Unmanned Aerial Vehicle (UAV) can play an important role in wireless systems as it can be deployed flexibly to help improve coverage and quality of communication. In this paper, we consider a ...UAV-assisted Mobile Edge Computing (MEC) system, in which a UAV equipped with computing resources can provide offloading services to nearby user equipments (UEs). The UE offloads a portion of the computing tasks to the UAV, while the remaining tasks are locally executed at this UE. Subject to constraints on discrete variables and energy consumption, we aim to minimize the maximum processing delay by jointly optimizing user scheduling, task offloading ratio, UAV flight angle and flight speed. Considering the non-convexity of this problem, the high-dimensional state space and the continuous action space, we propose a computation offloading algorithm based on Deep Deterministic Policy Gradient (DDPG) in Reinforcement Learning (RL). With this algorithm, we can obtain the optimal computation offloading policy in an uncontrollable dynamic environment. Extensive experiments have been conducted, and the results show that the proposed DDPG-based algorithm can quickly converge to the optimum. Meanwhile, our algorithm can achieve a significant improvement in processing delay as compared with baseline algorithms, e.g., Deep Q Network (DQN).
The new development trends including Internet of Things (IoT), smart city, enterprises digital transformation and world's digital economy are at the top of the tide. The continuous growth of data ...storage pressure drives the rapid development of the entire storage market on account of massive data generated. By providing data storage and management, cloud storage system becomes an indispensable part of the new era. Currently, the governments, enterprises and individual users are actively migrating their data to the cloud. Such a huge amount of data can create magnanimous wealth. However, this increases the possible risk, for instance, unauthorized access, data leakage, sensitive information disclosure and privacy disclosure. Although there are some studies on data security and privacy protection, there is still a lack of systematic surveys on the subject in cloud storage system. In this paper, we make a comprehensive review of the literatures on data security and privacy issues, data encryption technology, and applicable countermeasures in cloud storage system. Specifically, we first make an overview of cloud storage, including definition, classification, architecture and applications. Secondly, we give a detailed analysis on challenges and requirements of data security and privacy protection in cloud storage system. Thirdly, data encryption technologies and protection methods are summarized. Finally, we discuss several open research topics of data security for cloud storage.
This paper models the messages embedded by spatial least significant bit (LSB) matching as independent noises to the cover image, and reveals that the histogram of the differences between pixel gray ...values is smoothed by the stego bits despite a large distance between the pixels. Using the characteristic function of difference histogram (
DHCF
), we prove that the center of mass of
DHCF
(
DHCF COM
) decreases after messages are embedded. Accordingly, the
DHCF COMs
are calculated as distinguishing features from the pixel pairs with different distances. The features are calibrated with an image generated by average operation, and then used to train a support vector machine (SVM) classifier. The experimental results prove that the features extracted from the differences between nonadjacent pixels can help to tackle LSB matching as well.
Compared to traditional distributed computing environments such as grids, cloud computing provides a more cost-effective way to deploy scientific workflows. Each task of a scientific workflow ...requires several large datasets that are located in different datacenters, resulting in serious data transmission delays. Edge computing reduces the data transmission delays and supports the fixed storing manner for scientific workflow private datasets, but there is a bottleneck in its storage capacity. It is a challenge to combine the advantages of both edge computing and cloud computing to rationalize the data placement of scientific workflow, and optimize the data transmission time across different datacenters. In this study, a self-adaptive discrete particle swarm optimization algorithm with genetic algorithm operators (GA-DPSO) was proposed to optimize the data transmission time when placing data for a scientific workflow. This approach considered the characteristics of data placement combining edge computing and cloud computing. In addition, it considered the factors impacting transmission delay, such as the bandwidth between datacenters, the number of edge datacenters, and the storage capacity of edge datacenters. The crossover and mutation operators of the genetic algorithm were adopted to avoid the premature convergence of traditional particle swarm optimization algorithm, which enhanced the diversity of population evolution and effectively reduced the data transmission time. The experimental results show that the data placement strategy based on GA-DPSO can effectively reduce the data transmission time during workflow execution combining edge computing and cloud computing.
With the development of intelligent transportation system (ITS) and vehicle to X (V2X), the connected vehicle is capable of sensing a great deal of useful traffic information, such as queue length at ...intersections. Aiming to solve the problem of existing models' complexity and information redundancy, this paper proposes a queue length sensing model based on V2X technology, which consists of two sub-models based on shockwave sensing and back propagation (BP) neural network sensing. First, the model obtains state information of the connected vehicles and analyzes the formation process of the queue, and then it calculates the velocity of the shockwave to predict the queue length of the subsequent unconnected vehicles. Then, the neural network is trained with historical connected vehicle data, and a sub-model based on the BP neural network is established to predict the real-time queue length. Finally, the final queue length at the intersection is determined by combining the sub-models by variable weight. Simulation results show that the sensing accuracy of the combined model is proportional to the penetration rate of connected vehicles, and sensing of queue length can be achieved even in low penetration rate environments. In mixed traffic environments of connected vehicles and unconnected vehicles, the queuing length sensing model proposed in this paper has higher performance than the probability distribution (PD) model when the penetration rate is low, and it has an almost equivalent performance with higher penetration rate while the penetration rate is not needed. The proposed sensing model is more applicable for mixed traffic scenarios with much looser conditions.
