Search

Tensor-ring (TR) decomposition was recently studied and applied for low-rank tensor completion due to its powerful representation ability of high-order tensors. However, most of the existing TR-based methods tend to suffer from deterioration when the selected rank is larger than the true one. To address this issue, this article proposes a new low-rank sparse TR completion method by imposing the Frobenius norm regularization on its latent space. Specifically, we theoretically establish that the proposed method is capable of exploiting the low rankness and Kronecker-basis-representation (KBR)-based sparsity of the target tensor using the Frobenius norm of latent TR-cores. We optimize the proposed TR completion by block coordinate descent (BCD) algorithm and design a modified TR decomposition for the initialization of this algorithm. Extensive experimental results on synthetic data and visual data have demonstrated that the proposed method is able to achieve better results compared to the conventional TR-based completion methods and other state-of-the-art methods and, meanwhile, is quite robust even if the selected TR-rank increases.

Time series anomaly detection (TSAD) is an essential problem faced in several fields, e.g. fault detection, fraud detection, and intrusion detection, etc. Although TSAD is a crucial problem in anomaly detection, few solutions in anomaly detection are suitable for it at present. Recently, some researchers use GAN-based methods such as TAnoGAN and TadGAN to solve TSAD problem. However, problems such as model collapse, low generalization capability and poor accuracy still exist. In this paper, we proposed a Dilated Convolutional Transformer-based GAN (DCT-GAN) to enhance accuracy and improve generalization capability of the model. Specifically, DCT-GAN utilize several generators and a single discriminator to alleviate the mode collapse problem. Each generator consists of a dilated convolutional neural network and a Transformer block to obtain fine-grained and coarse-grained information of the time series, which is a useful component to improve generalization capability. We also use weight-based mechanism to balance these generators. Experiments verify the effectiveness of our method and each part of DCT-GAN.

In the recent past, the cloud materials computing plays a vital role for keeping higher range of information in state of art of cloud environment. The information has to be kept in cloud may have large size that occupies more memory space in the cloud environment. The service provider have limitations in getting cloud space and providing space to the users to store more data limited and available space of cloud. We have proposed in this paper, an accurate and efficient video/image materials compression algorithm to minimize the data size to store in the cloud with less memory space. The novel algorithm for compression of image materials using block compressive sensing double density wavelet transform (BCS-DDWT) algorithm is proposed to compress materials. Compression of the image materials could be prepared based on various wavelets at variouspositions of decomposition. The concert investigation of BCS-DDWT with wavelets at 4 various positions of decomposition using BCS-DDWTcould be shown in the results. The performance of BCS-DDWTcompression is balanced by calculating parameters such as peak signal to noise ratio, mean square error, and bits per pixeland compression ratio.

Despite that convolutional neural networks (CNNs) have shown high-quality reconstruction for single image dehazing, recovering natural and realistic dehazed results remains a challenging problem due to semantic confusion in the hazy scene. In this article, we show that it is possible to recover textures faithfully by incorporating semantic prior into dehazing network since objects in haze-free images tend to show certain shapes, textures, and colors. We propose a semantic-aware dehazing network (SDNet) in which the semantic prior is taken as a color constraint for dehazing, benefiting the acquisition of a reasonable scene configuration. In addition, we design a densely connected block to capture global and local information for dehazing and semantic prior estimation. To eliminate the unnatural appearance of some objects, we propose to fuse the features from shallow and deep layers adaptively. Experimental results demonstrate that our proposed model performs favorably against the state-of-the-art single image dehazing approaches.

Light field (LF) cameras, which can record real-word scenes from multiple viewpoints in a single shot, are widely used in 3D reconstruction, re-focusing, and virtual reality etc. However, the inherent trade-off between spatial resolution and angular resolution of LF images hinders their applications for scenarios requiring high resolutions. In this paper, we propose a novel intra-inter view interaction network for LF image super-resolution, termed as LF-IINet, to exploit the correlations among all views and simultaneously preserve the parallax structure of LF views. The proposed LF-IINet consists of two parallel branches. Specifically, the top branch extracts global inter-view information, and the bottom branch first independently maps each view to deep representations and then models the correlations among all intra-view features via proposed multi-view context block (MCB). The two branches interact with each other by proposed inter-assist-intra feature updating module (IntraFUM, where the intra feature are updated with the assistance of the inter feature) and intra-assist-inter feature updating module (InterFUM, where the inter feature are updated with the assistance of the intra feature). In this way, our LF-IINet incorporates rich angular and spatial information for LF image super-resolution. Extensive comparison with state-of-the-art methods demonstrates that our method achieves superior performance visually and quantitatively with reasonable parameters and FLOPs. Furthermore, quantitative results also show that our method is effective for LF images with both small and large disparities.

In this research paper, CBIR algorithm development using RGB histogram-based block contour method to improve the retrieval performance is presented along with the simulation results. CBIR to extract the visual content of an image automatically like color, texture, size, direction, distance, nearness or its shape using HSV colour RGB histogram & block contour methods is proposed here in this paper. The work presented in this paper is a new methodology of the picture retrievals by the combination of different parameters of the query image with the help of RGB histograms & the block contours. Simulations are carried out in the Matlab environment and the simulation results are observed. The CBIR based system is going to be tested using different types of test images for varieties & finally the nearest test outcomes will be got & be tabulated neatly. Here, in this proposed work using different sizes of the blocks & the no. of characteristics & the time obtained for extracting those realistic parameters could be found out & also other parameters such as the recalling, precision, characteristics were calculated and compared with existing systems. The precision and recall are used to calculate the performance of the designed system. The results presented gives precision values & the values of the recall parameter of the developed & existing CBIR systems, which shows the efficacy of the proposed methodology that is superior. Here, the observation is – the developed methodology will be highly unique, its performance will be more superior to the existing systems. Finally, to conclude, it could be iterated that this contributory work was developed to show about the RGB histogram & block contour concept involvement to extract the different features of the images and carry out the performance of system (retrieval). Finally, the results of the simulation gives the improved performance of the system (retrieval) over the others, thus showing the profoundness or the effectiveness of the research work done.

