments, CC has shown to be a more comprehensive yet appropriate evaluation metric.

Nowadays, researchers have developed various deep neural networks for processing point clouds effectively. Due to the enormous parameters in deep learning-based models, a lot of manual efforts have to be invested into annotating sufficient training samples. To mitigate such manual efforts of annotating samples for a new scanning device, this letter focuses on proposing a new neural network to achieve domain adaptation in 3D object classification. Specifically, to minimize the data discrepancy of intra-class objects in different domains, an Asymmetrical Siamese module is designed to align the intra-class features. To preserve the discriminative information for distinguishing inter-class objects in different domains, a Conditional Adversarial module is leveraged to consider the classification information conveyed from the classifier. To verify the effectiveness of the proposed method on object classification in heterogeneous point clouds, evaluations are conducted on three point cloud datasets, which are collected in different scenarios by different laser scanning devices. Furthermore, the comparative experiments also demonstrate the superior performance of the proposed method on the classification accuracy.

Semantic segmentation in high-resolution aerial images is a fundamental and challenging task with a wide range of applications. Although many segmentation methods with convolutional neural networks have achieved inspiring results, it is still difficult to distinguish regions with similar spectral features only using high-resolution data. Besides, the traditional data-independent upsampling methods may lead to sub-optimal results. This letter proposes a multisensor data fusion model (MSDFM). Following the classical encoder-decoder structure, MSDFM regards colored digital surface models (colored-DSM) data as a complementary input for further detailed feature extraction. A data-dependent upsampling (DUpsampling) method is adopted in the decoder stage instead of the common up-sampling approaches to improve the classification accuracy of pixels of the small objects. Extensive experiments on Vaihingen and Potsdam datasets demonstrate that our proposed MSDFM outperforms most related models. Significantly, segmentation performance for the car category surpasses state-of-the-art methods over the ISPRS Vaihingen dataset.

System-architecture design optimization of flow-based microfluidic biochips has been extensively investigated over the past decade. Most of the prior work, however, is still based on chip architectures with dedicated storage units and this, not only limits the performance of biochips, but also increases their fabrication cost. To overcome this limitation, a distributed channel-storage architecture can be implemented, where fluid samples can be cached temporarily in flow channels instead of using a dedicated storage. This new concept of fluid storage, however, requires a careful arrangement of fluid samples to enable the channels to fulfill the dual functions of transportation and caching. Moreover, to avoid cross-contamination between different fluidic flows, wash operations are necessary to remove the residue left in flow channels. In this article, we formulate the first practical system level design and wash optimization problem for microfluidic biochips with distributed channel storage architecture, considering high-level synthesis, physical design, and wash optimization simultaneously, and present a top-down design flow to solve this problem systematically. Given the protocol of a biochemical application and the corresponding design requirements, our goal is to generate a chip architecture with low fabrication cost. Meanwhile the biochemical application can be executed efficiently with an optimized wash scheme. Experimental results on multiple benchmarks confirm that our approach leads to short completion time of biochemical applications, low chip cost, as well as high wash efficiency.

Recent advances in continuous-flow microfluidics have enabled highly integrated lab-on-a-chip biochips. These chips can execute complex biochemical applications precisely and efficiently within a tiny area, but they require a large number of control ports and the corresponding control logic to generate required pressure patterns for flow control, which, consequently, offset their advantages and prevent their wide adoption. In this article, we propose the first flow-control layer co-synthesis flow called MiniControl, for continuous-flow microfluidic biochips under strict constraints for control ports, incorporating high-level synthesis, physical design, and control system design simultaneously, which has never been considered in previous work. With the maximum number of allowed control ports specified in advance, this synthesis flow aims to generate biochip architectures with high execution efficiency and the corresponding control systems with optimized timing performance. Besides, the overall cost of a biochip can be reduced and the tradeoff between a control system and execution efficiency of biochemical applications can be evaluated for the first time. The experimental results demonstrate that MiniControl leads to high execution efficiency, low platform cost, as well as excellent timing performance, while strictly satisfying the given control-port constraints.

Continuous-flow microfluidic biochips have attracted high research interest over the past years. Inside such a chip, fluid samples of milliliter volumes are efficiently transported between devices (e.g., mixers, heaters, etc.) to automatically perform various laboratory procedures in biology and biochemistry. Each transportation task, however, requires an exclusive flow path composed of multiple contiguous microchannels during its execution period. Excess/waste fluids, in the meantime, should be discarded by independent flow paths connected to waste ports. All these paths are etched in a very tiny chip area using multilayer soft lithography and driven by flow ports connecting with external pressure sources, forming a highly integrated chip architecture that determines the final performance of biochips. In this article, we propose a new and practical design flow called PathDriver+ (PD+) for the architecture design of microfluidic biochips, integrating the actual fluid manipulations into both high-level synthesis and physical design, which has never been considered in prior work. With this design flow, highly efficient chip architectures with a flow-path network that enables the actual fluid transportation and removal can be constructed automatically. Meanwhile, fluid volume management between devices and flow-path minimization are realized for the first time, thus, ensuring the correctness of assay outcomes while reducing the complexity of chip architectures. Additionally, diagonal channel routing is implemented to fundamentally improve the chip performance. The tradeoff between the numbers of channel intersections and fluidic ports is evaluated to further reduce the fabrication cost of biochips. The experimental results on multiple benchmarks confirm that the proposed design flow leads to high assay execution efficiency and low overall chip cost.

Interconnect delay is a key factor that affects the chip performance in layer assignment. Particularly in the advanced process technologies of 5 nm and beyond, interconnect delay has grown significantly due to the increase of circuit scale. Moreover, coupling effect existed in wires reduces the accuracy of delay evaluation. On the other hand, the size of vias is often ignored in layer assignment, which enlarges the mismatch between global routing and detailed routing. To solve these problems, we proposeVPT, a timing-aware layer assignment algorithm considering via pillars, which includes the following five key techniques: 1) via pillar structure combined with nondefault-rule (NDR) wires is adopted to form a net delay optimization system for advanced process technologies; 2) a synthetical model that can adapt to varying types and sizes of both vias and wires is designed to evaluate overflow effectively; 3) a sorting strategy is devised to reduce uncertainty of layer assignment flow and improve stability of the proposed algorithm; 4) an awareness strategy based on multiaspect congestion assessment is designed to reduce overflow significantly; and 5) a net scalpel algorithm is devised to minimize the maximum delay of nets, so that the timing behaviors can be improved systematically. The experimental results on multiple benchmarks confirm that the proposed algorithm leads to lower delay and less overflow, while achieving the best solution quality among the existing algorithms with the shortest runtime.

Complex networks in real world are always in the state of evolution and composed of numerous overlapping communities. The discovery of overlapping communities in dynamic networks plays an important role in community detection research. In recent years, methods based on incremental clustering have become increasingly popular owing to their high efficiency. However, few of them can deal with communities that are both overlapping and dynamic. In this article, we propose an incremental clustering algorithm for discovering overlapping communities in dynamic networks. In the initial snapshot of a dynamic network, a degree-based seed selection strategy with concise and effective rules is employed to obtain stable and high-quality overlapping communities, in which the degree of nodes is the number of their neighboring nodes in the subgraph composed of free nodes. In the subsequent snapshots, a four-staged framework based on cascade information diffusion is proposed to update the communities incrementally. In this framework, a cascade information diffusion model is used to simulate the evolution of communities and then the fitness of nodes to the communities they belong to is updated based on node similarity. Experiments conducted on both real-world and artificial datasets show that the proposed algorithm can discover overlapping communities in dynamic networks effectively and outperform to the state-of-art baseline algorithms.

Person search, consisting of jointly or separately trained person detection stage and person Re-ID stage, suffers from significant challenges such as inefficiency and difficulty in acquiring discriminative features. However, certain work has either turned to the end-to-end framework whose performance is limited by task conflicts or has consistently attempted to obtain more accurate bounding boxes (Bboxes). Few studies have focused on the impact of sample-specificity in person search datasets for training a fine-grain Re-ID model, and few have considered obtaining discriminative Re-ID features from Bboxes in a more efficient way. In this paper, a novel sample-enhanced and instance-sensitive (SEIE) framework is designed to boost performance. By analyzing the structure of person search framework, our method refines the two stages separately. For the detection stage, we re-design the usage of Bbox and a sample enhancement combination is proposed to further enhance the quality and quantity of Bboxes. SEC can suppress false positive detection results and randomly generate high-quality positive samples. For the Re-ID stage, we contribute an instance similarity loss to exploit the similarity between classless instances, and an Omni-scale Re-ID backbone is employed to learn more discriminative features. We obtain a more efficient and discriminative person search framework by concatenating the two stages. Extensive experiments demonstrate that our method achieves state-of-the-art performance with a high speed, and significantly outperforms other existing methods.

