Search

Classification methods for streaming data are not new, but very few current frameworks address all three of the most common problems with these tasks: concept drift, noise, and the exorbitant costs associated with labeling the unlabeled instances in data streams. Motivated by this gap in the field, we developed an active learning framework based on a dual-query strategy and Ebbinghaus's law of human memory cognition. Called CogDQS, the query strategy samples only the most representative instances for manual annotation based on local density and uncertainty, thus significantly reducing the cost of labeling. The policy for discerning drift from noise and replacing outdated instances with new concepts is based on the three criteria of the Ebbinghaus forgetting curve: recall, the fading period, and the memory strength. Simulations comparing CogDQS with baselines on six different data streams containing gradual drift or abrupt drift with and without noise show that our approach produces accurate, stable models with good generalization ability at minimal labeling, storage, and computation costs.

This paper studies the coverage performance of unmanned aerial vehicle (UAV)-assisted simultaneous wireless information and power transfer (SWIPT) networks under the nonlinear and linear energy harvesting (EH) models in the rich scattering scenarios including smart farming and smart ranching, where the none-line-of-sight (NLoS) links are the dominate component of the wireless channel. Multiple UAVs are equipped with directional antennas to transfer information and energy to ground users (GUs). Power splitting (PS) or time switching (TS) architecture is employed at GUs. In order to evaluate the system performance in fading channels, the information and energy coverage probabilities of the system are discussed, and by using the stochastic geometry approach and the approximate scaling method, the general and lower bound explicit expressions of the coverage probabilities are derived. Numerical results show that the coverage performance of PS-based systems is superior to that of TS-based systems. Moreover, although the linear EH model yields better results than the nonlinear one, as the linear EH model is too ideal, its yielded results may mismatch practical EH circuits, and the ones yielded by the nonlinear EH model is much closer to practice, as the nonlinear EH model is based on real data measurement. Additionally, the nonlinear EH model has a relatively small effect on the harvested energy coverage probability, and the linear EH model introduces greater bias for TS-based system than that for PS-based one.

This paper presents a recursive feature elimination (RFE) mechanism to select the most informative genes with a least square kernel extreme learning machine (LSKELM) classifier. Describing the generalization ability of LSKELM in a way that is related to small norm of weights, we proposed a ranking criterion to evaluate the importance of genes by the norm of weights obtained by LSKELM network. The proposed method is called LSKELM-RFE algorithm, which first employs the original genes to build a LSKELM classifier, and then ranks the genes according to their importance given by the norm of LSKELM network output weights, and finally removes a least important gene. Benefiting from the random mapping mechanism of the extreme learning machine (ELM) kernel, there are no parameter of LSKELM-RFE needs to be manually tuned. A comparative study among our proposed algorithm and other two famous RFE algorithms has shown that LSKELM-RFE outperforms other RFE algorithms in both the computational cost and generalization ability.

As one of the most complex social problems around the world, crime may bring the risk of dying or losing property to the public if not handled properly. Crime prediction which aims at predicting crime incidents before they happen is of great importance to fight against crime. Previous studies are concerned primarily with day-level crime prediction and have certain limitations on modeling complex spatial–temporal-categorical dependency contained in the criminal activities as well as utilizing external factors to facilitate the forecast. In this paper, we develop a novel Neural Attentive framework for Hour-level Crime prediction (NAHC) to cope with these challenges. Specifically, we first adopt the priori knowledge-based data enhancement strategy to alleviate the zero-inflated issue raised in hour-level settings. Then, multi-graph convolutional networks are applied to capture spatial dependency from different aspects. After that, we integrate gated recurrent units with a temporal attention mechanism to jointly address temporal dependency and capture time-sensitive external factors. A categorical attention mechanism is proposed for dealing with categorical dependency and finally a fully connected network is utilized to generate the final prediction results. Extensive experiments on two real-world crime datasets demonstrate the effectiveness of our framework over the state-of-the-art comparing methods.

Deep neural networks (DNNs) have been applied in various machine learning tasks with the success of deep learning technologies. However, they are surprisingly vulnerable to adversarial examples, which can easily fool deep neural networks. Due to this drawback of deep neural networks, numerous methods have been proposed to eliminate the effect of adversarial examples. Although they do play a significant role in protecting deep neural networks, most of them all have one flaw in common. They are only effective for certain types of adversarial examples. This paper proposes an ensemble denoiser based on generative adversarial networks (GANs) to protect deep neural networks. This proposed method aims to remove the effect of multiple types of adversarial examples before they are fed into deep neural networks. Therefore, it is model-independent and cannot modify deep neural networks’ parameters. We employ a generative adversarial network for this proposed method to learn multiple mappings between adversarial examples and benign examples. Each mapping behaves differently for different types of adversarial examples. Therefore, we integrate these mappings as the ultimate method to defend against multiple types of adversarial examples. Experiments are conducted on the MNIST and CIFAR10 datasets. We compare this proposed method with several existing excellent methods. Results show that this proposed method achieves better performance than other methods when defending against multiple types of adversarial examples. The code is available at https://github.com/Afreadyang/ensemble-ape-gan

