Search

Due to that multivariate time series, multistep forecasting technology has a guiding role in many fields, such as electricity consumption, traffic flow detection, and stock price prediction, many approaches have been proposed, seeking to realize accurate prediction based on historical data. However, multivariate time series in real-world applications often contain complex and non-linear interdependencies between time steps and series, for which traditional approaches that just model dependencies in time dimension may fail to make forecasting accurately. In addition, the traditional cyclic multistep prediction strategy leads to error accumulation and consequently results in the reduction of prediction performance. To address these limitations, we propose a novel Deep Multivariate Time Series Multistep Forecasting Network based on the Encoder-Decoder model, abbreviated as DualMNet. DualMNet uses the temporal patterns module to capture long-term patterns between time steps, and, simultaneously, employs the spatial patterns module to discover the interdependencies between time series. Furthermore, the decoder utilizes the historical data of the target sequence to predict the long time-series sequences at the final forward operation, significantly ameliorating the issue of error accumulation. Finally, the conducted t-test results, based upon the extensive experimental results on the three benchmark multivariate time series datasets, they demonstrate that the multistep predictive performance of DualMNet is significantly superior to those of the comparison models, and the ablation study shows that integrating all the components of DualMNet together results in robust forecasting performance. [ABSTRACT FROM AUTHOR]

Recently, many outstanding techniques for Time series forecasting (TSF) have been proposed. These techniques depend on necessary and sufficient data samples, which is the key to train a good predictor. Thus, an Active learning (AL) algorithmic framework based on Support vector regression (SVR) is designed for TSF, with the goal to choose the most valuable samples and reduce the complexity of the training set. To evaluate the quality of samples comprehensively, multiple essential criteria, such as informativeness, representativeness and diversity, are considered in a two clustering-based consecutive stages procedure. In addition, considering the imbalance of time series data, a range of values might be seriously under-represented but extremely important to the user. Thus, it is unreasonable to assign the same prediction cost to each sample. To address this imbalance problem, a multiple criteria cost-sensitive active learning algorithm in the virtue of weight SVR architecture, abbreviated as MAW-SVR, ad hoc for imbalanced TSF, is proposed. By introducing the cost-sensitive scheme, each sample is endowed with a penalty weight, which can be dynamically updated in the AL procedure. The experimental comparisons between MAW-SVR and the other six AL algorithms on a total of thirty time series datasets verify the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

With the rapid development of deep learning, in recent years, many excellent deep learning models have been developed to solve the problem of video frame prediction. Among them, most models directly generate predicted target frames. However, the predicted frames obtained in this way are often fuzzy and not realistic enough. In order to solve this problem, this paper first attempts to integrate the attention mechanism with Convolutional Long Short-Term Memory, and correspondingly proposes a new deep learning model, abbreviated as AttConvLSTM. One prominent and original characteristic of this newly constructed model is that, each of its layer calculates the attention weight of the obtained information, focusing on the information key part. Although the proposed AttConvLSTM model effectively improves the prediction accuracy, it still does not solve the problem that the prediction frames directly generated by classical deep learning models are often fuzzy and not realistic. Therefore, inspired by the concept of optical flow, this work further develops a novel Deep Pixel Restoration AttConvLSTM (DPRAConvLSTM) model. This model cleverly uses the input frames and the end-to-end characteristics of deep learning. We innovatively restore the pixels of the input frames to the predicted frames, thereby avoiding the defects that typical deep learning models can easily cause, when directly generating the predicted frames. The experimental results effectively confirm that the finally formed DPRAConvLSTM model can not only improve the accuracy of prediction, but also obtain clearer and more realistic prediction frames. [ABSTRACT FROM AUTHOR]

Graph clustering, a basic problem in machine learning and artificial intelligence, facilitates a variety of real-world applications. How to perform a task of graph clustering, with a relatively high-quality optimization decision and an effective yet efficient way to use graph information, to obtain a more excellent assignment for discrete points is not an ordinary challenge that troubles scholars. Often, many preeminent works on graph clustering neglect an essential element that the defined clustering loss may destroy the feature space. This is also a vital factor that leads to unrepresentative nonsense features that generate poor partitioning decisions. Here, we propose an end-to-end variational graph clustering (EVGC) algorithm focusing on preserving the original information of the graph. Specifically, the KL loss with an auxiliary distribution serves as a specific guide to manipulate the embedding space, and consequently disperse data points. A graph auto-encoder plays a propulsive role in maximumly retaining the local structure of the generative distribution of the graph. And each node is represented as a Gaussian distribution in dealing with separating the true embedding position and uncertainty from the graph. Experimental results reveal the importance of preserving local structure, and our EVGC system outperforms state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

In this work, an Incremental Learning Algorithm via Dynamically Weighting Ensemble Learning (DWE-IL) is proposed to solve the problem of Non-Stationary Time Series Prediction (NS-TSP). The basic principle of DWE-IL is to track real-time data changes by dynamically establishing and maintaining a knowledge base composed of multiple basic models. It trains the base model for each non-stationary time series subset, and finally combine each base model with dynamically weighting rules. The emphasis of the DWE-IL algorithm lies in the update of data weights and base model weights and the training of the base model. Finally, the experimental results of the DWE-IL algorithm on six non-stationary time series datasets are presented and compared with those of several other excellent algorithms. It can be concluded from the experimental results that the DWE-IL algorithm provides a good solution to the challenges of the NS-TSP tasks and has significantly superior performance over other comparative algorithms. [ABSTRACT FROM AUTHOR]

