Search

In recent years, medical image transmission using a multi-cloud system has played a significant role in e-Healthcare infrastructure. It allows medical practitioners to easily store, retrieve, and share patients' medical information across multiple stakeholders. However, multi-cloud image transmission may be vulnerable to multiple security breaches, such as authentication, confidentiality, and security issues. Motivated by these issues, this paper proposes a data-hiding scheme for secure medical image transmission in a multi-cloud environment. The proposed scheme ensures imperceptible robustness and watermark security at a low computational cost. Here, the medical image is divided into a number of shares using Neighbor Mean Interpolation (NMI). To achieve confidentiality, Electronic Patient Healthcare Record (EPHR) is encrypted using Double Scan Pixel Position Shuffling (DSPPS) approach. Then, the encrypted EPHR is divided into shares and embedded in the cover medical image shares. Finally, a minimum of 50% of watermarked image shares are utilized to retrieve the original medical image and encrypted EPHR, consequently reducing multi-cloud latency and computational burden. Experimental results show that the proposed scheme shows high imperceptibility, robustness, and watermark security at a low computational cost. Comparative analysis with some of the recent popular data hiding schemes shows that the proposed scheme has improved imperceptibility and robustness by 10%–15% (approximately) with higher watermark security at a low computational cost. [ABSTRACT FROM AUTHOR]

Highlights • A new data-dependent method for determining the trimming level in robust clustering. • We monitor the cluster structure as the trimming level changes. • The robust clustering constrains the ratio of eigenvalues of dispersion matrices. • The "car-bike" plot exhibits cluster stability as the eigenvalue constraint varies. • Sizable bibliography relating the work to that in the machine learning and pattern recognition fields. Abstract Monitoring the properties of single sample robust analyses of multivariate data as a function of breakdown point or efficiency leads to the adaptive choice of the best values of these parameters, eliminating arbitrary decisions about their values and so increasing the quality of estimators. Monitoring the trimming proportion in robust cluster analysis likewise leads to improved estimators. We illustrate these procedures on a sample of 424 cows with bovine phlegmon. For clustering we use a method which includes constraints on the eigenvalues of the dispersion matrices, so avoiding thread shaped clusters. The "car-bike" plot reveals the stability of clustering as the trimming level changes. The pattern of clusters and outliers alters appreciably for low levels of trimming. [ABSTRACT FROM AUTHOR]

Abstract Data reconciliation has played a significant role in rectifying process data which can meet the conservation laws in industrial processes. Generally, the actual measurements are often easily contaminated by different gross errors. Thus, it is essential to build robust data reconciliation methods to alleviate the impact of gross errors and provide accurate data. In this paper, a novel robust estimator is proposed to improve the robustness of data reconciliation method, which is based on a new robust estimation function. First, the main robust properties are analyzed with its objective and influence functions for the proposed robust estimator. Then, the effectiveness of the new robust data reconciliation method is demonstrated on a linear numerical case and a nonlinear example. Moreover, it is further used to a practical industrial evaporation production process, which also demonstrates that the process data can be better reconciled with the proposed robust estimator. [ABSTRACT FROM AUTHOR]

Abstract Manifold based feature extraction has been proved to be an effective technique in dealing with the unsupervised classification tasks. However, most of the existing works cannot guarantee the global optimum of the learned projection, and they are sensitive to different noises. In addition, many methods cannot catch the discriminative information as much as possible since they only exploit the local structure of data while ignoring the global structure. To address the above problems, this paper proposes a novel graph based feature extraction method named low-rank and sparsity preserving embedding (LRSPE) for unsupervised learning. LRSPE attempts to simultaneously learn the graph and projection in a framework so that the global optimal projection can be obtained. Moreover, LRSPE exploits both global and local information of data for projection learning by imposing the low-rank and sparse constraints on the graph, which promotes the method to obtain a better performance. Importantly, LRSPE is more robust to noise by imposing the l 2 , 1 sparsity norm on the reconstruction errors. Experimental results on both clean and noisy datasets prove that the proposed method can significantly improve classification accuracy and it is robust to different noises in comparison with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Based on the cognitive psychology theory of coping, we examined how the ability of developing market firms to confront and cope with advanced market importers' pressure to adopt emerging technologies may influence their adoption of such technologies. We also determined how this relationship is moderated by the disruptive and incremental key features of technology. To do so, we collected survey data via the LinkedIn accounts of Pakistani firms exporting to advanced economies. Our results show that confrontation-coping mediates the influence of importer pressure on exporter intentions to adopt emerging technology. Further, we found the positive effects of such pressure on confrontation-coping to be stronger when the technology is robustly disruptive. We also found that confrontation-coping strongly influences intentions to adopt in the presence of highly incremental technology. Our study makes theoretical contributions to technology adoption research and coping theory, as well as practical contributions to both exporting firms and emerging technology providers. Our findings also have important policy implications. • Importers' pressure positively influences confrontation-coping approach in emerging technology adoption. • The effects of importers' pressure on confrontation-coping are stronger under radically disruptive technology features. • Confrontation-coping approach mediates the effects of importers' pressure on intention to adopt emerging technology. • High incremental technology features positively moderate the confrontation-coping effects on intention to adopt technology. [ABSTRACT FROM AUTHOR]