This paper studies the UAV-assisted wireless powered network, where a UAV is dispatched to wirelessly charge multiple ground nodes (GNs) by using radio frequency (RF) energy transfer and then the GNs use their harvested energy to upload the sensed information to the UAV. At each moment, the UAV is scheduled to charge the GNs or only one GN is scheduled to upload its data. An optimization problem is formulated to minimize the average age of information (AoI) of the GNs by jointly optimizing the trajectory of the UAV and the scheduling of information transmission and energy harvesting of GNs. As the problem is a combinational optimization problem with a set of binary variables, it is difficult to be solved. Thus, it is modeled as a Markov problem with large state spaces and a deep Q network (DQN)-based scheme is proposed to find its near optimal solution on the basis of the deep reinforcement learning (DRL) framework. Two nets are structured with artificial neural network (ANN), where one is for evaluating the reward of the action performed in current state, and the other is for predicting realistic action. The corresponding state spaces, the efficient action spaces and reward function are designed. Simulation results demonstrate the convergence of the proposed DQN scheme, which also show that the proposed DQN scheme gets much smaller average AoI than the three other known schemes. Moreover, by involving the energy punishment in the reward, the UAV may save its energy but yield higher AoI. Additionally, the effects of the packet size, the transmit power, and the distribution area of GNs on the GNs’ average AoI are also discussed, which are expected to provide some useful insights.

Nowadays, mining opinion or sentiment from the online user-generated texts has become a research hot-spot. Although, a large amount of lexicon-based Chinese polarity detection works have been done, yet the existing methods have one common flaw that even the same word can have opposite polarities among different seed-lexicons, or polarity fuzziness. Therefore, in order to further enhance the performance of Chinese sentiment polarity detection, in this paper, we start from a two-aspect lexicon expansion, specifically, detecting sentiment polarity for new words and revising sentiment polarity for words already defined in seed-lexicons, so that the polarity fuzziness can be avoided. Then, we formulate a novel sentiment polarity detection framework for Chinese (SPDFC) with more effort to fine-grained sentiment processing, involved in symmetrical mapping, sentiment feature pruning and text representation. In this way, the word polarity can be directly taken as features, further penetrating into polarity detection phase. According to the experimental results, compared to other classical and state-of-the-art methods, the proposed the framework SPDFC can achieve the best overall performance from the perspective of Chinese polarity detection, sentiment feature pruning as well as text representation.

Reservoir computing (RC), as a brain-inspired neuromorphic computing algorithm, is capable of fast and energy-efficient temporal data analysis and prediction. Hardware implementation of RC systems could significantly reduce the computing time and energy, but it is hindered by current physical devices. Recently, dynamic memristors have proved to be promising for hardware implementation of such system, benefiting from their fast and low-energy switching, nonlinear dynamics, and short-term memory behavior. In this work, we review striking results that leverage dynamic memristors to enhance the data processing abilities of RC systems based on resistive switching devices and magnetoresistive devices. The critical characteristic parameters of memristors affecting the performance of RC systems, such as reservoir size and decay time, are identified and discussed. Finally, we summarize the challenges this field faces in reliable and accurate task processing, and forecast the future directions of RC systems.

Community detection has long been a fundamental problem in network analysis. A great deal of previous research has regarded community detection as an optimization process, where a variety of internal quality metrics are typically treated as objective functions, such as modularity (Q) and weighted community clustering (WCC). However, purely optimizing a predefined quality metric probably results in an extreme unbalance in the scale of the detected communities, e.g., few giant communities with many very small communities. To reveal the true mesoscopic structure inside a big network under the suitable number of communities, we propose a novel community detection framework called LL-GMR, which is a local learning framework based on generalized metric with neighboring regularization. LL-GMR is qualified for both nonoverlapping and overlapping detection tasks. In LL-GMR, we propose a generalized representation and illustrate that it can be instantiated into 12 well-known internal quality metrics. When the generalized metric is used as an objective function, we encode node-level and community-level neighborhood information into two regularization terms to alleviate the dilemma of unbalanced communities. The experimental results show that our LL-GMR consistently outperforms other state-of-the-art community detection approaches in terms of discovering ground-truth communities in six real-life networks.

The main computational cost of building a support vector machine (SVM) training model lies in tuning the hyperparameters, including the kernel parameters and penalty constant C . This paper introduces a new kernel, the random radial basis function (RRBF) kernel, which all kernel parameters can be assigned to randomly. The key idea of the RRBF is to extend a one-dimensional parameter to d -dimensional parameters by simple modification of the traditional RBF kernel. We prove the universal approximation capability of a SVM with the RRBF kernel, proposing a simple model selection algorithm. The experiments on benchmark datasets show that SVM with the RRBF kernel clearly outperforms the traditional RBF kernel and other popular kernels, and the results are quite insensitive to C . Compared with other kernels, a SVM with the RRBF kernel is not sensitive to the penalty constant C , and it can be tuned in a wide range. Additionally, this property also enables a SVM to find the hyperparameters quickly. A simulation of parameter sensitivity study also show that a SVM is more stable w.r.t. to the different choices of kernel parameters.

Accurate and timely traffic flow prediction is a critical part of the steps to alleviate traffic congestion. Fully considering the spatial–temporal dependencies of traffic flow is the key to accura...

