Search

A growing number of web APIs published on the Internet allows mashup developers to discover appropriate web APIs for polishing mashups. Developers often have to manually pick and choose several web APIs from extremely massive candidates, which is a laborious and cumbersome task. Fortunately, recommender system comes into existence. Some approaches perform recommendations in cloud platforms by utilizing historical records of Mashup-API interactions stored in edge nodes. However, many of these methods often pay more attention to recommendation accuracy while ignoring recommendation diversity, i.e., there are usually popular web APIs in recommendation list while most of the other novel web APIs are absent. The poor recommendation diversity may limit the usefulness of the recommendation results due to the lack of novelty. In order to implement an accurate and diversified web API recommendation, a novel MF-based recommendation approach named Div_PreAPI is put forward in this paper. Div_PreAPI integrates a weighting mechanism and neighborhood information into matrix factorization (MF) to implement diversified and personalized APIs recommendations. Finally, we conduct a series of experiments on a real-world dataset. Experimental results show the effectiveness of our proposal.

The cyber-physical cloud systems (CPCSs) release powerful capability in provisioning the complicated industrial services. Due to the advances of machine learning (ML) in attack detection, a wide range of ML applications are involved in industrial CPCSs. However, how to ensure the implementation efficiency of these applications, and meanwhile avoid the privacy disclosure of the datasets due to data acquisition by different operators, remain challenging for the design of the CPCSs. To fill this gap, in this article a privacy-aware deployment method (PDM), named PDM, is devised for hosting the ML applications in the industrial CPCSs. In PDM, the ML applications are partitioned as multiple computing tasks with certain execution order, like workflows. Specifically, the deployment problem is formulated as a multiobjective problem for improving the implementation performance and resource utility. Then, the most balanced and optimal strategy is selected by leveraging an improved differential evolution technique. Finally, through comprehensive experiments and comparison analysis, PDM is fully evaluated.

With the development of the Internet of Things (IoT), the number of mobile terminal devices is increasing rapidly. Due to high transmission delay and bandwidth limitation, computing power requirements for IoT devices are getting higher and higher. Recently, edge computing is an effective way to reduce system delay, and blockchain solves the security problem of edge computing. In this paper, a three-layer network model, named blockchain-based mobile edge computing system (BMEC), is proposed for clone block identification. Specifically, a neural network based clone block identification (NCBI) method is proposed to prevent clone block attacks. After that, the Prim algorithm is applied to BMEC to generate a weighted undirected graph minimum spanning tree that is composed of edge blocks. This can divide a main chain into several side chains to improve the transaction speed of blockchain. Finally, the blockchain is constructed based on the time slicing round-robin scheduling algorithm to control resources from edge servers and regulate edge devices’ activities based on the predefined rules of priority, application type, and past behavior. Experimental results show that our clone block identification method can achieve block validation effectively in BMEC, and our construction of blockchain delay is lower than conventional edge computing methods.

In this paper, we focus on the design of optimal relay and jammer selection strategy in relay-aided wireless networks. Different from previous works, assuming that the channel state information (CSI) of illegitimate nodes was available and only an eavesdropper existed, we first analyze disadvantages of joint relay and jammer selection (JRJS), average optimal relay selection (AORS), traditional maximum relay selection (TMRS) schemes. Then, we design an optimal relay and jammer selection strategy where the ratio of received SNRs at the destination generated by any two relays is maximized. By applying proposed strategy, computation complexity can be reduced. Moreover, we derive the lower and upper bounds of the secrecy outage probability based on the assumptions of existence of only illegitimate node and symmetric case for mathematical convenience. Finally, simulation shows that the proposed strategy operating with no CSI of illegitimate nodes can work efficiently compared with JRJS, TMRS and AORS strategies.

Retail products belonging to the same category usually have extremely similar appearance characteristics such as colors, shapes, and sizes, which cannot be distinguished by conventional classification methods. Currently, the most effective way to solve this problem is fine-grained classification methods, which utilize machine vision + scene to perform fine feature representations on a target local region, thereby achieving fine-grained classification. Fine-grained classification methods have been widely used for recognizing birds, cars, airplanes, and many others. However, the existing fine-grained classification methods still have some drawbacks. In this paper, we propose an improved fine-grained classification method based on self-attention destruction and construction learning (SADCL) for retail product recognition. Specifically, the proposed method utilizes a self-attention mechanism in the destruction and construction of image information in an end-to-end fashion so that to calculate a precise fine-grained classification prediction and large information areas in the reasoning process. We test the proposed method on the Retail Product Checkout (RPC) dataset. Experimental results demonstrate that the proposed method achieved an accuracy above 80% in retail commodity recognition reasoning, which is much higher than the results of other fine-grained classification methods.