Image fusion synthesizes a new image from multiple images of the same scene. The synthesized image should be suitable for human visual perception and follow-up high-level image-processing tasks. However, existing methods focus on fusing low-level features, ignoring high-level semantic perception information. We propose a new end-to-end model to obtain a more semantically consistent image in infrared and visible image fusion, termed semantic-supervised dual-discriminator generative adversarial network (SDDGAN). In particular, we design an information quantity discrimination (IQD) block to guide fusion progress. For each source image, the block determines the weight for preserving each semantic object's feature. By this way, the generator learns to fuse various semantic objects via different weights to preserve their characteristics. Moreover, the dual discriminator is employed to identify the distribution of infrared and visible information in the fused image. Each discriminator acts on a certain modality (infrared/visible) of different semantic objects in the fused image to preserve and enhance their modality features. Thus, our fused image is more informative. Both the thermal radiation in the infrared image and the visible image texture details can be well preserved. Qualitative and quantitative experiments demonstrate the superiority of our SDDGAN over state-of-the-art methods in terms of visual effects, efficiency, and quantitative metrics.

In the process of digital image acquisition, color inconsistency is a common issue due to the influence of photographic conditions. The inconsistency of color affects the quality of digital orthophoto products and subsequent applications significantly, and this issue remains challenging both in the academia and industry. This paper proposes a color equalization method for aerial image based on block adjustment and an improved color balance model based on the analysis of causes for color deviation. Two nonlinear functions are used to simulate the process of color deviation and correct the color of images. Due to the existence of error, the color corrected images still have minor deviations in the color of the overlapped regions. Therefore, this research introduces an error equation to address this issue and uses the least square principle to calculate the adjustment. The simulation experiments and real experiments are carried out on several groups of aerial image data respectively. The results show that the method not only achieves better visual effect but also has a higher adjustment precision. Finally, the rationality and parameters of the model proposed in this paper are discussed.

The satellite-terrestrial networks (STN) utilize the spacious coverage and low transmission latency of Low Earth Orbit (LEO) constellation to distribute requested content for ground subscribers. With the development of storage and computing capacity of satellite onboard equipment, it is considered promising to leverage in-network caching technology on STN to improve content distribution efficiency. However, traditional ground network caching schemes are not suitable in STN, considering dynamic satellite propagation and time-varying topology. More specifically, the unevenness of user distribution results in difficulties for assurance of quality of experience. To address these problems, we firstly propose a density-based block division algorithm to divide the content subscribers into a series of blocks with different sizes according to user density. The LEO satellite orbit and time-varying network model is established to describe STN topology. Next, we propose an approximate minimum coverage vertex set algorithm and a novel cache node selection algorithm for optimal user blocks matching. The simulation results prove that the proposed density-based content distribution method can obviously reduce the average transmission delay of content distribution under different network conditions and has better stability and self-adaptability under continuous time variation.

The growth of transferring data via networks and the internet yield to safe them through communication. The image encryption process is a valuable strategy for protecting image information and it is used as an effective way of communicating several sensitive data with continuous use of images in all forms of visual media. In this paper, an efficient method of image encryption is proposed based on PRESENT-SPECK algorithms with a hybrid method for key generation called Henon and Arnold-cat map that is suggested for sequences. The proposed method petitioned the image data into the block for encryption. The total blocks joined and produced an encrypted image. The proposed method tested with various types, and the generated key also have passed various tests.

We consider a hierarchical structure of a permissioned blockchain with three types of participant: providers, collectors, and governors. Providers forward transactions to collectors; collectors upload received transactions to governors after verifying and labeling them; and governors validate a portion of the labeled transactions they receive, pack valid transactions into a block, and append the block to the ledger. This model has various fields of application including data collection from the Internet-of-Things and second-hand markets. Our main contribution is to propose a reputation-based protocol to help governors evaluate the reliability of collectors. Specifically, given a transaction, each governor runs a softmax-based function to calculate a probability for each collector that sent and labeled this transaction. The probabilities, calculated using collectors' reputations as inputs, represent the likelihood of the lead governor selecting the labeled transaction from collectors to consider for further validation. After the lead governor verifies a transaction, all collectors' reputations are updated in line with the agreement of their labeling and the validity of the transaction as found by the lead governor. We show, both theoretically and empirically, that our protocol can significantly reduce governors' verification workloads while maintaining firm liveness and high incentives.

The past few years have witnessed an exponential growth of diverse Internet of Things (IoT) devices as well as compelling applications ranging from industrial production, intelligent transport, warehouse logistics to medical care. Dramatic advances in IoT technology not only bring enormous economic opportunities but also challenges. Recently, the integration of IoT and blockchain (BCoT) is considered a promising solution . Blockchain technology provides a secure and scalable framework to improve the data management of IoT devices. However, the huge computation and energy consumption in the blockchain consensus process prevents it from being directly applied as a generic platform for IoT. In this paper, we propose a cloud mining pool-aided BCoT architecture. The IoT devices can rent the computation resource from the cloud services dynamically. Then, the individual cloud miners are grouped into several mining pools to share block rewards to earn a steady profit and reduce the income variance. Based on this architecture, we study the mining pool selection problem and analyze the colony behaviors of IoT devices. We propose a centralized evolutionary game-based pool selection algorithm. In addition, considering the non-cooperative relationship among multiple miners, we also propose a lightweight distributed reinforcement learning algorithm, named the WoLF-PHC algorithm.

Dimensionality reduction is commonly used for identifying and analyzing patterns in the visual analysis of multi-dimensional datasets. The selection of subspaces is a core building block in projecting high-dimensional data to low-dimensional space, which is usually illustrated as a scatterplot for analysts to easily understand and explore. This process involves human prior knowledge and domain-specific requirements. Thus, quantifying and tracking the changes of projections across subspaces remain challenging. Existing methods can neither quantify the subsets-based changes of dimensionality reduction results when switching subspaces nor automatically and comprehensively display overall and subtle differences among dimensionality reduction results.To address this, we developed EvoSets, a novel visual analytics system designed to help users understand how subspaces affect dimensionality reduction results. The effects are quantified based on subsets' distribution to tracking the sensitivity of dimensionality reduction results across subspaces. System supports the exploration of the overall evolution of the dimensionality reduction results for helping users track the convergence and divergence behavior changes of subsets based on an extended Bubble Sets visualization. Similarities are intuitively illustrated, and dissimilarities are highlighted among projections based on layout constraints. The usefulness and effectiveness are evaluated with a user study and two case studies on multi-dimensional datasets.