As an emerging lab-on-a-chip technology platform, digital microfluidic biochips (DMFBs) have been widely used for executing various laboratory procedures in biochemistry and biomedicine such as gene sequencing and near-patient diagnosis, with the advantages of low reagent consumption, high precision, and miniaturization and integration. With the ongoing rapid deployment of DMFBs, however, these devices are now facing serious and complicated security challenges that not only damage their functional integrity but also affect their system reliability. In this article, we present a systematic review of DMFB security, focusing on both the state-of-the-art attack and defense techniques. First, the overall security situation, the working principle, and the corresponding fabrication technology of DMFBs are introduced. Afterwards, existing attack approaches are divided into several categories and discussed in detail, including denial of service, intellectual property piracy, bioassay tampering, layout modification, actuation sequence tampering, concentration altering, parameter modification, reading forgery, and information leakage. To prevent biochips from being damaged by these attack behaviors, a number of defense measures have been proposed in recent years. Accordingly, we further classify these techniques into three categories according to their respective defense purposes, including confidentiality protection, integrity protection, and availability protection. These measures, to varying degrees, can provide effective protection for DMFBs. Finally, key trends and directions for future research that are related to the security of DMFBs are discussed from several aspects, e.g., manufacturing materials, biochip structure, and usage environment, thus providing new ideas for future biochip protection.

As the scale of VLSI circuits increases rapidly, multi-FPGA prototyping systems have been widely used for logic verification. Due to the limited number of connections between FPGAs, however, the routability of prototyping systems is a bottleneck. As a consequence, timing division multiplexing (TDM) technique has been proposed to improve the usability of prototyping systems, but it causes a dramatic increase in system delay. In this paper, we propose ALIFRouter, a practical architecture-level inter-FPGA router, to improve the chip performance by reducing the corresponding system delay. ALIFRouter consists of three major stages, including i) routing topology generation, ii) TDM ratio assignment, and iii) system delay optimization. Additionally, a multi-thread parallelization method is integrated into the three stages to improve the efficiency of ALIFRouter. With the proposed algorithm, major performance indicators of multi-FPGA systems such as signal multiplexing ratio can be improved significantly.

The emergence of continuous-flow microfluidics has led to a revolution in biochemistry and biomedicine. On such a microscale lab-on-a-chip system, complex biochemical assays, e.g., DNA analysis and drug discovery, can be executed efficiently without any human intervention. Owing to the high complexity of chip architecture and assay protocol, considerable effort has been directed towards the design automation of such chips over the past decade. Existing methods, however, perform the corresponding design tasks including binding, scheduling, placement, and routing separately, leading to serious gaps between different steps and may even cause design failure. To overcome these drawbacks, in this paper, we propose a one-pass architecture synthesis flow called BigIntegr, for continuous-flow microfluidic lab-on-a-chip, integrating all the design steps into an “organic whole”, which has never been considered in prior work. With the proposed BigIntegr, the aforementioned design tasks can be synchronized seamlessly and performed in a combined manner, thereby eliminating the gaps between design steps. As a result, biochip architectures with both high efficiency and low cost can be generated without any design adjustments and modifications. Experimental results on multiple benchmarks demonstrate the effectiveness of the proposed automation flow.

An interaction between pharmacological agents can trigger unexpected adverse events. Capturing richer and more comprehensive information about drug-drug interactions (DDIs) is one of the key tasks in public health and drug development. Recently, several knowledge graph (KG) embedding approaches have received increasing attention in the DDI domain due to their capability of projecting drugs and interactions into a low-dimensional feature space for predicting links and classifying triplets. However, existing methods only apply a uniformly random mode to construct negative samples. As a consequence, these samples are often too simplistic to train an effective model. In this paper, we propose a new KG embedding framework by introducing adversarial autoencoders (AAEs) based on Wasserstein distances and Gumbel-Softmax relaxation for DDI tasks. In our framework, the autoencoder is employed to generate high-quality negative samples and the hidden vector of the autoencoder is regarded as a plausible drug candidate. Afterwards, the discriminator learns the embeddings of drugs and interactions based on both positive and negative triplets. Meanwhile, in order to solve vanishing gradient problems on the discrete representation-an inherent flaw in traditional generative models-we utilize the Gumbel-Softmax relaxation and the Wasserstein distance to train the embedding model steadily. We empirically evaluate our method on two tasks: link prediction and DDI classification. The experimental results show that our framework can attain significant improvements and noticeably outperform competitive baselines. Supplementary information: Supplementary data and code are available at https://github.com/dyf0631/AAE_FOR_KG.

Tracking a suspicious car or a person in a city efficiently is crucial in urban safety management. But how can we complete the task with the minimal number of spatiotemporal searches when massive camera records are involved? To this end, this study proposes a strategy named intermediate searching at heuristic moments (IHMs). At each step, we determine which moment is the best one for the search based on a heuristic indicator. Then, at that moment, locations are searched one by one in descending order of predicted appearing probabilities until a search hit is obtained. We iterate this step until we derive the object's current location. Five searching strategies are compared via experiments. Among these strategies, the IHMs strategy is validated as the most efficient. IHMs can save up to 1/3 of the total cost. This result provides evidence that “searching at intermediate moments can save cost”.

Scene understanding in 3-D point clouds requires to annotate points manually at the model training stage. To reduce manual efforts in labeling points, this letter focuses on proposing an efficient method to implement semiautomatic segmentation of 3-D objects in 3-D point clouds. Specifically, to handle point clouds with high point density, supervoxels are treated as basic operating units during the object segmentation procedure. To obtain the valuable boundaries for guiding 3-D object segmentation, we propose to filter meaningless boundaries obtained by a traditional boundary detection method. Once valuable boundaries are obtained, we propose a boundary-aware Markov random field (MRF) model to consider the object-boundary constraint into generating the boundary-preserved segmentation results. Extensive experiments on two data sets show the effectiveness of our proposed framework on segmenting 3-D objects from point cloud scenes.

Siamese tracking methods have become the focus of visual tracking in recent years. Advanced Siamese trackers perform well on certain benchmarks, but there are still some limitations. First, most Siamese trackers adopt the initial frame as a single template, which leads to underfitting and reduces the ability to predict instances. Second, mainstream trackers report a rectangular bounding box as a prediction, resulting in poor accuracy of non-rigid objects. Therefore, we propose the template enhancement and mask generation for Siamese tracking. Given that the essence of Siamese trackers is instance learning, we propose constructing an alternative template explicitly to address the underfitting of the instance space. Moreover, in order to improve the tracking accuracy, we obtain the descriptor aggregation to transform the semantic segmentation outputs for mask prediction. Finally, we propose the SiamEM through the fusion of the above approaches. Comprehensive experiments show that template enhancement and mask generation significantly improve Siamese trackers on benchmarks.

To improve the success probability of a mission execution, scheduled checkpointing is often implemented to save completed portions of the mission task so that a system can resume the mission execution effectively after its restoration whenever the system failure occurs. This paper considers a repairable computing system subject to the scheduled checkpointing. The checkpointing intervals are deterministic, but can be even or uneven. The system repair time is fixed while the system time-to-failure can follow any arbitrary type of distributions. The maximum number of repairs is specified by a certain threshold value. A multi-valued decision diagram (MDD)-based analytical approach is proposed to evaluate the exact success probability of a mission execution for the considered repairable system. The proposed approach enables generating a compact mission MDD model where identical subMDD models can be merged to improve computational efficiency and reduce storage requirement. The MDD model, once being constructed, can be reused for system reliability evaluations using different input parameter values. A benchmark study is presented to show the efficiency of proposed MDD approach. A case study is performed to illustrate the application of the proposed MDD approach to facilitate decision making about proper system design and parameter selection.