With the emergence and development of the Internet of Vehicles (IoV), quick response time and ultralow delay are required. Cloud computing services are unfavorable for reducing delay and response time. Mobile edge computing (MEC) is a promising solution to address this problem. In this paper, we combined MEC and IoV to propose a specific vehicle edge resource management framework, which consists of fog nodes (FNs), data service agents (DSAs), and cars. A dynamic service area partitioning algorithm is designed to balance the load of DSA and improve the quality of service. A resource allocation framework based on the Stackelberg game model is proposed to analyze the pricing problem of FNs and the data resource strategy of DSA with a distributed iteration algorithm. The simulation results show that the proposed framework can ensure the allocation efficiency of FN resources among the cars. The framework achieves the optimal strategy of the participants and subgame perfect Nash equilibrium.

The latency of cloud computing is high for the reason that it is far from terminal users. Edge computing can transfer computing from the center to the network edge. However, the problem of load balancing among different edge nodes still needs to be solved. In this paper, we propose a load balancing strategy by task allocation in edge computing based on intermediary nodes. The intermediary node is used to monitor the global information to obtain the real-time attributes of the edge nodes and complete the classification evaluation. First, edge nodes can be classified to three categories (light-load, normal-load, and heavy-load), according to their inherent attributes and real-time attributes. Then, we propose a task assignment model and allocate new tasks to the relatively lightest load node. Experiments show that our method can balance load among edge nodes and reduce the completion time of tasks.

The performance of multiple input multiple output (MIMO) wireless networks is limited mainly by concurrent interference among sensor nodes. Effective link scheduling algorithms with the technology of successive interference cancellation (SIC) can maximize throughput in MIMO wireless networks. Most previous works on link scheduling in MIMO wireless networks did not consider SIC. In this paper, we propose a MIMO-SIC (MSIC) algorithm under the SINR model. First, a mathematical framework is established for the cross-layer optimization of routing and scheduling, with constraints of traffic balance and link capacity. Second, the interference regions are divided to characterize the level of interference between links. Finally, we propose a distributed link scheduling algorithm based on MSIC to eliminate the interference between competing links in the MIMO network. Experimental results show that the MSIC algorithm can increase the end-to-end throughput per unit by approximately 73% on average compared with non-SIC algorithms.

In this paper, we propose a compression sensing ghost imaging algorithm to reduce the computation time with high image quality via compression sensing based on the total variation reconstruction. A small amount of measurements can be used for shortening the sampling time. The total variation is used as criteria during the search process. It makes the ghost image achieving a high image reconstruction quality. The simulation results demonstrate that the proposed method can enhance imaging quality with the reduced computation time.

With the rapid development of the Internet of Things (IoT), the number of mobile terminal devices is increasing. Massive data are generated by mobile terminal devices, resulting in high delay and high energy consumption. In most cases, however, a low delay means high energy consumption. To balance energy consumption and delay, we adopt a tradeoff strategy that can realize optimal energy consumption with a delay threshold in this paper. First, we introduce the role of the delay threshold in reducing delay. Then, we describe the delay and energy consumption of the mobile terminal layer, fog node layer and cloud server layer with queue theory. Nonlinear programming is used to solve the energy optimization problem by calculating the optimal workload of each layer. We design a cloud-fog cooperation scheduling algorithm to reduce energy consumption. A task offloading algorithm is also designed to complete tasks when their nodes leave. The experimental results show that the energy consumption is reduced by approximately 22%, while the delay is 12.5% less than the first come first served (FCFS) approach.

