Search

Behavioral decision systems may suffer from poor performance due to the failure in capturing the vibrations of environmental information. To better capture such vibrations and then make more accurate predictions, a parallel deep neural network based on dual fusions including feature and decision is proposed, called DFFD-Net. DFFD-NET is composed of two parts, the feature fusion network and the driving data network. The feature fusion model adopts two different operations, deconvolution and linear weighting, to fuse local features and global features, respectively. Deconvolution is applied between the convolutional layers, while linear weighting is operated among the outputs of SPP and LSTM. To further improve the accuracy of the prediction, the decisions generated from both networks are further weighed to get the final decision. Experimentally, DFFD-NET is implemented in the benchmarks BDDV and TORCS, and the results show that the final performance is benefited from both feature fusion and decision fusion. From the comparison, DFFD-NET can get state-of-the-art results on both perplexity and precision by only using the images captured from the front-facing camera as well as a few sensing data.

Industry 4.0 places special emphasis on the use of intelligent models to discover patterns in data. In this article, we propose a novel Takagi–Sugeno–Kang (TSK) fuzzy system with low model complexity for multiview data pattern discovery. Compared with the classic TSK fuzzy systems, the proposed one has three merits: First, we introduce a transformation matrix to relax the strict binary label matrix of the training set so that the margins between classes become more discriminative. Second, we introduce two kinds of sparsity regularizations, i.e., cross-rule and cross-view, to reduce indiscriminative fuzzy rules and consequent parameters so that the model complexity is significantly reduced. Third, we introduce the alternating direction method of multipliers to optimize the objective function so that we have compact closed-form solutions in each iteration. Extensive experiments on different kinds of multiview image datasets indicate the promising performance for data pattern discovery with low model complexity.

Infectious diseases pose a serious threat to human life, the Genome Wide Association Studies (GWAS) can analyze susceptibility genes of infectious diseases from the genetic level and carry out targeted prevention and treatment. The susceptibility genes for infectious diseases often act in combination with multiple susceptibility sites; therefore, high-order epistasis detection has become an important means. However, due to intensive computational burden and diversity of disease models, existing methods have drawbacks on low detection power, high computation cost, and preference for some types of disease models. Furthermore, these methods are exposed to repeated query and model inversion attacks in the process of iterative optimization, which may disclose Single Nucleotide Polymorphism (SNP) information associated with individual privacy. Therefore, in order to solve these problems, this paper proposed a safe harmony search algorithm for high-order gene interaction detection, termed as HS-DP. Firstly, the linear weighting method was used to integrate 5 objective functions to screen out high-order SNP sets with high correlation, including K2-Score, JS divergence, logistic regression, mutual information, and Gini. Then, based on the Differential Privacy (DP) theory, the function disturbance mechanism was introduced to protect the security of individual privacy information associated with the objective function, and we proved the rationality of the disturbance mechanism theoretically. Finally, the practicability and superiority of the algorithm were verified by experiments. Experimental results showed that the algorithm proposed in this paper could improve the detection accuracy to the greatest extent while guaranteeing privacy.

A textile bandwidth-enhanced coupled-mode substrate-integrated cavity antenna with a slot is presented. The original coupled-mode substrate-integrated cavity antenna is of two close resonances for the odd and even coupled modes, and a rectangular slot is added on the top layer to introduce a third resonance. Parameters are optimized to merge the bands of the three resonances to realize a widened −10 dB impedance band to cover the Medical Body Area Network band, 2.45 GHz Industrial Scientific Medical band and Long-Term Evolution Band7. The proposed antenna can operate in a −10 dB impedance band of 2.32–2.69 GHz with a 14.9% fractional bandwidth according to the measurements on a fabricated prototype. Simulation and measurement results illustrate the robustness of the proposed textile antenna in the vicinity of the human body and cylindrical bending conditions. In addition, the simulated specific absorption rate of the antenna radiation in the human body is lower than the IEEE and EN limits.