Time series prediction (TSP) is a process of using data collected at different times in the past for statistical analysis, so as to speculate on the trend of things, where the non-stationary and non-linear characteristics of data portray a hard setting for predictive tasks. Obviously, there will be no single model that could perform the best for all TSP issues. Dynamic Ensemble Selection (DES) technique achieves more accurate and robust performance than a single model, due to that it aims to select an ensemble of the most competent models in a dynamic fashion according to each test sample. A variety of DES approaches have been proposed to address pattern classification problems, but little work has been conducted on the research of TSP adopting the DES paradigm. Commonly, the DES approaches work by the definition of a single criterion to evaluate the capability of base classifiers. However, only one criterion is often inadequate for the comprehensive evaluation of classifier power. Thus, in this paper, a multiple criteria Dynamic Ensemble Pruning (DEP) technique exploiting meta-learning ad-hoc for TSP, termed DEP-TSPmeta, based on the inspiration from a state-of-the-art META-DES framework specifically presented for classification tasks, is developed. Within DEP-TSPmeta, Extreme Learning Machines (ELMs) and Hierarchical Extreme Learning Machines (H-ELMs) are integrated as the base models, and four distinct meta-attributes collections, i.e., hard prediction, local accuracy, global accuracy, and prediction confidence, are presented. Each set of meta-attributes corresponds to a specific assessment criterion, i.e., the prediction accuracy in local area of the eigenspace, the overall local accuracy, the prediction accuracy in global area of the decision space, and the confidence level of predictor. A desirable meta-predictor, obtained by training on the strength of these meta-attributes, is the key to deciding whether a base predictor is capable of predicting the unseen instance well or not. Those incapable base predictors determined by the meta-predictor will be pruned and the capable predictors will be expanded into the final dynamic ensemble system. The size of the sets of meta-attributes is specified dynamically by genetic algorithm for different time series benchmark datasets. Empirical results on eight benchmark datasets with different time granularities have verified that, the proposed DEP-TSPmeta algorithm possesses dramatically improved prediction performance at different granularities, when compared against three other DES approaches and four static selective ensemble learning methods. [ABSTRACT FROM AUTHOR]

In Time Series Forecasting (TSF), researchers usually assume that there is enough training data can be obtained, with the old a'nd new data satisfying the same distribution. However, time series data always produces some time-varying characteristics over time, which will lead to relatively large differences between old and new data. As we all know, single-source TSF Transfer Learning (TL) faces the problem of negative transfer. Addressing this issue, this paper proposes a new Multi-Source TL algorithm, abbreviated as the MultiSrcTL algorithm, and a novel Active Multi-Source Transfer Learning, abbreviated as the AcMultiSrcTL algorithm, with the latter one integrating Multi-Source TL with Active Learning (AL), and taking the former one as its sub-algorithm. We introduce domain adaptation theory into this work, and analyze the expected target risk of TSF under the multi-source setting, accordingly. For the development of MultiSrcTL, we make full use of source similarity and domain dependability, using the Maximum Mean Discrepancy statistical indicator to measure the similarity between domains, so as to promote better transfer. A domain relation matrix is constructed to describe the relationship between source domains, so that the source-source and source-target relations are adequately considered. In the design of AcMultiSrcTL, Kullback-Leibler divergence is used to measure the similarity of related indicators to select the appropriate source domain. The uncertainty sampling method and the distribution match weighting technique are integrated, obtaining a new sample selection scheme. The empirical results on six benchmark datasets demonstrate the applicability and effectiveness of the two proposed algorithms for multi-source TSF TL. [ABSTRACT FROM AUTHOR]

In unsupervised transfer learning, it is extremely valuable to effectively extract knowledge from the vast amount of untagged data that exists by utilizing tagged data from other similar databases. In general, the data in the real world often resides in the low-dimensional manifold embedded in the high-dimensional environment space. However, the current subspace transfer learning methods do not consider the nonlinear geometry structure inside the data, so the local similarity information between the data may be lost in the learning process. In order to improve this respect, we propose a new subspace transfer learning algorithm, namely Laplacian Regularized Low-Rank Sparse Representation Transfer Learning (LRLRSR-TL). After introducing the low-rank representation and sparse constraints, the method incorporates Laplacian regularization term to represent the global low-dimensional structure and capture the inherent nonlinear geometry information of the data. Experimental investigation conducted based on five different cross-domain visual image datasets shows that the proposed method has outstanding performance compared with several state-of-the-art transfer learning methods. [ABSTRACT FROM AUTHOR]

Ensemble pruning can effectively overcome several shortcomings of the classical ensemble learning paradigm, such as the relatively high time and space complexity. However, each predictor has its own unique ability. One predictor may not perform well on some samples, but it will perform very well on other samples. Blindly underestimating the power of specific predictors is unreasonable. Choosing the best predictor set for each query sample is exactly what dynamic ensemble pruning techniques address. This paper proposes a hybrid Time Series Prediction (TSP) algorithm to implement one-step-ahead prediction task, integrating Dynamic Ensemble Pruning (DEP), Incremental Learning (IL), and Kernel Density Estimation (KDE), abbreviated as the EnsPKDE&IncLKDE algorithm. It dynamically selects proper predictor sets based on the kernel density distribution of all base learners' prediction values. Due to the characteristic of TSP problems that samples arrive in chronological order, the idea of IL is naturally introduced into EnsPKDE&IncLKDE, while DEP is a common technology to address the concept drift issue inherent in IL. The algorithm is divided into three subprocesses: 1) Overproduction, which generates the original ensemble learning system; 2) Dynamic Ensemble Pruning (DEP), achieved by one subalgorithm called EnsPKDE; 3) Incremental Learning (IL), realized by one subalgorithm termed IncLKDE. Benefited from the advantages of integrating Dynamic Ensemble Pruning scheme, Incremental Learning paradigm and Kernel Density Estimation, in the experimental results, EnsPKDE&IncLKDE demonstrates superior prediction performance to several other state-of-the-art algorithms in fulfilling time series forecasting tasks. [ABSTRACT FROM AUTHOR]

