Search

Abstract Neural network models for dynamic systems can be trained either in parallel or in series-parallel configurations. Influenced by early arguments, several papers justify the choice of series-parallel rather than parallel configuration claiming it has a lower computational cost, better stability properties during training and provides more accurate results. Other published results, on the other hand, defend parallel training as being more robust and capable of yielding more accurate long-term predictions. The main contribution of this paper is to present a study comparing both methods under the same unified framework with special attention to three aspects: (i) robustness of the estimation in the presence of noise; (ii) computational cost; and, (iii) convergence. A unifying mathematical framework and simulation studies show situations where each training method provides superior validation results and suggest that parallel training is generally better in more realistic scenarios. An example using measured data seems to reinforce such a claim. Complexity analysis and numerical examples show that both methods have similar computational cost although series-parallel training is more amenable to parallelization. Some informal discussion about stability and convergence properties is presented and explored in the examples. [ABSTRACT FROM AUTHOR]

This paper presents a comprehensive study on clustering: exiting methods and developments made at various times. Clustering is defined as an unsupervised learning where the objects are grouped on the basis of some similarity inherent among them. There are different methods for clustering the objects such as hierarchical, partitional, grid, density based and model based. The approaches used in these methods are discussed with their respective states of art and applicability. The measures of similarity as well as the evaluation criteria, which are the central components of clustering, are also presented in the paper. The applications of clustering in some fields like image segmentation, object and character recognition and data mining are highlighted. [ABSTRACT FROM AUTHOR]

Computational dentistry uses computerized methods and mathematical models for dental image analysis. One of the fundamental problems in computational dentistry is accurate tooth instance segmentation in high-resolution mesh data of intra-oral scans (IOS). This paper presents a new computational model based on deep neural networks, called Mask-MCNet , for end-to-end learning of tooth instance segmentation in 3D point cloud data of IOS. The proposed Mask-MCNet localizes each tooth instance by predicting its 3D bounding box and simultaneously segments the points that belong to each individual tooth instance. The proposed model processes the input raw 3D point cloud in its original spatial resolution without employing a voxelization or down-sampling technique. Such a characteristic preserves the finely detailed context in data like fine curvatures in the border between adjacent teeth and leads to a highly accurate segmentation as required for clinical practice (e.g. orthodontic planning). The experiments show that the Mask-MCNet outperforms state-of-the-art models by achieving 98% Intersection over Union (IoU) score on tooth instance segmentation which is very close to human expert performance. [ABSTRACT FROM AUTHOR]

This paper is concerned with the non-fragile H ∞ state estimation problem for a class of discrete-time networked system with probabilistic diverging disturbance and multiple missing measurements. The measurement missing phenomenon is assumed to occur randomly and the missing probability for each sensor is governed by an individual random variable satisfying a certain probabilistic distribution over the interval [ 0 , 1 ] . The aim of this paper is to estimate the networked system by designing a non-fragile H ∞ estimator such that the augmented estimation error system is asymptotically mean square stable with a prescribed H ∞ disturbance attention level γ . By using the Lyapunov method and stochastic analysis, we derive a sufficient condition for the existence of the desired estimator. By solving the linear matrix inequalities (LMIs), the estimator gain matrix is given. Two numerical examples are employed to demonstrate the effectiveness and applicability of the proposed design technique. [ABSTRACT FROM AUTHOR]

Image set representation and classification is an important problem in computer vision and pattern recognition area. It has been widely used in many computer vision applications. In this paper, a new image set representation and classification method has been proposed. The main contributions of this paper are twofold: (1) a new image set representation model, called attributed covariate-relation graph (ACRG), has been proposed for image set representation and modeling. ACRG aims to represent image set with an attributed graph model which involves both image features and their spatial structure simultaneously. (2) A new graph data based sparse representation and classification method, called Graph Sparse Representation Classification (GSRC) has been proposed to achieve ACRG classification. Experimental results on several datasets demonstrate the benefits of the proposed ACRG representation and GSRC classification. [ABSTRACT FROM AUTHOR]

Rolling bearings are necessary parts in rotary machines. However, the problem of early fault diagnosis for rolling bearings is difficult to solve due to its low signal-to-noise ratio and non-linear and non-stationary signal. Based on a detailed investigation of rolling bearing vibration signals, this paper proposes a method for determining whether a fault occurs by comparing the high-frequency band power. If a fault occurs, we first de-noise the vibration signals using wavelet de-noising and then extract the fault characteristics in both the time domain and the time-frequency domain to avoid the limitations of using only one domain. Finally, the fault location is identified using the grey correlation method. According to the method application results, the recognition accuracy using the method proposed in this paper is satisfactory, proving that the method has superior performance. [ABSTRACT FROM AUTHOR]

In this paper, the problem of adaptive synchronization for time-delay neutral-type multi-slave neural networks with Markovian jumping parameters and stochastic noise is researched. The adaptive synchronization model which contains a drive system and multiple response systems is presented. By using of the generalized It o ^ ’ s formula and the M-matrix method, the sufficient condition is obtained to guarantee that the error control system is stable, and the update law of the feedback controller is designed to ensure that every slave system synchronizes with master system. Finally, a numerical example is given to illustrate the effectiveness of the method and result obtained in this paper. [ABSTRACT FROM AUTHOR]

