With the explosive growth of mobile data and the unprecedented demand for computing power, resource-constrained edge devices cannot effectively meet the requirements of Internet of Things (IoT) ...applications and Deep Neural Network (DNN) computing. As a distributed computing paradigm, edge offloading that migrates complex tasks from IoT devices to edge-cloud servers can break through the resource limitation of IoT devices, reduce the computing burden and improve the efficiency of task processing. However, the problem of optimal offloading decision-making is NP-hard, traditional optimization methods are difficult to achieve results efficiently. Besides, there are still some shortcomings in existing deep learning methods, e.g., the slow learning speed and the weak adaptability to new environments. To tackle these challenges, we propose a Deep Meta Reinforcement Learning-based Offloading (DMRO) algorithm, which combines multiple parallel DNNs with Q-learning to make fine-grained offloading decisions. By aggregating the perceptive ability of deep learning, the decision-making ability of reinforcement learning, and the rapid environment learning ability of meta-learning, it is possible to quickly and flexibly obtain the optimal offloading strategy from a dynamic environment. We evaluate the effectiveness of DMRO through several simulation experiments, which demonstrate that when compared with traditional Deep Reinforcement Learning (DRL) algorithms, the offloading effect of DMRO can be improved by 17.6%. In addition, the model has strong portability when making real-time offloading decisions, and can fast adapt to a new MEC task environment.
The sixth generation (6G) networks are expected to provide a fully connected world with terrestrial wireless and satellite communications integration. The design concept of 6G networks is to leverage ...artificial intelligence (Ai) to promote the intelligent and agile development of network services. intelligent services inevitably involve the processing of large amounts of data, such as storage, computing, and analysis, such that the data may be vulnerable to tampering or contamination by attackers. in this article, we propose a blockchain-based data security scheme for Ai applications in 6G networks. Specifically, we first introduce the 6G architecture (i.e., a space-air-ground-underwater integrated network). Then we discuss two Ai-enabled applications, indoor positioning and autonomous vehicle, in the context of 6G. Through a case study of an indoor navigation system, we demonstrate the effectiveness of blockchain in data security. The integration of Ai and blockchain is developed to evaluate and optimize the quality of intelligent service. Finally, we discuss several open issues about data security in the upcoming 6G networks.
Internet of Things (IoT) anomaly detection is significant due to its fundamental roles of securing modern critical infrastructures, such as falsified data injection detection and transmission line ...faults diagnostic in smart grids. Researchers have proposed various detection methods fostered by machine learning (ML) techniques. Federated learning (FL), as a promising distributed ML paradigm, has been employed recently to improve detection performance due to its advantages of privacy-preserving and lower latency. However, existing FL-based methods still suffer from efficiency, robustness, and security challenges. To address these problems, in this article, we initially introduce a blockchain-empowered decentralized and asynchronous FL framework for anomaly detection in IoT systems, which ensures data integrity and prevents single-point failure while improving the efficiency. Further, we design an improved differentially private FL based on generative adversarial nets, aiming to optimize data utility throughout the training process. To the best of our knowledge, it is the first system to employ a decentralized FL approach with privacy-preserving for IoT anomaly detection. Simulation results on the real-world dataset demonstrate the superior performance from aspects of robustness, accuracy, and fast convergence while maintaining high level of privacy and security protection.
The proliferation of unmanned aerial vehicles (UAVs) leads to various applications in different fields. Due to the easy deployment and dynamic reconfigurability of UAVs, they can provide and support ...multiple services for users, such as surveillance, sensing, and logistics. However, the increasing attention to UAV applications exposes it to security threats. The openness and multi-connectivity characteristics make UAV networks more vulnerable to malicious attacks. In this article, to protect the security of UAV networks, we present a deep reinforcement learning approach to detect malicious attacks in UAV aerial computing networks. We first provide the framework of UAV aerial computing networks and potential applications. Intrusion threats in UAV aerial computing networks are then discussed. Next, we present a case study of deep-reinforcement-learning-em-powered intrusion detection to protect the security services. Finally, we present the conclusion and several promising research directions.