Synthesizing high dynamic range (HDR) images from multiple low-dynamic range (LDR) exposures in dynamic scenes is challenging. There are two major problems caused by the large motions of foreground objects. One is the severe misalignment among the LDR images. The other is the missing content due to the over-/under-saturated regions caused by the moving objects, which may not be easily compensated for by the multiple LDR exposures. Thus, it requires the HDR generation model to be able to properly fuse the LDR images and restore the missing details without introducing artifacts. To address these two problems, we propose in this paper a novel GAN-based model, HDR-GAN, for synthesizing HDR images from multi-exposed LDR images. To our best knowledge, this work is the first GAN-based approach for fusing multi-exposed LDR images for HDR reconstruction. By incorporating adversarial learning, our method is able to produce faithful information in the regions with missing content. In addition, we also propose a novel generator network, with a reference-based residual merging block for aligning large object motions in the feature domain, and a deep HDR supervision scheme for eliminating artifacts of the reconstructed HDR images. Experimental results demonstrate that our model achieves state-of-the-art reconstruction performance over the prior HDR methods on diverse scenes.

Recently, 3D deep learning technologies require a large amount of supervised 3D point-cloud data to learn statistical models for various ITS-related tasks, e.g. object classification, object detection, object segmentation, etc. However, manually annotating 3D point-cloud data is time-consuming and labor-intensive. Therefore, this paper aims at co-locating 3D objects from mobile LiDAR point clouds without any help of supervised training data. To realize it, we propose a new framework to implement 3D object co-localization for automatically extracting the objects of the same category from different point-cloud scenes. Specifically, to search and exploit the co-information from objects in different point-cloud scenes, we formulate a 3D object co-localization problem as a maximal subgraph matching problem. During the graph construction procedure, to handle the inconsistent representation of objects in different scenes, we propose a multi-scale clustering method to represent objects by a pyramid structure. In addition, because the maximal subgraph matching problem is NP-hard, we propose a stochastic search algorithm to generate the co-localization results. Extensive experiments on the point-cloud data collected by the Reigl VMX450 mobile LiDAR system demonstrate the promising performance of the proposed framework.

Distance metric learning aims to learn a positive semidefinite matrix such that similar samples are preserved with small distances while dissimilar ones are mapped with big values above a predefined margin. It can facilitate to improve the performance of certain learning tasks. In this article, distance metric learning and clustering are integrated into an unified framework via rank-reduced regression. First, distance metric learning is proved to be consistent with rank-reduced regression, which provides a new perspective to learn structured regularization matrices. Second, orthogonal and non-negative rank-reduced regression problems are addressed individually for clustering, and the corresponding algorithms with proved convergence are proposed. Finally, both distance metric learning and clustering are addressed simultaneously in the problem formulation, which may trigger some new insights for learning an effective clustering oriented low-dimensional embedding. To show the superior performance of the proposed method, we compare it with several state-of-the-art clustering approaches. And, extensive experiments on the test datasets demonstrate the superiority of the proposed method.

Layer assignment, a major step in global routing of integrated circuits, is usually performed to assign segments of nets to multiple layers. Besides the traditional optimization goals such as overflow and via count, interconnect delay plays an important role in determining chip performance and has been attracting much attention in recent years. Accordingly, in this paper, we propose MiniDelay, a timing-aware layer assignment algorithm to minimize delay for advanced technology nodes, taking both wire congestion and coupling effect into account. MiniDelay consists of the following three key techniques: 1) a non-default-rule routing technique is adopted to reduce the delay of timing critical nets, 2) an effective congestion assessment method is proposed to optimize delay of nets and via count simultaneously, and 3) a net scalpel technique is proposed to further reduce the maximum delay of nets, so that the chip performance can be improved in a global manner. Experimental results on multiple benchmarks confirm that the proposed algorithm leads to lower delay and few vias, while achieving the best solution quality among the existing algorithms with the shortest runtime.

Recent advances in resistive synaptic devices have enabled the emergence of brain-inspired smart chips. These chips can execute complex cognitive tasks in digital signal processing precisely and efficiently using an efficient neuromorphic system. The neuromorphic synapses used in such chips, however, are very sensitive to the external environment, thereby weakening their resistance to malicious modifications such as hardware Trojans and backdoors. Accordingly, in this paper, we propose HTcatcher, a security verification technique for hardware threat detection in neuromorphic computing systems, incorporating finite state machine and feature verification simultaneously, which has never been considered in prior work. Furthermore, we propose a pseudo-random matrix verifying technique for memory optimization, which can reduce the memory overhead of the multi-dimensional features in the system significantly. Experimental results confirm that the proposed method can identify the malicious modifications in the system accurately, while reducing the memory usage by 25%-50%.

As the scale of VLSI circuits and fabrication costs increase rapidly, multi-FPGA prototyping systems are widely adopted in industry to make logic verification faster and cheaper. Since routing signals can usually exceed the number of I/O pins in an FPGA, timing division multiplexing (TDM) technique is required to solve this problem. FPGA routing for developing a prototyping system is a big challenge due to the signal delay of TDM. This paper presents MSFRoute, a multi-stage FPGA routing framework for timing division multiplexing technique, to optimize the signal delay and the routability for prototyping systems. In this work, a TDM ratios assignment algorithm with an efficient parallelization method is proposed to optimize inter-FPGA signal delay. Meanwhile, we propose a practical system clock period optimization method to solve critical signal delay problem. Experimental results show that our routing framework reduces TDM ratios by up to 88.3% with an average reduction rate of 41.8%. With the proposed parallelization method, total flow of MSFRoute can get up to 4.38X speedup with a 2.77X speedup on average.

Continuous-flow microfluidic biochips have attracted high research interest over the past years. Inside such a chip, fluid samples of milliliter volumes are efficiently transported between devices (e.g., mixers, etc.) to automatically perform various laboratory procedures in biology and biochemistry. Each transportation task, however, requires an exclusive flow path composed of multiple contiguous microchannels during its execution period. Excess/waste fluids, in the meantime, should be discarded by independent flow paths connected to waste ports. All these paths are etched in a very tiny chip area using multilayer soft lithography and driven by flow ports connecting with external pressure sources, forming a highly integrated chip architecture that dominates the performance of biochips. In this paper, we propose a practical synthesis flow called PathDriver for the design automation of microfluidic biochips, integrating the actual fluid manipulations into both high-level synthesis and physical design, which has never been considered in prior work. Given the protocols of biochemical applications, PathDriver aims to generate highly efficient chip architectures with a flow-path network that enables the manipulation of actual fluid transportation and removal. Additionally, fluid volume management between devices and flow-path minimization are realized for the first time, thus ensuring the correctness of assay outcomes while reducing the complexity of chip architectures. Experimental results on multiple benchmarks demonstrate the effectiveness of the proposed synthesis flow.

Creating stereoscopic 3D media content has wide applications in virtual reality. In this paper, we are interested in a challenging application, casual stereoscopic photography, that allows ordinary users to create a stereoscopic photo using two images captured by a hand-held monocular camera. To handle the geometric constraints and disparity adjustment for casually captured left and right images, we present a coarse-to-fine framework. In the coarse stage, we propose a unified reinforcement learning-based method, in which the produced stereo image is iteratively adjusted and evaluated in the term of visual comfort. In addition, to further enhance the visual comfort of the stereoscopic image produced in the coarse stage, we introduce another independent recurrent network to fine-tune its disparity range. Lastly, we perform comprehensive experiments to evaluate our method and demonstrate the applicability of our model for real images.

The emergence of flow-based microfluidic biochips (FBMBs) has increased the automation level of biochemical procedures, and these lab-on-a-chip devices are now being used for enzyme-linked immunosorbent assay, point-of-care diagnosis, etc. As fabrication technology advances, the feature size of FBMBs keeps shrinking, thereby introducing a series of knotty challenges to the physical design of FBMBs. In particular, timing-sensitive bioassays, such as forensic DNA typing and chromatin immunoprecipitation, require a highly accurate time-control of fluids within a limited completion time. However, existing work does not consider the real-time requirements of these bioassays. In this paper, we formulate the first practical timing-driven flow-channel network construction problem for FBMBs and present a performance-driven placement and routing algorithm for solving this problem. Given the design specifications of a biochip and its biochemistry application, our goal is to construct a high-quality flow-channel network with minimized timing delay and total cost. The experimental results on 14 benchmarks confirm that our algorithm leads to better timing behavior and lower chip cost.

