Green computation has emerged as one of the key goals of cloud resource provisioning. The cloud resource clusters (CRCs) composed of heterogeneous performance servers are powered by uninterruptible power supplies (UPSs). However, due to the inherent nonlinear losses of UPSs, CRCs face challenges in computing resource provisioning with regard to sustainable energy consumption. Meanwhile, to alleviate the backlog in service queues, we propose a joint resource configuration and instance placement optimization problem that comprehensively models the energy consumption during instances processing in CRCs. Specifically, based on the length of the execution intervals of these two phases, this problem is decomposed into two subproblems in a dual-timescale framework. In a long timescale, we explore the temporal correlation of historical request data to pre-configure resources. Subsequently, the Lyapunov optimization method is employed to decompose the energy consumption problem of servers supported by each UPS into multiple subproblems across short timescale, while ensuring the stability of service queues. Furthermore, we use instance continuous relaxation to derive the optimal placement solution ideally, and design a double optimal gradient descent strategy for its practical implementation. Evaluation results demonstrate that the proposed strategy achieve measurable energy reduction in CRCs while maintaining flexibility during resource scaling.

Camouflaged Object Detection (COD) is a formidable computer vision challenge due to the striking resemblance between camouflaged objects and their surroundings. Despite progress in existing methods, they still face significant limitations, particularly in addressing the issues of fuzzy boundaries and the inadequate fusion of local and global features. To address these challenges, we present a multi-scale COD network named Multi-Scale Local-Global Fusion (MSLGF). MSLGF incorporates a Multi-Scale Fusion Module (MSFM), which skillfully integrates feature maps at multiple scales to produce high-fidelity edge features. Additionally, to refine the detection process, a Local-Global Feature Fusion Module (LGFFM) combines the local edge details with global semantic information of camouflaged targets, significantly enhancing the accuracy of COD. Experimental results show that MSLGF achieves remarkable performance across 3 benchmark datasets, i.e., Camouflaged Object Dataset (CAMO), Camouflaged Object Dataset with 10,000 Images (COD10K), and NC4K. Specifically, MSLGF attains a structure-measure from 0.879 to 0.894 and a weighted F-measure between 0.817 and 0.856. The source code is publicly available at https://github.com/tc-fro/MSLGF.

SUMMARY: Identifying cell states associated with disease progression or experimental perturbations from single-cell Assay for Transposase Accessible Chromatin using sequencing (scATAC-seq) data is critical for unraveling disease pathogenesis. However, the high dimensionality, extreme sparsity, and nearly binary nature of scATAC-seq data pose significant challenges. Here, we present reDA, a cluster-free computational framework that performs differential abundance testing based on the random walk with restart. Through comprehensive experiments on simulated and real datasets, reDA outperforms six baseline methods, demonstrating superior accuracy, computational efficiency, and the ability to capture disease-specific molecular signatures. AVAILABILITY AND IMPLEMENTATION: The reDA along with detailed documentation is freely available at https://github.com/Jinsl-lab/reDA. It can be seamlessly integrated into existing scATAC-seq analysis workflows.

Non-terrestrial networks (NTNs) are integrated with terrestrial networks to form space-air-ground integrated networks (SAGINs), providing seamless global coverage and supporting the development of the digital economy. However, when it comes to the actual design and deployment of SAGINs, the heterogeneity, self-organization, and flexibility of SAGIN pose challenges for precise modeling and quantitative analysis. In this regard, this paper proposes a multi-dimensional analysis model based on stochastic geometry for SAGIN, which considers the randomness of ground users’ (GUs) distribution and the multi-dimensional coverage characteristics of NTN nodes. The model determines the policies for GUs to access NTNs by adopting the maximum received average signal-to-interference-plus-noise ratio (SINR) association policy (AP) and the balanced satellite load AP. Specifically, we analyze the interference distribution of different links in the terahertz (THz) band and their Laplace transforms, then derive the uplink connectivity expressions of ground-to-space links with/without aerial relays under the two APs. Numerical results validate the accuracy of the theoretical model and explore the impact of APs, SINR thresholds, THz channel propagation coefficients, and aerial relay numbers on SAGIN connectivity, providing theoretical guidance for the deployment of THz SAGINs.