Thanks to social media platforms, topics are diffused online. The ones which diffuse rapidly and widely are known as viral topics. Predicting the popularity of viral topics is important to online recommendation systems and marketing services. However, the task is still challenging due to the fact that the popularity of viral topics is highly dynamic and little research has been focused on how to predict the popularity accurately for viral topics. This paper first uses data collected from the largest BBS in China to find high correlations for the short-term popularity of viral topics. Based on this finding, this paper then utilizes a time series feature space to capture the behaviors of popularity of viral topics and presents a method for predicting the short-term popularity of a given viral topic by using only data of historical popularity of the topic. This paper demonstrates that our method outperforms a baseline model and one of the most sophisticated methods in the terms of MAPE (mean absolute percentage error) and RAE (relative absolute error). Furthermore, this paper gives out how long the minimum observation period is in order to predict promptly. Finally, this paper uses two cases to show the effectiveness and simplicity of our method. [ABSTRACT FROM AUTHOR]

In this paper, the H ∞ filtering problem is investigated for a class of discrete-time arbitrary switched neural networks with missing measurements, stochastic perturbations, and communication delays. Based on the average dwell time approach and a set of Kronecker delta functions, a unified measurement model is established to represent the phenomena of missing measurements, time delays and nonlinearities. The aim of this paper is to design an H ∞ filter such that the filter error dynamics is exponentially mean-square stable and the H ∞ performance requirement is satisfied simultaneously. By using the Lyapunov stability theory and the matrix technology, the design method of the desired filter is given in terms of a matrix inequality which can be solved by using the available software. Finally, a numerical example is provided to illustrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

With the wide use of consumer electronics and the rapid development of online shopping, more and more ad videos are developed for IDTV and mobile users. However, a huge amount of time spending on the Internet advertising somehow brings users uncomfortable viewing experience rather than effectively generates high consumption of advertised products. Therefore, it is urgent to find a viewer-friendly and advertiser-beneficial solution to launch ads. This paper is the first attempt to improve the effectiveness of advertising through combining online shopping information with an ad video and directing viewers to proper online shopping places. The proposed ActiveAd framework includes four main components. Firstly, an ad video analysis component detects both syntactic and semantic elements from ad videos, e.g. FMPIs (Frame Marked with Production Information), visual concepts, and textual keywords within the ad videos. Our ad video analysis provides a comprehensive solution to extract meaningful elements from ad videos. Secondly, a visual linking by search component is proposed to collect websites which contain similar images as FMPIs. Features used for the visual search are weighted and fused in order to ensure the uniformity of search results. Thirdly, different kinds of tags and product categories extracted from collected websites are aggregated in order to identify the representative text of the product. Finally, query keywords are selected through calculating cosine similarity from two kinds of keywords, i.e. keywords identified from tag aggregation and keywords obtained through ad video analysis (visual concept detection and textual keyword detection). A query vector is generated by selected keywords and used to retrieve product online. In this paper, a powerful cross-media contextual search including visual search, tag aggregation and textual search is achieved with the help of ad video analysis. Experiments demonstrate that our proposed ActiveAd achieves product recommendation effectively and efficiently. [ABSTRACT FROM AUTHOR]

The problem of H ∞ control for a fish population logistic model with the invasion of alien species is studied via a T–S fuzzy control approach in this paper. Firstly, the harvested capability induced by economic factors and purification capability induced by invasion of alien species are analyzed. Secondly, the corresponding bio-economic model is established by taking the above two factors into account. Thirdly, the singularity-induced bifurcation (SIB) and impulsive behavior of the resultant bio-economic model are investigated. After that, a T–S fuzzy system is used to describe the nonlinear system for the bio-economic model with added input disturbance. A sufficient condition is proposed to satisfy H ∞ norm of the system by using the Lyapunov theory and a linear matrix inequality approach. Finally, a modified differential transform method is exploited to present the invasion system to analyze the characters. The application of H ∞ controller according to actual events demonstrates the effectiveness of the method used in this paper. [ABSTRACT FROM AUTHOR]

This paper proposes an online tracking algorithm that employs a confidence combinatorial map model. Drifting is a problem that easily occurs in object tracking and most of the recent tracking algorithms have attempted to solve this problem. In this paper, we propose a confidence combinatorial map that describes the structure of the object, based on which the confidence combinatorial map model is developed. The model associates the relationship between the object in the current frame and that in the previous frame. On the strength of this relationship, more precisely classified samples can be selected and are employed in the model update stage, which directly influences the occurrence of the tracking drift. The proposed algorithm was estimated on several public video sequences and the performance was compared with several state-of-the-art algorithms. The experiments demonstrate that the proposed algorithm outperforms other comparative algorithms and gives a very good performance. [ABSTRACT FROM AUTHOR]

This paper is concerned with the problem of H ∞ fuzzy filtering design with immeasurable premise variables for nonlinear systems presented as T–S model. First, the time derivatives of the membership functions are discussed and some linear matrices inequalities (LMIs) are obtained to bound it. Then, a new non-quadratic Lyapunov function which has the diagonal form is constructed to get some LMIs to design the filtering. In the end, two numerical examples are given to show that better H ∞ performance can be obtained by the method in this paper than others in the literature. [ABSTRACT FROM AUTHOR]

Support vector regression with chaotic sequence and simulated annealing algorithm in previous forecasting research paper has shown its superiority to effectively avoid trapping into a local optimum. However, the proposed chaotic simulated annealing (CSA) algorithm in previous published literature as well as the original SA algorithm could not realize the mechanism of temperature decreasing continuously. In addition, lots of chaotic sequences adopt Logistic mapping function which is distributed at both ends in the interval [0,1], thus, it could not excellently strengthen the chaotic distribution characteristics. To continue exploring any possible improvements of the proposed CSA and chaotic sequence, this paper employs the innovative cloud theory to be hybridized with CSA to overcome the discrete temperature annealing process, and applies the Cat mapping function to ensure the chaotic distribution characteristics. Furthermore, seasonal mechanism is also proposed to well arrange with the cyclic tendency of electric load, caused by economic activities or climate cyclic nature. This investigation eventually presents a load forecasting model which hybridizes the seasonal support vector regression model and chaotic cloud simulated annealing algorithm (namely SSVRCCSA) to receive more accurate forecasting performance. Experimental results indicate that the proposed SSVRCCSA model yields more accurate forecasting results than other alternatives. [ABSTRACT FROM AUTHOR]

