The emergence of edge computing has witnessed a fast-growing volume data on devices belonging to different stakeholders which, however, cannot be shared among them due the lack trust. By exploiting blockchain's non-repudiation and non-tampering properties that enable trust, we develop blockchain-based big sharing framework support various applications across resource-limited edges. In particular, devise number novel resource-efficient techniques for framework: (1) PoC...

The Multipath TCP (MPTCP) protocol, featured by its ability of capacity aggregation across multiple links and connectivity maintenance against single-path failure, has been attracting increasing attention from the industry academy. packet scheduling is a unique fundamental mechanism for design implementation MPTCP, which responsible distributing traffic over subflows. existing multipath schedulers are facing challenges network heterogeneities, comprehensive QoS goals, dynamic environments,...

Software-Defined Network (SDN) is a promising network paradigm that separates the control plane and data in network. It has shown great advantages simplifying management such new functions can be easily supported without physical access to switches. However, Ternary Content Addressable Memory (TCAM), as critical hardware storing rules for high-speed packet processing SDN-enabled devices, supplied each device with very limited quantity because it expensive energy-consuming. To efficiently use...

Semantic segmentation plays a pivotal role in the intelligent interpretation of remote sensing images (RSIs). However, conventional methods predominantly focus on learning representations within spatial domain, often resulting suboptimal discriminative capabilities. Given intrinsic spectral characteristics RSIs, it becomes imperative to enhance potential these by integrating context alongside information. In this paper, we introduce spectrum-space collaborative network (SSCNet), which is...

Cooperative communication (CC) can offer high channel capacity and reliability in an efficient low-cost way by forming a virtual antenna array among single-antenna nodes that cooperatively share their antennas. It has been well recognized the selection of relay plays critical role performance multiple source-destination pairs. Unfortunately, all prior work made unrealistic assumption spectrum resources are unlimited each pair communicate over dedicated with no mutual interference. In this...

Caching popular videos at mobile edge servers (MESs) has been confirmed as a promising method to improve users (MUs) perceived quality of experience (QoE) and alleviate the server load. However, with multiple bitrate encoding techniques prevalently employed in modern streaming services, caching deployment is challenging for following three facts: (1) cooperative should be explored MUs located overlapped coverage areas MESs; (2) there exists tradeoff consideration either high or diversity...

Federated Learning (FL) is a promising machine learning paradigm to cooperatively train global model with highly distributed data located on mobile devices. Aiming optimize the communication efficiency for gradient aggregation and synchronization among large-scale devices, we propose relay-assisted FL framework. By breaking traditional transmission-order constraint exploiting broadcast characteristic of relay nodes, design novel scheme named Partial Synchronization Parallel (PSP), in which...

Oblique Decision Tree (ODT) separates the feature space by linear projections, as opposed to conventional (DT) that forces axis-parallel splits. ODT has been proven have a stronger representation ability than DT, it provides way create shallower tree structures while still approximating complex decision boundaries. However, its learning efficiency is insufficient, since projections cannot be transmitted child nodes, resulting in waste of model parameters. In this work, we propose an enhanced...

In recent years, as a compromise between privacy and performance, few-sample model compression has been widely adopted to deal with limited data resulting from security concerns. However, when the number of available samples is extremely limited, class imbalance becomes common tricky problem. Achieving an equal across all classes often costly impractical in real-world applications, previous studies on have mostly ignored this significant issue. Our experiments comprehensively demonstrate...

As a variation of random linear network coding, segmented coding (SNC) has attracted great interest in data dissemination over lossy networks due to its low computational cost. In order guarantee the success decoding, SNC can adopt feedbackless forward error correction (FEC) approach by applying block code input packets before segmentation at source node. particular, if empirical rank distribution transfer matrices segments is known advance, several classes coded achieve close-to-optimal...

Optimization is an important research field, especially in engineering, physical sciences, and economics. The main purpose of optimization to maximize the profit minimize cost production as well loss system. Evolutionary computation algorithms, such genetic algorithm particle swarm (PSO) have been successfully employed solving various problems. Owing its application potential promising performance discovering optimal solution, PSO has recognized a powerful technique attracted ever-increasing...

The software-defined network (SDN) enabled mobile edge greatly facilitates resource management and promotes many emerging applications. However, user mobility may cause the SDN controller to set flow rules frequently, introduce additional setup latency, delay jitter, undermine latency-sensitive services. Proactive is an effective way eliminate but existing work fails maximize hit ratio, a metric for evaluating quality of proactive decisions, which critical In this paper, we study how...

Propelled by recent advances in Mobile Edge Computing (MEC) and the Internet of Things (IoT), digital twin technique has been envisioned as a de-facto driving force to bridge virtual physical worlds through creating portrayals objects. In virtue flourishing edge intelligence abundant IoT data, data-driven modelling facilitates implementation maintenance twins, where simulations objects are usually performed based on Deep Neural Networks (DNNs). A significant advantage adopting twins is...

A large number of data centers have been deployed and available for public renting with the rapid development cloud computing recently. Meanwhile, proliferation automotive electronics has made rich resources in various forms computation communication. It is challenging but great significance to make use these an efficient way. In this paper, we propose a two-tier center architecture that leverages excessive storage parking lots. Such form auxiliary vehicular (VDC) such pressure on...

Currently, the logistic industry has introduced 3D reconstruction to monitor package placement in warehouse. Previous solutions mainly utilize computer vision or sensor-based methods, which are restricted line-of-sight battery life. Therefore, we propose a passive RFID-based solution, called RF-3DScan, perform on tagged packages, including orientation and stacking. The basic idea is that moving antenna can obtain RF-signals from tags attached packages with 1D linear mobile scanning. Through...

Software Defined Networking (SDN) brings numbers of advantages along with many challenges. One particular concern is on the control-plane resilience, while existing protection approaches proposed for SDN networks mainly focus data-plane. In order to achieve carrier-grade recovery from link failures, we adopt dedicated scheme towards finding optimal routing traffic. To this end, study a weighted cost minimization problem, in which traffic load balancing and flow table rule placement are...

Mobile Augmented Reality (MAR) applications usually contain computation-intensive tasks which far outstrip the capability of mobile devices. One way to overcome this is offloading MAR remote clouds. However, wide area network delay hard reduce. Thanks edge computing, we can offload nearby servers. Prior studies focus on either single-task or dependent for a single user. In article, study decision from multiple users, each comprised chain tasks, over generic cloud-edge system consisting group...