Display omitted
Acute liver injury (ALI) caused by sepsis is a fearful disease with high mortality and poor prognosis. This study aimed to explore the roles and mechanism of Maresin 1 (MaR1) in ...lipopolysaccharide/d-galactosamine (LPS/D-GalN)-induced ALI.
We established an ALI mouse model induced by LPS/D-GalN. Each group was treated with or without LPS/D-GalN or MaR1. For the vitro experiments, RAW264.7, NCTC1469 cells, and bone marrow-derived macrophages (BMDMs) were stimulated with LPS. The effects of MaR1 on the reactive oxygen species (ROS), pyroptosis and inflammatory response in macrophages were investigated.
MaR1 significantly inhibited an excessive inflammatory response and proinflammatory markers during LPS/D-GalN-induced ALI. MaR1 markedly decreased the levels of ROS, tumor necrosis factor-α, and interleukin-1β (IL-1β) in macrophages, and limited hepatocyte apoptosis in vitro. Upon exploring the mechanisms underlying the protective role of MaR1, we found MaR1 markedly upregulated the nuclear factor erythroid 2–related factor 2 (Nrf2) and heme oxygenase-1 (HO-1), and considerably reduced the phosphorylation of p38, ERK, and nuclear factor-kappa B (NF-κB)-p65. Knocking down Nrf2 decreased the effect of MaR1. Furthermore, we observed that MaR1 reduced inflammatory injury by inhibiting M1 macrophages and promoting M2 macrophage polarization. Finally, we observed that MaR1 could inhibit the production of gasdermin D N-terminus (GSDMD-N) in vivo. In vitro, MaR1 could significantly suppressed the expression of NLR family pyrin domain containing 3 (NLRP3) inflammasome, GSDMD-N, and IL-1β caused by LPS and nigericin stimulation in BMDMs.
MaR1 could ameliorate inflammation during LPS/D-GalN induced ALI by suppressing mitogen-activated protein kinase /NF-κB signaling and NLRP3 inflammasome-induced pyroptosis, activating macrophage M1/M2 polarization and Nrf2/HO-1 signaling. This provides new evidence for the potential of developing MaR1 for ALI treatment.
The increasing development of Internet of Things (IoT) has led to the emergence of Internet of connected vehicles (IoCVs). These vehicles with various functionalities have the potential prospects for ...improving the quality of experience (QoE) of vehicle users. Moreover, the use of unmanned aerial vehicles (UAVs) in flying networks extends the connectivity and universality of IoT, and these UAVs with caching and communication capacities can support various services. However, due to the heterogeneity of vehicular networks and flying networks, the communication performance and content distribution between UAVs and IoCVs expose new challenges in heterogeneous networks (HetNets). Therefore, in this paper, a novel content distribution mechanism between UAVs and IoCVs is proposed to improve the QoE of vehicle users. Specifically, we first develop a novel content distribution architecture for UAVs and IoCVs in HetNets, where the content is distributed by UAV content providers to IoCVs. Next, we establish an optimization problem of content distribution between UAVs and IoCVs to minimize the transmission delay. In order to stimulate UAVs and IoCVs to join content distribution, the utilities of UAVs and IoCVs are formulated, respectively. Moreover, we design a coalition game between UAVs and IoCVs to determine the optimal strategy of content distribution. Finally, simulation results demonstrate that the proposed mechanism can significantly improve the performance of content distribution compared with the conventional mechanisms.
Abstract
Motivation
The large-scale multidimensional omics data in the Genomic Data Commons (GDC) provides opportunities to investigate the crosstalk among different RNA species and their regulatory ...mechanisms in cancers. Easy-to-use bioinformatics pipelines are needed to facilitate such studies.