Extreme learning machine (ELM) and its variants have been widely used in the field of object recognition and other complex classification tasks. Traditional deep learning architectures like Convolutional Neural Network (CNN) are capable of extracting high-level features, which are the key for the models to make right decisions. However, traditional deep architectures are confronted with solving a tough, non-convex optimization problem, which is a time-consuming process. In this paper, we propose two hierarchical models, i.e., Random Recursive Constrained ELM (R2CELM) and Random Recursive Local- Receptive-Fields-Based ELM (R2ELM-LRF), which are constructed by stacking with CELM or ELM-LRF, respectively. Besides, inspired by the stacking generalization philosophy, random projection and kernelization are incorporated as their constitutive elements. R2CELM and R2ELM-LRF not only fully inherit the merits of ELM, but also take advantage of the superiority of CELM and ELM-LRF in the field of image recognition, respectively. The essence of CELM is to constrain the weight vectors from the input layer to the hidden layer to be consistent with the directions from one class to another class, while ELM-LRF is adept at exploiting the local structures in images through many local receptive fields. In the empirical results, R2CELM and R2ELM-LRF demonstrate their better performance in testing accuracy on the six benchmark image recognition datasets, compared with their basic learners and other state-of-the-art algorithms. Moreover, the proposed two deep ELM models need less training time when compared with traditional Deep Neural Network (DNN) based models. [ABSTRACT FROM AUTHOR]

Noisy and nonstationary real-world time series predictions (TSPs) are challenging tasks. Confronted with these challenging tasks, the predictive power of traditional shallow models is commonly not satisfactory enough. While the research on deep learning (DL) has made milestone breakthrough in recent years, and DL paradigm has gradually become indispensable for accomplishing these complex tasks. In this work, a cascading deep architecture based on weak results (DeepCascade-WR) is established, which possesses deep models' marked capability of feature representation learning based on complex data. In DeepCascade-WR, weak prediction results are defined, innovating the forecasting mode of traditional TSP. The original data will be properly reconstituted with prior knowledge, generating attribute vectors with valid predictive information. DeepCascade-WR possesses online learning ability and effectively avoids the retraining problem, owing to the property of OS-ELM, one base model of DeepCascade-WR. Besides, ELM is exploited as another base model of DeepCascade-WR, therefore, DeepCascade-WR naturally inherits some valuable virtues from ELM, including faster training speed, better generalization ability and the avoidance of being fallen into local optima. Ultimately, in the empirical results, DeepCascade-WR demonstrates its superior predictive performance on five benchmark financial datasets, i.e., ^DJI, ^GSK, ^HSI, JOUT, and S&P 500 Index, compared with its base learners and other state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

In this paper, we investigate a class of nonlinear fractional differential equations with integral boundary condition. By means of Krasnosel'skiĭ fixed point theorem and contraction mapping principle we prove the existence and uniqueness of solutions for a nonlinear system. By means of Bielecki-type metric and the Banach fixed point theorem we investigate the Ulam–Hyers and Ulam–Hyers–Rassias stability of nonlinear fractional differential equations. Besides, we discuss an example for illustration of the main work. [ABSTRACT FROM AUTHOR]

Based on support vector machine (SVM), incremental SVM was proposed, which has a strong ability to deal with various classification and regression problems. Incremental SVM and incremental learning paradigm are good at handling streaming data, and consequently, they are well suited for solving time series prediction (TSP) problems. In this paper, incremental learning paradigm is combined with incremental SVM, establishing a novel algorithm for TSP, which is the reason why the proposed algorithm is termed double incremental learning (DIL) algorithm. In DIL algorithm, incremental SVM is utilized as the base learner, while incremental learning is implemented by combining the existing base models with the ones generated on the new data. A novel weight update rule is proposed in DIL algorithm, being used to update the weights of the samples in each iteration. Furthermore, a classical method of integrating base models is employed in DIL. Benefited from the advantages of both incremental SVM and incremental learning, the DIL algorithm achieves desirable prediction effect for TSP. Experimental results on six benchmark TSP datasets verify that DIL possesses preferable predictive performance compared with other existing excellent algorithms. [ABSTRACT FROM AUTHOR]

The goal to improve prediction accuracy and robustness of predictive models is quite important for time series prediction (TSP). Multi-model predictions ensemble exhibits favorable capability to enhance forecasting precision. Nevertheless, a static ensemble system does not always function well for all the circumstances. This work proposes six novel dynamic ensemble selection (DES) algorithms for TSP, including one DES algorithm based on Predictor Accuracy over Local Region (DES-PALR), two DES algorithms based on the Consensus of Predictors (DES-CP) and three Dynamic Validation Set determination algorithms. The first dynamic validation set determination algorithm is designed based on the similarity between the Predictive value of the test sample and the Objective values of the training samples. The second one is constructed based on the similarity between the Newly constituted sample for the test sample and All the training samples. Finally, the third one is developed based on the similarity between the Output profile of the test sample and the Output profile of each training sample. These proposed algorithms successfully realize dynamic ensemble selection for TSP. Experimental results on twelve benchmark time series datasets have demonstrated that the proposed DES algorithms greatly improve predictive performance when compared against current state-of-the-art prediction algorithms and the static ensemble selection techniques. [ABSTRACT FROM AUTHOR]