This article focuses on the security control for Takagi–Sugeno (T–S) fuzzy systems with adaptive event-triggered mechanism (AETM) and multiple cyber-attacks, which include deception attacks and denial-of-service (DoS) attacks. A multiple cyber-attacks model is first established for T–S fuzzy systems by considering deception attacks and DoS attacks at the same time. An AETM is introduced to relieve the network load, where the threshold of event-triggering condition can be adaptively adjusted while preserving the system performance. Then a novel mathematical model for T–S fuzzy systems with multiple cyber-attacks and AETM is proposed first. Based on the built model, sufficient conditions to guarantee the exponentially mean square stability of the system are achieved by utilizing the Lyapunov stability theory. Moreover, the controller gains are derived with the help of a linear matrix inequality technique. Finally, simulated examples are presented for illustrating the effectiveness of the proposed method.

Graph convolution networks (GCNs) have become one of the most popular deep neural network-based models in many real-world applications. GCNs can extract features take advantage of both graph structure and node attributes based on convolutional neural networks. Existing GCN models represent nodes by aggregating the graph structure and node attributes from their neighbors which usually disrupt the node similarities in the feature space. In this paper, we propose the MSF-GCN, a graph convolutional network with multi-similarity attributed matrices fusion for node classification. The key idea behind the MSF-GCN is that not only the topology but also the attributes similarities are taken into consideration for node presentation. Specifically, we first apply a GAT-based module to obtain a general representation of the original graph. Next, we construct two k-nearest neighbor graphs based on node attributes with cosine similarity and heat kernel similarity. To balance the disparity between the graph structure and node attributes for each similarity matrix, we develop a self-attention network to integrate the node attributes with topological features. Furthermore, we design a gated-fusion network to merge the cosine similarity vector and heat kernel vector. In our experiments on four real-world datasets, results show that our MSF-GCN model can extract more correlation information from the node attributes and graph structure, and outperform seven state-of-the-art methods.

Computational fluid dynamics (CFD) has been proven to be a versatile tool for indoor environment simulations. The discretization of computational domain (mesh generation) determines the reliability of CFD simulation and computational cost. For cases with complex/irregular geometries, the widely utilized tetrahedral meshes have critical limitations, including low accuracy, considerate grid number and computing cost. To overcome these disadvantages, the current research developed a polyhedral meshes based meshing strategy for indoor environment simulations. This study applied tetrahedral, hexahedral and polyhedral meshes for evaluating indoor environment cases developed from previous studies. Simulation accuracy, computing time and physical storage of different mesh types were compared. The results show that the polyhedral meshes could save almost 95% of computing time without sacrificing model accuracy, compared with the other two mesh types with the approximately same grid numbers. Due to its large mesh information, the polyhedral meshes occupied the most physical memory. Overall, the polyhedral meshes based meshing strategy produced a superior performance (model accuracy and computing time) for indoor environment simulations and shows a great potential in engineering applications.

Vulnerability assessment—a critical issue for networks—attempts to foresee unexpected destructive events or hostile attacks in the whole system. In this article, we consider a new Markov global connectivity metric—Kemeny constant, and take its derivative called Markov criticality to identify critical links. Markov criticality allows us to find links that are most influential on the derivative of Kemeny constant. Thus, we can utilize it to identity a critical link ( i , j ) from node i to node j , such that removing it leads to a minimization of networks’ global connectivity, i.e., the Kemeny constant. Furthermore, we also define a novel vulnerability index to measure the average speed by which we can disconnect a specified ratio of links with network decomposition. Our method is of high efficiency, which can be easily employed to calculate the Markov criticality in real-life networks. Comprehensive experiments on several synthetic and real-life networks have demonstrated our method’s better performance by comparing it with state-of-the-art baseline approaches.

Previous crowdsourcing studies often adopted the individual-oriented approach that outsources a task to an individual worker or team formation-based approach that outsources a task to an artificially formed team of workers. Nowadays, workers are often naturally organized into groups through social networks. To address such common issue of grouped workers in real crowdsourcing systems, this article explores a novel crowdsourcing paradigm in which the task allocation targets are naturally existing worker groups but not individual workers or artificially formed teams as before. Because a natural group might not possess all required skills and needs to coordinate with other groups in the social network contexts for performing a complex task, a concept of contextual crowdsourcing value is presented to measure a group’s capacity to complete a task by coordinating with its contextual groups, which determines the priority that the group is assigned the task; then, the task allocation algorithms, including the allocations of groups and the workers actually participating in executing the task, are designed. The experiments on a real-world dataset show that our presented group-oriented approach can nearly always achieve better synergy performance, consistency performance, conflict performance, adaptability, and effectiveness on reducing costs, as compared with previous benchmark individual-oriented and team formation approaches.

A hyper-heuristic algorithm is a general solution framework that adaptively selects the optimizer to address complex problems. A classical hyper-heuristic framework consists of two levels, including the high-level heuristic and a set of low-level heuristics. The low-level heuristics to be used in the optimization process are chosen by the high-level tactics in the hyper-heuristic. In this study, a Cooperative Multi-Stage Hyper-Heuristic (CMS-HH) algorithm is proposed to address certain combinatorial optimization problems. In the CMS-HH, a genetic algorithm is introduced to perturb the initial solution to increase the diversity of the solution. In the search phase, an online learning mechanism based on the multi-armed bandits and relay hybridization technology are proposed to improve the quality of the solution. In addition, a multi-point search is introduced to cooperatively search with a single-point search when the state of the solution does not change in continuous time. The performance of the CMS-HH algorithm is assessed in six specific combinatorial optimization problems, including Boolean satisfiability problems, one-dimensional packing problems, permutation flow-shop scheduling problems, personnel scheduling problems, traveling salesman problems, and vehicle routing problems. The experimental results demonstrate the efficiency and significance of the proposed CMS-HH algorithm.