It is a typical problem in the field of object detection to simultaneously detect objects with large scale variation in one image. Recently proposed state-of-the-art object detectors generally learn pyramidal feature representation to deal with the scale variation, which has been proved effective via various feature pyramid networks. However, the majority of the feature pyramid networks based on heuristic feature fusion strategies may be suboptimal, as excess human guidance will restrict the self-learning of deep neural networks. An adaptive feature pyramid is bound to provide a significant performance boost. In this paper, we propose a novel feature pyramid network named CATFPN that consists of Scale-Wise Feature Concatenation (SWFC) module and Global Context (GC) block. The SWFC module evenly distributes semantic features for each feature layer and the GC block introduces a self-attention mechanism. As a feature pyramid network, the CATFPN can be applied to any detector based on multi-scale features. We adopt the CATFPN in typical RetinaNet and Faster R-CNN detector models, without bells and whistles, achieving 1.1% AP and 0.7% AP improvements over FPN on the MS COCO benchmark, respectively. Our competitive performance reported on the test-dev subset of COCO achieves 42.3% AP.

Pixel value differencing steganography (PVDS) technique efficiently identifies the edge and smooth regions from an image, therefore, the PVDS technique is more suitable for concealing the secret information in an image. Notwithstanding the advantages, the PVDS techniques give rise to some major issues. Most of the PVDS techniques suffer from boundary issue (BI). Further, the majority of the PVDS techniques are exposed to pixel difference histogram (PDH) analysis. In this paper, two improved PVDS based techniques, such as (1) indicator-based PVDS (IPVDS) and (2) multi-directional overlapped PVDS (MDOPVDS) has been proposed to address the BI as well as PDH issue. The IPVDS technique utilizes the concept of indicator pixel in a 2×3 pixel block. On the other hand, the MDOPVDS technique utilizes the pixel overlap strategy in a 3×3 pixel block using all three directions, such as (1) horizontal, (2) vertical, and (3) diagonal. Results of the proposed technique are evaluated in terms of the conflicting metrics like peak signal-to-noise ratio (PSNR), capacity, and security. Further, it is observed that the proposed technique maintains a good symmetry between the aforementioned conflicting metrics. Additionally, both the proposed technique successfully avoids the BI.

The development of an efficient and fast cryptosystem has become significant with the widespread use of internet and advancements in networking technology. A colour image encryption/decryption technique using image block generation from block-based Sequency-based Mapped Real Transform (SMRT) is introduced in this paper to achieve this goal. The encryption architecture uses a confusion-diffusion approach and begins by partitioning individual colour components of plain image into fixed-size blocks. This is followed by XOR operation between generated diffusion keys and the image blocks to achieve diffusion. SMRT of the diffused image block is found and confusion induced by image block operations. Encrypted image is obtained through inverse SMRT and compilation of encrypted colour components. The proposed cryptosystem demonstrates excellent features including high sensitivity, complex keystream, strong security, high encryption and decryption efficiency and simple structure.

Given the considerable complexity of process plants, there has been a great deal of research focused on aiding the design of plant layout through mathematical optimisation, i.e. optimising the positioning of the equipment in the plant for space and cost efficiency. Recently, the use of modular approaches within the construction industry, whereby work is performed off-site before being assembled on-site, has become a popular and powerful way of reducing build schedules and costs. Modular approaches have many other real applications where items must be packed to minimise the connections between them (e.g. piping, wiring, modular office and factory layouts) and consider the modular layout of the system. In this paper, we provide a formulation of the problem that, in addition to the standard layout problem, considers a modular block layout to allow modular construction and transportation of the plant. The problem is represented as a directed network, with the aim to pack the items into predefined containers and minimise the rectilinear distance between the connected items. We propose mixed-integer linear programming (MILP) models for the 2-dimensional and 3-dimensional problems and solve them using the state-of-the-art mathematical programming solver, Gurobi. Because of the combinatorial nature of the problem, solutions involving a large number of items may not converge and a suboptimal solution must be considered. However, our results suggest that even in the case of optimising a large number of items, the suboptimal solutions found after a reasonable number of iterations where deemed, by a domain expert, to be a good enough starting point to continue the design process, especially in the early concept phase.

Blockchain allows for secure management of a shared ledger by agreement protocols, where transactions are validated over network without central authorities. Although the agreement protocol has been thoroughly conducted of propagation and consensus researches, mobility of nodes in unstructured overlay networks has not received much attention. Besides, current dynamic propagation schemes waste travel hops and are low of delivery ratio. In this paper, we propose a social characteristic-based propagation-efficient protocol NefSBFT to agree on system state plus consensus mechanisms in public blockchains. We devise a propagation technique (travel hops of at least $\frac{1}{3}$ savings, delivery ratio above $0.93$ , etc.) for message multicasting when exploiting real nodes' social characteristics of intermittent connectivity and frequent partitions. This propagation technique is executed in the improved FastBFT to achieve transaction ordering and block verification, thus, no controllable mobility is required during the whole system's execution. NefSBFT achieves fast propagation, small message complexity and few resource consumption of travel hops and running nodes for complete protocol execution. We analyze NefSBFT's security against DDOS attack of non-primary failure. The experiments show the performance tradeoff under different parameters, compare the propagation efficiency with Erlay and Flooding, and clarify NefSBFT's impact on the whole system performance through comparison.

Apache Hadoop is an open-source software library which integrates a wide variety of software tools and utilities to facilitate the distributed batch processing of big data sets. Hadoop ecosystem comprises two major components - Hadoop Distributed File System (HDFS), which is primarily used for storage and MapReduce, which is primarily used for processing of the files. The performance of Hadoop holds back when it comes to storage and processing of small files. Small files are essentially the files that are significantly smaller in size when compared to the default block size of HDFS. This is because each small file consumes a block individually leading to excessive memory requirement, access time and processing time. Scaling the memory, allowing access latencies and processing delays beyond a limit is not an option. Henceforth, in this paper, a Systematic Literature Review has been performed to provide a comprehensive and exhaustive gestalt of the small files' problem in Hadoop. The paper defines a comprehensive taxonomy of Hadoop ecosystem and its’ existent small files problem. Further, the study also attempts to critically analyze the solutions that have been proposed to overcome this problem. These solutions have been analytically studied to identify the set of parameters that should be considered in impending while proposing solutions pertaining to this problem.