Secure search over encrypted remote data is crucial in cloud computing to guarantee the data privacy and usability. To prevent unauthorized data usage, fine-grained access control is necessary in multi-user system. However, authorized user may intentionally leak the secret key for financial benefit. Thus, tracing and revoking the malicious user who abuses secret key needs to be solved imminently. In this paper, we propose an escrow free traceable attribute based multiple keywords subset search system with verifiable outsourced decryption (EF-TAMKS-VOD). The key escrow free mechanism could effectively prevent the key generation centre (KGC) from unscrupulously searching and decrypting all encrypted files of users. Also, the decryption process only requires ultra lightweight computation, which is a desirable feature for energy-limited devices. In addition, efficient user revocation is enabled after the malicious user is figured out. Moreover, the proposed system is able to support flexible number of attributes rather than polynomial bounded. Flexible multiple keyword subset search pattern is realized, and the change of the query keywords order does not affect the search result. Security analysis indicates that EF-TAMKS-VOD is provably secure. Efficiency analysis and experimental results show that EF-TAMKS-VOD improves the efficiency and greatly reduces the computation overhead of users' terminals.

Cloud computing provides flexible data management and ubiquitous data access. However, the storage service provided by cloud server is not fully trusted by customers. Searchable encryption could simultaneously provide the functions of confidentiality protection and privacy-preserving data retrieval, which is a vital tool for secure storage. In this paper, we propose an efficient large universe regular language searchable encryption scheme for the cloud, which is privacy-preserving and secure against the off-line keyword guessing attack (KGA). A notable highlight of the proposal over other existing schemes is that it supports the regular language encryption and deterministic finite automata (DFA) based data retrieval. The large universe construction ensures the extendability of the system, in which the symbol set does not need to be predefined. Multiple users are supported in the system, and the user could generate a DFA token using his own private key without interacting with the key generation center. Furthermore, the concrete scheme is efficient and formally proved secure in standard model. Extensive comparison and simulation show that this scheme has function and performance superior than other schemes.

How to improve the performance of single failure recovery has been an active research topic because of its prevalence in large-scale storage systems. We argue that when erasure coding is deployed in a clustered file system (CFS), existing single failure recovery designs are limited in different aspects: neglecting the bandwidth diversity property in a CFS architecture, targeting specific erasure code constructions, and no special treatment on load balancing during recovery. In this paper, we propose CAR, a cross-rack-aware recovery algorithm that is designed to improve the performance of single failure recovery of a CFS that employs Reed-Solomon codes for general fault tolerance. For each stripe, CAR finds a recovery solution that retrieves data from the minimum number of racks. It also reduces the amount of cross-rack repair traffic by performing intra-rack data aggregation prior to cross-rack transmission. Furthermore, by considering multi-stripe recovery, CAR balances the amount of cross-rack repair traffic across multiple racks. Evaluation results show that CAR can effectively reduce the amount of cross-rack repair traffic and the resulting recovery time.

Mobile devices usually mount a depth sensor to resolve ill-posed problems, like salient object detection on cluttered background. The main barrier of exploring RGBD data is to handle the information from two different modalities. To cope with this problem, in this paper, we propose a boundary-aware cross-modal fusion network for RGBD salient object detection. In particular, to enhance the fusion of color and depth features, we present a cross-modal feature sampling module to balance the contribution of the RGB and depth features based on the statistics of their channel values. In addition, in our multi-scale dense fusion network architecture, we not only incorporate edge-sensitive losses to preserve the boundary of the detected salient region, but also refine its structure by merging the estimated saliency maps of different scales. We accomplish the multi-scale saliency map merging using two alternative methods which produce refined saliency maps via per-pixel weighted combination and an encoder-decoder network. Extensive experimental evaluations demonstrate that our proposed framework can achieve the state-of-the-art performance on several public RGBD-based datasets.

Recent reports show that projection neural networks with a low-dimensional state space can enhance computation speed obviously. This paper proposes two projection neural networks with reduced model dimension and complexity (RDPNNs) for solving nonlinear programming (NP) problems. Compared with existing projection neural networks for solving NP, the proposed two RDPNNs have a low-dimensional state space and low model complexity. Under the condition that the Hessian matrix of the associated Lagrangian function is positive semi-definite and positive definite at each Karush-Kuhn-Tucker point, the proposed two RDPNNs are proven to be globally stable in the sense of Lyapunov and converge globally to a point satisfying the reduced optimality condition of NP. Therefore, the proposed two RDPNNs are theoretically guaranteed to solve convex NP problems and a class of nonconvex NP problems. Computed results show that the proposed two RDPNNs have a faster computation speed than the existing projection neural networks for solving NP problems.

In the cloud computing environment with massive information services and decision-making resources, the accuracy and reliability of information are more important than previous single closed systems. Therefore, ensuring the reliability of information and the stable operation of the system are the core problems in the research fields such as the Internet Plus and the Internet of Things. The connectivity and diagnosability are two important measures for the fault tolerance of multiprocessor systems. The g -good-neighbor conditional connectivity ( Rg -connectivity) is the minimum number of nodes that make the graph disconnected, and each node has at least g neighbors in every remaining component. The g -good-neighbor conditional diagnosability ( g -GNCD) is the maximum number of faulty processors that has been correctly identified in a system, and any fault-free processor has no less than g fault-free neighbors. Exchanged X -cubes are a class of irregular networks, obtained by deleting links from hypercubes and some variant networks of hypercubes ( X -cubes). They not only combine the advantages of X -cubes but also reduce the interconnection complexity. Exchanged X -cubes classify its nodes into two different classes clusters with a unique connecting rule. In this paper, we propose the generalized exchanged X -cubes framework so that architecture can be constructed by different connecting rules. Furthermore, we study the Rg -connectivity and g -GNCD of generalized exchanged X -cubes under the PMC and MM ∗ models. As applications, the Rg -connectivity and g -GNCD of generalized exchanged hypercubes, dual-cube-like networks, generalized exchanged crossed cubes, and locally generalized exchanged twisted cubes are determined, respectively.

Task allocation is a significant issue in crowd sensing, which trades off the data quality and sensing cost. Existing task allocation works are based on the assumption that there is plenty of users available in the candidate pool. However, for some specific applications, there may be only a few candidate users, resulting in the poor completion of tasks. To tackle this problem, in this paper, we investigate the task allocation problem with the assistance of social networks. We select a subset of users; if a user can not complete the task, he can propagate the task information to his friends. The object of this problem is to maximize the expected number of completed tasks. We prove that the task allocation problem is an NP-hard and submodular problem and then propose a native greedy selection (NGS) algorithm, which selects the user with maximum margin gain in each round. To improve the efficiency of the NGS algorithm, we further propose a fast greedy selection algorithm (FGS), which selects the user who can actually complete the maximum number of tasks. Experimental results show that although FGS gets slightly worse results in terms of the expected number of completed tasks, it can greatly reduce the running time of seed selection.

Recent advances in continuous-flow microfluidics have enabled highly integrated lab-on-a-chip biochips. These chips can execute complex biochemical applications precisely and efficiently within a tiny area, but they require a large number of control ports and the corresponding control logic to generate required pressure patterns for flow control, which, consequently, offset their advantages and prevent their wide adoption. In this paper, we propose the first synthesis flow called MiniControl, for continuous-flow microfluidic biochips (CFMBs) under strict constraints for control ports, incorporating high-level synthesis and physical design simultaneously, which has never been considered in previous work. With the maximum number of allowed control ports specified in advance, this synthesis flow generates a biochip architecture with high execution efficiency. Moreover, the overall cost of a CFMB can be reduced and the tradeoff between control logic and execution efficiency of biochemical applications can be evaluated for the first time. Experimental results demonstrate that MiniControl leads to high execution efficiency and low overall platform cost, while satisfying the given control port constraint strictly.

Flow-based microfluidic biochips (FBMBs) have attracted much attention over the past decade. On such a micrometer-scale platform, various biochemical applications, also called bioas-says, can be processed concurrently and automatically. To improve execution efficiency and reduce fabrication cost, a distributed channel-storage architecture (DCSA) can be implemented on this platform, where fluid samples can be cached temporarily in flow channels close to components. Although DCSA can improve the execution efficiency of FBMBs significantly, it requires a careful arrangement of fluid samples to enable the channels to fulfill the dual functions of transportation and caching. In this paper, we formulate the first flow-layer physical design problem considering DCSA, and propose a top-down synthesis algorithm to generate efficient solutions considering execution efficiency, washing, and resource usage simultaneously. Experimental results demonstrate that the proposed algorithm leads to a shorter execution time, less flow-channel length, and a higher efficiency of on-chip resource utilization for biochemical applications compared with a direct approach to incorporate distributed storage into existing frameworks.