Predicting grain losses and waste rate (LWR) is critical for agricultural planning and grain policy development. Capturing the stage interaction and generating robust features are the main challenges in grain LWR prediction. In this article, we propose MTGA, a Multitask Gated recurrent unit (GRU) Autoencoder, approach to 1) obtain the robust feature representation for the prediction task and 2) explore the time-ordered interactions among different stages of the grain chain. Specifically, we design multiple GRU encoder–decoder pairs to co-reconstruct the stage features in a common space for robust feature learning. Then, an attention mechanism is proposed better to fuse the reconstructed features from the GRU encoder–decoder pairs. Furthermore, we utilize the multitask for reconstructed loss and grain LWR prediction. We introduce the reconstructed loss task as an auxiliary task to help us to represent the robust features. Besides, we introduce the LWR prediction as main task to learn the parameters for prediction task. We collected the data with questionnaires, interviews, or data from grain management institutes for experiments. The evaluation results show that grain LWR prediction by our approach achieves the best results compared to several state-of-the-art prediction models. Moreover, our method gains overall performance decline of 12.5–18.3% on mean absolute error and root mean square error metrics.

Tourism is one of the largest service industries and a popular leisure activity participated by people with friends or family. A significant problem faced by the tourists is how to plan sequences of points of interest (POIs) that maintain a balance between the group preferences and the given temporal and spatial constraints. Most traditional group itinerary recommendation methods adopt predefined preference aggregate strategies without considering the group members’ distinctive characteristics and inner relations. Besides, POI textual information is beneficial to capture overall group preferences but is rarely considered. With these concerns in mind, this paper proposes an AMT-IRE (short for Attentive Multi-Task learning-based group Itinerary REcommendation) framework, which can dynamically learn the inner relations between group members and obtain consensus group preferences via the attention mechanism. Meanwhile, AMT-IRE integrates POI categories and POI textual information via another attention network. Finally, the group preferences are used in a variant of the orienteering problem to recommend group itineraries. Extensive experiments on six datasets validate the effectiveness of AMT-IRE.

With the development of Cloud and 5G technology, edge devices have been widely used in various areas. However, the limited battery energy and processing ability of edge devices hinder the usage scope of those devices. Prior studies have typically managed to immigrate virtual machines (VMs) or offload tasks to reduce energy consumption and shorten execution time. In our work, we consider devices that can obtain energy from a green energy source (such as wind energy, or solar energy). First, we use a clustering method to divide nodes into some clusters, each with some edge nodes to ensure the clusters have a minimum distance (defined by energy transferring attenuation ratios between nodes) between nodes in the cluster; the cluster center is a node with a VM. Then, based on the clustering method, a scheduling heuristic is proposed to transfer energy, immigrate VM, and allocate tasks. The simulation result shows that our proposed method reduces both the total energy consumption and the energy consumption from outside of the system (ECFO).

In this paper, we present an improved Efficient Neural Network (ENet) for semantic segmentation, and named the proposed network as Efficient Residual Neural Network (ERNet). The ERNet network contains two processing streams: one is pooling stream, which is used to obtain high-dimensional semantic information; the other is residual stream which is used to record low-dimensional boundary information. The ERNet has five stages, each stage contains several bottleneck modules. The output of each bottleneck in the ERNet network is fed into the residual stream. Starting from the second stage of ERNet, pooling stream and residual stream through concatenating are used as inputs for each down-sampling or up-sampling bottleneck. The identity mapping of residual stream shortens the distance between the near input and output terminals of each stage network in ERNet, alleviates the problem of vanishing gradient, strengthens the propagation of low-dimensional boundary features, and encourages feature reuse of low-dimensional boundary features. We tested ERNet on CamVid, Cityscape, and SUN RGB-D datasets. The segmentation speed of ERNet is close to that of ENet, but the segmentation accuracy is higher than that of ENet.

This paper addresses the hybrid-triggered security control design for the networked control system (NCS) under multiple cyber attacks. A hybrid-triggered scheme (HTS) is introduced to mitigate the burden of the network transmission. Besides, a new model of multiple cyber attacks is built by simultaneously considering deception attacks and DoS attacks. In addition, A novel NCS model based on multiple cyber attacks is established with the hybrid-triggered scheme. Then, based on Lyapunov stability theory, criteria for guaranteeing the closed-loop system stability and achieving hybrid-triggered security controller design are derived. Finally, an illustrative example is given to validate the usefulness of the theoretical results.

We demonstrate an efficient restoration method based on sky segmentation and block optimized transmission (SSBOT) to restore the visibility of single haze image under non-uniform scattering medium. The SSBOT method uses sky region segmentation to determine the haze-opaque region, and estimates the global atmospheric light using quadtree-decomposition. The proposed SSBOT estimates the transmission in every sub-images of the degraded image with dark channel method with coefficient correction. The experimental results show that SSBOT can efficiently restore images degraded by non-uniform dense scattering medium. The proposed method can be used for various security and surveillance applications.