Image-based intelligent detection of road cracks with high accuracy and efficiency is vital to the overall condition assessment of the pavement. However, significant problems of continuous cracks interruption and background discrete noise misidentification are frequently observed in current semantic segmentation of pavement cracks, which mainly caused by traditional segmentation convolutional neural networks. This paper proposes a skip-level round-trip sampling block structure with the implementation of convolutional neural networks, thereby constructed a novel pixel level semantic segmentation network called CrackW-Net. After that, two datasets, including the widely recognized Crack500 dataset and a self-built dataset, were used to train two versions CrackW-Net, FCN, U-Net and ResU-Net. Meanwhile, comparative experiments are conducted among all these network models for crack detection. Results show that CrackW-Net without residual block performs the best in the task of pavement crack segmentation.

Recent progress on intelligent fault diagnosis is mainly attributed to the explosive development of convolutional neural networks (CNN). Many existing CNN-based fault diagnosis models can extract abundant features from the measured vibration signals but cannot explore enough discriminative features under strong noise conditions. This poses a challenge for industrial applications. To address this problem, we develop a new deep CNN model, called a multireceptive field denoising residual convolutional network (MF-DRCN). The major contributions are: 1) a multireceptive field denoising (MFD) block is designed to enhance the deep features extracted by the CNN model and filter out the interference feature information; 2) an adaptive feature integration (AFI) module is embedded in the CNN model to adaptively integrate features, so as to make better use of the extracted information; and 3) an end-to-end CNN model called MF-DRCN is developed based on MFD and AFI. The experimental results demonstrate that MF-DRCN has better feature extraction and anti-interference capabilities than the other seven competitive methods. Specifically, under strong noise conditions with SNR = -6 dB, MF-DRCN achieves 84.51% and 86.45% diagnostic accuracy respectively on the planetary gearbox data set and the industrial pump data set, which suggests MF-DRCN is a promising intelligent fault diagnosis approach.

This paper presents the concept of Boundary-Based Predictive Controller (BBPC) as an effective tool to control industrial processes with on-off actuator, for which the control goal is defined to keep the process output within the desired range. An example use of BBPC is shown in application to control of dissolved oxygen (DO) concentration in the laboratory activated sludge setup with biological reactor. It is suggested how to identify dynamical parameters of the proposed DO concentration model and how to provide adaptability required to ensure desired control performance in the presence of significant changes of process load disturbance. Practical implementation in Programmable Logic Controller (PLC) in the form of a general purpose library function block is also presented. Experimental comparison with conventional on-off controller shows robustness and superiority of the proposed BBPC.

DNN (Deep Neural Network) processing units, or DPUs, are one of the most energy-efficient platforms for DNN applications. However, designing new DPUs for every DNN model is very costly and time-consuming. In this paper we propose an alternative approach: to specialize coarse-grained reconfigurable architectures (CGRAs), which are already quite capable of delivering high performance and high energy efficiency for compute-intensive kernels. We identify a small set of architectural features on a baseline CGRA to enable high performance mapping of depthwise convolution (DWC) and pointwise convolution (PWC) kernels, which are the most important building block in recent light-weight DNN models. Our experimental results using MobileNets demonstrate that our proposed CGRA enhancement can deliver 8 18× improvement in area-delay product depending on layer type, over a baseline CGRA with a state-of-the-art CGRA compiler. Moreover, our proposed CGRA architecture can also speed up 3D convolution with similar efficiency as previous work, demonstrating the effectiveness of our architectural features beyond depthwise separable convolution layers.

Erasure coding is widely used in distributed storage systems (DSSs) to efficiently achieve fault tolerance. However, when the original data need to be updated, erasure coding must update every encoded block, resulting in long update time and high bandwidth consumption. Exiting solutions are mainly focused on coding schemes to minimize the size of transmitted update information, while ignoring more efficient utilization of bandwidth among update racks. In this paper, we propose a parallel Cross-rack Pipelining Update scheme (CPU), which divides the update information into small-size units and transmits these units in parallel along with an update pipeline path among multiple racks. The performance of CPU is mainly determined by slice size and update path. We formulate the proposed pipelining update scheme as an optimization problem, based on a new theoretical pipelining update model. We prove the optimization problem is NP-hard and develop a heuristic algorithm to solve it based on the features of practical DSSs and our implementations, including Big chunk and Small overhead. We implement CPU and conduct experiments on Amazon EC2 under a variety of scenarios. The results show that CPU can reduce the average update time by 48.2%, compared with the state-of-the-art update schemes.

Accurate breast lesion segmentation is a great help in the initial stage of breast cancer treatment planning. Ultrasound is considered the safe and cheapest method for the breast screening process. However, ultrasound images inherently contain speckle noise, unclear boundaries, and complex shapes, making it more challenging for automatic segmentation methods. This work proposes a multiscale dual attention-based network (MDA-Net) for concurrent segmentation of breast lesions images. The multiscale fusion (MF) block is introduced that addresses the classical fixed receptive field issues, and helps to extract more semantic features and aims to achieve more features diversity. A dual-attention (dA) is also proposed, which is a hybrid of channel-based attention (cA) and lesion attention (lA) blocks that improves the feature representation capability and adaptatively learns a discriminative representation of high-level features. As a result, a combination of two attention blocks helped the proposed network to concentrate on a more relevant field of view of targets. The MDA-Net is extensively tested on both self-collected private datasets and two public UDIAT, BUSIS datasets. Furthermore, our method is also evaluated on MRI datasets to observe the broad applicability of our method in a different imaging modality. The MDA-Net has achieved the DSC of 87.68%, 91.85%, 90.41%, 83.47% on UDIAT, BUSIS, Private, and RIDER breast MRI datasets (p-value https://github.com/ahmedeqbal/MDA-Net .

In this paper, an array thermal camera equipment is developed to capture multiple infrared images with spatial and parallax information. Based on the captured images, an end-to-end method called spatial-parallax prior network (SPPN) is proposed. Specifically, we design a spatial parallax prior block with two symmetric branches to extract spatial and parallax features in an interactive guidance manner. Then, to effectively integrate spatial and parallax features, we introduce a channel attention mechanism to enable the network to focus on and fuse the most useful information adaptively. In this way, spatial and parallax information can be fully utilized without any explicit alignment operation. Finally, considering the scarcity and poor quality of infrared training data, we leverage transfer learning to better train the network. Extensive experimental results demonstrate that the proposed SPPN consistently outperforms the current state-of-the-art methods, providing a highly effective and scalable solution for the improvement of infrared image quality.

