Search

D2D-assisted mobile edge computing has attracted much attention due to its great potential to reduce the pressure on edge servers and improve the utilization of mobile devices. However, users are usually reluctant to share resources with neighbor devices, considering the limitations on resources and energy, and the concerns about security and privacy. In this paper, we firstly propose a blockchain-based resource-sharing system to solve the trust issues between unfamiliar participants. Under this system, we jointly consider resource trading and computation offloading to reduce energy consumption on the premise of maximizing the utilities of both providers and requesters. Resource trading is modeled as Stackelberg Game, and computation offloading is formalized as a mixed optimization problem. Finally, we propose the corresponding algorithms to efficiently get the optimal trading and offloading strategy. The simulation results show the effectiveness of incentivizing more participants. [ABSTRACT FROM AUTHOR]

With the development of big data, analyzing the environmental benefits of transportation systems by artificial intelligence has become a hot issue in recent years. The ground traffic changes can be overlooked from a high-altitude perspective, using the technology of multi-temporal remote sensing change detection. We proposed a novel unsupervised algorithm by combining the image transformation and deep learning method. The new algorithm for remote sensing images is named multi-attention slow feature analysis (ASFA). In this model, three parts perform different functions respectively. The first part records to the K-BoVW to classify the categories of the ground objects as a channel parameter. The second part is a residual convolution with multiple attention mechanisms including temporal, spatial, and channel attention. Feature extraction and updating are completed at this link. Finally, we put the updated features in the slow feature analysis to highlight the variant components which we want and then generate the change map visually. Experiments on three very high-resolution datasets verified that the ASFA has a better performance than four basic change detection algorithms and an improved SFA algorithm. More importantly, this model works well for traffic road detection and helps us analyze the environmental benefits of traffic changes. [ABSTRACT FROM AUTHOR]

High resolution remote sensing image cloud removal can bring a lot of convenience for human activities. However, the existing cloud removal algorithms have a variety of disadvantages. First of all, they have the disadvantages of long computing time and large consumption of computing resources. Secondly, the effect of recovery needs to be improved. In order to improve the above two points, a near real‐time effective algorithm is proposed, namely MSAR‐Defognet (multiple scale attention residual network using for cloud remove), which consumes less computing power and space and has superior cloud removal effect. On the one hand, several different large‐scale filters are chosen to extract the weak information effectively, while can save the computing power and shorten the image processing time. On the other hand, the fine‐grained convolution residual block with channel attention mechanism is used to enhance the network's ability to extract cloud features. In addition, a data set which is closer to the real cloud shape and has higher richness to train the cloud removal network, so that the parameters obtained by training have stronger robustness and can adaptively remove clouds with different thickness. Experiments show that, compared with other advanced network models, the network not only has the advantage of fast processing speed, but also has better image restoration effect in high‐resolution remote sensing image restoration. It can meet the requirements of many hard real‐time tasks, so that remote sensing images can play a greater value for human activities. [ABSTRACT FROM AUTHOR]

Dynamic provisioning of computational resources in cloud computing system is a challenging problem. With many VMs being deployed in clouds, managing so much resources to stable work becomes a critical problem. Therefore, how to meet the different quality of service (QoS), we consider the service quality requirements is very important. In this paper, we address this problem. We first establish a QoS scheduling model by incorporating the cloud characteristics, and then, we develop a task scheduling objects to ensure faults can be tolerated during the task exaction. Finally, we proposed a QoS-aware scheduling algorithm, QoS-DPSO, to satisfy the QoS required in cloud computing systems. For the target requirements of QoS requirement, we take the time, reliability and cost as a single object problem. Experimental results show that QoS-DPSO can effectively improve the performance and obtain the high reliability. [ABSTRACT FROM AUTHOR]

• A remote sensing image scene classification algorithm base on neural architecture search (NAS) is proposed. • A search strategy is proposed to search for the most appropriate neural architecture in the pre-defined search space. • A performance estimation strategy to evaluate the performance of search strategy. • The proposed method saves time and manpower while achieves better accuracy compared with the manually design method. Remote sensing image scene classification (RSISC) is one of the bases of visual question answering for remote sensing data (RSVQA). In the conventional deep learning based solutions of RSISC, domain experts have to manually design the neural architecture, which is costly in both time and manpower. In this paper, AutoRSISC, a high resolution remote sensing image scene classification method based on neural architecture search (NAS) is proposed. AutoRSISC algorithm samples the neural architecture in a certain proportion to reduce the redundancy in the search space which is based on the continuous relaxation of the neural architecture representation. Edge normalization is introduced to make architecture search more efficient. The conventional deep learning approaches take days or more just to manually design the appropriate neural architecture according to the current data set. The experimental results show that our method saves time and manpower compared with the existing manually designed RSISC methods. Our AutoRSISC algorithm took 7.6 h from the automatic design of the most appropriate neural architecture to the end of all experiments according to the UCM data set, and the classification accuracy rate of the final test set reached 97.85%. And our AutoRSISC algorithm took 101.7 h from the automatic design of the most appropriate neural architecture to the end of all experiments according to the NWPU45 data set, and the classification accuracy rate of the final test set reached 94.66%. [ABSTRACT FROM AUTHOR]