Imbalanced data classification is a major challenge in the field of data mining and machine learning, and oversampling algorithms are a widespread technique for re-sampling imbalanced data. To address the problems that existing oversampling methods tend to introduce noise points and generate overlapping instances, in this paper, we propose a novel oversampling method based on density peaks clustering. Firstly, density peaks clustering algorithm is used to cluster minority instances while screening outlier points. Secondly, sampling weights are assigned according to the size of clustered sub-clusters, and new instances are synthesized by interpolating between cluster cores and other instances of the same sub-cluster. Finally, comparative experiments are conducted on both the artificial data and KEEL datasets. The experiments validate the feasibility and effectiveness of the algorithm and improve the classification accuracy of the imbalanced data.

In recent years, significant progress has been achieved in face image editing due to the success of Generative Adversarial Network (GAN). However, state-of-the-art face editing methods mainly suffer from the following two limitations: 1) they are only applicable to face images with relative low-resolutions and 2) multi-attribute face editing may generate uncontrollable changes in non-target face attribute categories. To solve these problems, we propose a novel High-Quality Generative Adversarial Network (HQ-GAN) for controllable editing of multiple face attributes in high-resolution images. HQ-GAN has two novel ideas to break the limitations of resolution and controllability correspondingly: 1) fine-grained textures and realistic details of high-resolution face images are better preserved with the aid of textural features extracted by the wavelet transform module and 2) desired multi-attribute targets of face editing are emphasized using a weighted binary cross-entropy (BCE) loss so that the influence on non-target attributes is greatly reduced. To the best of our knowledge, HQ-GAN is the first attempt to achieve continuous editing of multiple face attributes on high-resolution images of the CelebA-HQ using only 28 000 training samples. Extensive qualitative results demonstrate the superiority of the proposed method in rendering realistic high-resolution face images with accurate attribute modification, and comprehensive quantitative results show that the proposed method significantly outperforms state-of-the-art face editing methods.

Substantial improvements have been achieved in the field of face recognition due to the successful application of deep neural networks. However, existing methods are sensitive to both the quality and quantity of the training data. Despite the availability of large-scale datasets, the long tail data distribution induces strong biases in model learning. In this paper, we present a Face Augmentation Generative Adversarial Network (FA-GAN) to reduce the influence of imbalanced deformation attribute distributions. We propose to decouple these attributes from the identity representation with a novel hierarchical disentanglement module. Moreover, Graph Convolutional Networks (GCNs) are applied to recover geometric information by exploring the interrelations among local regions to guarantee the preservation of identities in face data augmentation. Extensive experiments on face reconstruction, face manipulation, and face recognition demonstrate the effectiveness and generalization ability of the proposed method.

The bearing state signal collected by the vibration sensor contains a large amount of environmental noise in actual processes, which leads to a reduction in the accuracy of the convolutional network in identifying bearing faults. To solve this problem, a one-dimensional convolutional neural network with a multiscale kernel (MSK-1DCNN) is proposed for the classification information enhancement of the input. A two-layer multiscale convolution structure (MSK) is used at the front of the network. MSK has five convolutional kernels with different sizes, and those kernels are used to extract features with varying resolutions in the original signal. In the multiscale convolution structure, the ELU activation function is used instead of the ReLU function to improve the antinoise ability of MSK-1DCNN, also by adding pepper noise to the training set data to destroy the input data and forcing the network to learn more representative features to improve the robustness of the network. Experimental results illustrate that the improved methods proposed in this paper effectively enhance the diagnostic performance of MSK-1DCNN under intense noise, and the diagnostic accuracy is higher than that of other comparison algorithms.

Nowadays, with the continuous development of science and technology, the social demand for the network is more and more, and with the continuous expansion of the network scale, the complexity of the network is increasing day by day. How to locate the fault accurately and quickly from a large number of alarm information has become a problem. To solve this problem, we must use computer technology to study the automatic analysis technology of alarm correlation. Therefore, this paper applies data mining technology to communication network alarm analysis, and based on fuzzy theory, it can accurately describe the relationship between network alarm and fault reason, and combines data mining technology with fuzzy theory to form the network alarm correlation analysis method of fuzzy association rule mining. On this basis, in order to mine the fuzzy association rules of the fuzzy alarm database directly and avoid the interference in the process of converting the alarm database to the transaction database, this paper proposes a dynamic time window fuzzy association rule mining algorithm. Through the simulation analysis, compared with the traditional data mining technology, the fuzzy association rules mining method combined with the fuzzy theory has better performance, and the further proposed dynamic time window fuzzy association rules mining algorithm greatly improves the accuracy of the association rules confidence, and has good application performance in the network alarm correlation analysis.

Clustering ensemble can overcome the instability of clustering and improve clustering performance. With the rapid development of clustering ensemble, we find that not all clustering solutions are effective in their final result. In this paper, we focus on selection strategy in selective clustering ensemble. We propose a multiple clustering and selecting approach (MCAS), which is based on different original clustering solutions. Furthermore, we present two combining strategies, direct combining and clustering combining, to combine the solutions selected by MCAS. These combining strategies combine results of MCAS and get a more refined subset of solutions, compared with traditional selective clustering ensemble algorithms and single clustering and selecting algorithms. Experimental results on UCI machine learning datasets show that the algorithm that uses multiple clustering and selecting algorithms with combining strategy performs well on most datasets and outperforms most selective clustering ensemble algorithms.