Traffic estimation is a popular approach to acquire traffic conditions in urban areas. At present, using the traffic data to realize the low-cost traffic estimation has already been widely favored. Although those data include various sensitive element, people ignore the harm caused by information leakage while the data are used. Additionally, the transmission of vehicle data also requires a very large communication bandwidth. To address those problems, we focus on the privacy-preserving vehicle data and reducing the amount of ciphertext data to achieve a city-scale traffic estimation. Meanwhile, we present a novel framework that integrates compressive sensing (CS) technology into privacy- preserving vehicle data. Furthermore, outsourcing vehicle data to the cloud is adopted to overcome the limitations of the in-vehicle sensors. In particular, we present a feasible computational scheme for traffic estimation, further improve the capacity of privacy- preserving and decrease system energy consumption. Finally, we validate the effectiveness of the scheme proposed through the real-world dataset.

This paper presents a routability-driven track assignment algorithm (RDTA) to efficiently estimate routability. Routability has become a very challenging issue in modern IC design and it can be effectively estimated by routing congestion. Track assignment is a stage towards bridging the gap between global routing and detailed routing. And track assignment can also analyze routing congestion more accurate than other routing stages like global routing. Some works have used track assignment to estimate routability. In this work, wire segments extracted from a global routing solution are assigned to proper tracks considering local nets, via locations and pin access. The overlap between wire segments extracted from a global routing solution can be effectively reduced by the algorithm so that the solution of RDTA can effectively estimate the routability.

In the field of object detection, the research on the problem of detecting small face is the most extensive, but when there are objects with obvious scale differences in the image, the detection performance is not obvious, which is due to the scale invariance properties of the deep convolutional neural networks. Although in recent years, there have been some methods proposed to solve this problem such as FPN and SNIP, which is based on feature pyramid. However, they have not fundamentally solved the problem. A regional cascade multi‐scale detection method has been proposed. First, a global detector and several local detectors have been trained, respectively. The global detector is trained by the original training set, while the local detector is trained by the sub‐training set generated by the original training set. Second, the global detector can detect object roughly and the local detectors can produce more detailed results that improve the performance of global detector. Finally, to integrate the detection results of global detector and local detectors as the output, non‐maximum suppression methods are used. The method can be carried in any depth model of object detection, has good scalability, and is more suitable for dense face detection.

We propose an overlapping community discovery algorithm that combines node influence and [Formula: see text]-connected neighbors for effectively detecting the overlapping community structure of complex networks. On the basis of the node influence and [Formula: see text]-connected neighbors, our method accurately detects the core node community and uses the improved similarity between the node and community to expand the core node community. Accordingly, the discovery and optimization of network overlapping communities are realized. Experiments on artificial and real-world networks demonstrate that our method significantly and consistently outperforms other comparison methods.

Object classification model used in point clouds requires to be retrained when applying on heterogeneous point clouds that are collected from different kinds of laser scanning systems. The model training procedure needs supervised information from the corresponding laser scanning systems. However, the acquisition of supervised information is labor-intensive and time-consuming. This letter proposes a new framework to exploit objects from point clouds with supervised information (source domain) to directly classify objects from heterogeneous point clouds with no supervised information (target domain). More specifically, to alleviate occlusions and point density variations, intraclass variations in object classification, the proposed framework integrates a bag-of-words model to effectively describe 3-D objects of point clouds. To alleviate the difference of point clouds collected from various devices, a joint distribution adaption model is exploited to build an effective feature transformation to accomplish the adaption in the source and target domains. The proposed framework is validated on data sets, which contain three kinds of point clouds. Extensive experiments show the effectiveness of the proposed framework on classifying 3-D objects in heterogeneous point clouds.

High-dimensional features are extensively accessible in machine learning and computer vision areas. How to learn an efficient feature representation for specific learning tasks is invariably a crucial issue. Due to the absence of class label information, unsupervised feature representation is exceedingly challenging. In the last decade, deep learning has captured growing attention from researchers in a broad range of areas. Most of the deep learning methods are supervised, which is required to be fed with a large amount of accurately labeled data points. Nevertheless, acquiring sufficient accurately labeled data is unaffordable in numerous real-world applications, which is suggestive of the needs of unsupervised learning. Toward this end, quite a few unsupervised feature representation approaches based on deep learning have been proposed in recent years. In this paper, we attempt to provide a comprehensive overview of unsupervised deep learning methods and compare their performances in text categorization. Our survey starts with the autoencoder and its representative variants, including sparse autoencoder, stacked autoencoder, contractive autoencoder, denoising autoencoder, variational autoencoder, graph autoencoder, convolutional autoencoder, adversarial autoencoder, and residual autoencoder. Aside from autoencoders, deconvolutional networks, restricted Boltzmann machines, and deep belief nets are introduced. Then, the reviewed unsupervised feature representation methods are compared in terms of text clustering. Extensive experiments in eight publicly available data sets of text documents are conducted to provide a fair test bed for the compared methods.

In intelligent transportation systems, there are many tasks that rely on the detection of road congestion, such as traffic signal scheduling and traffic accident detection. As traditional methods for traffic congestion detection are difficult to use, expensive, and may cause damage to the road surface, this paper presents a method for road congestion detection that is based on multidimensional visual features and a convolutional neural network (CNN). This method first detects the density of foreground objects by using a gray-level co-occurrence matrix; second, the speed of moving objects is detected by using the Lucas-Kanade optical flow with pyramid implementation. Third, a Gaussian mixture model is used to model the background, and the CNN is then used to accurately detect the final foreground from the candidate foregrounds. Finally, the proposed method performs road congestion detection in terms of a multidimensional feature space, including traffic density, traffic velocity, road occupancy, and traffic flow. Furthermore, we propose an information entropy method using a histogram of optical flow to enhance the accuracy and reliability of road congestion detection. Simulation results via quantitative and qualitative assessment indicate that the proposed method is able to significantly outperform the state-of-the-art road-traffic congestion detection methods due to the fusion of multidimensional features using the CNN.

Nowadays, high-bandwidth networks are more easily accessible than ever before. However, existing distributed graph-processing frameworks, such as GPS, fail to efficiently utilize the additional bandwidth capacity in these networks for higher performance, due to their inefficient computation and communication models, leading to very long waiting times experienced by users for the graph-computing results. The root cause lies in the fact that the computation and communication models of these frameworks generate, send and receive messages so slowly that only a small fraction of the available network bandwidth is utilized. In this paper, we propose a high-performance distributed graph-processing framework, called BlitzG, to address this problem. This framework fully exploits the available network bandwidth capacity for fast graph processing. Our approach aims at significant reduction in (i) the computation workload of each vertex for fast message generation by using a new slimmed-down vertex-centric computation model and (ii) the average message overhead for fast message delivery by designing a light-weight message-centric communication model. Evaluation on a 40Gbps Ethernet, driven by real-world graph datasets, shows that BlitzG outperforms GPS by up to 27x with an average of 20.7x.

Erasure coding has been extensively employed for data availability protection in production storage systems by maintaining a low degree of data redundancy. However, how to mitigate the parity update overhead of partial stripe writes in erasure-coded storage systems is still a critical concern. In this paper, we study this problem from two new perspectives: data correlation and stripe organization. We propose CASO, a correlation-aware stripe organization algorithm, which captures data correlation of a data access stream and uses the data correlation characteristics for stripe organization. It packs correlated data into a small number of stripes to reduce the incurred I/Os in partial stripe writes, and further organizes uncorrelated data into stripes to leverage the spatial locality in later access. We implement CASO over Reed-Solomon codes and Azure's Local Reconstruction Codes, and show via extensive tracedriven evaluation that CASO reduces up to 29.8 percent of parity updates and reduces the write time by up to 46.7 percent.

The goal of an image denoising algorithm is to preserve the details of clean images while reducing the noise in noisy images. Some existing image denoising algorithms preserve the details by using external information. However, external information needs to be obtained from external images or regions similar to the noisy images or regions. In this letter, we propose a region-aware image denoising algorithm (RAID) by exploring parameter preference. The proposed RAID algorithm is based on the observation that different regions of noisy images prefer denoised results that differ due to being obtained with different denoising parameters. The RAID algorithm, first, measures the extent of preferences of denoising parameters for different image regions. Then, it combines the denoised results obtained by using the various denoising parameters according to the extent of preferences determined in the previous step to get the final denoised image. Experimental results show that the proposed RAID algorithm can be combined with some existing image denoising algorithms to improve their denoising performance. Our denoised results are better at preserving the details while reducing the noise than existing algorithms which use the same parameter for the whole image.