The novel method of deception detecting based on speech signal is proposed in this study. Extracting prosodic and non-linear dynamics (NLD) feature sets from speech signal and applying relevance vector machine (RVM) classification method is the primary target of this paper. Here, the sustained speaker-depended phonation samples of deception and non-deception were applied. In this paper, 30 prosodic features and 18 NLD features were selected which show significant correlations to deception state. Moreover, the RVM classification model based on sparse bayesian learning (SBL) was introduced which is a bayesian extension of the support vector machine (SVM) and not be restricted by the Mercer׳s condition. In the experiments, the deception corpus of Soochow University is exploited to test our approach. Firstly, the experiment of feature performance test was carried out. It is demonstrated that the combination of prosodic and NLD features is the most effectively method for detecting deceptive speech. Secondly, the property of RVM classification model is measured. The experiment results show that RVM technology requires much fewer basic functions and demands much less decision time than the SVM algorithm. Furthermore, during the test of correct classification accuracy of RVM, it shows that RVM is much higher than the classical model of SVM and radial basis function neural network (RBFNN). Finally, the robustness test of RVM is processed and received better performance than SVM and RBFNN methods when the signal to noise ratio (SNR) falls. In general, the proposed deception detecting method based on the combined features and RVM classifier is novel, convenient and practical, moreover, it achieves higher classification accuracy, less detection time, property of generalization, and the strong robustness. [ABSTRACT FROM AUTHOR]

As a support vector machine (SVM) has good generalization ability, it has been implemented in various applications. Yet in the process of resolving the mathematical model, it needs to compute the kernel matrix, the dimension of which is equal to the number of data points in the dataset, thereby costing a very high amount of memory. Some improved algorithms are proposed to extract the boundary of the dataset so that the number of data points participating in the training process decreases and the training process can be accelerated. But the prediction accuracy of most of these algorithms is so low that many support vectors are discarded. Moreover, those methods all need to perform the main computation by the kernel function in linear feature space, which increases the computational cost. In this paper, the concept “relative density” is proposed to extract the subset containing support vectors. The measure “relative density” is designed to be more meticulous so that the new method performs more precisely than existing methods. The proposed method makes use of the fact that it has good local characteristics to perform the computations in original space without having to use any kernel function. Therefore, efficiency is also improved. Furthermore, the proposed method can be used to detect noise data, by which an inseparable problem can be transformed into a separable problem so that cross validation can be avoided in various SVM algorithms. This is an advantage that none of the existing SVM methods has. Yet another advantage of this method is that it can be considered as a framework to be used in various SVM methods. This paper presents the details of the proposed accelerated algorithm, having a time complexity of O( n log n ), that decreases training time significantly without decreasing prediction accuracy. The effectiveness and efficiency of the method is demonstrated through experiments on artificial and public datasets. [ABSTRACT FROM AUTHOR]

This paper provides a simple forecasting framework for nonlinear and non-stationary time series using Wavelet based nonlinear models. The proposed method exploits the ability of wavelets to detect non-stationarities that may be present in a given time series in combination with higher order nonlinear Volterra Models. The utility of the proposed model is verified using two examples: the first based on a synthetically generated times series with nonlinear and non stationary features; the second case study examined in the paper pertains to forecasting of number of pilgrims visiting the well known religious shrine at Katra in the state of Jammu and Kashmir in India. Further, the proposed model was applied to 3 time series from M3 competition. The results show that the proposed models perform better when compared with the performance of some well known benchmark models. The long term predictive capability of the wavelet based nonlinear models has also been studied separately. [ABSTRACT FROM AUTHOR]

This paper focuses on a new kind of artificial neural networks – the Laplace transform artificial neural networks (LTANN). It is proposed to use the Laplace transform instead of ordinary weights and a linear activation function of an artificial neuron. This extension allows to use artificial neural networks in new areas. The ordinary description of artificial neural networks is a special case of the description proposed in this paper. Three models of different geological structures based on the LTANN are discussed in this paper. Using these models, it is possible to classify an unknown geological structure as the structure without anomaly, the structure with a sinkhole or the structure with a loose zone. [ABSTRACT FROM AUTHOR]

Abstract: An artificial neural network (ANN) is a powerful mathematical framework used to either model complex relationships between inputs and outputs or find patterns in data. It is based on an interconnected group of artificial neurons, and it employs a connectionist approach to computation when processing information. ANNs have been successfully used for a great variety of applications, such as decision making, quantum chemistry, radar systems, face identification, gesture recognition, handwritten text recognition, medical diagnosis, financial applications, robotics, data mining, and e-spam filtering. In the speech community, neural architectures have been used since the beginning of the 1980s, and ANNs have been proven useful to accomplish several speech processing tasks, e.g., to extract linguistically motivated features, to perform speech detection, and to generate local scores to be used for different goals. In recent years, there has been a renewed interest in the use of ANNs for speech applications due to a major advance made in pre-training the weights in deep neural networks (DNNs). It seems that a new trend to move the speech technology forward through the use of NNs has begun, and it can therefore be instructive to review key ANN applications to automatic speech processing. In this paper, several ANN-based applications for speech processing will be presented, ranging from speech attribute extraction to phoneme estimation and/or classification. Furthermore, it will be shown that ANNs play a key role in several important speech applications, such as large vocabulary continuous speech recognition (LVCSR) and automatic language recognition. The goal of the paper is to summarize chief ANN approaches to speech processing using the experience gathered in the last seven years in our laboratories. [Copyright &y& Elsevier]