In this paper, we present a machine learning classifier which is used for pedestrian detection based on XGBoost. Our approach, the Genetic Algorithm is introduced to optimize the parameter tuning ...process during training an XGBoost model. In order to improve the classification accuracy, HOG and LBP features are used to describe pedestrians in a way of tandem fusion, then input into GA-XGBoost classifier proposed in this paper to form a new static image pedestrian detection algorithm. The pedestrian feature extraction and machine learning are decoupled by storing the extracted pedestrian feature as feature files in the experiment, so that training can be exacuted many times and algorithms can be camparied conveniently. Experimental show that our pedestrian detection algorithm has improved the accuracy of pedestrian detection in the static image. The Area Under the ROC Curve (AUC) value reaches 0.9913.
•Fusing spatial and temporal features is effective in fMRI classification.•Models considering sequence achieve better results than timing invariant models.•fMRI scans longer than one minute contain ...enough information for ADHD diagnosis.•deep-learned features outperform hand-crafted features in fMRI analysis.
Attention Deficit/Hyperactivity Disorder (ADHD) is one kind of neurodevelopmental disorders common in children. Due to the complexity of the pathological mechanism, there is a lack of objective diagnostic methods up to now. This paper aimed to propose automatic ADHD diagnostic method using resting state functional magnetic resonance imaging (rs-fMRI) data with the spatio-temporal deep learning models. Unlike traditional methods, this paper constructed a deep learning method called 4-D CNN based on granular computing which were trained based on derivative changes in entropy, and can calculate granularity at a coarse level by stacking layers. Considering the structure of rs-fMRI as time-series 3-D frames, several models of spatial and temporal granular computing and fusion were proposed, including feature pooling, long short-term memory (LSTM) and spatio-temporal convolution. This paper introduced an approach to augment dataset which can sample one subject's rs-fMRI frames into several relatively short term pieces with a fixed stride. The public dataset of ADHD-200 Consortium was used to train and validate our method. And the results of evaluations showed that our method outperformed traditional methods on the dataset (accuracy: 71.3%, AUC: 0.80). Therefore, our 4-D CNN method can be used to build more accurate automatic assistant diagnosis tool of ADHD.
Anomaly detection has a wide range of applications in security area such as network monitoring and smart city/campus construction. It has become an active research issue of great concern in recent ...years. However, most algorithms of the existing studies are powerless for large-scale and high-dimensional data, and the intermediate data extracted by some methods that can handle high-dimensional data will consume lots of storage space. In this paper, we propose a novel sparse representation framework that learns dictionaries based on the latent space of variational auto-encoder. For large-scale data sets, it can play the role of dimensionality reduction to obtain hidden information, and extract more high-level features than hand-crafted features. At the same time, for the storage of normal information, the space cost can be greatly reduced. To verify the versatility and performance of the proposed learning algorithm, we have experimented on different types of anomaly detection tasks, including KDD-CUP data set for network intrusion detection, Mnist data set for image anomaly detection, and UCSD pedestrian's data set for abnormal event detection in surveillance videos. The experimental results demonstrate that the proposed algorithm outperforms competing algorithms in all kinds of anomaly detection tasks.
In recent years, the power costs of cloud data centers have become a practical concern and have attracted significant attention from both industry and academia. Most of the early works on data center ...energy efficiency have focused on the biggest power consumers (i.e., computer servers and cooling systems), yet without taking the networking part into consideration. However, recent studies have revealed that the network elements consume 10–20% of the total power in the data center, which poses a great challenge to effectively reducing network power cost without adversely affecting overall network performance. Based on the analysis on topology characteristics and traffic patterns of data centers, this paper presents a novel approach, called VMPlanner, for network power reduction in the virtualization-based data centers. The basic idea of VMPlanner is to optimize both virtual machine placement and traffic flow routing so as to turn off as many unneeded network elements as possible for power saving. We formulate the optimization problem, analyze its hardness, and solve it by designing VMPlanner as a stepwise optimization approach with three approximation algorithms. VMPlanner is implemented and evaluated in a simulated environment with traffic traces collected from a data center test-bed, and the experiment results illustrate the efficacy and efficiency of this approach.
The increase of network size and sensory data leads to many serious problems to the wireless sensor networks due to the limited energy. Data prediction method is helpful to reduce network traffic and ...increase the network lifetime accordingly, especially by exploring data correlation among the sensory data. Data prediction can also be used to recover abnormal/lost data in case these sensor nodes fail to work. The current prediction methods in wireless sensor networks do not make full usage of the spatial-temporal correlation between wireless sensor nodes, and thus leads to higher prediction error relatively. This paper proposes a novel model for multi-step sensory data prediction in wireless sensor network. Firstly, we introduce the artificial neural networks based on 1-D CNN (One-Dimensional Convolutional Neural Network) and Bi-LSTM (Bidirectional Long and Short-Term Memory) to get the abstract features of different attributes via the pre-processed sensory data. Then, these abstract features are used to obtain one-step prediction. Finally, the multi-step prediction is introduced by using historical data and the prediction results of the previous step iteratively. Experiment results show that after selecting suitable node combinations in which the spatial-temporal correlation is highlighted, the proposed multi-step predictive model can predict multi-step (short and medium term) sensory data, and its performance is better compared with other related methods.