Color correction plays an important role in the image processing field. But substantial research on the assessment of color correction is still insufficient. In this paper, we present an image quality assessment metric for color correction. It assesses the color consistency between the reference and target/result images of color correction according to their color contrast similarity and color value difference. Both the average difference and difference span are considered during the assessment. To compensate for the scene difference between the reference and target/result images of color correction, we propose to use an image registration algorithm to build their matching relationship, upon which a matching image is built. The matching image has the same scene as the target image and the same color feature as the reference image, and thus the matching image is regarded as the real reference image of our color correction assessment. Furthermore, we combine a confidence map of the matching image and a saliency map of the target/result image as a weighting map for assessment, which helps to improve the consistency between the objective and subjective assessment results. The experimental results show that our color correction assessment metric has better correlation, accuracy, and monotonicity with users' subjective scores than 19 state-of-the-art metrics.

With the development of cloud computing, the coexistence of multiple cloud service providers appears in the current cloud market. Due to heterogeneous instance types, different bandwidths and various price models among multiple clouds, it is a challenging issue to schedule a deadline-constrained scientific workflow across multiple clouds. Existing research for workflow scheduling are mostly in the traditional distributed computing environment (such as grid), and only a few primal contributions are made in the cloud environment. This paper proposes a scheduling strategy for a deadline-constrained scientific workflow across multiple clouds. In order to minimize the execution cost of the workflow while meeting its deadline, our strategy utilizes the discrete particle swarm optimization technique, and adopts randomly two-point crossover operator and randomly single point mutation operator of the genetic algorithm. Besides, the strategy optimizes the performance for both computation cost and data transfer cost across multiple clouds. Our strategy is evaluated through well-known workflows, and experimental results show that it performs better than other state-of-the-art strategies.

Modern storage systems adopt erasure coding to maintain fault tolerance with low storage redundancy. However, how to improve the performance of degraded reads in erasure-coded storage has been a critical issue. We revisit this problem from two different perspectives that are neglected by existing studies: data placement and encoding rules. To this end, we propose encoding-aware data placement (EDP), which mitigates the number of I/Os in degraded reads during a single failure for general XOR-based erasure codes. EDP carefully selects appropriate parity units to be generated by sequential data based on the encoding rules and establishes their generation orders. We further refine the data placement for optimizing the degraded reads to any two sequential data units. Trace-driven evaluation results show that EDP significantly reduces I/Os in degraded reads and hence shortens the read time.

The recent advances of compressive sensing (CS) have witnessed a great potential of efficient compressive data gathering (CDG) in wireless sensor network systems (WSNSs). However, most existing work on CDG mainly focuses on multihop relaying strategies to improve the performance of data gathering. In this paper, we propose a mobile CDG scheme including a random walk-based algorithm and a kernel-based method for sparsifying sensory data from irregular deployments. The proposed scheme allows a mobile collector to harvest data by sequentially visiting a number of nodes along a random path. More importantly, toward building the gap between CS and machine learning theories, we explore a theoretical foundation for understanding the feasibility of the proposed scheme. We prove that the CS matrices, constructed from the proposed random walk algorithm combined with a kernel-based sparsity basis, satisfy the restricted isometry property. Particularly, we also show that m = O(klog(n/k)) measurements collected by a mobile collector are sufficient to recover a k-sparse signal and t = O(klog(n/k)) steps are required to collect these measurements in a network with n nodes. Finally, we also present extensive numerical results to validate the effectiveness of the proposed scheme by evaluating the performance in terms of energy consumption and the impact of packet losses. The numerical results demonstrate that the proposed scheme is able to not only significantly reduce communication cost but also combat unreliable wireless links under various packet losses compared to the stateof-the-art schemes, which provides an efficient alternative to data relaying approaches for CDG in WSNS.

Task allocation is a key problem in Mobile Crowd Sensing (MCS). Prior works have mainly assumed that participants can complete tasks once they arrive at the location of tasks. However, this assumption may lead to poor reliability in sensing data because the heterogeneity among participants is disregarded. In this study, we investigate a multitask allocation problem that considers the heterogeneity of participants (i.e., different participants carry various devices and accomplish different tasks). A greedy discrete particle swarm optimization with genetic algorithm operation is proposed in this study to address the abovementioned problem. This study is aimed at maximizing the number of completed tasks while satisfying certain constraints. Simulations over a real‐life mobile dataset verify that the proposed algorithm outperforms baseline methods under different settings.

Erasure coding has been extensively employed for data availability protection in production storage systems by maintaining a low degree of data redundancy. However, how to mitigate the parity update overhead of partial stripe writes in erasure-coded storage systems is still a critical concern. In this paper, we reconsider this problem from two new perspectives: data correlation and stripe organization, and propose CASO, a correlation-aware stripe organization algorithm. CASO captures data correlation of a data access stream. It packs correlated data into a small number of stripes to reduce the incurred I/Os in partial stripe writes, and further organizes uncorrelated data into stripes to leverage the spatial locality in later accesses. By differentiating correlated and uncorrelated data in stripe organization, we show via extensive trace-driven evaluation that CASO reduces up to 25.1% of parity updates and accelerates the write speed by up to 28.4%.

One of the challenging issues in high-resolution remote sensing images is classifying land-use scenes with high quality and accuracy. An effective feature extractor and classifier can boost classification accuracy in scene classification. This letter proposes a deep-learning-based classification method, which combines convolutional neural networks (CNNs) and extreme learning machine (ELM) to improve classification performance. A pretrained CNN is initially used to learn deep and robust features. However, the generalization ability is finite and suboptimal, because the traditional CNN adopts fully connected layers as classifier. We use an ELM classifier with the CNN-learned features instead of the fully connected layers of CNN to obtain excellent results. The effectiveness of the proposed method is tested on the UC-Merced data set that has 2100 remotely sensed land-use-scene images with 21 categories. Experimental results show that the proposed CNN-ELM classification method achieves satisfactory results.

Data fusion is used to integrate features from heterogeneous data sources into a consistent and accurate representation for certain learning tasks. As an effective technique for data fusion, unsupervised multimodal feature representation aims to learn discriminative features, indicating the improvement of classification and clustering performance of learning algorithms. However, it is a challenging issue since varying modality favors different structural learning. In this paper, we propose an efficient feature learning method to represent multimodal images as a sparse multigraph structure embedding problem. First, an effective algorithm is proposed to learn a sparse multigraph construction from multimodal data, where each modality corresponds to one regularized graph structure. Second, incorporating the learned multigraph structure, the feature learning problem for multimodal images is formulated as a form of matrix factorization. An efficient corresponding algorithm is developed to optimize the problem and its convergence is also proved. Finally, the proposed method is compared with several state-of-the-art single-modal and multimodal feature learning techniques in eight publicly available face image datasets. Comprehensive experimental results demonstrate that the proposed method outperforms the existing ones in terms of clustering performance for all tested datasets.

Computation offloading is a promising way to improve the performance as well as reducing the battery power consumption of a mobile application by executing some parts of the application on a remote server. Recent researches on mobile cloud computing mainly focus on the code partitioning and offloading techniques, assuming that mobile codes are offloaded to a prepared server. However, the context of a mobile device, such as locations and network conditions, changes continuously as it moves throughout the day, and there are multiple options of cloud resources, including remote cloud computing services and nearby cloudlets. In order to offload computation to the cloud resource with powerful processors as well as fast network connection, it needs to dynamically select the appropriate cloud resource and then offload mobile codes to it at runtime, according to the context of the mobile device and possible cloud resources. In this paper, we present a framework for context-aware computation offloading. First, a design pattern is proposed to enable an application to be computation offloaded on-demand. Second, an estimation model is presented to automatically select the cloud resource for computation offloading. Runtime data about computation tasks, contexts of the mobile device and possible cloud resources is collected and modeled at client side, in order to make an optimal offloading decision. A thorough evaluation on two real-world applications is proposed, and the results show that our approach can help reduce execution time by 6%-96% and power consumption by 60%-96% for computation-intensive applications.

Erasure coding has been increasingly used by distributed storage systems to maintain fault tolerance with low storage redundancy. However, how to enhance the performance of degraded reads in erasure-coded storage has been a critical issue. We revisit this problem from two different perspectives that are neglected by existing studies: data placement and encoding rules. To this end, we propose an encoding-aware data placement (EDP) approach that aims to reduce the number of I/Os in degraded reads during a single failure for general XOR-based erasure codes. EDP carefully places sequential data based on the encoding rules of the given erasure code. Trace-driven evaluation results show that compared to two baseline data placement methods, EDP reduces up to 37.4% of read data on the most loaded disk and shortens up to 15.4% of read time.