Mobile edge computing is a new cloud computing paradigm that utilizes small-sized edge clouds to provide real-time services to users. These mobile edge clouds (MECs) are located near users, thereby enabling users to seamlessly access applications that are running on MECs and to easily access MECs. Terminal devices can transfer tasks to MEC servers nearby to improve the quality of computing. In this paper, we study multi-user computation offloading problem for mobile-edge computing in a multichannel wireless interference environment. Then, we analyze the overhead of each mobile devices, and we propose strategies for task scheduling and offloading in a multi-user MEC system. For reducing the energy consumption, we propose a server partitioning algorithm that is based on clustering. We formulate the task offloading decision problem as a multi-user game, which always has a Nash equilibrium. The simulation results demonstrate that our scheme outperforms the traditional offloading strategy in terms of energy consumption.

In the practical application of node positioning in the Internet of Things (IOT), the distribution of beacon nodes is generally non-uniform, so there is a certain error in positioning accuracy. In order to make the positioning more accurate, The MMSDV-Hop localization algorithm which improved DV-Hop localization algorithm is proposed in this paper. At first, this algorithm needs to determine the valid beacon nodes in a local range by selecting threshold value, and after using minimization criterion of mean-square error and correcting to obtain the final average hop distance. The dynamic weight is added with the hop number and the number of valid nodes as weights to determine the distance between the unknown nodes and the beacon nodes. A Weighted centroid localization algorithm and a weighted least square method are used to obtain an estimated position separately and the final position is determined by the arithmetic mean value of the two estimated positions. The Matlab simulation experiment shows that compared with the DV-Hop localization algorithm, the improved MMSDV-Hop localization algorithm has increased significantly in the positioning accuracy.

With the development of cloud computing in the Internet of Things and the wide application based on location services, the location trajectory information of mobile users is increasing. The risk of privacy leakage is also increasing. In order to protect the user’s trajectory privacy in the location service, we have designed a trajectory privacy protection method with several properties in the fog-based architecture. Fog computing extends the capabilities of cloud computing to the edge of the network, with local computing and storage capabilities, and a wide geographical mobility. Therefore, this paper uses the fog server instead of the traditional TTP anonymous server in the location-based privacy protection to solve the problem that performance bottleneck and concentrated attack in the TTP server anonymity process, and then completes our design with several properties through the fog server. The TRT algorithm implements k-anonymity of the trajectory. Finally, experimental analysis proves that our method can effectively enhance the user’s trajectory privacy.

Following the recent advances in the Internet of Things (IoT), it is drawing lots of attention to design distributed algorithms for various network optimization problems under the SINR (Signal-to-Interference-and-Noise-Ratio) interference model, such as spanner construction. Since a spanner can maintain a linear number of links while still preserving efficient routes for any pair of nodes in wireless networks, it is important to design distributed algorithms for spanners. Given a constant t > 1 as the required stretch factor, the problem of our concern is to design an efficient distributed algorithm to construct a t -spanner of the communication graph under SINR such that the delay for the task completion is minimized, where the delay is the time interval between the time slot that the first node commences its operation to the time slot that all the nodes finish their task of constructing the t -spanner. Our main contributions include four aspects. First, we propose a proximity range and proximity independent set (PISet) to increase the number of nodes transmitting successfully at the same time in order to reduce the delay. Second, we develop a distributed randomized algorithm SINR-Spanner to construct a required t -spanner with high probability. Third, the approximation ratio of SINR-Spanner is proven to be a constant. Finally, extensive simulations are carried out to verify the effectiveness and efficiency of our proposed algorithm.

With the booming development of big data technology and health care applications, data in the medical field is characterized by explosive growth, and medical data is valuable, which is the privacy data of patients. However, the characteristics and storage environment of medical big data have brought great challenges to the realization of privacy protection of medical data. In order to ensure the protection of data privacy when sharing medical data, we propose a medical data privacy protection framework based on blockchain (MPBC). In this framework, we protect privacy by adding differential privacy noise into federated learning. In addition, the growing volume of medical data could make blockchain storage problematic. Therefore, a storage mode is proposed to reduce the storage burden of blockchain. The raw data are stored locally and only the hash value calculated by IPFS are stored in blockchain. To enhance the performance, a mechanism is used to validate transactions and aggregate the model. Security analysis shows that our method is a safe and effective way to implement medical data.