Massive machine communication is predicted to provide widespread and unparalleled connectivity for cellular Internet of Things (IoT) applications via multiple-input multiple-output (MIMO) and grant-free random access (GF-RA) techniques. Compressed sensing (CS) has been widely advocated to support massive connectivity due to the bursty nature of traffic transmission. In this paper, the joint activity detection and channel estimation in MIMO-enabled GF-RA system is formulated as a block single measurement vector (SMV) problem and efficiently addressed by using Bayesian-based CS algorithms. First, the pattern coupled sparse Bayesian learning (PCSBL) and block sparse Bayesian learning (BSBL) algorithms are introduced to solve this problem, where the potential block sparsity properties induced by multi-antenna reception are exploited by assigning the structured hyperpriors. Then, by embedding the Generalized Approximate Message Passing (GAMP) technique into the PCSBL and BSBL frameworks to enable effective approximation of posterior distributions, we propose two computationally efficient Bayesian learning algorithms, i.e., GAMP-PCSBL and GAMP-BSBL. Fortunately, the proposed Bayesian algorithms allow automatic learning of block sparse solutions without requiring noise level and user sparsity ratio as explicit conditions. Simulation results show that the proposed algorithms provide improved performance gains over the standard CS-based methods.

Massive machine-type communications (mMTC) are anticipated to be supported by grant-free random access (GF-RA) and multiple-input multiple-output (MIMO) techniques. Compressed sensing (CS) is extensively advocated to accommodate massive connectivity due to bursty data transmission. In this paper, we formulate the joint activity detection and channel estimation for the MIMO-enabled GF-RA system as a block single measurement vector (SMV) problem. First, the hierarchical block sparse Bayesian learning (BSBL) framework is developed to solve this problem, where the potential block sparse properties induced by multiantenna reception are exploited by assigning the structured hyperprior. Then, by integrating the generalized approximate message passing (GAMP) approach into the BSBL formulation to effectively approximate the posterior distribution, we propose a computationally efficient Bayesian learning algorithm named GAMP-BSBL. Fortunately, the proposed Bayesian algorithms enable automatic learning of block sparse solutions without requiring noise level and user sparsity ratio as explicit conditions. Simulation results show that the proposed algorithms provide improved performance gains as compared with the standard CS methods.

Grant-free non-orthogonal multiple access (GF-NOMA) based on multiple-input multiple-output (MIMO) has attracted much attention as a promising technique to support massive connectivity and bursty data transmission in massive machine-type communication. In this paper, we propose two compressed sensing based multiuser detection (MUD) algorithms for the MIMO-enabled GF-NOMA system. First, the spatially enhanced variational Bayesian inference (SE-VBI) algorithm is developed for MUD by exploiting the Gaussian mixture prior and diversity combining technique. Then, by applying the covariance-free (CoFe) strategy to the SE-VBI framework to estimate the diagonal elements of the posterior covariance, we propose a low-complexity MUD method named SE-CoFe-VBI. In particular, the proposed algorithms integrate the multivariate nature of the transmitted signal, i.e., discreteness, sparsity, and spatial correlation. Simulation results show that the proposed algorithms offer improved detection performance over the state-of-the-art spatially enhanced sparse Bayesian learning method.

The metaverse is a human-centric beyond-reality virtual world, in which people use virtual identities to live, work, and socialize. Due to the openness and sharing of metaverse applications, the virtual-real identity link (VRIL) may cause uncertainties and unpredictable risks. At present, the research on VRIL risks is still in its infancy and VRIL risk predictions lack a comprehensive theoretical system and methodological tool. In this paper, we first construct a VRIL attack model, according to which an attacker can link a user’s real and virtual identities together using the information observed in the real and virtual worlds. Then we propose the tuple frequency-based VRIL prediction (TupPre) model and discover the population distribution, recursive hypergeometric (RH) distribution, and approximate binomial distribution of the tuple frequency (i.e., the occurrence times of attribute value combinations) given incomplete information. Focusing on the tuple frequency estimation error in biased samples, we introduce attribute value correlation knowledge to improve the prediction performance. The experimental results on generated and real-world datasets show that the TupPre model has excellent performance, with a mean area under the curves (AUCs) of 0.86 to 0.98 on these datasets, and it performs even more superior with certain background knowledge (mean AUC 0.95~0.98). The discovered basic distribution rules of the tuple frequency and the proposed quantitative analysis method for metaverse VRIL risk predictions construct the foundation of the identity privacy framework for the metaverse.

Targeted sentiment analysis aims to identify the sentiment polarity of specific target mentions in a sentence. Existing methods employ neural networks to extract the relations between target mentions and their contexts. Recent approaches based on graph convolutional networks can model the syntactic relations extracted by an external parser into adjacency matrices. However, online reviews are informal and complex, the syntactic structures provided by the parser can be incorrect in these syntax-insensitive scenarios. To remedy this defect, we design a novel integrated syntactic and semantic tree (IS2tree) by labeling semantic relations between the target mention and contexts in a syntactic dependency tree. Furthermore, a dual-channel graph convolutional network (DCGCN) is proposed to encode the contextual information associated with the target mention by dynamic semantic pruning mechanisms and to also retain the syntactic relations. Experimental results demonstrate that the IS2tree has a favorable generalization capability comparing to the state-of-the-art baselines on four public datasets.