In this paper, a novel dual weights optimization Incremental Learning (w2IL) algorithm is developed to solve Time Series Forecasting (TSF) problem. The w2IL algorithm utilizes IELM as the base learner, while its incremental learning scheme is implemented by employing a newly designed Adaptively Weighted Predictors Aggregation (AdaWPA) subalgorithm to aggregate the existing base predictors with the ones generated upon the new data. There exist two major innovations within w2IL, namely, the well-designed Adaptive Samples Weights Initialization (AdaSWI) and AdaWPA subalgorithms. The AdaSWI subalgorithm initializes the samples' weights adaptively based on the generated base models' prediction errors, and fine-tunes the samples' weights based on the distances from the samples to the clustering centers of base models' training datasets, achieving more appropriate samples weights initialization. While the AdaWPA algorithm adaptively adjusts base predictors' weights based on prediction instances and integrates the base predictors employing these adjusted weights. Besides, the AdaWPA subalgorithm makes use of Fuzzy C-Means (FCM) clustering algorithm for distance measurement, further reducing computational complexity and storage space of the algorithm. The w2IL algorithm constructed in this way possesses significantly superior prediction performance compared with other existing good algorithms, which has been verified through experimental results on six benchmark real-world TSF datasets. [ABSTRACT FROM AUTHOR]

Emotions play an important role in human decision-making process, and consequently, they should be embedded into the reasoning process in our efforts to model human reactions. Adnan Khashman et al. have proposed an emotional backpropagation (EmBP) learning algorithm and have successfully applied it to several practical pattern recognition tasks. However, the design of the emotional input values to the EmBP is not reasonable and may thus cause the failure of its entire implementation. Aimed at improving this weakness, we propose a novel self-organizing map-based emotional neural network (EmSOM) learning algorithm. In contrast to EmBP, the emotional input values of EmSOM are determined based upon its correspondingly associated SOM blocks, and moreover, the network hierarchy has been taken into account in its design, thus improving the deficiencies of EmBP to a certain extent. Furthermore, we incorporate a sparse online SOM (SOR-SOM) algorithm into our emotional neural network learning algorithm and establish a hybrid sparse online relational SOM-based emotional neural network (Em-SOR-SOM) model, so that those advantages of SOR-SOM can be exploited to further boost the recognition performance of the model. The EmSOM and Em-SOR-SOM algorithms have been compared with SBP and EmBP, and several other recent algorithms, and their effectiveness and efficiency have been numerically confirmed by the experiments we presented on the ORL face database and three benchmark credit datasets. [ABSTRACT FROM AUTHOR]

A major assumption in traditional machine leaning is that the training and testing data must be in the same feature space and have the same distribution. However, in many real-world applications, this assumption may not hold. In recent years, transfer learning has emerged as a new learning paradigm to cope with this considerable challenge. It focuses on exploiting previously learnt knowledge by leveraging information from an old source domain to help learning in a new target domain. In this work, we integrate the knowledge-leverage-based Transfer Learning mechanism with a Rank-based Reduce Error ensemble selection approach to fulfill the transfer learning task, called RankRE-TL. Ensemble selection is important for improving both efficiency and predictive accuracy of an ensemble system. It aims to select a proper subset of the whole ensemble, which usually outperforms the whole one. Therefore, we appropriately modify the Reduce Error (RE) pruning technique and design a new Rank-based Reduce Error ensemble selection method (RankRE) to deal with the transfer learning task. The design idea of RankRE is to find the candidate classifier which is expected to improve the classification performance of the extended subensemble the most. In the RankRE-TL algorithm, the initial Support Vector Machine (SVM) ensemble is learnt based upon dynamic training dataset regrouping. And simultaneously, a new construction method of validation set is designed for RankRE-TL, which differs from the method used in conventional ensemble selection paradigm. [ABSTRACT FROM AUTHOR]

This work proposes a novel greedy randomized dynamic ensemble selection (DES) algorithm combined with path-relinking, variable neighborhood search (VNS) and greedy randomized adaptive search procedure (GRASP) algorithms, abbreviated DyPReVNsGraspEnS. Instead of simply selecting the classifiers with the best competence under certain criterions, DyPReVNsGraspEnS makes greedy randomized selection of appropriate classifiers to form the ensemble. It realizes random multi-start search, is capable to easily escape from the local optimums, and possesses a high probability to find the optimal subensemble. It effectively strengthens the link between iterations and solves the problem of no memory by integrating the path-relinking technique. Moreover, the algorithm properly extends the neighborhood with the help of VNS, having a higher competence of global optimization. Most important of all, DyPReVNsGraspEnS is developed based upon the framework of DES paradigm, therefore, it inherits numerous advantages of DES. Empirical investigations are conducted based on twelve benchmark datasets, including six real-world credit/finance datasets and six datasets drawn from other different fields with more than two classes. To clearly articulate the performance of each strategy in the proposed algorithm, experiments for the incorporation of different strategies are implemented separately on all the datasets. The experimental results demonstrate that, in comparison with other classical ensemble learning techniques, DyPReVNsGraspEnS achieves significantly superior generalization performance. And it can not only be used for regions like credit risk assessment, but is applicable to much broader application fields as well. [ABSTRACT FROM AUTHOR]