In recent years, edge computing has attracted significant attention because it can effectively support many delay-sensitive applications. Despite such a salient feature, edge computing also faces many challenges, especially for efficiency and security, because edge devices are usually heterogeneous and may be untrustworthy. To address these challenges, we propose a unified framework to provide efficiency and confidentiality by coded distributed computing. Within the proposed framework, we use matrix multiplication, a fundamental building block of many distributed machine learning algorithms, as the representative computation task. To minimize resource consumption while achieving information-theoretic security, we investigate two highly-coupled problems, (1) task allocation that assigns data blocks in a computing task to edge devices, and (2) linear code design that generates data blocks by encoding the original data with random information. Specifically, we first theoretically analyze the necessary conditions for the optimal solution. Based on the theoretical analysis, we develop an efficient task allocation algorithm. Using the task allocation, we then design secure coded computing schemes, for two cases, (1) with redundant computation and (2) without redundant computation. Moreover, we also theoretically analyze the optimization of the proposed scheme. Finally, we conduct extensive simulation experiments to demonstrate the effectiveness of the proposed schemes.

(Aim) To detect COVID-19 patients more accurately and more precisely, we proposed a novel artificial intelligence model. (Methods) We used previously proposed chest CT dataset containing four categories: COVID-19, community-acquired pneumonia, secondary pulmonary tuberculosis, and healthy subjects. First, we proposed a novel VGG-style base network (VSBN) as backbone network. Second, convolutional block attention module (CBAM) was introduced as attention module into our VSBN. Third, an improved multiple-way data augmentation method was used to resist overfitting of our AI model. In all, our model was dubbed as a 12-layer attention-based VGG-style network for COVID-19 (AVNC) (Results) This proposed AVNC achieved the sensitivity/precision/F1 per class all above 95%. Particularly, AVNC yielded a micro-averaged F1 score of 96.87%, which is higher than 11 state-of-the-art approaches. (Conclusion) This proposed AVNC is effective in recognizing COVID-19 diseases.

Herein, we present an improved electrocardiogram (ECG) steganography for the protection of patients’ sensitive data, such as blood pressure, glucose level, lipid profile, and other personal health information. Based on the integer wavelet transform (IWT), we concealed secret bits in an ECG host using the standard deviation (SD) block, coefficient alignment technique, and least significant bit replacement. By computing the SD of a host block before bit embedding, data bits can be effectively embedded in the IWT coefficients. Simulations revealed that the payload of the proposed method is superior to that of existing techniques when the payload size is larger than 15.5 Kb, and our signal-to-noise ratio (SNR) is also better than theirs. In addition, our method is superior to other ECG steganographic methods in terms of the peak SNR and hiding capability. The proposed method not only provides good perceived quality but also protection against attacks. With its short implementation time, our proposed method can be applied in portable biometric devices or wearable electronics.

Belief rule base (BRB) model suffers from the rule explosion problem when it is applied in modeling complex systems. The rule explosion problem makes it difficult to establish and optimize the BRB model effectively. Aiming at this problem, a new multilayer BRB (MLBRB) model is proposed, which consists of the extracting block and the processing block. In the extracting block, the inputs are first divided into two groups, and then each group is used to construct a hierarchical BRB model. The outputs of extracting block are treated as the inputs of the processing block. To obtain the optimal MLBRB, the layerwise learning strategy and the layer adaptive growth strategy are proposed to optimize these two blocks, respectively. A case study for the safety assessment of the liquefied natural gas storage tank is conducted to verify the effectiveness of the proposed method.

Current robots can perform repetitive tasks well, but are constrained to environment and task variations. Teaching a robot by demonstration is a powerful approach to solve the problem. The learning methods using large sensory and joint state information are extremely difficult to efficiently learn demonstration policy. This paper proposes a learning-by-imitation approach that learns demonstration policy for robotic manipulation skill acquisition from what-where-how interaction data. The method can improve the robotic adaptability to environment and tasks with fewer training inputs. RGB-D image interaction demonstration is used. At each time step we interact with an object and select a high-level action. The demonstration is formed through multi-step interactions. An imitation learning architecture (OPLN) consists of objects list network (OLN) and policy learning network (PLN) is proposed. OLN and PLN are constructed respectively with Long Short-Term Memory (LSTM) neural networks. OLN learns objects sequence feature extracted from demonstration data while PLN learns policy. An action and a target object are obtained as outputs to control robot’s manipulation. The experiments show that the Block Stacking skill and Pick and Place skill can be successfully acquired, and the method can adapt to environment variations and generalize to similar tasks.

Magnetocardiography (MCG) has been extensively investigated and evaluated in various clinical studies for its potential in detecting the early stages of cardiac diseases. In particular, the establishment of a technology that can provide detailed information on the lesion parts of the heart is expected. The estimation result of the current spatial filter method, such as the exact low-resolution brain electromagnetic tomography, contains errors and has insufficient estimation accuracy for clinical applications. The information of sensors located at the ends cannot be utilized, and the amount of information that affects the estimation result is different for each sensor, which causes the derivation of a biased estimated solution. Therefore, in this study, we considered that the amount of information of each sensor can be used equally by setting an analysis area larger than the sensor area and proposed a method focusing on the relationship between the analysis area of signal source estimation and the sensor plane. We simulated the most efficient and optimized analysis area to be used and performed the source signal estimation by eLORETA using the QRS-complex peak data of the actual MCGs used in adjusting the 51ch sensor directly above the xiphoid process. We compared the following three sizes of the analysis area: x = 120 mm, y = 120 mm, z = 100 mm (a); x = 180 mm, y = 180 mm, z = 100 mm (b); x = 240 mm, y = 240 mm, z = 100 mm (c). Thus, because the signals from the heart are originally considered to be a single block, the estimated solution is also expected to be a single block. The solution was estimated as a single block, except case with analysis area (a), which corresponds to the conventional method. In addition, the position and size of the estimated solution are similar to those of the heart obtained from the CT images. The goodness of fit of each analysis area was approximately 0.99 or more, which indicated that there was no significant difference. Thus, we demonstrated that it is possible to visualize the movement of the myocardium by estimating the time-series waveform of the MCG.