Federated Learning (FL) serves as a machine learning paradigm where distributed devices collaboratively train on local data, with their models subsequently aggregated on a central server. However, challenges arise due to unreliable communication channels, potential sign errors in model parameters, data heterogeneity, and resource limitations that can hinder full client participation. In this paper, firstly, we address these issues by proposing an optimization objective that minimizes FL loss while taking into account constraints on delay and energy consumption. Secondly, to counteract the model drift caused by data heterogeneity and packet errors, we introduce a proximal term in the local training process and incorporate packet errors into the global aggregation phase. Finally, we establish a theoretical convergence upper bound for our FL algorithm in complex non-convex situations, providing insights to guide the formulation of client sampling strategies and ensure FL algorithm convergence. We validate our algorithm’s superior accuracy on the MNIST and CIFAR-10 datasets.

Connected health is a rapidly advancing field that encompasses wireless, digital, mobile, and telehealth technologies. It aims to improve healthcare management by leveraging abundant health data shared by individuals for proactive and efficient care. Edge intelligence (EI), which integrates artificial intelligence (AI) with edge computing, has emerged as a transformative approach to connected health. This paper proposes an EI computing power collaboration framework for connected health. The framework leverages the computing power of edge devices, including consumer electronics, to enhance connected health services. In addition, the framework incorporates edge caching and blockchain technology for efficient healthcare data storage and secure EI computing power collaborations. Deep reinforcement learning, specifically the MuZero algorithm, is used to generate optimal strategies for adjusting the supply-demand relationship of EI computing power. The proposed framework enables responsive and economic healthcare services and empowers various compute-intensive connected health applications.

Since the outbreak of coronavirus (COVID-19) in 2019, wearing masks has been widely considered an effective method of reducing the risk of infection among people. However, incorrectly wearing a mask can significantly increase the risk of spreading the virus. To enable machines to automatically detect whether people are wearing masks correctly, we propose scenario-specific Faster-RCNN (SS-Faster-RCNN), a domain adaptation-based method for masked face detection. The frame-work is based on the Faster-RCNN and consists of two parts. The first part detects mask-wearing zones, and the last part aims to validate real mask faces in the candidate regions. The experimental results demonstrate that a trained feature extractor on a large mask face dataset can effectively enhance the model's performance on smaller mask face datasets for scenario-specific and non-scenario-specific cases. In addition, we also present videos for mask detection that consist of 858 seconds of video with 30 frames per second. The dataset mainly consists of images and videos from streets and subway stations. Overall, our method shows superior performance compared to others across different datasets. Codes, data, and evaluations are available at https://github.com/boranyang-ML/SSMFVD.

The metaverse aims to build an immersive virtual reality world to support the daily life, work, and recreation of people. In this survey, the status quo of the metaverse is investigated, and the technical framework of the metaverse is introduced from three aspects: 1) the generation of virtual worlds; 2) the connection of virtual and real objects; and 3) the transmission of data. Specifically, this survey first discusses the development and challenges of the related technologies for virtual world generation methods from three aspects: 1) the 3-D world generation; 2) immersive human–computer interaction experience; and 3) ecosystem. Second, we investigate the status quo of extended reality (XR), motion capture, and brain–computer interface technologies and evaluate the potential and research directions of these entrance technologies for the metaverse. Finally, network and data transmission technologies for the metaverse are reviewed from the Internet of Things (IoT), 5G/6G wireless, and edge computing aspects, the demand side of the metaverse in virtual-reality interpromotion, big data processing, and low-latency networking is discussed, and promising research hotspots are identified.

The high-speed movement of nodes and the burstiness of interactions in the Internet of Vehicles pose huge challenges to the trusted vehicle collaboration and data sharing. Aiming at the disadvantages of existing authentication mechanisms and trust management models for connected vehicles, this article proposes a trust management model enabled by blockchain to ensure the traceability, nontampering, unforgeability, and transparency of vehicular interactions. The proposed trust management model leverages Dirichlet distribution, reputation regression, and revocation punishment to objectively and accurately reflect the trust status of vehicles. Simulation results on real-world data sets show that the proposed trust management model advantageously improves the accuracy of malicious vehicle detection and the attack resistance of connected vehicles.