Metabolic defects are common pathological phenomena following traumatic brain injury (TBI) which contribute to poor prognosis. Brain-derived neurotrophic factor (BDNF) is an important regulator of neuronal survival, development, function, and plasticity. This study was designed to investigate the potential effects of BDNF on TBI-induced metabolic defects and their underlying molecular mechanisms. BDNF was added into cultured neurons to a concentration of 25, 50, and 100 ng/ml, respectively, right after mechanical injury and metabolite levels were analyzed 4 h post injury. The mitochondrial phosphorylated cAMP response element-binding protein (pCREB) distribution and complex V synthesis, as well as their roles in metabolic defects, were evaluated. We found that exogenous BDNF improved metabolic defects, especially the uncoupling of oxidative phosphorylation. BDNF increased pCREB in mitochondrial inner membrane and matrix and promoted mitochondrial complex V synthesis. We also found that these results were negatively regulated by the mitochondrial permeability transition pore (MPTP) antagonist CsA and positively regulated by the MPTP agonist atractyloside. BDNF’s protectional effects on metabolic defects were abolished by CREB knockout. When administrated in a dominant interfering CREB mutant (A-CREB) model, mitochondrial pCREB accumulation could still be observed, but the synthesis of complex V and alleviation of metabolic defects were repressed. Our data demonstrate that exogenous BDNF mitigates neuronal metabolic defects following mechanical injury by promoting the pCREB accumulation in mitochondrial inner membrane and matrix, which is regulated by MPTP opening, thus facilitating the synthesis of mitochondrial complex V. [ABSTRACT FROM AUTHOR]

Deep multi-layered neural networks have nonlinear levels that allow them to represent highly varying nonlinear functions compactly. In this paper, we propose a new deep architecture with enhanced model discrimination ability that we refer to as mlpconv-wise supervised pre-training network in network (MPNIN). The process of information abstraction is facilitated within the receptive fields for MPNIN. The proposed architecture uses the framework of the recently developed NIN structure, which slides a universal approximator, such as a multilayer perceptron with rectifier units, across an image to extract features. However, the random initialization of NIN can produce poor solutions to gradient-based optimization. We use mlpconv-wise supervised pre-training to remedy this defect because this pre-training technique may contribute to overcoming the difficulties of training deep networks by better initializing the weights in all the layers. Moreover, batch normalization is applied to reduce internal covariate shift by pre-conditioning the model. Empirical investigations are conducted on the Mixed National Institute of Standards and Technology (MNIST), the Canadian Institute for Advanced Research (CIFAR-10), CIFAR-100, the Street View House Numbers (SVHN), the US Postal (USPS), Columbia University Image Library (COIL20), COIL100 and Olivetti Research Ltd (ORL) datasets, and the results verify the effectiveness of the proposed MPNIN architecture. [ABSTRACT FROM AUTHOR]

In this paper, we analyze the boundary value problem of a class of multi-order fractional differential equations involving the standard Caputo fractional derivative with the general periodic boundary conditions: where $L(D)=\sum^{n}_{i=0}a_{i}D^{S_{i}}$ , $1\leq S_{0}<\cdots

This paper describes the development of an effective and efficient Hierarchical and Parallel Branch-and-Bound Ensemble Selection (H&PB&BEnS) algorithm. Using the proposed H&PB&BEnS, ensemble selection is accomplished in a divisional, parallel, and hierarchical way. H&PB&BEnS uses the superior performance of the Branch-and-Bound (B&B) algorithm in relation to small-scale combinational optimization problems, whilst also managing to avoid 'the curse of dimensionality' that can result from the direct application of B&B to ensemble selection problems. The B&B algorithm is used to select each partitioned subensemble, which enhances the predictive accuracy of each pruned subsolution, and then the working mechanism of H&PB&BEnS improves the diversity of the ensemble selection results. H&PB&BEnS realizes layer-wise refinement of the selected ensemble solutions, which enables the classification performance of the selected ensembles to be improved in a layer-by-layer manner. Empirical investigations are conducted using five benchmark classification datasets, and the results verify the effectiveness and efficiency of the proposed H&PB&BEnS algorithm. [ABSTRACT FROM AUTHOR]

Extreme learning machine (ELM) has several interesting and significant features. In this paper, a novel pruned Stacking ELMs (PS-ELMs) algorithm for time series prediction (TSP) is proposed. It employs ELM as the level-0 algorithm to train several models for Stacking. And our previously proposed reduce-error pruning for TSP (ReTSP)-Trend pruning technique is used to solve the problem that the level-0 learners might make many correlated error predictions. ReTSP-Trend refers to an evaluation measure for reduce-error pruning for TSP (ReTSP), which takes into account the time series trend and the forecasting error direction. What's more, ELM and simple averaging are used to generate the level-1 model. With the development of PS-ELMs, firstly, those essential advantages of ELM will be naturally inherited. Secondly, those specific defects of ELM are ameliorated to some extent, with the help of ensemble pruning paradigm. Thirdly, ensemble pruning is employed to raise the robustness and accuracy of time series forecasting, making up for the shortages of the existing research. Fourthly, our previously proposed pruning measure ReTSP-Trend is employed in PS-ELMs, which indeed guarantees that the remaining predictor which supplements the subensemble the most will be selected. And finally, the development of PS-ELMs will promote our investigation to the popular ensemble technique of Stacked Generalization. The experimental results on four benchmark financial time series datasets verified the validity of the proposed PS-ELMs algorithm. [ABSTRACT FROM AUTHOR]

Although ordering-based pruning algorithms possess relatively high efficiency, there remains room for further improvement. To this end, this paper describes the combination of a dynamic programming technique with the ensemble-pruning problem. We incorporate dynamic programming into the classical ordering-based ensemble-pruning algorithm with complementariness measure (ComEP), and, with the help of two auxiliary tables, propose a reasonably efficient dynamic form, which we refer to as ComDPEP. To examine the performance of the proposed algorithm, we conduct a series of simulations on four benchmark classification datasets. The experimental results demonstrate the significantly higher efficiency of ComDPEP over the classic ComEP algorithm. The proposed ComDPEP algorithm also outperforms two other state-of-the-art ordering-based ensemble-pruning algorithms, which use uncertainty weighted accuracy and reduce-error pruning, respectively, as their measures. It is noteworthy that, the effectiveness of ComDPEP is just the same with that of the classical ComEP algorithm. [ABSTRACT FROM AUTHOR]