Summary The tremendous parallel computing ability of cloud computing encourages investigators to research its drawbacks and advantages on processing large‐scale scientific applications such as workflows. The current cloud market is composed of numerous diverse public clouds and a local private cloud, and workflow scheduling is one of the biggest challenges on hybrid clouds due to the highly fragmented cloud market with respect to service provisions, pricing models, and bandwidths. In this paper, we propose an online‐scheduling strategy for continuous submitted scientific workflows on hybrid clouds, which aims to complete the deadline‐constrained applications as more as possible at a lower price. Firstly, a hierarchical iterative application partition (HIAP) algorithm is proposed to partition the application into a set of dependent tasks. Moreover, many online‐scheduling algorithms cooperated with HIAP are presented to finish the workflows with a low average payment. Our strategy takes into account the basic characteristics on hybrid clouds such as bandwidth constraints, data transfer cost and computational cost. Various well‐known workflows are used for evaluating the multiple scheduling algorithms and the results show that the MLF_ID approach can achieve a promising performance. Copyright © 2015 John Wiley & Sons, Ltd.

Summary Effective user interest prediction is significant for service providers in a set of application scenarios such as user behavior analysis and resource recommendation. However, existing approaches are either incomplete or proprietary. In this paper, user interest prediction based on the Markov chain modeling on clustered users is proposed with the following procedure: collect dataset from 4613 users and more than 16 million messages from Sina Weibo; obtain each user's interest eigenvalue sequence and establish single‐Markov chain model; and implement user clustering algorithm for the multi‐Markov chain construction in order to divide users into a set of predefined interest categories. The proposed solution is capable of predicting both long‐term and short‐term user interests based on a suitable selection of the initial state distribution, λ. The proposed solution also proves that short‐term interests are consistent with long‐term interests if the influences of social or user‐related events that cause interruptions (e.g., earthquake and birthday) are not considered. Furthermore, experiments show that the proposed solution is feasible and efficient and can achieve a higher accuracy of prediction than that of the other approaches such as Support Vector Machine (SVM) and K‐means. Copyright © 2015 John Wiley & Sons, Ltd.

The rapid development of the latest distributed computing paradigm, i.e., cloud computing, generates a highly fragmented cloud market composed of numerous cloud providers and offers tremendous parallel computing ability to handle big data problems. One of the biggest challenges in multiclouds is efficient workflow scheduling. Although the workflow scheduling problem has been studied extensively, there are still very few primal works tailored for multicloud environments. Moreover, the existing research works either fail to satisfy the quality of service (QoS) requirements, or do not consider some fundamental features of cloud computing such as heterogeneity and elasticity of computing resources. In this paper, a scheduling algorithm, which is called multiclouds partial critical paths with pretreatment (MCPCPP), for big data workflows in multiclouds is presented. This algorithm incorporates the concept of partial critical paths, and aims to minimize the execution cost of workflow while satisfying the defined deadline constraint. Our approach takes into consideration the essential characteristics of multiclouds such as the charge per time interval, various instance types from different cloud providers, as well as homogeneous intrabandwidth vs. heterogeneous interbandwidth. Various types of workflows are used for evaluation purpose and our experimental results show that the MCPCPP is promising.

With the sharp increase of very large-scale integrated (VLSI) circuit density, we are faced with many knotty issues. Particularly in the routing phase of VLSI physical design, the interconnection effects directly relate to the final performance of circuits. However, the optimization capability of traditional rectilinear architecture is limited; thus, both academia and industry have been devoted to nonrectilinear architecture in recent years, especially octilinear architecture, which is the most promising because it can greatly improve the performance of modern chips. In this article, we design FH-OAOS, an obstacle-avoiding algorithm in octilinear architecture, by constructing an obstacle-avoiding the octilinear Steiner minimal tree (OAOSMT). Our approach first constructs an obstacle-free Euclidean minimal spanning tree (OFEMST) on the given pins based on Delaunay triangulation (DT). Then, two lookup tables about OFEMST’s edge are generated, which can be seen as the information center of FH-OAOS and can provide information support for algorithm operation. Next, an efficient obstacle-avoiding strategy is proposed to convert the OFEMST into an obstacle-avoiding octilinear Steiner tree (OAOST). Finally, the generated OAOST is refined to construct the final OAOSMT by applying three effective strategies. Experimental results on various benchmarks show that FH-OAOS achieves 66.39 times speedup on average, while the average wirelength of the final OAOSMT is only 0.36% larger than the best existing solution.

Cloud management becomes increasingly complex and brings high costs, especially with the advent of hybrid cloud. In a hybrid cloud, numerous resources like Virtual Machines (VMs) and Physical Machines in different clouds have to be managed together to make the whole hybrid cloud work cost-effectively. For controlling the management cost, in particular the manual management cost, many programs have been developed to take over manual management tasks or reduce their complexity and difficulty. These programs are usually hard-coded by languages like Java and C++, which bring enough capability and flexibility but also cause high programming effort and cost. As the architecture-based runtime model is causally connected with the corresponding running system automatically, constructing a hybrid cloud management system based on the architecture-based runtime models of clouds can benefit from the model-specific natures, and thus reduce the development workload. This paper proposes a runtime architecture based approach to developing the management programs in a simple but powerful enough manner. First of all, the manageability (such as APIs, configuration files and scripts) of different kinds of clouds, is abstracted as a runtime architecture based model of cloud software architecture, which can automatically and immediately propagate any observable runtime changes of the target platforms to the corresponding architecture models, and vice versa. Second, we provide a unified model of cloud software architecture, according to the domain knowledge of current cloud platforms, such as Cloud Stack, Open Stack and Eucalyptus. Third, the synchronization between the unified model and cloud runtime models is ensured through model transformation, thus, all the management tasks of the hybrid cloud, could be carried out through executing programs on the unified model, which decreases the complexity of use and management. The experiment on a real-world hybrid cloud demonstrates the feasibility, effectiveness and benefits of the new approach to managing hybrid clouds.

Saliency detection has attracted considerable attention, and numerous approaches aimed at locating meaningful regions in images have been presented. Nevertheless, accurate saliency detection algorithms remain in urgent demand. Many algorithms work well when dealing with simple images, but work poorly with complex images that contain small‐scale and high‐contrast structures. Moreover, most existing local and global regional saliency detection methods measure image saliency through region contrast. Such measurement is achieved by directly computing the difference between non‐adjacent regions. In this study, the authors introduce a new perspective for evaluating region contrast. We propose a novel multi‐scale saliency region detection method by optimising the shortest path of two non‐adjacent regions in the colour space and by measuring the region contrast from different scales. The final saliency maps indicate that the proposed method can work well with images containing small patches, but with high contrast. The proposed approach can also make the foreground significantly more uniform. Experimental results on three public benchmark datasets show that the proposed method achieves better precision–recall curve than some state‐of‐the‐art methods.

Abstract Task allocation is an important issue in wireless sensor networks (WSNs), and the existing traditional solutions to this problem in high‐performance computing cannot be directly implemented in WSNs because of limitations such as resource availability and shared communication medium. In this paper, we address the task allocation problem for a heterogeneous WSN, and a trust dynamic task allocation algorithm is proposed. Firstly, to ensure the nodes in the same coalition are mutually closer in distance, a discrete particle swarm optimization (PSO) is designed to generate a structure of the parallel coalitions. Secondly, in order to minimize the execution time of the tasks, save the energy cost of the nodes and balance the load of the network, we design task strategies and payoff functions by invoking the game theory in WSNs and propose a PSO with the redesigned fitness function to find the Nash equilibrium point for the purpose of improving the effectiveness of scheduling and the reliability of the network. In this step, the sink node will play the role of trust manager, and it will allocate tasks based on the Nash equilibrium point, which is a trust solution to make sure all tasks can be finished. Finally, the extensive experiments are conducted to compare our algorithm with two other algorithms. The experimental results show the feasibility and effectiveness of our algorithm, which can obtain a good balance between local solution and global exploration and achieve superior energy efficiency and network reliability within a short period. Copyright © 2014 John Wiley & Sons, Ltd.

