Search

The virtual machine (VM) allocation problem in cloud computing has been widely studied in recent years, and many algorithms have been proposed in the literature. Most of them have been successfully applied to batch processing models such as MapReduce; however, none of them can be applied to streaming workflow well because of the following weaknesses: 1) failure to capture the characteristics of tasks in streaming workflow for the short life cycle of data streams; 2) most algorithms are based on the assumptions that the price of VMs and traffic among data centers (DCs) are static and fixed. In this paper, we propose a streaming workflow allocation algorithm that takes into consideration the characteristics of streaming work and the price diversity among geo-distributed DCs, to further achieve the goal of cost minimization for streaming big data processing. First, we construct an extended streaming workflow graph (ESWG) based on the task semantics of streaming workflow and the price diversity of geo-distributed DCs, and the streaming workflow allocation problem is formulated into mixed integer linear programming based on the ESWG. Second, we propose two heuristic algorithms to reduce the computational space based on task combination and DC combination in order to meet the strict latency requirement. Finally, our experimental results demonstrate significant performance gains with lower total cost and execution time. [ABSTRACT FROM PUBLISHER]

The long-standing Acid Growth Theory of plant cell elongation posits that auxin promotes cell elongation by stimulating cell wall acidification and thus expansin action. To date, the paucity of pertinent genetic materials has precluded thorough analysis of the importance of this concept in roots. The recent isolation of mutants of the model grass species Brachypodium distachyon with dramatically enhanced root cell elongation due to increased cellular auxin levels has allowed us to address this question. We found that the primary transcriptomic effect associated with elevated steady state auxin concentration in elongating root cells is upregulation of cell wall remodeling factors, notably expansins, while plant hormone signaling pathways maintain remarkable homeostasis. These changes are specifically accompanied by reduced cell wall arabinogalactan complexity but not by increased proton excretion. On the contrary, we observed a tendency for decreased rather than increased proton extrusion from root elongation zones with higher cellular auxin levels. Moreover, similar to Brachypodium, root cell elongation is, in general, robustly buffered against external pH fluctuation in Arabidopsis thaliana. However, forced acidification through artificial proton pump activation inhibits root cell elongation. Thus, the interplay between auxin, proton pump activation, and expansin action may be more flexible in roots than in shoots. [ABSTRACT FROM AUTHOR]

Inspired by nature, we combine the easy decoration of polydopamine with the attractive biomimetic silification to develop a facile synthetic route toward raspberry-like nanocomposite particles, and further lead to the superhydrophobic and superoleophilic surfaces by mimicking the lotus leaf surface structures in the usage of these particles. In this approach, monodisperse polystyrene (PS) particles are used as the template particles, and then, follows with a subsequent polydopamine (PDA) coating step through the self-polymerization of dopamine in a weakly alkaline aqueous environment (pH = 8.5). The obtained core–shell PS/PDA particles are used as the active substrates for the biomimetic silification under the ambient conditions, allowing a well-controlled synthesis of raspberry-like PS/SiO 2 nanocomposite particles with a tunable surface roughness. Upon adjusting the concentration of silica precursor, the surface geometry and the coverage degree of silica nanoparticles of PS/PDA composite particles can be easily tailored. The whole procedure is carried out in a mild environment, no intricate instruments or toxic reagents are involved. In addition, these raspberry-like PS/SiO 2 nanocomposite particles self-assemble onto the glass slides driven by capillary force during drying, forming a hierarchical dual-sized rough structure, which is analogous to the surface morphology of lotus leaf in nature. Making full use of this hierarchical surface, superhydrophobic and superoleophilic surfaces can be successfully achieved via a rational surface modification of this lotus leaf-like surface structure. The superhydrophobic performances can be readily adjusted by varying the scale ratio of the micro/nano surface structures. [ABSTRACT FROM AUTHOR]

Deep nonnegative matrix factorization (DMF) is a particularly useful technique for learning data representation in low-dimensional space. To further obtain the complex hidden information and keep the geometrical structures of the high-dimensional data, we propose a novel deep matrix factorization model with the graph regularization (called DGsnMF). For solving the model with multi-variables, we design a forward–backward splitting scheme. After that, the convergence analysis is attached to the proposed algorithm and it is proved to converge to a critical point. Empirical experiments on benchmark datasets show that the proposed method is superior to the compared methods. [ABSTRACT FROM AUTHOR]