In this work, we investigate the existence and uniqueness of the solutions for a class of nonlinear fractional differential equations with nonlocal integral boundary conditions. Our analysis relies on the fixed point index theory and a $u_{0}$-positive operator. Examples are discussed for the illustration of the main work. [ABSTRACT FROM AUTHOR]

The greedy randomized adaptive search procedure (GRASP) is an iterative two-phase multi-start metaheuristic procedure for a combination optimization problem, while path relinking is an intensification procedure applied to the solutions generated by GRASP. In this paper, a hybrid ensemble selection algorithm incorporating GRASP with path relinking (PRelinkGraspEnS) is proposed for credit scoring. The base learner of the proposed method is an extreme learning machine (ELM). Bootstrap aggregation (bagging) is used to produce multiple diversified ELMs, while GRASP with path relinking is the approach for ensemble selection. The advantages of the ELM are inherited by the new algorithm, including fast learning speed, good generalization performance, and easy implementation. The PRelinkGraspEnS algorithm is able to escape from local optima and realizes a multi-start search. By incorporating path relinking into GRASP and using it as the ensemble selection method for the PRelinkGraspEnS the proposed algorithm becomes a procedure with a memory and high convergence speed. Three credit datasets are used to verify the efficiency of our proposed PRelinkGraspEnS algorithm. Experimental results demonstrate that PRelinkGraspEnS achieves significantly better generalization performance than the classical directed hill climbing ensemble pruning algorithm, support vector machines, multi-layer perceptrons, and a baseline method, the best single model. The experimental results further illustrate that by decreasing the average time needed to find a good-quality subensemble for the credit scoring problem, GRASP with path relinking outperforms pure GRASP (i.e., without path relinking). [ABSTRACT FROM AUTHOR]

Credit scoring, which is also called credit risk assessment has attracted the attention of many financial institutions and much research has been carried out. In this work, a new Extreme Learning Machines' (ELMs) Ensemble Selection algorithm based on the Greedy Randomized Adaptive Search Procedure (GRASP), referred to as ELMsGraspEnS, is proposed for credit risk assessment of enterprises. On the one hand, the ELM is used as the base learner for ELMsGraspEnS owing to its significant advantages including an extremely fast learning speed, good generalization performance, and avoidance of issues like local minima and overfitting. On the other hand, to ameliorate the local optima problem faced by classical greedy ensemble selection methods, we incorporated GRASP, a meta-heuristic multi-start algorithm for combinatorial optimization problems, into the solution of ensemble selection, and proposed an ensemble selection algorithm based on GRASP (GraspEnS) in our previous work. The GraspEnS algorithm has the following three advantages. (1) By incorporating a random factor, a solution is often able to escape local optima. (2) GraspEnS realizes a multi-start search to some degree. (3) A better performing subensemble can usually be found with GraspEnS. Moreover, not much research on applying ensemble selection approaches to credit scoring has been reported in the literature. In this paper, we integrate the ELM with GraspEnS, and propose a novel ensemble selection algorithm based on GRASP (ELMsGraspEnS). ELMsGraspEnS naturally inherits the inherent advantages of both the ELM and GraspEnS, effectively combining their advantages. The experimental results of applying ELMsGraspEnS to three benchmark real world credit datasets show that in most cases ELMsGraspEnS significantly improves the performance of credit risk assessment compared with several state-of-the-art algorithms. Thus, it can be concluded that ELMsGraspEnS simultaneously exhibits relatively high efficiency and effectiveness. [ABSTRACT FROM AUTHOR]

The mineralogy characterization of dust fall in atmosphere is important in understanding and improving air quality. In this paper, dust fall samples were collected in the suburb of four areas of northwest China during April to May 2012. The size distribution, mineral phase and composition, morphology, and surface charge of dust fall were investigated, respectively, by particle size analyzer, X-ray powder diffraction spectrometer (XRD), scanning electron microscopy (SEM), and zeta potential analyzer. The average volume size of dust fall was from 59.17 to 62.88 μm, and the dust fall in Tuoketuo County of Inner Mongolia Autonomous Region had the finest particles (59.17 μm), while the number percentage of fine particulate matter (<1.0 μm) in dusts was about 88.36 % of total particles. The main minerals of dust fall samples are composed of quartz, calcilte, muscotive, albite, clinochlore, and gypsum. And four dust fall samples had the same main mineral phase. Minerals of surface soil were identified as an important source of atmospheric dust fall. The morphological of the atmospheric dust fall presented irregular square, sphere, agglomerate elongated particles, and granular aggregates. Zeta potentials of four dust fall samples were negative in tested pH range. Moreover, their zeta potentials decreased with increasing pH of the solution. The surface charge of dust fall was strongly affected by the quantity of carbonate minerals (calcite and dolomite) in samples. The simulated zeta potential result of multimineral dusts indicated that the magnitude and tendencies of dust's zeta potential were dominated by the main mineral phase in dust fall. [ABSTRACT FROM AUTHOR]

This paper concerns the boundary value problem of a class of fractional differential equations involving the Riemann-Liouville fractional derivative with nonlocal integral boundary conditions. By using the properties of the Green's function and the monotone iteration technique, one shows the existence of positive solutions and constructs two successively iterative sequences to approximate the solutions, especially numerically simulates the conclusion by an example. [ABSTRACT FROM AUTHOR]