The development of an image-based fish classification system using Convolutional Neural Network (CNN) has the advantages of no longer directly conducting features extraction and several features analysis. These steps has been involved by cascading convolution from initial to final block, where the initial, middle, and final blocks produce low-, middle-, and high-level features, respectively. Due to cascading convolution, CNN produces only high-level features. However, fish classification requires not only high-level features but also low-level features such as points, lines, and textures for representing edge spines, gill covers, fins, and skin textures in order to achieve higher performance; furthermore, CNN generally has not yet incorporated low-level features in the last block. In this paper, we proposed Multi-Level Residual (MLR) as a new residual network strategy by combining low-level features of the initial block with high-level features of the last block by applying Depthwise Separable Convolution. We also proposed MLR-VGGNet as a new CNN architecture inherited from VGGNet and strengthened it using Asymmetric Convolution, MLR, Batch Normalization, and Residual features. Our experimental results show that MLR-VGGNet achieved an accuracy of 99.69%, outperformed original VGGNet relative up to 10.33% and other CNN models relative up to 5.24% on Fish-gres and Fish4-Knowledge dataset.

Blockchain technology is an emerging solution to various financial applications that require a secure and tamper-proof transactions system. One such application is the land registry. Management of transactions for land registration is a tedious task. It is highly insecure and subject to forgery land records, Issues in verification, mediators, etc. This article presents a scalable and novel property/land registration framework based on blockchain technology. The transparent and immutable nature of blockchain technology makes it reliable for intrusive and fraudulent land registration activities. The framework uses the InterPlanetary File System (IPFS), a Peer-to-Peer (P2P) swarm network. It allows the sharing and storing of data in an efficient, decentralized, and transparent manner. This article also proposes a Trusted Node Consensus Algorithm (TNCA) based on the miners' trust value that minimizes the computational overhead of broadcasting the new block. The proposed approach - trusted node consensus algorithm requires lesser time to add the block into the blockchain, and message exchange per consensus is 58.94% lesser than the traditional Proof-of-Work (PoW) approach and 26.44% lesser time than the existing load-balanced method.

To enhance the conventional LSB technique of digital image watermarking, the paper introduces a novel approach of LSB technique based on matrix multiplication process. This technique selects the non-consecutive matrix of pixels to replace the last three bits of each RGB components of cover image by watermark image. The filtering process is applied on each block of matrix to select the suitable block for embedding process. Extraction process of watermark is just the reverse of the embedding process. The non-uniform substitution of bits makes the system more vigorous in terms of robustness, imperceptibility and security. Although the proposed method is non blind type of digital watermarking, the original image is required at destination side for the extraction process. MATLAB tool is used for the evaluation of the proposed system. The strength of the given methodology is highlighted by experimental results and tabulated for statistical attacks. This technique is suitable for content authentication and copyright protection applications.

Internet of Things (IoT) can be conveniently deployed while empowering various applications, where the IoT nodes can form clusters to finish certain missions collectively. As energy-efficient operations are critical to prolong the lifetime of the energy-constrained IoT devices, the Unmanned Aerial Vehicle (UAV) can be dispatched to geographically approach the IoT clusters towards energy-efficient IoT transmissions. This paper intends to maximize the system energy efficiency by considering both the IoT transmission energy and UAV propulsion energy, where the UAV trajectory and IoT communication resources are jointly optimized. By applying large-system analysis and Dinkelbach method, the original fractional optimization is approximated and reformulated in the form of subtraction, and further a block coordinate descent framework is employed to update the UAV trajectory and IoT communication resources iteratively. Extensive simulation results are provided to corroborate the effectiveness of the proposed method.

A previously unknown form of compromising emanations has been discovered. LED status indicators on data communication equipment, under certain conditions, are shown to carry a modulated optical signal that is significantly correlated with information being processed by the device. Physical access is not required; the attacker gains access to all data going through the device, including plaintext in the case of data encryption systems. Experiments show that it is possible to intercept data under realistic conditions at a considerable distance. Many different sorts of devices, including modems and Internet Protocol routers, were found to be vulnerable. A taxonomy of compromising optical emanations is developed, and design changes are described that will successfully block this kind of "Optical TEMPEST" attack., 26 pages, 11 figures

Solving inverse problems, where we find the input values that result in desired values of outputs, can be challenging. The solution process is often computationally expensive and it can be difficult to interpret the solution in high-dimensional input spaces. In this paper, we use a problem from additive manufacturing to address these two issues with the intent of making it easier to solve inverse problems and exploit their results. First, focusing on Gaussian process surrogates that are used to solve inverse problems, we describe how a simple modification to the idea of tapering can substantially speed up the surrogate without losing accuracy in prediction. Second, we demonstrate that Kohonen self-organizing maps can be used to visualize and interpret the solution to the inverse problem in the high-dimensional input space. For our data set, as not all input dimensions are equally important, we show that using weighted distances results in a better organized map that makes the relationships among the inputs obvious., 16 figures and 4 tables

In order to be deployed on storage-limited devices, blockchains generally provide lightweight clients which only store all the block headers rather than all the blocks. However, a lightweight client is hard to verify a newly-issued transaction, thus making the zero-confirmation transactions between lightweight clients impossible. In particular, transaction verification needs to verify that each referred output of the transaction is not previously spent. The conventional lightweight client design is unscalable as it can only support such operation in the complexity of O(NT), where NT is the total number of transactions in the system. The latest proposals suggest to summarize all the unspent outputs in an ordered Merkle tree. Therefore, a lightclient can request proof of presence and/or absence of an element in it to prove whether a referred output is previously spent or not, in the complexity of O(log(NU)), where NU is the total number of unspent output in the system. However, updating such ordered Merkle tree is slow, thus making the system impractical — by our evaluation, when a new block is generated in Bitcoin, it takes more than one minute to update the ordered Merkle tree. We propose a practical client, TICK, to solve this problem. TICK uses the AVLhashtree to store all the unspent outputs. The AVLhashtree can be updated in the time of O(M*log(NU)), where M is the number of elements that need to be inserted or removed from the AVLhashtree. By evaluation, when a new block is generated, the AVLhashtree can be updated within 1 second. Similarly, the proof can also be generated in the time of O(log(NU)). Therefore, TICK is practical and scalable. Benefited by the AVLhashtree, a storage-limited device can efficiently and cryptographically verify transactions. In addition, rather than requiring new miners to download the entire blockchain before mining, TICK allows new miners to download only a small portion of data to start mining. We implement TICK for Bitcoin and provide an experimental evaluation on its performance by using the current Bitcoin blockchain data. Our result shows that the proof for verifying whether an output of a transaction is spent or not is only several KB. The verification is very fast – generating a proof generally takes less than 1 millisecond, and verifying a proof even takes much less time. In addition, to start mining, new miners only need to download several GB data, rather than downloading over 230 GB data.