With the rapid development of Vehicular Ad-hoc Network (VANETs), Frequently communication between vehicles and base stations has generated a large amount of trajectory information. The vehicle trajectory data can be used for real-time traffic management, intelligent driving and onboard entertainment, but it brings huge storage pressure and risk of privacy leakage. Although existing trajectory protection algorithms can generate a large number of similar trajectories, these virtual trajectories are easily identified by an attacker and cannot be virtualized according to vehicles needs. Based on the existing rotation algorithms, we proposes a virtual trajectory generation algorithm(VTG), which generates corresponding virtual points according to the user's needs at each positions and form virtual trajectories through connecting virtual position points. At the same time, the edge node are regarded as trusted third party to ensure physical control in the privacy protection model and served as a bridge between users and Location Based Services (LBS) while storing part of trajectory data. Finally, the effectiveness and security of the method are verified through a large number of simulations, our experiments indicate that the method can provide better privacy protection for users.

Edge computing, as an extension of cloud computing, subcontracts the personal private data to edge nodes on the edge network of Internet of Things (IoT) to decrease transmission delay and network congestion. So, a major security concern in edge computing is access control issues for shared data. In this paper we introduce a scheme without bilinear pairing encryption (Un-BPE) to provide access control in edge and cloud communication. To achieve confidentiality, verifiability and access control, the secret key is generated by Key Trust Authority (KTA), end users and edge node together, and saved in cloud platform; the operations of verification are performed by the adjacent edge node; and the operations of encryption and decryption are performed by the terminal device. We verify the efficiency of our scheme in terms of the security of the encryption algorithm and the performance of the system. The analysis of the proposed scheme reveals better computational efficiency.

With the emergence and development of the Internet of Vehicles (IoV), higher demands are placed on the response speed and ultra-low delay of the vehicle. Cloud computing services are not friendly to reducing latency and response time. Mobile Edge Computing (MEC) is a promising solution to this problem. In this paper, we introduce MEC into the IoV to propose a specific vehicle edge resource management framework, which consists of fog nodes (FN), data service agents (DSA), and cars. We proposed a dynamic service area partitioning algorithm that enables the DSA to adjust the service area and provide a more efficient service for the vehicle. A resource allocation framework based on Stackelberg game model is proposed to analyze the pricing problem of FN and data resource strategy of DSA. We use the distributed iterative algorithm to solve the problem of game equilibrium. Our proposed resource management framework is finally verified by numerical results, which show that the allocation efficiency of FN resources among the cars is ensured, and we also get a subgame perfect nash equilibrium.

Two-way communication is required to support control functions like packet acknowledgement and channel feedback. Most previous works on the transmission capacity of wireless ad hoc networks, however, focused on one-way communication; reverse communication from the destination to the source was ignored. In this paper, we first establish mathematical expression for two-way transmission capacity under the fixing transmission distance (i.e., the distance between the source and the destination is a constant), by introducing the concept of two-way outage and setting different rate requirements in both directions. Next, based on the concept of guard zone and cooperative communication, methods of increasing two-way transmission capacity are proposed. Simulation results show that the proposed methods can improve two-way transmission capacity significantly.

With the development of Internet of Things (IoT), the number of mobile terminal devices is increasing rapidly. Because of high transmission delay and limited bandwidth, in this paper, we propose a novel three-layer network architecture model which combines cloud computing and edge computing (abbreviated as CENAM). In edge computing layer, we propose a computational scheme of mutual cooperation between the edge devices and use the Kruskal algorithm to compute the minimum spanning tree of weighted undirected graph consisting of edge nodes, so as to reduce the communication delay between them. Then we divide and assign the tasks based on the constrained optimization problem and solve the computation delay of edge nodes by using the Lagrange multiplier method. In cloud computing layer, we focus on the balanced transmission method to solve the data transmission delay from edge devices to cloud servers and obtain an optimal allocation matrix, which reduces the data communication delay. Finally, according to the characteristics of cloud servers, we solve the computation delay of cloud computing layer. Simulation shows that the CENAM has better performance in data processing delay than traditional cloud computing.