Consumers are increasingly influenced by product reviews when purchasing goods or services. At the same time, deceptive reviews usually mislead users. It is inefficient and inaccurate to manually identify deceptive reviews in massive reviews. Therefore, automatically identifying deceptive reviews has become a research trend. Most of existing methods are less effective since they are lack of deeply understanding of reviews. We propose a neural network method with bidirectional long short-term memory (BiLSTM) and feature combination to learn the representation of deceptive reviews. We conduct a large amount of experiments and demonstrate the effectiveness of our proposed method. Specifically, in the mixed-domain detection experiment, the results prove that our model is effective by making comparisons with other neural network-based methods. BiLSTM gives more than 3% improvement in F1 score compared with the most advanced neural network method. Since feature selection plays an important role in this direction, we combine features to improve the performance. Then we get 87.6% F1 value which outperforms the state-of-the-art method. Moreover, in the cross-domain detection experiment, our method achieves 82.4% F1 value which is about 6% higher than the state-of-the-art method on restaurant domain, and it is also robust on doctor domain. [ABSTRACT FROM AUTHOR]

For the multi-label classification task of remote sensing images (RSIs), it is difficult to accurately extract feature information from complex land covers, and it is easy to generate redundant features by ordinary convolution extraction features. This paper proposes a multi-label classification model for multi-source RSIs that combines dense convolution and an attention mechanism. This method adds fusion channel attention and a spatial attention mechanism to each dense block module of the DenseNet, and the sigmoid activation function replaces the softmax activation function in multi-label classification. The improved model retains the main features of RSIs to the greatest extent and enhances the feature extraction of the images. The model can integrate local features, capture global dependencies, and aggregate contextual information to improve the multi-label land cover classification accuracy of RSIs. We conducted comparative experiments on the SEN12-MS and UC-Merced land cover dataset and analyzed the evaluation indicators. The experimental results show that this method effectively improves the multi-label classification accuracy of RSIs. [ABSTRACT FROM AUTHOR]

Traffic jam has grown to be a more and more difficult problem to be solved in big cities around the world, and people are getting less chance to take taxis. In order to remit this issue, we propose a recommendation strategy based on taxi traces data for passenger by the roads to make it easier. Considering the scale of taxi traces data, Hadoop is employed to handle the traces data, whose tasks include filtering and cleaning of the data, mapping taxi traces, and computing the average passage time and empty taxi arrival rate on the roads. When a user uploads his position and the time, assisted by weather condition gain from the Internet, we get the very model that corresponds to the date and the weather; the time interval is thought to be the expected waiting time between the moment when user requests the service and the moment when the cumulative number of empty taxi is greater than or equal to 1 after adding the time the taxi spends on the road, and is pushed to the user. The experiment is conducted on the base of a real-world dataset generated by over 12,000 taxis over a period of 3 months in Beijing. Experimental results demonstrate that the processing speed of Hadoop is nine times faster than serial's, which displays the feasibility of Hadoop in the application of massive traces data. In addition, the accuracy of the recommendation strategy reaches up to 88.75 %, and it meets the demand of real-time service. [ABSTRACT FROM AUTHOR]

Classification and segmentation of point clouds have attracted increasing attention in recent years. On the one hand, it is difficult to extract local features with geometric information. On the other hand, how to select more important features correctly also brings challenges to the research. Therefore, the main challenge in classifying and segmenting the point clouds is how to locate the attentional region. To tackle this challenge, we propose a graph-based neural network with an attention pooling strategy (AGNet). In particular, local feature information can be extracted by constructing a topological structure. Compared to existing methods, AGNet can better extract the spatial information with different distances, and the attentional pooling strategy is capable of selecting the most important features of the topological structure. Therefore, our model can aggregate more information to better represent different point cloud features. We conducted extensive experiments on challenging benchmark datasets including ModelNet40 for object classification, as well as ShapeNet Part and S3DIS for segmentation. Both the quantitative and qualitative experiments demonstrated a consistent advantage for the tasks of point set classification and segmentation. [ABSTRACT FROM AUTHOR]