With the rapid development of the Internet of Things (IoT), more and more data are generated by smart devices to support various edge services. Since these data may contain sensitive information, security and privacy of data aggregation has become a key challenge in IoT. To tackle this problem, a Blockchain based Secure Data Aggregation strategy, namely (BSDA), is proposed for edge computing empowered IoT. Specifically, in order to restrict task receivers (i.e., Mobile Data Collectors (MDC)) to search and accept tasks, the block header is intergraded with a security label including task security level and task completion requirement. Accordingly, new block generation rules are developed to improve system performance in throughput and transaction latency. Furthermore, BSDA decomposes both sensitive tasks and task receivers into groups against privacy disclosure. On the other hand, a deep reinforcement learning method, the Improved double bootstrapped Deep Deterministic Policy Gradient (IDDPG), is developed to design energy efficient MDC routes under the constrains that the security levels of MDCs should be higher than the security levels of data aggregation tasks. Simulation results indicate that (i) as a privacy-preserving strategy, BSDA obtains high throughput and low transaction latency; (ii) BSDA outperforms certain contemporary strategies in aggregation ratio and energy cost.

The sixth generation (6G) era is expected to provide even higher levels of massive connectivity/Internet of Things (IoT), tremendous data rate and low latency than the 5G communication. Therefore, the future 6G wireless networks would confront with much more severe spectrum scarcity problems, which makes the new radio in unlicensed spectrum (NR-U) technology attractive. Meanwhile, the high densely deployed massive IoT devices lead to fearful inter-and intra-cell interference issues. To address these challenges, a coordinated multi-point (CoMP) technology can be adopted. In this work, we introduce a CoMP based NR-U network, particularly for 6G enabled massive IoT scenarios. Under the proposed network, we introduce a spatial listen-before-talk (LBT) scheme to control mobile network operators (MNOs) to coexist with the incumbent WiFi devices orthogonally, which can significantly improve the spectrum efficiency. To suppress the strong co-channel interference among multiple MNOs, we investigate a joint beamforming coordination and user selection problem, which is NP-hard. To deal with this problem, we first adopt a fractional programming and an integer replacement method to transform the objective problem into a tractable one. Then, we introduce a semi-distributed alternating direction method of multipliers and block coordinate update (ADMM-BCU) algorithm to find a suboptimal solution, which only requires limited information exchange via a CoMP server and can help reduce energy consumption. Theoretical analysis and numerical results demonstrate the effectiveness of the proposed algorithm for large-scale 6G IoT scenarios.

Blockchain is starting to be deployed in the Internet of Things (IoT) to enable autonomous device-to-device transactions. However, traditional block-based blockchain techniques, such as Bitcoin and Ethereum, are not suitable for IoT environments due to their low throughput, high computation overhead, and costly transaction fee. To satisfy the requirements of IoT environments, Directed-Acyclic-Graph (DAG) based approaches, aiming to provide cheap blockchain services with low latency and high throughput, are emerging. This paper presents a set of comprehensive experimental studies on IOTA, a representative DAG-based blockchain. We aim to exhibit its unique characteristics mainly from three aspects: performance, security, and system robustness. We have developed a series of benchmark tools and judiciously selected typical configurations to perform experimental examinations with a real private IOTA network. Our studies reveal several interesting findings: 1) The throughput of IOTA is higher than the traditional block-based blockchain but far less than the reported thousands of transactions per second (TPS) in its whitepaper, even with scaling-up configurations; 2) The database query heavily impacts the performance of IOTA, even more than its mining (i.e., Proof of Work, PoW) process; 3) The system robustness of IOTA is closely related to the frequency of the incoming transactions while the milestone sent by the centralized coordinator has little effect on the system robustness. We make our benchmark tools public and expect our works can inspire system architects, application designers, and practitioners with new optimization directions and potential application cases for further exploration.

Blockchains are currently gaining attention as a newly emerging technology in both academia and industry, capable of impacting a variety of domains beyond cryptocurrencies. Performance modeling can be used to provide us with a deeper understanding of the behavior and dynamics within blockchain peer-to-peer networks. Blockchain system architects can leverage network models to properly tune their system and to reduce design costs significantly. In this article, we focus on the original and well-established Bitcoin blockchain network. In particular, we propose a random graph model for performance modeling and analysis of the inventory-based protocol for block dissemination. This model addresses the impact of key blockchain parameters on the overall performance of Bitcoin. We derive some explicit and closed-form equations for block propagation delay and traffic overhead in the Bitcoin network. We also adapt our model to study the impact of deploying a relay network and investigate the effect of the relay network size on the network performance and decentralization. We implement our model using the popular network simulator OMNet++. We validate the accuracy of our theoretical model and its implementation with our dataset mined from the Bitcoin network. Our results show the tradeoff between the default number of connections per node, network bandwidth, and block size in order to compute the optimal block propagation delay over the network. Additionally, we found that bigger relay networks can jeopardize the decentralization of the Bitcoin network.

Computer aided diagnosis have made a significant breakthrough in skin lesion diagnosis employing deep learning (DL) frameworks over the years, but it hardly reveals the transparency of the DL architecture. To mitigate this issue, this article proposes an image visibility filter (IVF) based DL framework for skin lesion diagnosis. The proposed IVF-DL network employs a ResNet architecture where visibility patches, extracted from the image visibility graph (IVG), are used as the convolutional kernels to extract salient features from dermoscopic images. The primary aim of this article is not only to classify skin lesions but also to depict the interpretable results after each residual block in a supervised manner. An optimal performance has been obtained by tuning three hyperparameters of the proposed method. Furthermore, the final interpretable result has been analyzed via IVG to resemble its spatial characteristics. Experimental results reveal the efficacy of the proposed method both qualitatively and quantitatively.