The continuous growth of mobile devices in recent years has created a variety of opportunities for people to utilize the crowdsourcing technique to execute various intelligent computing and processing tasks, e.g., electricity load forecasting. However, there are few research in the field of real-time and accurate forecasting of electricity load in a dynamic environment, and this leads to an unsatisfactory result when applying the forecasting method to the real environment. In view of this challenge, in this paper, we propose a dynamic mobile crowdsourcing selection method for electricity load forecasting considering the dynamic arrivals of both crowdsourcing tasks and candidate workers to help the crowdsourcing platform find the ideal workers for the crowdsourcing tasks. Concretely, in our method, a system model is firstly established to quantify the ability of candidate workers in executing the crowdsourcing task when both workers and tasks arrive at or leave the platform dynamically; afterwards, a dynamic worker selection method is proposed based on the ability threshold of workers and the task priority. Finally, through a set of simulated experiments, we validate the feasibility of our proposal in terms of effectiveness and efficiency when making accurate electricity load forecasting through mobile crowdsourcing technique.

With the development of Internet of Things, the number of network devices is increasing, and the cloud data center load increases; some delay-sensitive services cannot be responded to timely, which results in a decreased quality of service (QoS). In this paper, we propose a method of resource estimation based on QoS in edge computing to solve this problem. Firstly, the resources are classified and matched according to the weighted Euclidean distance similarity. The penalty factor and Grey incidence matrix are introduced to correct the similarity matching function. Then, we use regression-Markov chain prediction method to analyze the change of the load state of the candidate resources and select the suitable resource. Finally, we analyze the precision and recall of the matching method through simulation experiment, validate the effectiveness of the matching method, and prove that regression-Markov chain prediction method can improve the prediction accuracy.

Cloud computing technology is widely used at present. However, cloud computing servers are far from terminal users, which may lead to high service request delays and low user satisfaction. As a new computing architecture, fog computing is an extension of cloud computing that can effectively solve the aforementioned problems. Resource scheduling is one of the key technologies in fog computing. We propose a resource scheduling method for fog computing in this paper. First, we standardize and normalize the resource attributes. Second, we combine the methods of fuzzy clustering with particle swarm optimization to divide the resources, and the scale of the resource search is reduced. Finally, we propose a new resource scheduling algorithm based on optimized fuzzy clustering. The experimental results show that our method can improve user satisfaction and the efficiency of resource scheduling.

The design of routing protocols for Underwater Acoustic Sensor Networks (UASNs) poses many challenges due to long propagation, high mobility, limited bandwidth, multi-path and Doppler effect. Because of the void-hole caused by the uneven distribution of nodes and sparse deployment, the selection of next hop forwarding nodes only based on the state of current node may result in the failure of forwarding in the local sparse region. In order to reduce the probability of encountering void holes in the sparse networks, in this paper we present weighting depth and forwarding area division DBR routing protocol, called WDFAD-DBR. The novelties of WDFAD-DBR lie in: firstly, next forwarding nodes are selected according to the weighting sum of depth difference of two hops, which considers not only the current depth but also the depth of expected next hop. In this way, the probability of meeting void holes is effectively reduced. Secondly, the mechanisms for forwarding area division and neighbor node prediction are designed to reduce the energy consumption caused by duplicated packets and neighbors' requests, respectively. Thirdly, we make theoretical analyses on routing performance in case of considering channel contending with respect to delivery ratio, energy consumption and average end-to-end delay. Finally we conduct extensive simulations using NS-3 simulator to verify the effectiveness and validity of WDFAD-DBR.

With the development of Internet of Things (IoT), the massive data generated by it forms big data, and the complexity of dealing with big data brings challenges to resource scheduling in edge computing. In order to solve the problem of resource scheduling and improve the satisfaction of users in edge computing environment, we propose a user-oriented improved spectral clustering scheduling algorithm (ISCM) in this paper. Based on the improved k-means algorithm, the ISCM algorithm solves the problem that the clustering result is sensitive to the initial value and realizes the reclustering, which makes the obtained clustering results more stable. Finally, the edge computing resource scheduling scheme is obtained based on the clustering results. The experimental results show that the resource scheduling scheme based on improved spectral clustering algorithm is superior to traditional spectral clustering algorithm in edge computing environment.