Abstract: Similarity measure plays an important role in many image processing fields. This paper introduces the medium mathematic systems, and establishes a novel image medium similarity measure between two pixels and that of between two image sets based on the measure of medium truth degree. Moreover, an image edge detection algorithm, an image matching algorithm and an image medium fidelity measure method governed by the medium similarity measure are discussed in this paper. Experimental results show that the proposed similarity measure is effective. [Copyright &y& Elsevier]

In this paper, the global dissipativity and exponential state estimation for quaternion-valued memristive neural networks are investigated. By starting from basic quaternion properties, several algebraic conditions ensuring the global dissipativity and state estimation problems are derived. It is noteworthy that, based on the vector ordering approach, one can compare the "magnitude" of two different quaternion-valued, and thus the closed convex hull derived by two different quaternion-valued connections can be derived. Simulation results are given to show the validate of the mathematical model and the derived conclusions of the memristive system. [ABSTRACT FROM AUTHOR]

This paper is concerned with an improved event-triggered control for a class of networked control systems (NCSs) under stochastic cyber-attacks with limited communication bandwidths. In order to reduce the unnecessary data transmissions, an adaptive event-triggered approach is employed to locally determine the sensor measurements whether to be transmitted or not, where the triggering thresholds can take much real-time information on the NCSs into consideration, such as the triggering error, last transmitted signal, and current sampled one. It is assumed that the network transmissions may be attacked by two types of randomly occurring cyber-attacks, then a novel mathematical model is achieved and three sufficient conditions are derived to guarantee the asymptotical stability of the closed-loop system. Especially, two augmented Lyapunov-Krasovskii functionals (LKFs) are constructed and an improved reciprocal convex technique is proposed to reduce the conservatism. Finally, two numerical examples are presented to show the effectiveness of the obtained results. [ABSTRACT FROM AUTHOR]

Abstract: In this paper we present the Tree Echo State Network (TreeESN) model, generalizing the paradigm of Reservoir Computing to tree structured data. TreeESNs exploit an untrained generalized recursive reservoir, exhibiting extreme efficiency for learning in structured domains. In addition, we highlight through the paper other characteristics of the approach: First, we discuss the Markovian characterization of reservoir dynamics, extended to the case of tree domains, that is implied by the contractive setting of the TreeESN state transition function. Second, we study two types of state mapping functions to map the tree structured state of TreeESN into a fixed-size feature representation for classification or regression tasks. The critical role of the relation between the choice of the state mapping function and the Markovian characterization of the task is analyzed and experimentally investigated on both artificial and real-world tasks. Finally, experimental results on benchmark and real-world tasks show that the TreeESN approach, in spite of its efficiency, can achieve comparable results with state-of-the-art, although more complex, neural and kernel based models for tree structured data. [Copyright &y& Elsevier]

Abstract: This paper studied region-of-interest (ROI) problem of computed tomography. It is necessary to use almost local projection data to reduce radiation exposure or time in medical imaging when only a small part of the patient''s body needs to be viewed. Improving the quality of reconstructed ROI and reducing radiation exposure are our aims. However, the traditional local tomography algorithm has difficulty in reconstructing the ROI due to significant truncation artifacts. In this paper, a new grey model based method is reported for ROI image reconstruction from truncated projection data. By using grey model, the proposed method can extrapolate the truncated projection data, and reconstruct the ROI from a set of its projections. As a result, about 75% of full projection data are saved, as compared with other traditional approachs, in reconstructing a local region of 32 pixels in radius in an image of 256×256 pixels. Experimental results show that the proposed method exhibits more saving in exposure as compared with other local tomography algorithms and results in better quality of the reconstructed image. [Copyright &y& Elsevier]

Abstract: In this paper, we propose a system for face identification. Given two query face images, our task is to tell whether or not they are of the same person. The main contribution of this paper comes from two aspects: (1) We adopt the one-shot similarity kernel [35] for learning the similarity of two face images. The learned similarity measures are then used to map a face image to reference images. (2) We propose a graph-based method for selecting an optimal set of reference images. Instead of directly working on the image features, we use the learned similarity to the reference images as the new features and compute the corresponding matching score of the two query images. Our approach is effective and easy to implement. We show encouraging and favorable results on the “Labeled Faces in the Wild” – a challenging data set of faces. [Copyright &y& Elsevier]

Abstract: Motion saliency detection aims at finding the semantic regions in a video sequence. It is an important pre-processing step in many vision applications. In this paper, we propose a new algorithm, Temporal Spectral Residual, for fast motion saliency detection. Different from conventional motion saliency detection algorithms that use complex mathematical models, our goal is to find a good tradeoff between the computational efficiency and accuracy. The basic observation for salient motions is that on the cross section along the temporal axis of a video sequence, the regions of moving objects contain distinct signals while the background area contains redundant information. Thus our focus in this paper is to extract the salient information on the cross section, by utilizing the off-the-shelf method Spectral Residual, which is a 2D image saliency detection method. Majority voting strategy is also introduced to generate reliable results. Since the proposed method only involves Fourier spectrum analysis, it is computationally efficient. We validate our algorithm on two applications: background subtraction in outdoor video sequences under dynamic background and left ventricle endocardium segmentation in MR sequences. Compared with some state-of-art algorithms, our algorithm achieves both good accuracy and fast computation, which satisfies the need as a pre-processing method. [Copyright &y& Elsevier]