As the basic model for very large scale integration routing, the Steiner minimal tree (SMT) can be used in various practical problems, such as wire length optimization, congestion, and time delay estimation. In this paper, an effective algorithm based on particle swarm optimization is presented to construct a multilayer obstacle-avoiding X-architecture SMT (ML-OAXSMT). First, a pretreatment strategy is presented to reduce the total number of judgments for the routing conditions around obstacles and vias. Second, an edge transformation strategy is employed to make the particles have the ability to bypass the obstacles while the union-find partition is used to prevent invalid solutions. Third, according to the feature of ML-OAXSMT problem, we design an edge-vertex encoding strategy, which has the advantage of simple and effective. Moreover, a penalty mechanism is proposed to help the particle bypass the obstacles, and reduce the generation of via at the same time. Experimental results show that our algorithm from a global perspective of multilayer structure can achieve the best solution quality among the existing algorithms. Finally, to our best knowledge, we redefine the edge cost and then construct the obstacle-avoiding preferred direction X-architecture Steiner tree, which is the first work to address this problem and can offer the theory supports for chip design based on non-Manhattan architecture.

Obstacle-avoiding Steiner minimal tree (OASMT) construction has become a focus problem in the physical design of modern very large-scale integration (VLSI) chips. In this article, an effective algorithm is presented to construct an OASMT based on X-architecturex for a given set of pins and obstacles. First, a kind of special particle swarm optimization (PSO) algorithm is proposed that successfully combines the classic genetic algorithm (GA), and greatly improves its own search capability. Second, a pretreatment strategy is put forward to deal with obstacles and pins, which can provide a fast information inquiry for the whole algorithm by generating a precomputed lookup table. Third, we present an efficient adjustment method, which enables particles to avoid all the obstacles by introducing some corner points of obstacles. Finally, an excellent refinement method is discussed to further enhance the quality of the final routing tree, which can improve the quality of the solution by 7.93% on average. To our best knowledge, this is the first time to specially solve the single-layer obstacle-avoiding problem in X-architecture. Experimental results show that the proposed algorithm can further shorten wirelength in the presence of obstacles. And it achieves the best solution quality in a reasonable runtime among the existing algorithms.

One of challenging issues for task allocation problem in wireless sensor networks (WSNs) is distributing sensing tasks rationally among sensor nodes to reduce overall power consumption and ensure these tasks finished before deadlines. In this paper, we propose a soft real-time fault-tolerant task allocation algorithm (FTAOA) for WSNs in using primary/backup (P/B) technique to support fault tolerance mechanism. In the proposed algorithm, the construction process of discrete particle swarm optimization (DPSO) is achieved through adopting a binary matrix encoding form, minimizing tasks execution time, saving node energy cost, balancing network load, and defining a fitness function for improving scheduling effectiveness and system reliability. Furthermore, FTAOA employs passive backup copies overlapping technology and is capable to determinate the mode of backup copies adaptively through scheduling primary copies as early as possible and backup copies as late as possible. To improve resource utilization, we allocate tasks to the nodes with high performance in terms of load, energy consumption, and failure ratio. Analysis and simulation results show the feasibility and effectiveness of FTAOA. FTAOA can strike a good balance between local solution and global exploration and achieve a satisfactory result within a short period of time.

Cloud Computing is evolving as a key computing paradigm for sharing resources. One type of Cloud, which provides platform resources including all the elements of application runtime environment, is regarded as PaaS Cloud. The management of PaaS Cloud is a complex task, up to the point, where manual operation is hard to be cost effective. As the application runtime environment is supported by a set of dynamically composed, distributed elements. What is more, in order to achieve a management target, multiple operations have to be applied over the distributed and heterogeneous elements of PaaS Cloud. To improve the management of PaaS Cloud, this paper proposes to support the configuration and deployment of application runtime environment in PaaS Cloud with an autonomous engine. The automation is enabled by the definition of a domain-specific information model, which captures all the related information with the same abstractions, describing the application runtime environment, PaaS Cloud infrastructure and management targets. On top of that, a technique based on Satisfiability is described, which automatically analyses the state of the managed objects and plans required operations for maintaining it. The result from a case study is provided to validate the feasibility of this approach.

With the wide adoption of cloud computing, the scientific applications are migrated to cloud for execution. The complex structure of scientific applications bring challenges to optimization scheduling scientific applications across multiple heterogeneous clouds. In this paper, the directed acyclic graphs (DAGs) are adopted to represent scientific applications, which have different priorities in the process of scheduling. We propose a dynamic multi-cloud priority list scheduling algorithm (DMPLS), combining with workloads preemptive strategy and feedback mechanism to schedule scientific applications in time. Our algorithm regulates the workloads scheduling dynamically based on the updated information about the actual workloads execution time. The experimental results show that the proposed algorithm reduces the average time to complete the applications compared with First-Come-First-Service and Round-Robin algorithm. Moreover, the advantage of the DMPLS algorithm is more significant under the severe resources confliction situations.

Today, Smart Home monitoring services have attracted much attention from both academia and industry. However, in the conventional monitoring mechanism the remote camera can not be accessed for remote monitoring anywhere and anytime. Besides, traditional approaches might have the limitation in local storage due to lack of device elasticity. In this paper, we proposed a Cloud-based monitoring framework to implement the remote monitoring services of Smart Home. The main technical issues considered include Data-Cloud storage, Local-Cache mechanism, Media device control, NAT traversal, etc. The implementation shows three use scenarios: (a) operating and controlling video cameras for remote monitoring through mobile devices or sound sensors; (b) streaming live video from cameras and sending captured image to mobile devices; (c) recording videos and images on a cloud computing platform for future playback. This system framework could be extended to other applications of Smart Home.

Due to a few realistic challenges (e.g. lack of protocol support, limitation of NAT and firewall, etc), it is difficult to access residential multimedia services from heterogeneous network environment. In this paper, we propose a system architecture for accessing residential multimedia services from either local or remote networks. The proposed solution includes UPnP-based local multimedia access, Cloud-based remote multimedia access, and a few corresponding technical approaches (for instance, security, NAT traversal, etc) are also considered. The prototype implementation and evaluation shows feasibility and efficiency of proposed solution.

Topology control is one of the most fundamental problems in wireless sensor networks (WSNs). It is of great importance for prolonging network lifetime, reducing radio interference and energy consumption, increasing the efficiency of media access control (MAC) protocols and routing protocols, among other things. In this paper, the problem is transformed into a model of multi-criteria degree constrained minimum spanning tree (mcd-MST), and a non-dominated discrete particle swarm optimization (NDPSO) is designed to deal with this problem. To obtain a better approximation of true Pareto front, the phenotype sharing function of the objective space is applied in the definition of fitness function in NDPSO. Furthermore, a topology control scheme based on NDPSO is proposed in this paper. Simulation results show that the topology derived under the proposed scheme has low total power consumption, high robust structure and low contention among nodes, and it also can effectively prolong the lifetime of network.

Data aggregation has been emerged as a basic approach in wireless sensor networks (WSNs) in order to reduce the number of transmissions of sensor nodes. Since multi-source data obtained from different nodes represent redundancy or complement property, as an effective tool to deal with the conflicts, the use of game theory for WSNs is provided. The authors propose a common aggregation model, which is independent of the specific application environments, based on the evolutionary game theory called evolutionary game-based data aggregation model (EGDAM) in WSNs. EGDAM made up of formal definition, functional model and general process is defined to map the competition and cooperation in aggregation procedure into games, and well-avoid perfect rationality. The authors then put the theoretic model into application. Guided by our model, an evolutionary game-based adaptive weighting algorithm named EGWDA is provided for the pixel-level data aggregation with homogeneous sensors. Reasonable weights distribution of sensors can be achieved during the aggregation in WSNs. The experiments on both the self-constructed data and the one from reference made satisfied performances.

Acceleration coefficients controlled the impact of the particle's own experiences and the other particles' experiences on the trajectory of each particle. The setting of acceleration played a key role in the performance of particle swarm optimization. To efficiently control the local search and convergence to the global optimum solution, a good investigation to the key role of the setting of acceleration coefficients was made. A new recommended value for acceleration coefficients and corresponding PSO algorithm were presented basing on the investigation. In the new automation strategy, an unsymmetrical transfer range of acceleration coefficients were considered and it obtained preferable effects when changing c1from 2.75 to 1.25 and changing c2from 0.5 to 2.25. Four benchmark functions were selected as test functions. All four functions were tested with different dimensions and different population sizes. The experimental results illustrate that the new method of setting acceleration coefficients speeds up the convergence of PSO and improves the performance of PSO. Furthermore, it also can reserve more diversity of the swarm at the beginning period of the algorithm and thus have more ability to escape from local minimum