Building extraction, which is a fundamental task in the community of remote sensing image analysis, has been extensively applied in various applications related to smart cities. Due to the complicated background information in urban areas, how to extract building footprints from high-resolution aerial images is challenging. The recent achievements of deep learning have shed light on building extraction and other remote sensing domain tasks. However, the heavy consumption of computational resources and the design of the neural architectures became the biggest bottleneck of utilizing deep learning techniques to improve the performance. In this work, we developed a Neural Architecture Search (NAS) algorithm, dubbed BuildingNAS, for building extraction from high-resolution aerial images. In particular, we built an efficient candidate operation set upon Separable Factorized Residual Blocks as our cell-level search space. Different from previous NAS in semantic segmentation tasks, we employed the hierarchical search space and proposed the Single-Path Sampling strategy to eliminate excessive GPU memory comsumption in searching process. In addition, we proposed an entropy regularized objective for the optimization of architecture parameters. As the result, the larger batch size can be adopted in the whole pipeline to accelerate the searching process, and make the resulted architecture more stable and accurate. We evaluated our proposed algorithm in WHUBuilding Dataset, the derived network achieved mIoU of 86.95% with only 2.05G FLOPs and 3.10 M parameters. The comparison results demonstrate that the network discovered by our algorithm can achieve great efficiency-accuracy trade-off. • The attempt of applying neural architecture search algorithm in segmentation of aerial images. • More lightweight hierarchical search space for neural architecture search of segmentation task. • Entropy regularized objective makes the searching process more effectively. • Better trades off the accuracy and efficiency of neural networks by using neural architecture search. • Achieved mIoU of 86.85% with only 2.05G Flops and 3.10 M parameters on WHUBuilding Dataset. [ABSTRACT FROM AUTHOR]

The segmentation of high-resolution (HR) remote sensing images is very important in modern society, especially in the fields of industry, agriculture and urban modelling. Through the neural network, the machine can effectively and accurately extract the surface feature information. However, using the traditional deep learning methods requires plentiful efforts in order to find a robust architecture. In this paper, we introduce a neural network architecture search (NAS) method, called NAS-HRIS, which can automatically search neural network architecture on the dataset. The proposed method embeds a directed acyclic graph (DAG) into the search space and designs the differentiable searching process, which enables it to learn an end-to-end searching rule by using gradient descent optimization. It uses the Gumbel-Max trick to provide an efficient way when drawing samples from a non-continuous probability distribution, and it improves the efficiency of searching and reduces the memory consumption. Compared with other NAS, NAS-HRIS consumes less GPU memory without reducing the accuracy, which corresponds to a large amount of HR remote sensing imagery data. We have carried out experiments on the WHUBuilding dataset and achieved 90.44% MIoU. In order to fully demonstrate the feasibility of the method, we made a new urban Beijing Building dataset, and conducted experiments on satellite images and non-single source images, achieving better results than SegNet, U-Net and Deeplab v3+ models, while the computational complexity of our network architecture is much smaller. [ABSTRACT FROM AUTHOR]

Deforestation in the Amazon rainforest results in reduced biodiversity, habitat loss, climate change, and other destructive impacts. Hence obtaining location information on human activities is essential for scientists and governments working to protect the Amazon rainforest. We propose a novel remote sensing image classification framework that provides us with the key data needed to more effectively manage deforestation and its consequences. We introduce the attention module to separate the features which are extracted from CNN(Convolutional Neural Network) by channel, then further send the separated features to the LSTM(Long-Short Term Memory) network to predict labels sequentially. Moreover, we propose a loss function by calculating the co-occurrence matrix of all labels in the dataset and assigning different weights to each label. Experimental results on the satellite image dataset of the Amazon rainforest show that our model obtains a better F 2 score compared to other methods, which indicates that our model is effective in utilizing label dependencies to improve the performance of multi-label image classification. [ABSTRACT FROM AUTHOR]

The efficient and accurate extraction of building feature information in remote-sensing images has become one of the most important elements of satellite remote-sensing image research. The paper proposes a convolutional neural network with a symmetric encoding-decoding structure. Alternating convolutional blocks and maximum pooled under-sampling at the encoder end are used to complete the relevant operations. The convolutional blocks are operated by linear residual blocks, and complementary zeros are added after 3 × 3 convolutional layers to ensure consistency in feature-map dimensions. A traditional ReLU activation function is replaced with a SELU activation function in order to retain more feature information during training and to solve the problem of dead neurons. A 1 × 1 convolutional layer and a Sigmoid function are finally introduced to complete the final building extraction. The experimental results show that the model is more effective in denselypopulated urban areas than in Alpine towns, but the overcrowding of buildings also causes difficulties in accurate edge segmentation. [ABSTRACT FROM AUTHOR]