In many electronic commerce systems, detecting significant clusters is of great value to the analysis, design, and optimization of the commerce behaviors. In this article, we propose a new dynamical approach to detect the cluster configuration fast and accurately which can be applied to electronic commerce systems. First, we analyze the two-stage game in which the leader group members make contributions prior to the follower group, and propose an exact index, i.e., the leadership , to characterize the key leaders. Then an efficient dynamical system is used to guarantee the cluster configuration converges to an optimal state, which assigns each node to the corresponding cluster based on quality optimization, repeatedly. Our method is of high efficiency—the exponential term in the proposed dynamical system makes the convergence to be very fast with a nearly linear time. Extensive experiments on multiple types of datesets demonstrate the state-of-the-art performance of proposed method.

With the explosion of social media networks, many modern applications are concerning about people's connections, which leads to the so-called social computing . An elusive question is to study how opinion communities form and evolve in real-world networks with great individual diversity and complex human connections. In this scenario, the classic K-means technique and its extended versions could not be directly applied, as they largely ignore the relationship among interactive objects. On the other side, traditional community detection approaches in statistical physics would be neither adequate nor fair: they only consider the network topological structure but ignore the heterogeneous-objects’ attributive information. To this end, we attempt to model a realistic social media network as a discrete-time dynamical system, where the opinion matrix and the community structure could mutually affect each other. In this paper, community detection in social media networks is naturally formulated as a multi-objective optimization problem (MOOP), i.e., finding a set of densely connected components with similar opinion vectors. We propose a novel and powerful graph K-means framework, which is composed of three coupled phases in each discrete-time period. Specifically, the first phase uses a fast heuristic approach to identify those opinion leaders who have relatively high local reputation; the second phase adopts a novel dynamic game model to find the locally Pareto-optimal community structure; and the final phase employs a robust opinion dynamics model to simulate the evolution of the opinion matrix. We conduct a series of comprehensive experiments on real-world benchmark networks to validate the performance of GK-means through comparisons with the state-of-the-art graph clustering technologies.

Single-cell RNA-seq (scRNA-seq) is being used widely to resolve cellular heterogeneity. With the rapid accumulation of public scRNA-seq data, an effective and efficient cell-querying method is critical for the utilization of the existing annotations to curate newly sequenced cells. Such a querying method should be based on an accurate cell-to-cell similarity measure, and capable of handling batch effects properly. Herein, we present Cell BLAST, an accurate and robust cell-querying method built on a neural network-based generative model and a customized cell-to-cell similarity metric. Through extensive benchmarks and case studies, we demonstrate the effectiveness of Cell BLAST in annotating discrete cell types and continuous cell differentiation potential, as well as identifying novel cell types. Powered by a well-curated reference database and a user-friendly Web server, Cell BLAST provides the one-stop solution for real-world scRNA-seq cell querying and annotation., Single-cell RNA-seq (scRNA-seq) is being widely used to resolve cellular heterogeneity. Here, the authors present a cell-querying method built on a neural network-based generative model and a customized cell-to-cell similarity metric.

The potential of random pattern based computational ghost imaging (CGI) for real-time applications has been offset by its long image reconstruction time and inefficient reconstruction of complex diverse scenes. To overcome these problems, we propose a fast image reconstruction framework for CGI, called “DeepGhost”, using deep convolutional autoencoder network to achieve real-time imaging at very low sampling rates (10–20%). By transferring prior-knowledge from STL-10 dataset to physical-data driven network, the proposed framework can reconstruct complex unseen targets with high accuracy. The experimental results show that the proposed method outperforms existing deep learning and state-of-the-art compressed sensing methods used for ghost imaging under similar conditions. The proposed method employs deep architecture with fast computation, and tackles the shortcomings of existing schemes i.e., inappropriate architecture, training on limited data under controlled settings, and employing shallow network for fast computation.

The association-rule-based approach is one of the most common technologies for building recommender systems and it has been extensively adopted for commercial use. A variety of techniques, mainly including eligible rule selection and multiple rules combination, have been developed to create effective recommendation. Unfortunately, little attention has been paid to the scalability concern of rule-based recommendation methods. However, the computational complexity of rule-based methods shall increase drastically with the growth of both online customers and rules, which are usually several millions in typical e-commerce platforms. Moreover, the dynamic change of users’ actions requires rule-based methods make recommendations in nearly real-time, which further highlights the scalability issue of rule-based recommender systems. In this article, we present a distributed framework that can scale different association-rule-based recommendation methods in a unified way. Specifically, based on the summarization of existing rule-based approaches, a generic tree-type structure is defined to store separate kinds of patterns, and an efficient algorithm is designed for mining eligible patterns along with computing recommendation scores. To handle the ever-increasing number of online customers, a distributed framework is proposed, where two load-balanced strategies for partitioning tree are put forward to fit sparse and dense data, respectively. Extensive experiments on five real-life data sets demonstrate that the efficiency of association-rule-based recommender systems can be significantly improved by the proposed framework.

In recent years, as the basic medical science is improved, the prevention and treatment of bedsore have made great progress. However, from the incidence rate of bedsore worldwide, its downward trend is extremely weak, so the nursing of a bedsore is still a major problem in the medical field. To explore the construction of patient service system based on quality function deployment (QFD) in the Internet of Things (IoT) environment, in this study, with the support of IoT technology, deep learning algorithm and QFD method are used to build patient service model to achieve the detection and nursing reminder of patients' physical condition. The basic framework of patient service system is constructed, and the system performance is simulated and analyzed in the simulation environment. The results show that when the data collection and analysis of health monitoring, functional analysis and the functional architecture of IoT are further carried out, it is found that the service system built in this study is more standardized, and it can monitor the physiological data of patients who are bedridden for a long time and cannot turn over in real time, so as to have a preliminary understanding of the patients' physical condition. Through the results of the service system, patients can get personalized care that varies from person to person, thus reducing the pressure of medical staff, and doctors can have a clearer real-time understanding of patients' physical condition. Therefore, in this study, the patient service system constructed has a timely avoidance effect on bedsore and achieves the expected demand, to provide an experimental basis for the service treatment of patients in the later medical industry.