Recent human clinical trials results demonstrated successful treatment for certain genetic forms of cystic fibrosis (CF). To extend treatment opportunities to those afflicted with other genetic forms of CF disease, structural and biophysical characterization of CF transmembrane conductance regulator (CFTR) is urgently needed. In this study, CFTR was modified with various tags, including a His purification tag, the SUMOstar (SUMO*) domain, an extracellular FLAG epitope, and an enhanced green fluorescent protein (EGFP), each alone or in various combinations. Expressed in HEK293 cells, recombinant CFTR proteins underwent complex glycosylation, compartmentalized with the plasma membrane, and exhibited regulated chloride-channel activity with only modest alterations in channel conductance and gating kinetics. Surface CFTR expression level was enhanced by the presence of SUMO* on the N-terminus. Quantitative mass-spectrometric analysis indicated approximately 10 % of the total recombinant CFTR (SUMO*-CFTR-EGFP) localized to the plasma membrane. Trial purification using dodecylmaltoside for membrane protein extraction reproducibly recovered 178 ± 56 μg SUMO*-CFTR-EGFP per billion cells at 80 % purity. Fluorescence size-exclusion chromatography indicated purified CFTR was monodisperse. These findings demonstrate a stable mammalian cell expression system capable of producing human CFTR of sufficient quality and quantity to augment future CF drug discovery efforts, including biophysical and structural studies. [ABSTRACT FROM AUTHOR]

As is well known, the Greedy Ensemble Pruning (GEP) algorithm, also called the Directed Hill Climbing Ensemble Pruning (DHCEP) algorithm, possesses relatively good performance and high speed. However, because the algorithm only explores a relatively small subspace within the whole solution space, it often produces suboptimal solutions of the ensemble pruning problem. Aiming to address this drawback, in this work, we propose a novel Randomized GEP (RandomGEP) algorithm, also called the Randomized DHCEP (RandomDHCEP) algorithm, that effectively enlarges the search space of the classical DHCEP while maintaining the same level of time complexity with the help of a randomization technique. The randomization of the classical DHCEP algorithm achieves a good tradeoff between the effectiveness and efficiency of ensemble pruning. Besides, the RandomDHCEP algorithm naturally inherits the two intrinsic advantages that a randomized algorithm usually possesses. First, in most cases, its running time or space requirements are smaller than well-behaved deterministic ensemble pruning algorithms. Second, it is easy to comprehend and implement. Experimental results on three benchmark classification datasets verify the practicality and effectiveness of the RandomGEP algorithm. [ABSTRACT FROM AUTHOR]

Ensemble selection, which aims to select a proper subset of the original whole ensemble, can be seen as a combinatorial optimization problem, and usually can achieve a pruned ensemble with better performance than the original one. Ensemble selection by greedy methods has drawn a lot of attention, and many greedy ensemble selection algorithms have been proposed, many of which focus on the design of a new evaluation measure or on the study about different search directions. It is well accepted that diversity plays a crucial role in ensemble selection methods. Many evaluation measures based on diversity have been proposed and have achieved a good success. However, most of the existing researches have neglected the substantial local optimal problem of greedy methods, which is just the central issue addressed in this paper, where a new Ensemble Selection (GraspEnS) algorithm based on Greedy Randomized Adaptive Search Procedure (GRASP) is proposed. The typical greedy ensemble selection approach is improved by the random factor incorporated into GraspEnS. Moreover, the GraspEnS algorithm realizes multi-start searching and appropriately expands the search range of the typical greedy approaches. Experimental results demonstrate that the newly devised GraspEnS algorithm is able to achieve a final pruned subensemble with comparable or better performance compared with its competitors. [ABSTRACT FROM AUTHOR]

Primary neuroendocrine cancer of the breast (NECB) is an extremely rare tumor. In 2003, the World Health Organization (WHO) recognized this category with three well-described subtypes: small cell, large cell, and carcinoid-like carcinoma; very few peer-review publications based on the WHO definition were encountered in the literature, and we conducted a literature search to investigate the reported incidence, diagnosis, prognosis, hormone receptor status, and treatment options for this rare tumor. Confirming the breast as an origin of neuroendocrine tumor represents a challenge. The diagnosis is mainly dependent on the exclusion of other extra-mammary organs based on clinical, radiological, and pathological data. Except for the very rare type small cell carcinoma, estrogen and progesterone receptors were reported to be expressed in 90 and 83 % of NECB, respectively. It is hypothesized that primary breast neuroendocrine carcinoma differentiates from the epithelial cells during the carcinogenesis process; the prognosis of non-small cell primary NECB seems to improve as the amount of mucinous component increases in the tumor specimen. Management similar to interventions utilized to manage the usual ductal-type carcinoma has been attempted in the past, such as chemotherapy and hormonal therapy; however, due to the rarity of the tumor, none of the published studies are randomized nor do they have a large number of patients. Additionally, none of reports analyzed NECB based on its distinct subtypes. These limitations make recommendations largely based on anecdotal and small observatory studies and call for the need for further research in this extremely rare tumor. [ABSTRACT FROM AUTHOR]