Image interpretation algorithms based on deep learning are becoming increasingly important in land cover information acquisition. We propose CSSwin-unet, a network designed for the semantic segmentation of remote sensing images. CSSwin-unet is based on Swin-unet, follows the U-shaped codec structure of U-Net, but utilizes Swin transformer blocks with superior global modelling capabilities to constitute the codec. In addition, we design a parallel branch in the encoder with a context aggregation module (CAM) to enhance contextual information extraction and alleviate the semantic ambiguity problem resulting from occlusion. To address the problem of semantic information mismatch between codecs and improve the model's ability to extract spatial information, we constructed a space extraction module (SEM) in the skip connections, which replaces the direct copying of encoder features in Swin-unet. To reduce information loss during the downsampling process and strengthen the segmentation capacity of the network, we designed a feature shrinkage module (FSM) in the downsampling session. We conducted comprehensive ablation experiments on a dataset we produced ourselves and compared the results with other advanced methods. The test results showed significant improvement, with mIoU, mF1, and OA values improving by 2.83%, 2.47%, and 2.05%, respectively, compared to the second best performing model, Swin-unet. The above results prove the excellent performance of CSSwin-unet. [ABSTRACT FROM AUTHOR]

Semi-supervised multi-view clustering in the subspace has attracted sustained attention. The existing methods often project the samples with the same label into the same point in the low dimensional space. This hard constraint-based method magnifies the dimension reduction error, restricting the subsequent clustering performance. To relax the labeled data during projection, we propose a novel method called label relaxation-based semi-supervised non-negative matrix factorization (LRSNMF). In our method, we first employ the Spearman correlation coefficient to measure the similarity between samples. Based on this, we design a new relaxed non-negative label matrix for better subspace learning, instead of the binary matrix. Also, we derive an updated algorithm based on an alternative iteration rule to solve the proposed model. Finally, the experimental results on three real-world datasets (i.e., MSRC, ORL1, and ORL2) with six evaluation indexes (i.e., accuracy, NMI, purity, F-score, precision, and recall) show the advantages of our LRSNMF, with comparison to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In recent years, the model compression technique is very effective for deep neural network compression. However, many existing model compression methods rely heavily on human experience to explore a compression strategy between network structure, speed, and accuracy, which is usually suboptimal and time-consuming. In this paper, we propose a framework for automatically compressing models through the actor–critic structured deep reinforcement learning (DRL) which interacts with each layer in the neural network, where the actor network determines the compression strategy and the critic network ensures the decision accuracy of the actor network through predicted values, thus improving the compression quality of the network. To enhance the prediction performance of the critic network, we impose the L 1 norm regularizer on the weights of the critic network to obtain a distinct activation output feature on the representation, thus enhancing the prediction accuracy of the critic network. Moreover, to improve the decision performance of the actor network, we impose the L 1 norm regularizer on the weights of the actor network to improve the decision accuracy of the actor network by removing the redundant weights in the actor network. Furthermore, to improve the training efficiency, we use the proximal gradient method to optimize the weights of the actor network and the critic network, which can obtain an effective weight solution and thus improve the compression performance. In the experiment, in MNIST datasets, the proposed method has only a 0.2% loss of accuracy when compressing more than 70% of neurons. Similarly, in CIFAR-10 datasets, the proposed method compresses more than 60% of neurons, with only 7.1% accuracy loss, which is superior to other existing methods. In terms of efficiency, the proposed method also cost the lowest time among the existing methods. [ABSTRACT FROM AUTHOR]

[Display omitted] • Data augmentation based on spectral difference and content difference. • Spectral subtraction based on maximum or minimum values. • Augmentation of all data or training data based on spectral and content differences. • Model construction based on spectral difference and content difference. • Prediction for content of new samples through ensemble averaging. Soil analysis makes for developing precision agriculture and monitoring land quality, while the models available for spectroscopy-based chemometrics are constrained by limited samples from small areas. The paper proposed sample expansion and model construction based on spectral difference and content difference, realizing data augmentation and deep learning applied to original samples with limited numbers. The spectral subtraction based on maximum or minimum values exploited the maximum or minimum values to acquire the spectral difference and content difference, which provided a new data form for model construction. Keeping enhanced samples whose spectral difference and content difference were all zero was useful for improving model performance. Augmentation of all data or training data based on maximum or minimum values-based spectral subtraction, which sorted the contents and made them the maximum or minimum values in sequence, achieved sample expansion by the spectral difference and content difference. The model utilized the random vector functional link (RVFL) network, extreme learning machine (ELM), and one-dimensional convolutional neural network (1D CNN), which could predict the content of new samples through ensemble averaging when predicting content difference. The experimental result showed the model of the spectral subtraction based on maximum or minimum values had a similar performance to that of the original samples. Augmentation of all data improved model performance by only RVFL and ELM. Augmentation of training data verified 1D CNN was better than RVFL and ELM. The paper implements a new data augmentation method and applies CNN to original samples with inadequate numbers, which lays the foundation for an improved model and applying spectral preprocessing. [ABSTRACT FROM AUTHOR]