Visibility restoration of an image degraded by scattering media (such as haze, fog, smog) is a challenging task which requires careful design of computational methods. The fundamental problem which limits clear image reconstruction is the random diffusion of light in the scattering medium. Recently, the dark channel prior method has emerged as a powerful approach for haze removal under adverse weather conditions. However, this method requires high computational time, and fails to achieve haze-free image in the sky region. To overcome these problems, we propose a novel imaging method based on quadtree theory combined with transmission optimization (QTCTO) to restore the visibility of images degraded by scattering medium. The proposed method uses the quadtree theory (for region segmentation) to estimate the global atmospheric light, while the transmission in the media is estimated by coefficient modification for the dark channel. The experimental results show that the proposed method is robust against scattering (under smoke and turbid water conditions) and has the advantage of low computational time. The proposed method can be used for security surveillance, remote sensing, and various military applications.

The problem of robust fault estimation of discrete-time nonlinear plant is investigated from the view of reducing its conservatism and restraining its on-line computational burden simultaneously. Firstly, an enhanced maximum-priority-based switching law is developed for subdividing the distribution types of normalized fuzzy weighting functions in a more flexible way. Then, a new fuzzy fault estimation observer is proposed with different switching modes in accordance with the updated value of the above switching law. More importantly, the proposed designing criterion is further optimized by considering the balance between reducing the conservatism and restraining the on-line computational burden. Finally, a set of simulation comparisons over the previous ones are provided to illustrate the advantages of our method developed in this paper.

Community detection is one of the hot topics in the complex networks. It aims to find subgraphs that are internally dense but externally sparsely connected. In this paper, a new method is proposed to identify the most influential nodes which are considered as cores of communities and achieve the initial communities. Then, by an expansion strategy, unassigned nodes are added to initial communities to expand communities. Finally, merging overlapping communities to get the final community structure. To evaluate the performance of the proposed node influence method (LGI), the susceptible–infected–removed (SIR) diffusion model are used. Testing with the synthetic networks and real-world networks, LGI can identify best nodes with high influence and is better than other centrality methods. Finally, experiments show that our proposed community detection algorithm based on influential nodes (LGIEM) is able to detect communities efficiently, and achieves better performance compared to other recent methods.

MapReduce is a widely-used programming model in cloud environment for parallel processing large-scale data sets. The combination of the high-level language with a SQL-to-MapReduce translator allows programmers to code using SQL-like declarative language, so that each program can afterwards be complied into a MapReduce jobflow automatically. This way is helpful to narrow the gap between non-professional users and cloud platforms, and thus significantly improve the usability of the cloud. Although a number of translators have been developed, the auto-generated MapReduce programs still suffered from extremely inefficiency. In this paper, we present an efficient C ost- A ware SQL-to-MapReduce T ranslator (CAT). CAT has two notable features. First, it defines two intra-SQL correlations: Generalized Job Flow Correlation (GJFC) and Input Correlation (IC), based on which a set of looser merging rules are introduced. Thus, both Top-Down (TD) and Bottom-Up (BU) merging strategies are proposed and integrated into CAT simultaneously. Second, it adopts a cost estimation model for MapReduce jobflows to guide the selection of a more efficient MapReduce jobflows auto-generated by TD and BU merging strategies. Finally, comparative experiments on TPC-H benchmark demonstrate the effectiveness and scalability of CAT.

Extreme learning machine for regression (ELR), though efficient, is not preferred in time-limited applications, due to the model selection time being large. To overcome this problem, we reformulate...

Hybrid cloud is a cost-efficient way to address the problem of insufficient resources for meeting the peak demand of its users for a service provider, which elastically scales up or down the cloud capability based on demand by combining local infrastructures and one or more public clouds. While, the combination introduces new challenges that must necessarily be addressed before adoption. To address these new challenges for improving the resource efficiency in hybrid clouds, much work tried to solve the decision problem of workload scheduling, resource provisioning, or both, where workload scheduling answers how to efficiently map workloads to available resources, and resource provisioning addresses how to optimally provision resources based on demand. In this article, we proposed a comprehensive taxonomy of workload scheduling and resource provisioning in hybrid cloud environments to investigate and classify 146 related research articles. Based on the investigation, we summarized the challenges which have not been addressed by these researches, and discussed future directions and trends in the area.