Wearing masks can effectively inhibit the spread and damage of COVID-19. A device-edge-cloud collaborative recognition architecture is designed in this paper, and our proposed device-edge-cloud collaborative recognition acceleration method can make full use of the geographically widespread computing resources of devices, edge servers, and cloud clusters. First, we establish a hierarchical collaborative occluded face recognition model, including a lightweight occluded face detection module and a feature-enhanced elastic margin face recognition module, to achieve the accurate localization and precise recognition of occluded faces. Second, considering the responsiveness of occluded face detection services, a context-aware acceleration method is devised for collaborative occluded face recognition to minimize the service delay. Experimental results show that compared with state-of-the-art recognition models, the proposed acceleration method leveraging device-edge-cloud collaborations can effectively reduce the recognition delay by 16% while retaining the equivalent recognition accuracy.

Edge caching enables low-delay and high-quality data services for the Industrial Internet. However, traditional popularity-based edge caching ignores the diversity and evolution of user interest, especially among user groups, and therefore has the limited quality of experience guarantees for users. In this regard, a recommendation-aided edge caching approach is proposed to leverage the time-varying user interest. Specifically, a dynamic interest capture model was proposed to mine the individual user interest, based on which, a group interest aggregation algorithm is then studied to determine the content caching strategies for edge nodes. Thereafter, an edge content recommendation is further proposed to optimize the cache hit ratio while ensuring a satisfying recommendation hit ratio based on the personalized user interest and given caching decision. The effectiveness of the proposed approach is finally validated by comparing it with other baseline approaches.

The flexible combination of pervasive portable smart devices and omnipresent high-speed access infrastructures has revolutionized the data sensing and knowledge acquisition in mobile crowdsensing (MCS), underpinning fine-grained city management and highly customizable Internet service applications. However, MCS applications are still confronted with unsolved challenges, such as task assignment, privacy risks, and misbehavior detection. In light of this, this article proposes PETA, a privacy-preserving edge task assignment framework for MCS, leveraging the powerful edge servers deployed between users and the platform to cluster and manage users according to user attributes. Furthermore, group signature is employed by PETA to anonymize and verify user identities for privacy-preserving task assignments. The theoretical analysis and simulation results validate the performance of PETA on identity anonymity, malicious user detection, and task completion rate.

To reconcile the conflict between ceaselessly growing mobile data demands and the network capacity bottleneck, we exploit the terminal-edge-cloud collaboration to design a streaming distribution framework, SD-TEC, with the major objective to avoid streaming interruptions caused by inter-cluster handovers and corresponding user defections. First, the merge-and-split rule in the coalition game is employed for virtualized passive optical network clustering to structurally reduce the inter-cluster handover frequency. Second, the terminal-edge collaboration leverages device-to-device communications to sustain streaming services when inter-cluster handovers inevitably occur, reducing the time of possible streaming interruptions and improving the quality of experience of multimedia services. Lastly, the edge-cloud collaboration proactively caches streaming contents to alleviate the traffic congestion of peak hours and considers user priorities and buffer queue underflow/overflow to manage both fronthaul and backhaul resources. Simulation results validate the efficiency of our proposed SD-TEC in reducing the traffic congestion and streaming interruptions caused by inter-cluster handovers.

Calcium signaling plays an important role in both physiological activities and engineered applications of molecular communication. Recent experimental studies in biology reveal that calcium signaling is closely related to mobility of biological cells. In this paper, we address communication-related issues of calcium signaling among a group of mobile cells. First, a mobility model of biological cells is established based on experimental studies in biology. Then, the mobility model is integrated with a widely accepted model of calcium signaling. Further, computer simulations are performed using the integrated model to examine the communication-related performance of calcium signaling among a group of mobile cells. A major finding from computer simulations is that there exists an optimal moving velocity of cells to maximize the range of signal propagation in a group of mobile cells.

To preserve the privacy of multimedia big data and achieve the efficient data aggregation in wireless multimedia sensor networks (WMSNs), a distributed compressed sensing--based privacy-preserving data aggregation (DCSPDA) approach is proposed in this article. First, in this approach, the original multimedia sensor data are compressed and measured by distributed compressed sensing (DCS) and the compressed data measurements are uploaded to the sink, by which the inherent characteristics between sensor data can be obtained. Second, the original multimedia data are jointly recovered and the common and innovation sparse components are obtained through solving the optimization problem and linear equations at the sink. Third, through least squares support vector machine (LSSVM) learning of the sparse components, the sparse position configuration can be determined and disseminated for each node to conduct the privacy-preserving data configuration. After receiving the configuration message, original multimedia sensor data are accordingly customized, compressed, and measured by the common measurement matrix, aggregated at the cluster heads, and transmitted to the sink. Finally, the aggregated multimedia sensor data are recovered by the sink according to the data configuration to achieve the privacy-preserving data aggregation and transmission. Our comparative simulation results validate the efficiency and scalability of DCSPDA and demonstrate that the proposed approach can effectively reduce the communication overheads and provide reliable privacy-preserving with low computational complexity for WMSNs.