The leader election problem is one of the fundamental problems in distributed computing. Different from most of the existing results studying the multi-leader election in static networks or one leader election in dynamic networks, in this paper, we focus on the multi-leader election in dynamic sensor networks where nodes are deployed randomly. A centralized simple leader election algorithm (VLE), a distributed leader election algorithm (NMDLE), and a multi-leader election algorithm (PSMLE) are proposed so as to elect multi-leaders for the purpose of saving energy and prolonging the network lifetime, respectively. Specifically, the proposed algorithms aim at using less leaders to control the whole network, which is controlled by at least k opt leaders, here k opt denotes the optimal number of network partitions. Then we analyze the impacts of the sleep scheme of nodes and node moving on energy consumption and establish a theoretical model for energy cost. Finally, we provide extensive simulation results valuating the correctness of theoretical analysis.

A block compressed sensing ghost imaging reconstruction algorithm based on a block sparse Bayesian is proposed to deal with the problem that the large-size target image limited by the memory space cannot be reconstructed with the existing compressed sensing ghost imaging scheme. The large-size target image is divided into several small-sized image blocks of the same size, which is separately subjected to a compressed sensing reconstruction solution. The reconstructed solutions of each image block can be combined into one whole image, resulting in the target image. The simulation results show that the block compressed sensing ghost imaging reconstruction algorithm with a block sparse Bayesian can perform well even when storage requirements are difficult to realize via reconstructing large-scale target images.

Global broadcasting is a fundamental problem in wireless multi-hop networks. In this paper, we propose two distributed deterministic algorithms for global broadcasting based on the Signal-to-Interference-plus-Noise-Ratio (SINR) model. In both algorithms, an arbitrary node can become the source node, and the rest of the nodes are divided into different layers according to their distance to the source node. A broadcast message is propagated from the source node to all the other nodes in a layer by layer fashion. Our first proposed algorithm (named TEGB) selects a Maximal Independent Set (MIS) for each layer. Subsequently, multiple subsets of the MIS are carefully selected so as to allow the most concurrent transmissions. Our theoretical analysis shows that TEGB has the time complexity of O(D log n), where n is the total number of nodes in the network and D is the diameter of the network. Compared with the popular algorithm DetGenBroadcast proposed in [1], TEGB has a logarithmic improvement in running time. Furthermore, we develop the second algorithm (named TBGB) to reduce the number of duplicated broadcast messages at each layer. To be specific, TBGB attempts to form a unidirectional spanning tree of the network. On the spanning tree, only the non-leaf nodes transmit the broadcast message. Therefore, the redundant broadcasts in the same layer are eliminated. Our theoretical analysis shows that TBGB has the time complexity of ΟDΔ log n), where Δ is the maximum node degree.

Network on chip (NoC) architectures have been proposed to resolve complex on-chip communication problems. An NoC-based mapping algorithm is shown in this paper. It can map irregular intellectual properties (IPs) cores onto regular tile 2-D mesh NoC architectures. The basic idea is to decompose a large IP into several dummy IPs or integrate several small IPs into one dummy IP, such that each dummy IP can fit into a single tile. It can also allocate buffer space according to the input/output degree and avoid connection congestion by adapting communication density. Experimental data indicate that using the algorithm proposed in this paper, the communication energy can be reduced about 7%.

A new method that integrated high level synthesis and floorplan are proposed to reduce the total power dissipation. Function units are sorted into several clusters according to their working voltages. Floorplan are executed with the information of cluster gained from high level synthesis, and then the high level synthesis resolutions are adjusted iteratively with the interconnect information and switching activity gained from floorplan. Not only function unit power and interconnect power, but also the voltage converting power can be reduced in our method. Experimental results indicate that, under the given resource and latency constrains, the interconnect power, level convert power and total power of our method can be reduced by 30.4%, 35.1% and 22.9% respectively.

Correct verification is necessary at every design stage of a complex digital system. TED (Tayor Expansion Diagram) can be used not only to bit-level logical function but also to word-level arithmetic function. The method of equivalence checking based on TED is discussed in this paper, then a verifying algorithm for circuit including black box is proposed. Experimental results indicate that a lot of errors can be found at the early design stage using the algorithm in this paper.

Power analysis attacks have attracted significant attention within the cryptographic community. Power analysis attack methods for encryption circuits are being discussed. Unique masking method (UMM) are being discussed, point out it is vulnerable to higher-order differential power analysis. Propose a new method which uses dynamic current model logic (DCML) circuit. The circuit can defeat higher-order differential power analysis (DPA) with increased reasonable area and power consumption. Our experiments show its efficiency.