As an e-commerce feature, the personalized recommendation is invariably highly-valued by both consumers and merchants. The e-tourism has become one of the hottest industries with the adoption of recommendation systems. Several lines of evidence have confirmed the travel-product recommendation is quite different from traditional recommendations. Travel products are usually browsed and purchased relatively infrequently compared with other traditional products (e.g., books and food), which gives rise to the extreme sparsity of travel data. Meanwhile, the choice of a suitable travel product is affected by an army of factors such as departure, destination, and financial and time budgets. To address these challenging problems, in this article, we propose a Probabilistic Matrix Factorization with Multi-Auxiliary Information (PMF-MAI) model in the context of the travel-product recommendation. In particular, PMF-MAI is able to fuse the probabilistic matrix factorization on the user-item interaction matrix with the linear regression on a suite of features constructed by the multiple auxiliary information. In order to fit the sparse data, PMF-MAI is built by a whole-data based learning approach that utilizes unobserved data to increase the coupling between probabilistic matrix factorization and linear regression. Extensive experiments are conducted on a real-world dataset provided by a large tourism e-commerce company. PMF-MAI shows an overwhelming superiority over all competitive baselines on the recommendation performance. Also, the importance of features is examined to reveal the crucial auxiliary information having a great impact on the adoption of travel products.

The False data injection attack (FDIA) against the Cyber-Physical Power System (CPPS) is a kind of data integrity attack. With more and more cyber vulnerabilities detected out, different types of FDIAs are emerging as severe threats to the stable operation of CPPS gradually. In this paper, the invasion pathway of the FDIA against CPPS is explored in detail, and a novel FDIA detection model based on ensemble learning is further provided. First, a pseudo-sample database is built to assist the training and evaluation of this model, and it's more important to update the model in the future. Furthermore, the optimal feature set is extracted to characterize the behavior of the FDIA, which improves the precision of the FDIA detection model. Finally, a focal-loss-lightgbm (FLGB) ensemble classifier is constructed to detect the FDIA behavior automatically and accurately. We illustrated the performance of this model by a fusion of measurement data and power system audit logs. This model utilizes the offline training way, the conclusion shows the high precision and stability of this model, which ensures the stable operation of the smart grid and improves the FDIA resistance ability of the CPPS.

Convolutional neural networks (CNN) with their deep feature extraction capability have recently been applied in numerous image fusion tasks. However, the image fusion of infrared and visible images leads to loss of fine details and degradation of contrast in the fused image. This deterioration in the image is associated with the conventional “averaging” rule for base layer fusion and relatively large feature extraction by CNN. To overcome these problems, an effective fusion framework based on visual saliency weight map (VSWM) combined with CNN is proposed. The proposed framework first employs VSWM method to improve the contrast of an image under consideration. Next, the fine details in the image are preserved by applying multi-resolution singular value decomposition (MSVD) before further processing by CNN. The promising experimental results show that the proposed method outperforms state-of-the-art methods by scoring the highest over different evaluation metrics such as Q0, multiscale structural similarity (MS_SSIM), and the sum of correlations of differences (SCD).

Nano-drug delivery systems (NDDS) are functional drug-loaded nanocarriers extensively applied in the healthcare and pharmaceutical areas. Recently, microfluidics has been demonstrated as one of the most promising techniques to fabricate high-performance NDDS with uniform morphology, size and size distribution, reduced batch-to-batch variations and controllable drug delivering capacity. Here, a brief review of the microfluidic-mediated NDDS is presented. The fundamentals of microfluidics are first interpreted with an emphasis on the fluid characteristics, design and materials for microfluidic devices. Then a comprehensive and in-depth depiction of the microfluidic-mediated fabrications of controllable NDDS with well-tailored internal structures and integrated functions for controlled encapsulation and drug release are categorized and reviewed, with particular descriptions about the underlying formation mechanisms. Afterwards, recently appreciated representative applications of the microfluidic-mediated NDDS for delivering multiple drugs are systematically summarized. Finally, conclusions and perspectives on further advancing the microfluidic-mediated NDDS toward more powerful and versatile platforms for therapeutic applications are discussed.

In the conventional sequence-to-sequence (seq2seq) model for abstractive summarization, the internal transformation structure of recurrent neural networks (RNNs) is completely determined. Therefore, the learned semantic information is far from enough to represent all semantic details and context dependencies, resulting in a redundant summary and poor consistency. In this paper, we propose a variational neural decoder text summarization model (VND). The model introduces a series of implicit variables by combining variational RNN and variational autoencoder, which is used to capture complex semantic representation at each step of decoding. It includes a standard RNN layer and a variational RNN layer [5]. These two network layers respectively generate a deterministic hidden state and a random hidden state. We use these two RNN layers to establish the dependence between implicit variables between adjacent time steps. In this way, the model structure can better capture the complex semantics and the strong dependence between the adjacent time steps when outputting the summary, thereby improving the performance of generating the summary. The experimental results show that, on the text summary LCSTS and English Gigaword dataset, our model has a significant improvement over the baseline model.

Sequential visual task usually requires to pay attention to its current interested object conditional on its previous observations. Different from popular soft attention mechanism, we propose a new attention framework by introducing a novel conditional global feature which represents the weak feature descriptor of the current focused object. Specifically, for a standard CNN (Convolutional Neural Network) pipeline, the convolutional layers with different receptive fields are used to produce the attention maps by measuring how the convolutional features align to the conditional global feature . The conditional global feature can be generated by different recurrent structure according to different visual tasks, such as a simple recurrent neural network for multiple objects recognition, or a moderate complex language model for image captioning and weakly supervised multiple objects segmentation. Experiments show that our proposed conditional attention model achieves the best performance on the SVHN (Street View House Numbers) dataset with / without extra bounding box; for image caption, our attention model generates better scores than the popular soft attention model; and for weakly supervised multiple objects segmentation, by simply describing a sentence for each image, our attention model can segment the salient regions corresponding to the meaningful noun words.