In the skeleton-based human action recognition domain, the spatial-temporal graph convolution networks (ST-GCNs) have made great progress recently. However, they use only one fixed temporal convolution kernel, which is not enough to extract the temporal cues comprehensively. Moreover, simply connecting the spatial graph convolution layer (GCL) and the temporal GCL in series is not the optimal solution. To this end, we propose a novel enhanced spatial and extended temporal graph convolutional network (EE-GCN) in this paper. Three convolution kernels with different sizes are chosen to extract the discriminative temporal features from shorter to longer terms. The corresponding GCLs are then concatenated by a powerful yet efficient one-shot aggregation (OSA) + effective squeeze-excitation (eSE) structure. The OSA module aggregates the features from each layer once to the output, and the eSE module explores the interdependency between the channels of the output. Besides, we propose a new connection paradigm to enhance the spatial features, which expand the serial connection to a combination of serial and parallel connections by adding a spatial GCL in parallel with the temporal GCLs. The proposed method is evaluated on three large scale datasets, and the experimental results show that the performance of our method exceeds previous state-of-the-art methods.

BACKGROUND Medical data mining and sharing is an important process to realize the value of medical big data in E-Health applications. However, medical data contains a large amount of personal private information of patients, there is a risk of privacy disclosure when sharing and mining. Therefore, how to ensure the security of medical big data in the process of publishing, sharing and mining has become the focus of current researches. OBJECTIVE The objective of our study is to design a framework based on differential privacy protection mechanism to ensure the security sharing of medical data. We developed a privacy Protection Query Language (PQL) that can integrate multiple machine mining methods and provide secure sharing functions for medical data. METHODS This paper adopts a modular design method with three sub-modules, including parsing module, mining module and noising module. Each module encapsulates different computing devices, such as composite parser, noise jammer, etc. In the PQL framework, we apply the differential privacy mechanism to the results of the module collaborative calculation to optimize the security of various mining algorithms. These computing devices operate independently, but the mining results depend on their cooperation. RESULTS Designed and developed a query language framework that provides medical data mining, sharing and privacy preserving functions. We theoretically proved the performance of the PQL framework. The experimental results showed that the PQL framework can ensure the security of each mining result, and the average usefulness of the output results is above 97%. CONCLUSIONS We presented a security framework that enables medical data providers to securely share the health data or treatment data, and developed a usable query language based on differential privacy mechanism that enables researchers to mine potential information securely using data mining algorithms. CLINICALTRIAL

Edge computing extends traditional cloud services to the edge of the network, and the highly dynamic and heterogeneous environment at the edge of the network makes the network security situation facing severe challenges. Therefore, it is of great theoretical and practical significance to study and build a high-precision Intrusion Detection Classification Model (IDCM) for network security in the emerging edge computing mode. This paper studies an improved k-dependency Bayesian network (KDBN) structural model that can accurately describe the dependence relationships among system variables and reduce the complexity of the Bayesian network structure by reducing the directed edges of weak dependence. On this basis, this paper constructs an IDCM based on improved KDBN by introducing the maximum a posterior criterion and a virtual augmentation method for samples of small category. The experiments use the KDDCup99 (10%) intrusion detection data set for verification, which show that the IDCM based on improved KDBN has high efficiency, high detection accuracy and high stability, which optimally addresses the issues discussed in many references, such as low detection accuracy and poor stability, for small categories (U2R and R2L) in the KDDCup99 (10%) intrusion detection data set.

Due to the large number of organs and the similar grayscale in abdominal medical images, accurately locating and identifying the liver in an abdominal image is a challenging problem. To improve the accuracies of liver detection and localization, this paper proposes an improved deep network that is combined with edge perception. The network improves the contour-detection accuracy of the liver via an edge-perception fusion module and captures the high-level semantic features of the abdominal image using a multiscale pyramid pooling layer. The complementary characteristics of the edge-related features can effectively preserve the clear boundaries of the liver, while rich global context information can be extracted from the combination of the auxiliary channel output and the pyramid pooling layer output. Many qualitative and quantitative experimental results demonstrate that the proposed model can effectively improve the performance of detection and localization networks, which can narrow the range of regions of interest, and can enhance the accuracy of subsequent segmentation and recognition.

Due to the space inconsistency between benchmark image and segmentation result in many existing semantic segmentation algorithms for abdominal CT images, an improved model based on the basic framework of DeepLab-v3 is proposed, and Pix2pix network is introduced as the generation adversarial model. Our proposed model realizes the segmentation framework combining deep feature with multi-scale semantic feature. In order to improve the generalization ability and training accuracy of the model, this paper proposes a combination of the traditional multi-classification cross-entropy loss function with the content loss function of generator output and the adversarial loss function of discriminator output. A large number of qualitative and quantitative experimental results show that the performance of our proposed semantic segmentation algorithm is better than the existing algorithms, and can improve the segmentation efficiency while ensuring the space consistency of the semantics segmentation for abdominal CT images.