Abstract Layout optimization of large-scale oil–gas gathering system is a kind of NP-hard problem in the field of system optimization. It involves a large number of network nodes, coupled optimization variables, complex network structures and hydraulic constraints, which cause the great difficulty in constructing optimization models and solution methods. In this paper, a high-dimensional mixed integer nonlinear layout optimization mathematical model involving the pipeline network structure parameters and pipeline design parameters is established, which can be applied to large-scale oil gathering system and gas gathering system universally. A modified particle swarm optimization (MPSO) algorithm with global search ability is proposed. The convergence theorem of the stochastic optimization algorithm is established based on the Poincare cycle theory. Global convergence of MPSO algorithm is proved, and the performance of MPSO algorithm is analyzed by numerical experiments. Based on dimension reduction planning and modularization thought, the grid dissection set partition method is proposed, and the theoretical foundation and complexity of the grid dissection method are discussed. In order to reduce the dimension of the layout optimization problem, the concept of the fuzzy set of adjacent position, and a novel approach for the well-station connection mode optimization are put forward. Based on the MPSO algorithm, grid dissection set partition method and solution method by fuzzy set of adjacent position, a combined optimization strategy for layout optimization model is proposed. The reliability and practicality of the proposed layout optimization model and combined optimization strategy are verified by the successful application of a real-world large-scale oil field with 661 wells. [ABSTRACT FROM AUTHOR]

Abstract Recent studies propose that different dynamical systems, such as climate, ecological and financial systems, among others, present critical transition points named to as tipping points (TPs). Climate TPs can severely affect millions of lives on Earth so that an active scientific community is working on finding early warning signals. This paper deals with the development of a time series segmentation algorithm for paleoclimate data in order to find segments sharing common statistical patterns. The proposed algorithm uses a clustering-based approach for evaluating the solutions and six statistical features, most of which have been previously considered in the detection of early warning signals in paleoclimate TPs. Due to the limitations of classical statistical methods, we propose the use of a genetic algorithm to automatically segment the series, together with a method to compare the segmentations. The final segments provided by the algorithm are used to construct a prediction model, whose promising results show the importance of segmentation for improving the understanding of a time series. [ABSTRACT FROM AUTHOR]

Abstract The recognition of license plates is very important for intelligent transportation systems. Generally, the performance of an intelligent recognition algorithm is greatly affected by different shooting angles, illumination conditions and backgrounds of the license plate images. This paper presents a sequence recognition approach for intelligent recognition of Chinese license plates. Firstly, a spatial transformer network (STN) is employed to adjust the inclined and deformed license plates such that all the plates have a uniform orientation and thus are easier to be recognized. Then, an improved convolutional neural network (CNN) is designed to extract sequence features of the rectified license plates. The features of different convolutional layers are integrated as input to a bi-directional recurrent neural network (BRNN), where the character segmentation is not needed. Finally, the recognition is accomplished by the BRNN and connectionist temporal classification (CTC). Due to the lack of adequate Chinese license plates, an effective training method is presented in which the network is pre-trained by sufficiently enough synthetic license plates and is fine-tuned by our collected real Chinese license plates. The experimental results show that our model achieves better recognition accuracy and lower average edit distance than some existing methods. [ABSTRACT FROM AUTHOR]

Highlights • A novel neural network model CID-STNN is firstly proposed to forecasting crude oil time series. • Complexity invariant distance is firstly used on learning rate to improve forecast accuracy. • Intrinsic mode functions by ensemble empirical mode decomposition are used to train the model. • The comparison results show that CID-STNN model has a better fitting ability than other models. Abstract In view of the applications of artificial neural networks in economic and financial forecasting, it is vital to improve the prediction methods and the forecasting accuracy for the neural networks. In this paper, a neural network architecture with novel learning rate which is controlled by the complexity invariant distance (CID) is developed for energy market forecasting, where the CID is generally utilized to measure the complexity differences between two time series by employing the Euclidean distance. Moreover, stochastic time strength neural network (STNN) is a kind of supervised neural network which is introduced to forecast the time series. Based on the above theories, a new neural network model called CID-STNN is proposed in this work, in an attempt to improve the forecasting accuracy. For comparing the forecasting performance of CID-STNN and STNN deeply, the ensemble empirical mode decomposition (EEMD) is applied to decompose time series into several intrinsic mode functions (IMFs), and these IMFs are utilized to train the models. Further, the empirical research is performed in testing the prediction effect of WTI and Brent by evaluating predicting ability of the proposed model, and the corresponding superiority is also demonstrated. [ABSTRACT FROM AUTHOR]

Abstract In this paper, we propose a novel end-to-end architecture termed Spatio-Temporal Convolutional features with Nested LSTM (STC-NLSTM), which learns the muti-level appearance features and temporal dynamics of facial expressions in a joint fashion. More precisely, 3DCNN is used to extract spatio-temporal convolutional features from the image sequences that represent facial expressions, and the dynamics of expressions are modeled by Nested LSTM, which is actually coupled by two sub-LSTMs, saying T-LSTM and C-LSTM. Namely, T-LSTM is used to model the temporal dynamics of the spatio-temporal features in each convolutional layer, and C-LSTM is adopted to integrate the outputs of all T-LSTMs together so as to encode the multi-level features encoded in the intermediate layers of the network. We conduct experiments on four benchmark databases, CK+, Oulu-CASIA, MMI and BP4D, and the results show that the proposed method achieves a performance superior to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Abstract Feature reduction is nowadays an important topic in machine learning as it reduces the complexity of the final model and makes it easier to interpret. In some applications, the features arise from multiple sources and it is not so important to select the individual features as to select the important sources. This leads to a group feature selection problem. In this paper, we consider the group feature selection in the multiclass classification setting based on the framework of support vector machines. We reformulate it as a sparse problem by prescribing the maximum number of active groups and propose a novel method based on the ADMM algorithm. We proposed the method in such a way that the main computational load is performed in the first iteration and the remaining iterations can be computed fast. This allows us to handle large problems. We demonstrate the good performance of our method on several real-world datasets. [ABSTRACT FROM AUTHOR]