Semi-supervised multi-view learning methods aim to boost the learning performance by conjunction with labeled data, because the label information can enhance the discriminant ability of the learned model. Recently, non-negative matrix factorization has received widespread attention in semi-supervised multi-view learning due to its powerful ability of feature extraction. However, the problem of very limited available labeled data is seldom considered. In this case, it is hard for existing approaches to obtain satisfied performance. Motivated by that the label propagation can classify a large number of unlabeled data with few labeled data, in this paper, we propose a novel semi-supervised multi-view learning approach to address the problem of sparse labeled data, called Label Propagation based Non-negative Matrix Factorization (LPNMF). In our model, the intrinsic manifold structure of data is constructed by the adaptive neighbors technology. Based on this intrinsic manifold structure, the label propagation is further employed to make full use of the limited labeled data. Besides, we design an efficient alternating algorithm for solving the optimization problem and provide theoretical analysis on its convergence properties and computational complexity. Finally, experiments on four real-world datasets demonstrate the advantage of our proposed methods, with comparison to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Non-negative matrix factorization is widely used in multi-view clustering due to its ability of learning a common dimension-reduced factor. Recently, it is combined with the label information to improve the clustering, but the affection of the dimension-reduction to the classes of the labeled data is seldom considered. Motivated by that the graph constraint can keep the geometric structure of the data, it is employed to restrict the class variation of the data caused by the dimension reduction, and a semi-supervised method called Graph-regularized Partially Shared Non-negative Matrix Factorization (GPSNMF) is proposed for multi-view clustering in this paper. In our method, the affinity graph of each view is constructed to encode the geometric information, and the corresponding multiplication update algorithm based on alternative iteration rule is derived. In the experiments, two clustering approaches are tested based on the results of the proposed GPSNMF, and four real-world databases with different label proportions are performed to demonstrate the advantages of our method over the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

This work aims to propose an event-triggered synchronization adaptive learning scheme for uncertain nonlinear multi-agent systems with communication link faults. In reality, the link faults are ubiquitous and responsible for modeling delays and disturbances in communications and also capturing time-varying communication weights between any two nodes in the network. To address this challenge, based on Lyapunov analysis, adaptive learning neural networks are employed to settle unknown link faults and system uncertainties. To reduce the consumption of communication resources, an event-triggered control strategy is introduced on the input side of the controller, whose triggering events are relative thresholds that can be spontaneously modified with the system states. In addition, a set of smooth functions are inserted in the Lyapunov function that assure the asymptotic stability of the system even with corrupted link faults. Meanwhile, it is rigorously verified that the synchronous tracking errors converge to a user-defined interval. Finally, the effectiveness of the proposed control protocol is demonstrated by a numerical simulation. [ABSTRACT FROM AUTHOR]

[Display omitted] • A method for rapid coal proximate analysis is proposed. • The method combines spectroscopy with deep learning. • A deep learning model named DR_TELM is proposed, which includes dilated convolution, multi-level residual connection and TELM. • The method proposed achieves high precision and fast speed. Proximate analysis of coal is of profound significance for understanding coal quality and promoting rational utilization of coal resources. Traditional coal proximate analysis mainly uses chemical analysis methods, which have the disadvantages of slow speed and high cost. This paper proposed an approach combining reflectance spectroscopy with deep learning (DL) for rapid proximate analysis of coal. First, 80 sets of coal spectral data are enhanced by data augmentation, outlier detection, and dimensional transformation to improve the number and quality of samples. Then, an analytical model combining dilated convolution, multi-level residual connection, and a two-hidden-layer extreme learning machine (TELM), named DR_TELM, was proposed. The model extracted effective features from coal spectral data by a convolutional neural network (CNN) and utilized TELM as a regressor to achieve feature identification and content prediction. The experimental results showed that DR_TELM achieved coefficients of determination (R2) of 0.981, 0.989, 0.990, 0.985, 0.989 and root mean square errors (RMSE) of 0.533, 1.833, 1.111, 1.808, 0.723 for the content prediction of moisture, ash, volatile matter, fixed carbon and higher heating value (HHV), respectively. And while ensuring high accuracy, the test time is only 0.034 s. It is fully demonstrated that DR_TELM can rapidly and accurately analyze coal. [ABSTRACT FROM AUTHOR]