The application of blockchain to Vehicular Edge Computing (VEC) has attracted significant interests. As the Internet of Things plays an essential and fundamental role for data collecting, data analyzing, and data management in VEC, it is vital to guarantee the security of the data. However, the resource-constraint nature of edge node makes it challenging to meet the needs to maintain long life-cycle IoT data since vast volumes of IoT data quickly increase. In this paper, we propose Acce-chain, a storage-elastic blockchain based on different storage capacities at the edge. Acce-chain supports re-write operation to re-write the historical block with a newly generated block without breaking the hash links between the blocks. As a result, Acce-chain ensures that the hot data can be efficiently accessed at the edge without incurring much communication costs or increasing the total size of the chain. To guarantee the security of the re-write process, we propose a new cryptographic primitive named Dynamic Threshold Trapdoor Chameleon Hash (DTTCH). To guarantee the verifiability of query operation, we design a novel storage structure named HybridStore to ensure the verifiable query for on-chain/off-chain IoT data. As a result, Acce-chain achieves both authorized re-write and verifiable query simultaneously. We provide security analysis for the DTTCH scheme and the IoT data query algorithms. We evaluate Acce-chain through experiments and the results show that the performance of the re-write operation is feasible in real-world VEC settings, and the query efficiency can achieve up to several magnitudes better than which of the baseline. The results also demonstrate that Acce-chain can provide high service quality for the latency-sensitive VEC systems.

This paper considers the distributed structured optimization problem of collaboratively minimizing the global objective function composed of the sum of local cost functions. Each local objective function involves a Lipschitz-differentiable convex function, a nonsmooth convex function, and a linear composite nonsmooth convex function. For such problems, we derive the synchronous distributed primal-dual splitting (S-DPDS) algorithm with uncoordinated stepsizes. Meanwhile, we develop the asynchronous version of the algorithm in light of the randomized block-coordinate method (A-DPDS). Further, the convergence results show the relaxed range and concise form of the acceptable parameters, which indicates that the algorithms are conducive to the selection of parameters in practical applications. Finally, we demonstrate the efficiency of S-DPDS and A-DPDS algorithms by numerical experiments.

Vehicular ad hoc networks (VANETs) have become an important branch of future 6G smart wireless communications. As an emerging key technology, multi-access edge computing (MEC) provides low-latency, high-speed, and high-capacity network services for the VANETs. In this paper, we propose a novel framework for blockchain-based, hierarchical multi-access edge computing for the future VANET ecosystem (BMEC-FV). In the underlying VANET environment, we propose a trust model to ensure the security of the communication link between vehicles. Multiple MEC servers calculate the trust between vehicles through computing offloading. Meanwhile, the blockchain system plays an important role to manage the entire BMEC-FV architecture. We aim to optimize the throughput and the quality of services (QoS) for MEC users in the lower layer of the system architecture. In this framework, the main challenge is how to effectively reach consensus among blockchain nodes while ensuring the performance of MEC systems and blockchains. The blocksize of blockchain nodes, the number of consensus nodes, reliable features of each vehicle, and the number of producing blocks for each block producer are considered in a joint optimization problem, which is modeled as a Markov decision process with state space, action space, and reward function. Since it is difficult for this to be solved by traditional methods, we propose a novel deep compressed neural network scheme. Simulation results illustrate the superiority of the BMEC-FV ecosystem.

Differential protection, as the key protection element in the power transformers, has always been threatened with sending false trips subjected to external transient disturbances. As a result, differential protection needs an additional block to distinguish between internal faults and external transient disturbances. The protection system should i) be able to perform based on raw data, ii) be able to learn fully temporal features and sudden changes in the transient signals, and iii) impose no assumption on noise. To address these challenges, a fast recurrent neural network, namely fast gated recurrent neural network (FGRNN). By removing the reset gate in the gated recurrent unit (GRU), the proposed network is capable of learning abrupt changes in addition to significantly reducing the computational time. Furthermore, a loss function based on an information theory concept is formulated in this paper to enhance the learning ability as well as robustness against non-Gaussian/Gaussian noises. A generalized form of mutual information is also adopted to form a noise model-free loss function, then incorporated with the designed deep network. Simulated and experimental examinations engaging various external factors, in addition to a comparison between the proposed fast GRNN, GRU, and seven firmly-established methods indicates the faster and more reliable performance of the proposed algorithm. Post-print / Final draft

An intelligent cleaning vehicle improves the efficiency of road cleaning to a great extent. In this case, road garbage recognition is fundamental and crucial. Usually, the pebbles are too small, and the sand has an inconspicuous boundary and unfixed shape on the roads. These issues make the stones and sand too hard to be detected by a garbage recognition system. Hence, we designed a novel semantic segmentation network that acquires the areas and categories of road garbage. We designed a Deep Supervision and High Fusion (DSHF) block to improve the road garbage segmentation accuracy. The designed block with a backbone network of HFCN and UNet++ is comparable with a model that only has either a deep supervision block or a high fusion block. According to the collected road garbage segmentation dataset comprising four categories (stones, leaves, sand and bottles), the model we designed has improved the metric value of MPA by 3% over the state-of-art methods and achieved the highest MIoU (Mean Intersection over Union) with the value of 77.92%. The results of our experiments show that the semantic segmentation of road garbage is feasible and that the proposed DSHF block is practical for improving the segmentation effect of road garbage.

The Hyperloop is a concept of a ground transportation system consisting of capsules (called pods) traveling at very high-speeds in near-vacuum tubes. The hyperloop aims to be a fast, cheap, and sustainable alternative to short-haul flights and high-speed rail. The small pod size requires very high frequencies to respond to future high levels of passenger and cargo demands. Media and representatives of the emerging Hyperloop industry acclaim the Hyperloop as a very capacity-effective transport system, however there is no clear scientific evidence proving that. A theoretical investigation is therefore necessary to understand which capacity the Hyperloop could safely provide and whether that could satisfy the future transport demand. This paper provides a comparative analysis of the capacity that the Hyperloop can offer for several operational scenarios and different signalling systems, including Moving-Block and the advanced concept of Virtual Coupling. Results show that Moving-Block could achieve required transport capacity levels only if pods could use high deceleration rates likely to be unsafe and uncomfortable to passengers. Virtual Coupling is instead observed to be a more satisfactory operational concept that could address transport demand while respecting safety and comfort standards if reliable pod platooning technologies are available.