Abstract The problem of disturbance rejection/attenuation for constant-input delayed linear multi-agent systems (MASs) with the directed communication topology is tackled in this paper, where a classic model reduction technique is introduced to transform the delayed MAS into the delay-free one. First, when the leader has no control input, a novel adaptive predictive extended state observer (ESO) using only relative state information of neighboring agents is designed to achieve disturbance-rejected consensus tracking. The stabilization analysis is presented via the Lyapunov function and sufficient conditions are derived in terms of linear matrix inequalities. Then the result is extended to disturbance-attenuated case where the leader has bounded control input which is only known by a portion of followers. Finally, two numerical examples are presented to illustrate the effectiveness of proposed strategies. The main contribution focuses on the design of adaptive predictive ESO protocols with the fully distributed property. [ABSTRACT FROM AUTHOR]

Abstract This paper suggests a novel way of dramatically improving the Naïve Bayes text classifier with our semantic tensor space model for document representation. In our work, we intend to achieve a perfect text classification with the semantic Naïve Bayes learning that incorporates the semantic concept features into term feature statistics; for this, the Naïve Bayes learning is semantically augmented under the tensor space model where the ‘concept’ space is regarded as an independent space equated with the ‘term’ and ‘document’ spaces, and it is produced with concept-level informative Wikipedia pages associated with a given document corpus. Through extensive experiments using three popular document corpora including Reuters-21578, 20Newsgroups , and OHSUMED corpora, we prove that the proposed method not only has superiority over the recent deep learning-based classification methods but also shows nearly perfect classification performance. [ABSTRACT FROM AUTHOR]

Abstract Data-driven graphs constitute the cornerstone of many machine learning approaches. Recently, it was shown that sparse graphs (sparse representation based graphs) provide a powerful approach to graph-based semi-supervised classification. In this paper, we introduce a new structured sparse graph that is derived by integrating manifold-type constraints on the sparse coefficients without any a priori graph or similarity matrix. Furthermore, we introduce a direct and efficient solution to the proposed optimization problem. Unlike recent sparse graph construction methods that are based on the use of hand-crafted constraints or a predefined reference similarity matrix, our constraints are directly defined on the graph weights themselves, and can provide additional information to both local and global structures of the sparse graph. Experiments conducted on several image databases show that the proposed graph can give better results than many state-of-the-art sparse graphs when applied to the problem of graph-based label propagation. [ABSTRACT FROM AUTHOR]

Inspired by the fact that the matrix formed by nonlocal similar patches in a natural image is of low rank, the nuclear norm minimization (NNM) has been widely used in various image processing studies. Nonetheless, nuclear norm based convex surrogate of the rank function usually over-shrinks the rank components since it treats different components equally, and thus may produce a result far from the optimum. To alleviate the aforementioned limitations of the nuclear norm, in this paper we propose a new method for image restoration via the non-convex weighted ℓ p nuclear norm minimization (NCW-NNM), which is able to accurately impose the image structural sparsity and self-similarity simultaneously. To make the proposed model tractable and robust, the alternating direction method of multiplier (ADMM) framework is adopted to solve the associated non-convex minimization problem. Experimental results on various image restoration problems, including image deblurring, image inpainting and image compressive sensing (CS) recovery, demonstrate that the proposed method outperforms many current state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Entity Linking (EL) is the task of resolving mentions to referential entities in a knowledge base, which facilitates applications such as information retrieval, question answering, and knowledge base population. In this paper, we propose a novel embedding method specifically designed for EL. The proposed model jointly learns word and entity embeddings which are located in different distributed spaces, and a bilinear model is introduced to simulate the interaction between words and entities. We treat EL as a ranking problem, and utilize a pairwise learning-to-rank framework with features constructed with learned embeddings as well as conventional EL features. Experimental results show the proposed model produces effective embeddings which improve the performance of our EL algorithm. Our method yields the state-of-the-art performances on two benchmark datasets CoNLL and TAC-KBP 2010. [ABSTRACT FROM AUTHOR]

Bladder wall segmentation from Magnetic Resonance (MR) images plays an important role in diagnosis. Since the thickness of the bladder wall is a key indication of bladder cancer. There are several methods that have been used for bladder wall segmentation, such as level sets and Active Shape Model (ASM). However, the weak boundaries, the artifacts inside bladder lumen and the complex background outside the bladder wall make the bladder wall segmentation very challenging. To overcome these difficulties and obtain accurate bladder walls, in this paper, a shape prior constrained particle swarm optimization (SPC-PSO) model is proposed to segment the inner and outer boundaries of the bladder wall. The bladder walls are divided into two categories: strong boundaries and weak boundaries by the proposed model. For the strong boundaries, the proposed model can reserve it. For the weak boundaries, the model applies the shape prior to guide the process of segmentation. Compared with some state-of-the-art methods, better results were obtained on bladder MR images from 11 patients by our proposed method. [ABSTRACT FROM AUTHOR]