Results
We have developed a user-friendly R/Bioconductor package, named GDCRNATools, for downloading, organizing and analyzing RNA data in GDC with an emphasis on deciphering the lncRNA-mRNA related competing endogenous RNAs regulatory network in cancers. Many widely used bioinformatics tools and databases are utilized in our package. Users can easily pack preferred downstream analysis pipelines or integrate their own pipelines into the workflow. Interactive shiny web apps built in GDCRNATools greatly improve visualization of results from the analysis.
Availability and implementation
GDCRNATools is an R/Bioconductor package that is freely available at Bioconductor (http://bioconductor.org/packages/devel/bioc/html/GDCRNATools.html). Detailed instructions, manual and example code are also available in Github (https://github.com/Jialab-UCR/GDCRNATools).
The popularity of the Android platform in smartphones and other Internet-of-Things devices has resulted in the explosive of malware attacks against it. Malware presents a serious threat to the ...security of devices and the services they provided, e.g. stealing the privacy sensitive data stored in mobile devices. This work raises a stacking ensemble framework SEDMDroid to identify Android malware. Specifically, to ensure individual's diversity, it adopts random feature subspaces and bootstrapping samples techniques to generate subset, and runs Principal Component Analysis (PCA) on each subset. The accuracy is probed by keeping all the principal components and using the whole dataset to train each base learner Multi-Layer Perception (MLP). Then, Support Vector Machine (SVM) is employed as the fusion classifier to learn the implicit supplementary information from the output of the ensemble members and yield the final prediction result. We show experimental results on two separate datasets collected by static analysis way to prove the effectiveness of the SEDMDroid. The first one extracts permission, sensitive API, monitoring system event and so on that are widely used in Android malwares as the features, and SEDMDroid achieves 89.07% accuracy in term of these multi-level static features. The second one, a public big dataset, extracts the sensitive data flow information as the features, and the average accuracy is 94.92%. Promising experiment results reveal that the proposed method is an effective way to identify Android malware.
As a distributed computing paradigm, edge computing has become a key technology for providing timely services to mobile devices by connecting Internet of Things (IoT), cloud centers, and other ...facilities. By offloading compute-intensive tasks from IoT devices to edge/cloud servers, the communication and computation pressure caused by the massive data in Industrial IoT can be effectively reduced. In the process of computation offloading in edge computing, it is critical to dynamically make optimal offloading decisions to minimize the delay and energy consumption spent on the devices. Although there are a large number of task offloading-decision models, how to measure and evaluate the quality of different models and configurations is crucial. In this article, we propose a novel simulation platform named ChainFL, which can build an edge computing environment among IoT devices while being compatible with federated learning and blockchain technologies to better support the embedding of security-focused offloading algorithms. ChainFL is lightweight and compatible, and it can quickly build complex network environments by connecting devices of different architectures. Moreover, due to its distributed nature, ChainFL can also be deployed as a federated learning platform across multiple devices to enable federated learning with high security due to its embedded blockchain. Finally, we validate the versatility and effectiveness of ChainFL by embedding a complex offloading-decision model in the platform, and deploying it in an Industrial IoT environment with security risks.
The proliferation of smart devices has led to a huge amount of data streaming in the Internet of Things (IoT). However, the resource-limited devices cannot satisfy the demands of computing-in-tensive ...but delay-sensitive applications. The data delivery among devices may be tampered with by malicious users. These pose new challenges to provide secure and intelligent services in IoT. Blockchain and reinforcement learning (RL) are promising techniques for establishing a secure environment and intelligent resource management. In this article, we introduce a novel software defined networking (SDN)-enabled architecture for edge-cloud orchestrated computing to support secure and intelligent services in IoT. We first introduce the SDN-enabled architecture by integrating cloud computing, edge computing, and IoT networks. Then we provide several applications of SDN-enabled architecture in edge-cloud orchestrated computing. Next, we propose the blockchain and RL envisioned solutions to implement secure and intelligent services in IoT. Moreover, a case study of blockchain- and RL-enabled secure and intelligent computing offloading is presented to validate its effectiveness. We finally provide our conclusion and discuss several promising research directions.