Conventional classification models for epileptic EEG signal recognition need sufficient labeled samples as training dataset. In addition, when training and testing EEG signal samples are collected from different distributions, for example, due to differences in patient groups or acquisition devices, such methods generally cannot perform well. In this paper, a cross-domain classification model with knowledge utilization maximization called CDC-KUM is presented, which takes advantage of the data global structure provided by the labeled samples in the related domain and unlabeled samples in the current domain. Through mapping the data into kernel space, the pairwise constraint regularization term is combined together the predictive differences of the labeled data in the source domain. Meanwhile, the soft clustering regularization term using quadratic weights and Gini-Simpson diversity is applied to exploit the distribution information of unlabeled data in the target domain. Experimental results show that CDC-KUM model outperformed several traditional non-transfer and transfer classification methods for recognition of epileptic EEG signals.

Beamforming algorithm is widely used in many signal processing fields. At present, the typical beamforming algorithm is MVDR (Minimum Variance Distortionless Response). However, the performance of MVDR algorithm relies on the accurate covariance matrix. The MVDR algorithm declines dramatically with the inaccurate covariance matrix. To solve the problem, studying the beamforming array signal model and beamforming MVDR algorithm, we improve MVDR algorithm based on estimated diagonal loading for beamforming. MVDR optimization model based on diagonal loading compensation is established and the interval of the diagonal loading compensation value is deduced on the basis of the matrix theory. The optimal diagonal loading value in the interval is also determined through the experimental method. The experimental results show that the algorithm compared with existing algorithms is practical and effective.

By igniting in the coal seam and injecting gas agent, underground coal gasification (UCG) causes coal to undergo thermochemical reactions in situ and, thus, to be gasified into syngas for power generation, hydrogen production, and storage. Compared with traditional mining technology, UCG has the potential sustainable advantages in energy, environment, and the economy. The paper reviewed the development of UCG projects around the world and points out that UCG faces difficulties in the field of monitoring and control in UCG. It is expounded for the current research status of monitoring and control in UCG, and clarified that monitoring and control in UCG is not perfect, remaining in the stage of exploration. To improve the problem of low coal gasification rate and gas production, and then to make full use of the potential sustainable advantages, the paper offers a perception platform of a UCG monitoring system based on the Internet-of-Things (IoT) and an optimal control model for UCG based on deep learning, and has an outlook on breakthrough directions of the key technologies related to the package structure design for moisture-proof and thermal insulation, antenna design, the strategy for energy management optimization, feature extraction and classification design for the network model, network structure design, network learning augmentation, and the control of the network model, respectively.

In solving the partial Fourier Multiple Measurement Vectors (FMMV) problem, existing greedy pursuit algorithms such as Simultaneous Orthogonal Matching Pursuit (SOMP), Simultaneous Subspace Pursuit (SSP), Hybrid Matching Pursuit (HMP), and Forward-Backward Pursuit (FBP) suffer from low recovery ability or need sparsity as a prior information. This paper combines SOMP and FBP to propose a Hybrid Orthogonal Forward-Backward Pursuit (HOFBP) algorithm. As an iterative algorithm, each iteration of HOFBP consists of two stages. In the first stage, α indices selected by SOMP are added to the support set. In the second stage, the support set is shrank by removing β indices. The choice of α and β is critical to the performance of this algorithm. The simulation results showed that, by using proper parameters, HOFBP has better performance than other greedy pursuit algorithms at the expense of more computing time in some cases. HOFBP does not need sparsity as a prior knowledge.

Distributed Compressed Sensing (DCS) is an important research area of compressed sensing (CS). This paper aims at solving the Distributed Compressed Sensing (DCS) problem based on mixed support model. In solving this problem, the previous proposed greedy pursuit algorithms easily fall into suboptimal solutions. In this paper, an intelligent grey wolf optimizer (GWO) algorithm called DCS-GWO is proposed by combining GWO and q-thresholding algorithm. In DCS-GWO, the grey wolves’ positions are initialized by using the q-thresholding algorithm and updated by using the idea of GWO. Inheriting the global search ability of GWO, DCS-GWO is efficient in finding global optimum solution. The simulation results illustrate that DCS-GWO has better recovery performance than previous greedy pursuit algorithms at the expense of computational complexity.