Abstract: Motivated by Salinas''s (2003) original discovery in and inspired by Oja''s (1982) seminal work in , in this paper, we propose a class of simplified background neural networks model with two subnetworks. Some basic dynamic properties including boundedness, global attractivity, stability, and complete convergence are analyzed rigorously. The main contributions in this paper are as follows: (1) The boundedness of the new model is verified and conditions for global attractivity are derived. (2) Conditions on asymptotically stable of equilibrium points are obtained. (3) Complete convergence for the new network is proved by constructing a novel energy function. Finally, numerical examples demonstrate our theoretical results. [Copyright &y& Elsevier]

Abstract: Infinite countable or uncountable systems of nonlinear ordinary and partial differential equations, which are discrete and continuous models, respectively, of real-world phenomena and processes were analysed in physics, biology, neuroscience, in studying of neural systems or in pure mathematics. Discrete models and corresponding infinite countable systems have been investigated by numerous authors in Banach sequence spaces . But continuous model and corresponding infinite uncountable systems have been investigated by a few authors only. It is interesting that we can attack the above problems by using the same topological fixed-point theory tools as in the countable case. It is the study of infinite uncountable systems of parabolic reaction-diffusion-convection equations that is the subject matter of this paper. Motivation for considering such systems and examples thereof are presented. The paper is an introduction to the study of infinite uncountable systems of parabolic equations. [Copyright &y& Elsevier]

Abstract: In this paper, we describe an XML document classification framework based on extreme learning machine (ELM). On the basis of Structured Link Vector Model (SLVM), an optimized Reduced Structured Vector Space Model (RS-VSM) is proposed to incorporate structural information into feature vectors more efficiently and optimize the computation of document similarity. We apply ELM in the XML document classification to achieve good performance at extremely high speed compared with conventional learning machines (e.g., support vector machine). A voting-ELM algorithm is then proposed to improve the accuracy of ELM classifier. Revoting of Equal Votes (REV) method and Revoting of Confusing Classes (RCC) method are also proposed to postprocess the voting result of v-ELM and further improve the performance. The experiments conducted on real world classification problems demonstrate that the voting-ELM classifiers presented in this paper can achieve better performance than ELM algorithms with respect to precision, recall and F-measure. [Copyright &y& Elsevier]

Abstract: The paper presents an approach for performing regression on large data sets in reasonable time, using an ensemble of extreme learning machines (ELMs). The main purpose and contribution of this paper are to explore how the evaluation of this ensemble of ELMs can be accelerated in three distinct ways: (1) training and model structure selection of the individual ELMs are accelerated by performing these steps on the graphics processing unit (GPU), instead of the processor (CPU); (2) the training of ELM is performed in such a way that computed results can be reused in the model structure selection, making training plus model structure selection more efficient; (3) the modularity of the ensemble model is exploited and the process of model training and model structure selection is parallelized across multiple GPU and CPU cores, such that multiple models can be built at the same time. The experiments show that competitive performance is obtained on the regression tasks, and that the GPU-accelerated and parallelized ELM ensemble achieves attractive speedups over using a single CPU. Furthermore, the proposed approach is not limited to a specific type of ELM and can be employed for a large variety of ELMs. [Copyright &y& Elsevier]

Abstract: This paper is an extension of a previous work presented in International Work Conference on Artificial Neural Network 2009 (IWANN 2009). The paper contains more details and results of the strategy known as Collaborative Distributed Environment by means of an Awareness & Artificial Neural Network strategy (CAwANN). CAwANN is part of the structure of Awareness-based learning Model for distriButed collAborative enviRonment (AMBAR) which is an awareness-based learning model, developed for distributed environments, that allows nodes to accomplish an effective collaboration by means of a multi-agent architecture in which agents are aware of its surroundings by means of a parametrical and flexible use of this information. CAwANN is an ANN-based strategy used to include learning abilities into AMBAR aiming to improve the effectiveness and efficiency of collaboration process by learning three different processes: (1) to collaborate based on levels of awareness; (2) to select a potential candidate to negotiate on saturated conditions; and (3) to decide whether or not a node must change the information that describes its current conditions related with collaboration. Based on the definitions of efficiency and effectiveness presented in this paper and the results obtained from simulated conditions CAwANN has an average efficiency of 100% and an average effectiveness of 86%. [Copyright &y& Elsevier]

Abstract: Maintaining power system security in the deregulated and unbundled electricity market is a challenging task for power system engineers. The idea is to short-list critical contingencies from a large list of contingencies and to rank the contingencies expected to drive the system towards instability. Timely corrective measures can then be planned to save the system from collapse and blackout. This paper presents a simple multi-output fuzzy-neural network for contingency ranking in a power system. A fuzzy composite performance index (FCPI), formulated by combining (i) voltage violations, (ii) line flow violations and (iii) voltage stability margin is being proposed in this paper for composite ranking of contingencies. The proposed approach is very effective in handling contingencies lying on the boundary between two severity classes. Feature selection using fuzzy curves has been employed to reduce the dimension of the network. The performance of the proposed method has been tested on a 69-bus practical Indian power system. [Copyright &y& Elsevier]

Abstract: The selection of hyper-parameters in support vector machines (SVM) is a key point in the training process of these models when applied to regression problems. Unfortunately, an exact method to obtain the optimal set of SVM hyper-parameters is unknown, and search algorithms are usually applied to obtain the best possible set of hyper-parameters. In general these search algorithms are implemented as grid searches, which are time consuming, so the computational cost of the SVM training process increases considerably. This paper presents a novel study of the effect of including reductions in the range of SVM hyper-parameters, in order to reduce the SVM training time, but with the minimum possible impact in its performance. The paper presents reduction in parameter C, by considering its relation with the rest of SVM hyper-parameters ( and ), through an approximation of the SVM model. On the other hand, we use some characteristics of the Gaussian kernel function and a previous result in the literature to obtain novel bounds for and hyper-parameters. The search space reductions proposed are evaluated in different regression problems from UCI and StatLib databases. All the experiments carried out applying the popular LIBSVM solver have shown that our approach reduces the SVM training time, maintaining the SVM performance similar to when the complete range in SVM parameters is considered. [Copyright &y& Elsevier]