Cryptotanshinone (CPT), a diterpene quinone isolated from Salvia miltiorrhiza, is recently reported to have obvious anticancer activities against diverse cancer cells. However, the effect and regulatory mechanism of CPT remain unclear in human chronic myeloid leukemia (CML) cells. In this study, we investigated the antiproliferative activity of CPT on the multidrug resistant CML cells K562/ADM. Our results demonstrated that CPT decreased the cell viability of K562/ADM cells by inducing cell cycle arrest and apoptosis through suppressing the expression of cyclin D1 and Bcl-2. Further studies indicated that CPT mainly functions at post-transcriptional levels, suggesting the involvement of eukaryotic initiation factor 4E (eIF4E). CPT significantly reduced the expression and activity of eIF4E in K562/ADM cells. Overexpression of eIF4E obvious conferred resistance to the CPT antiproliferation and proapoptotic activity as well as the cyclin D1 and Bcl-2 expressions. Knockdown of eIF4E significantly reduced the inhibitory effect of CPT in K562/ADM, confirming the participation of eIF4E during CPT function process. More importantly, the relative inhibitory efficiency of CPT positively correlated with the reductions on eIF4E in primary CML specimens. These results demonstrated that CPT played antitumor roles in K562/ADM cells by inhibiting the eIF4E regulatory system. Our results provide a novel anticancer mechanism of CPT in human CML cells. [ABSTRACT FROM AUTHOR]

Background: Antitubulin agents exhibit antiangiogenic effects in vitro and in vivo. We evaluated the safety and feasibility of administering a metronomic schedule of oral vinorelbine designed to optimize its antiangiogenic effects. Methods: Patient with advanced cancer who had progressive disease after standard therapy received oral vinorelbine 3 times weekly (i.e., Monday, Wednesday, Friday) at the 6 dose levels ranging from 20 mg (1 week on, 1 week off) to 50 mg (3 weeks on, 1 week off) in cohorts of 3-6 patients at each dose level using a standard phase I design. Dose-limiting toxicity (DLT) during cycle 1 included: (1) neutrophil nadir < 500/μL attributed to therapy, (2) platelet nadir < 50,000/μL attributed to therapy, (3) grade 3-4 non-hematologic toxicity attributed to therapy, and (4) neutropenia associated with grade 2 fever (i.e., febrile neutropenia). Results: Nineteen patients received 50 cycles of therapy (range 1-11 cycles) at 6 dose levels. There were no dose-limiting toxic events. There were no consistent changes in serum TIE-2 or VCAM-1 levels, or urinary VEGF. One patient with renal cell carcinoma had stable disease for 9 months, and another patient with metastatic prostate cancer had a 70% decline in serum prostate-specific antigen, which lasted 4 months. Conclusions: Oral vinorelbine may be given using a metronomic schedule, 50 mg thrice weekly for three of 4 weeks, with minimal toxicity in patients with advanced cancer. [ABSTRACT FROM AUTHOR]

The liquid ion exchange method, solid salt melt method and dry-wet circulation method were used to prepare natural porous antimicrobial materials with natural minerals, such as zeolite, spilite, palygorskite and montmorillonite, respectively. Atomic absorption spectrum and X-ray diffraction analysis were carried out to investigate the effects of Ag+, Cu2+ and Zn2+ on antimicrobial abilities of natural porous minerals, and the effect of preparation method on ion exchange capacity of antimicrobial material, respectively. The results show that for the ion exchange capacity, clay mineral is higher than fibrous mineral, i. e. both zeolite and montmorillonite are higher; the antimicrobial ability of material with Ag+ is the best; the exchange capacities of materials with Cu2+ or Zn2+ are all higher, but the antimicrobial ability of Cu2+ is better than that of Zn2+. [ABSTRACT FROM AUTHOR]

Circular back-propagation neural network (CBP) put forward by Sandro Ridella and Stefano Rovetta, a generalized model of multi-layer perceptron (MLP), possesses strong capabilities of generalization and adaptation to unknown inputs. And they can flexibly construct vector quantization (VQ) and radial basis function (RBF) networks under the CBP framework. With the original structure of CBP remaining unchanged, in this Letter a more generalized network model ICBP (Improved Circular Back-Propagation Neural Network) was designed by adding an extensive node with quadratic form to the original CBP inputs and endowing fixed values to the weights between this node and all the hidden nodes. An interesting property of ICBP is that although it has less adaptable weights, it is better in generalization and adaptability than CBP. Moreover, in order to partially solve the problem of local minima, we adopt the method of adding controlled noise to desired outputs. Finally, ithas been proved by experiments that ICBP is better than CBP in the capabilities of forecasting and function approximation. [ABSTRACT FROM AUTHOR]

Phaeosphaeria avenaria, one of the causal agents of stagonospora leaf blotch diseases in cereals, is composed of two subspecies, P. avenaria f. sp. triticea (Pat) and P. avenaria f. sp. avenaria (Paa). The Pat subspecies was grouped into Pat1–Pat3, based on restriction fragment length polymorphism (RFLP) and ribosomal DNA (rDNA) internal transcribed spacer (ITS) sequences in previous studies. Mating-type genes and their potential use in phylogeny and molecular classification were studied by DNA hybridization and PCR amplification. The majority of Pat1 isolates reported to be homothallic and producing sexual reproduction structures on cultural media had only the MAT1-1 gene. Minor sequence variations were found in the conserved region of MAT1-1 gene in Pat1 isolates. However, both mating-type genes, MAT1-1 and MAT1-2, were identified in P. avenaria isolates represented by ATCC12277 from oats (Paa) and the Pat2 isolates from foxtail barley (Hordeum jubatum L.). Cluster analyses based on mating-type gene conserved regions revealed that cereal Phaeosphaeria is not phylogenetically closely related to other ascomycetes, including Mycosphaerella graminicola (anamorph Septoria tritici). The sequence diversity of mating-type genes in Pat and Paa supports our previous phylogenetic relationship and molecular classification based on RFLP fingerprinting and rDNA ITS sequences. [ABSTRACT FROM AUTHOR]