Multi-view clustering (MVC) is an attractive clustering paradigm that can incorporate comprehensive information from multiple views. Among the MVC schemes, collective matrix factorization (CMF) has shown its great power in extracting shared information of multi-view data. Based on CMF, we propose a novel unified MVC framework, named Auto-weighted Collective Matrix Factorization with Graph Dual Regularization (ACMF-GDR). Specifically, we assign adaptive weights for each view and incorporate the smoothing cluster structure learning term to construct a unified auto-weighted CMF for MVC. Our ACMF-GDR model can obtain the cluster labels and common representations of the samples in a one-step manner. Furthermore, to make the common representations discriminative, graph dual regularization terms with orthogonality constraints are adopted on multiple views to preserve the geometrical structure of the decomposed factors simultaneously. Experimental results show the superior clustering performance of the proposed method. [ABSTRACT FROM AUTHOR]

[Display omitted] • A method for rapid and accurate detection of soil organic matter content. • The method is based on reflectance spectroscopy and machine learning. • Quality band combinations are obtained by spectral pre-processing methods. • Genetic strategy is introduced into the model to enhance its exploration capability. • We propose an improved hybrid extreme learning machine model. The continuous exploitation of mining resources and a number of other factors have led to serious soil pollution problems. Soil organic matter (SOM) can be used as an important measure of soil fertility and ecological environment quality in mining areas. The traditional method of measuring SOM content by chemical methods is costly and time-consuming, so it is important to develop a rapid, accurate and economical method to measure SOM content in reclaimed mines for the ecological restoration and the evaluation of the ecological reclamation effect of mines. In this paper, the visible-near infrared spectral data of soil were obtained using an open pit mine as the study area. The three pre-processing methods of multiple scattering correction, continuous removal and Savitzky-Golay smoothing were compared. Then the two-band ratio spectral index RI was constructed to obtain the sensitive band combinations. To address the problem that the HHO-TELM hybrid model tended to converge prematurely, the GHO-TELM model was proposed in this paper. GHO-TELM introduced a gene learning strategy in HHO-TELM. The crossover, mutation and selection mechanisms were used to cultivate high-quality examples, enhance the quality of individuals and prevent premature convergence of the model. GHO-TELM was compared with several machine learning models. The experimental results showed that GHO-TELM obtained the best performance indexes, with correlation coefficient (r) of 0.9586, and relative percentage deviation (RPD) of 3.0823, indicating that the model had a good prediction effect. [ABSTRACT FROM AUTHOR]

[Display omitted] • A method for rapid and accurate detection of cadmium content in saline soils is proposed. • The method is based on visible-near-infrared spectroscopy and machine learning. • We pre-processed the original reflection spectra using fractional order derivatives. • We constructed three-band spectral index by optimal band combination algorithm, and obtained the corresponding optimal band combinations. • We proposed the MSC-ELM model based on the two-hidden-layer extreme learning machine. Heavy metal pollution in saline-alkali land has a significant impact on the ecological environment and human health. Rapid and accurate inversion of cadmium (Cd) element content in the saline-alkali land is important for environmental protection, saline-alkali soil improvement and conversion of saline-alkali land to cultivated land. Using traditional chemical detection methods to detect the content of heavy metal elements requires a long testing time and has the drawback of high prices. In this paper, we select the saline-alkali land of Zhenlai County as the study area and combine visible-NIR spectroscopy with machine learning models to invert the Cd content in the saline-alkali land. We preprocess the original reflection spectra using fractional order derivatives (FOD), then construct six three-band spectral indices (TBIs) and obtain the corresponding optimal band combination parameters by the optimal band combination (OBC) algorithm. To address the shortcomings of two-hidden-layer extreme learning machine (TELM), this paper introduces new weight parameters among the nodes of the first hidden layer, further extends it to multiple layers on this basis, and proposes the MSC-ELM model. The improved model is compared with several models, such as random forest (RF), partial least squares (PLS) and extreme learning machine (ELM). And the model performance is analyzed and compared by introducing several performance indicators, such as root mean square error (RMSE) and the ratio of the performance to interquartile (RPIQ). The experimental results show that the FOD transformation can eliminate the baseline drift and reduce the spectral noise. The constructed TBIs can effectively enhance the correlation with Cd content relative to the original single band, reduce redundant information and enhance the spectral features. The MSC-ELM model achieves better performance metrics compared to the other models and obtains the optimal prediction performance. This study provides an accurate and rapid method for the detection of Cd content in saline soil, which is important for the improvement and ecological recovery of saline soil. [ABSTRACT FROM AUTHOR]