Abstract: For the analysis of natural neural responses it is necessary to evaluate and compare the reliability of the produced spike sequences. The same occurs in the development and evaluation of neural models, which should mimic the real neural centers that are being modeled. Several neural metrics have been proposed to analyze neural responses, and to tune and evaluate neural models. Neural metrics measure different characteristics of the neural code and can be grouped into distinct classes, as they follow a firing rate or time-code perspective. In this paper, several metrics belonging to the firing rate, spike train and firing event classes are reviewed. Using sets of neuronal responses and a set of models, the metrics are analyzed and compared to disclose their advantages and drawbacks. In most cases these metrics depend on a free parameter, that establishes their sensitivity to particular characteristics of the neural code. After showing that the incorrect choice of these parameters can lead to meaningless results, methods are presented in this paper to define a valid range of values for the parameters. These methods are based on a statistical analysis of the inter-trials errors. The application of neural metrics to the tuning and assessment of neural models of distinct classes reveals important results. Some of the analyzed metrics possess pronounced minima, specifically around the origin, which makes the optimization process more difficult; nonetheless, they provide insightful results for the evaluation of models. This paper also discusses the application of the neural metrics to evaluate neural models, providing relevant guidelines for their utilization. [Copyright &y& Elsevier]

Abstract: In this paper, we present some general analysis on global convergence of the recurrent neural networks (RNNs) with projection mappings in the critical case when , a matrix related to the weight matrices and the activation mappings of the networks, is nonnegative definite for some positive diagonal matrix . Considerable stability results have been obtained for the RNNs in the noncritical case when is positive definite. In contrast, only a few conclusions have been conducted under the critical conditions. Comparing with the existing critical studies, the present critical stability results in this paper require no additional assumption on the weight matrices, can be applied to the RNNs with general projection mappings other than nearest point projection mappings, and can serve for both two fundamental RNN models. The results established for several typical RNN models unify, sharpen or generalize most of the existing stability assertions. Two examples are given to show both theoretical importance and practical feasibility of the critical results obtained. [Copyright &y& Elsevier]

Abstract: Ridge regression (RR) for classification is a regularized least square method to model the linear dependency between covariate variables and labels. By applying appropriate techniques to encode the multivariate labels in face recognition as the vertices of the regular simplex which can separate points with highest degree of symmetry, RR maps the face images into a face subspace where the images from each individual will locate near their individual targets. However, as a holistic method, RR operates directly on a whole face region represented as a vector and thus cannot effectively recognize the faces with illumination variations and partial occlusions. In this paper, we present a novel algorithm, termed as local ridge regression (LRR). Different from RR, LRR emphasizes on each local face region matching rather than the whole. As a result, LRR can not only enhance the robustness to the local variations by utilizing the spatial and geometrical information of facial components, but also avoid the dimensionality reduction in the holistic RR as a preprocessing. Furthermore, an efficient cross-validation algorithm is adopted to select the regularization parameters in each local region. Experiments on two standard face databases demonstrate that the proposed algorithm significantly outperforms RR and the two popular linear face recognition techniques (Eigenface and Fisherface). Although we concentrate on RR in this paper, following the proposed line of the research, many current multi-category classifiers can also be applied in face recognition through combining the characteristics of face images and may obtain better recognition accuracies. [Copyright &y& Elsevier]

Abstract: Combining multiple neural networks appears to be a very promising approach in improving neural network generalisation since it is very difficult, if not impossible, to develop a perfect single neural network. In the building of an aggregated neural network model, a number of individual networks are developed from different data sets and/or different training algorithms. In this paper, individual networks are developed from bootstrap re-samples of the original training and testing data sets. Instead of combining all the developed networks, this paper proposes two selective combination techniques: forward selection and backward elimination. These two techniques essentially combine those individual networks that, when combined, can significantly improve model generalisation. In forward selection, individual networks are gradually added into the aggregated network until the aggregated network error on the original training and testing data sets cannot be further reduced. In backward elimination, all the individual networks are initially aggregated and some of the individual networks are then gradually eliminated until the aggregated network error on the original training and testing data sets cannot be further reduced. The proposed techniques are applied to dynamic nonlinear process modelling and classification of diabetes database. Application results demonstrate that the proposed techniques can significantly improve model generalisation and perform better than aggregating all the individual networks and the heuristic selective combination method where networks with better performance on the training and testing data are selected. [Copyright &y& Elsevier]

A type of machine vision based data glove with certain encoded features on its surface, strip glove is proposed in this paper. The machine vision device replaces the sensors attached on the glove and captures the codes on the glove to obtain the hand motion data. To handle the complex geometrical transformations in the strip glove motion, conformal geometric algebra is introduced as the mathematical tool. In the framework of conformal geometric algebra, the degrees of freedom in hand motion are assign to different planes geometrically to form palm and finger planes. The mathematical model of strip glove is established for the pose solution of the strip glove. The motion tracking of the strip glove is implemented in a binocular system. The particle filter algorithm is applied for tracking the colored blocks on a plane. A continuous motion model of finger segments is constructed in the binocular machine vision system by conformal geometric algebra according to hand motion characteristics, and the hand motion data is obtained during the tracking. Based on particle filter algorithm, the conformal geometric algebra method is applied to set particle parameters for the solution of the local occlusion problems caused by hand pose variation, and the tracking stability of the strip glove is improved. [ABSTRACT FROM AUTHOR]