The accuracy of current deep learning algorithms has certainly increased. However, deploying deep learning networks on edge devices with limited resources is challenging due to their inherent depth and high parameter count. Here, we proposed an improved YOLO model based on an attention mechanism and receptive field (RFA-YOLO) model, applying the MobileNeXt network as the backbone to reduce parameters and complexity, adopting the Receptive Field Block (RFB) and Efficient Channel Attention (ECA) modules to improve the detection accuracy of multi-scale and small objects. Meanwhile, an FPGA-based model deployment solution was proposed to implement parallel acceleration and low-power deployment of the detection algorithm model, which achieved real-time object detection for optical remote sensing images. We implement the proposed DPU and Vitis AI-based object detection algorithms with FPGA deployment to achieve low power consumption and real-time performance requirements. Experimental results on DIOR dataset demonstrate the effectiveness and superiority of our RFA-YOLO model for object detection algorithms. Moreover, to evaluate the performance of the proposed hardware implementation, it was implemented on a Xilinx ZCU104 board. Results of the experiments for hardware and software simulation show that our DPU-based hardware implementation are more power efficient than central processing units (CPUs) and graphics processing units (GPUs), and have the potential to be applied to onboard processing systems with limited resources and power consumption. [ABSTRACT FROM AUTHOR]

The semantic segmentation of high-resolution remote sensing images (HRRSIs) is a basic task for remote sensing image processing and has a wide range of applications. However, the abundant texture information and wide imaging range of HRRSIs lead to the complex distribution of ground objects and unclear boundaries, which bring huge challenges to the segmentation of HRRSIs. To solve this problem, in this paper we propose an improved squeeze and excitation residual network (SERNet), which integrates several squeeze and excitation residual modules (SERMs) and a refine attention module (RAM). The SERM can recalibrate feature responses adaptively by modeling the long-range dependencies in the channel and spatial dimensions, which enables effective information to be transmitted between the shallow and deep layers. The RAM pays attention to global features that are beneficial to segmentation results. Furthermore, the ISPRS datasets were processed to focus on the segmentation of vegetation categories and introduce Digital Surface Model (DSM) images to learn and integrate features to improve the segmentation accuracy of surface vegetation, which has certain prospects in the field of forestry applications. We conduct a set of comparative experiments on ISPRS Vaihingen and Potsdam datasets. The results verify the superior performance of the proposed SERNet. [ABSTRACT FROM AUTHOR]

Epilepsy is a common mental disorder that affects about 70 million people worldwide. Epileptic electroencephalogram (EEG) signal, an important means to judge epileptic seizure, needs neurologists' prior knowledge to mark manually. This marking method is time‐consuming and laborious. Currently, the existing automated diagnosis methods have achieved good results on one benchmark EEG dataset, most of which can achieve accuracy of more than 0.95. However, the method has limitations on the dataset, and the accuracy of the diagnosis results on another new dataset drops sharply to nearly 0.5. Aiming at the existing EEG signal diagnosis lacks stability and generalization ability, this paper proposed a multilayer‐weighted integrated self‐learning algorithm for different classifiers. For this algorithm, weighted voting was first conducted on the the diagnostic results by different classifiers to obtain a result, which was weighted again to produce the final diagnostic results. This algorithm improves the problem that the traditional self‐learning algorithm is greatly affected by data noise, which shows a strong stability in different data sets and in clinical epileptic EEG signal data detection, so as to reduce the workload of neurologists and provide support and assistance for the diagnosis and treatment of epilepsy. The experiment result shows that the algorithm can improve the stability and reliability of EEG automatic diagnosis of epilepsy. The accuracy and AUC area of its classification in two different public data sets and clinical data can reach 0.80 to 0.95. [ABSTRACT FROM AUTHOR]

This article focuses on data aggregation scheduling problem with delay constraint in wireless sensor networks. Prior works on this problem have dealt with a tree topology wireless sensor network. However, in fact it is more common that the topology of wireless sensor network is graph topology. Delay-constrained data aggregation problem is formulated. To solve this problem, we propose an algorithm based on dynamic programming in the shortest path tree of the wireless sensor network. This approach classifies conflicts into two types, tree-inside conflicts and tree-outside conflicts with the aggregating tree. First, scheduling transmission time utilizes a dynamic programming algorithm. Then, transmissions with tree-outside conflicts are removed with maximum weight independent set in tree-outside conflict graph. As the scheduling performance depends on the aggregation tree, we propose another idea, simultaneous execution of aggregation tree construction and scheduling. We propose a greedy algorithm in wireless sensor networks. This approach is to maximize the number of scheduled nodes in every time slot from deadline to time slot 1. Simulation results show that greedy algorithm in wireless sensor networks outperforms dynamic programming in the shortest path tree and naive algorithm in terms of the effectiveness and the average delay. [ABSTRACT FROM AUTHOR]