Pyrheliometer calibration must be done following strict procedures in order to ensure the required robustness and accuracy. These procedures are described in the ISO 9059:1990 and ASTM E 816 – 15 international standards. However, their application requires information that may not always be available or may be subjective, inaccurate or incomplete, as for example, the determination of “percent of cloud coverage” or “the existence of clouds 15° around the Sun”. The irradiance measurements made by the reference and test instruments involved should also be collected over wide periods after, close to and before solar noon, which might not always be the case depending on the weather conditions during calibration. When those data are not available, the standard cannot be applied properly, and the experts have to decide which data can be used for the calibration. In this study, the abovementioned two main standards for pyrheliometer calibration were thoroughly reviewed, and a harmonized protocol is proposed that uses only the main data recorded. Nineteen field pyrheliometers were calibrated to verify the proposed procedure, and the results show its robustness. After calibration, we analyzed the variability in the calibration constant and the influence of some experimental conditions on the calibration results. As in previous references, the results show that variations in solar elevation and wind speed during the day still influenced the calibration constants of most of the test devices. On the contrary, neither the angle between the wind direction and the solar azimuth nor Linke turbidity seemed to influence the calibration constants calculated. The influence of the Linke turbidity is low as the viewing geometry of all involved pyrheliometers is very similar to each other and as low turbidity prevailed. The correlation between the solar elevation and the wind speed was analyzed and calibration constants were found to vary linearly with solar elevation and wind speed, respectively. Pyrheliometer calibration measurement testing was carried out in Summer 2014 at the Plataforma Solar de Almeria (PSA) in the context of the Solar Facilities for the European Research Area 2 Project (SFERA2). [ABSTRACT FROM AUTHOR]

Given a classification task, an approach to improve accuracy relies on the use of abstaining classifiers. These classifiers are trained to reject observations for which predicted values are not reliable enough: these rejected observations belong to an abstaining area in the feature space. Two equivalent methods exist to theoretically compute the optimal abstaining area for a given classification problem. The first one is based on the posterior probability computed by the model and the other is based on the derivative of the ROC function of the model. Although the second method has proved to give the best results, in small-sample settings such as the one found in omics data, the estimation of posterior probabilities and derivative of ROC curve are both lacking of precision leading to far from optimal abstaining areas. As a consequence none of the two methods bring the expected improvements in accuracy. We propose five alternative algorithms to compute the abstaining area adapted to small-sample problems. The idea of these algorithms is to compute an accurate and robust estimation of the ROC curve and its derivatives. These estimation are mainly based on the assumption that the distribution of the output of the classifier for each class is normal or mixture of normal distributions. These distributions are estimated by a kernel density estimator or Bayesian semiparametric estimator. Another method works on the approximation of the convex hull of the ROC curve. Once the derivative of the ROC curve are estimated, the optimal abstaining area can be directly computed. The performance of our algorithms are directly related to their capacity to compute an accurate estimation of the ROC curve. A sensitivity analysis of our methods to the dataset size and rejection cost has been done on a set of experiments. We show that our methods improve the performances of the abstaining classifiers on several real datasets and for different learning algorithms. [ABSTRACT FROM AUTHOR]

In the era of big data, it is increasingly common that large amount of data is generated across multiple distributed sites and cannot be gathered into a centralized site for further analysis, which invalidates the assumption of traditional clustering techniques based on centralized models. The major challenge is that these distributed datasets cannot be trivially merged due to issues such as privacy concerns, limited network bandwidth among sites and limited computational capacity of a single site. To tackle this challenge, we propose an efficient distributed clustering scheme using boundary information (DCUBI), which features good flexibility and scalability. The main procedure of DCUBI consists of three steps: local-global-local. Firstly, each local site extracts the boundary points from its own local data and applies traditional clustering on boundary points only. Secondly, labeled boundary points from each site are sent to the central site as local representatives where boundary and cluster fusion is conducted to form the global clustering model. Finally, the global boundary and cluster information is sent back to each local site for refined local clustering. To demonstrate the effectiveness of DCUBI, we plug the well-known DBSCAN algorithm into DCUBI and comprehensive experiments are conducted using datasets with different properties. Experiment results clearly verify the quality of clustering by DCUBI as well as its superior time efficiency when the volume of data in each site is large. Furthermore, other popular clustering techniques especially those with high time complexity such as spectral clustering and affinity propagation clustering are also plugged into DCUBI to demonstrate the flexibility of the proposed scheme. [ABSTRACT FROM AUTHOR]

A novel methodology based deep belief networks and multiple models (DBNs-MMs) is presented to accomplish fault detection for complex systems. And firstly, historical datasets are collected and processed to train the DBNs, so that DBNs can be constructed to learn the nonlinear dynamic characteristics of complex system, and so a model with a specific architecture and some initial intelligence will be built up. Secondly, the operation condition and real-time measurement data are employed in DBNs-MMs to get a series of network outputs. Finally, the residuals can be obtained by comparing the measurement output and each DBN output. Then, the fault detection can be achieved by employing a properly adaptive threshold for each residual. Some faulty cases of the complex cryogenic propellant loading system have been used to demonstrate the effectiveness of the proposed fault detection methodology, and the result has shown its excellent performance. [ABSTRACT FROM AUTHOR]

Three-phase induction motors are extensively used in the industry due to their robustness characteristics, low cost and easy maintenance. Usually, it is necessary to implement drive and control systems for such motors, which requires the knowledge of their mechanical and electrical parameters. However, in some cases, these data are not immediately available, or the values of the parameters may change due to the wear of motor components. Such problems can be circumvented if an efficient parameter estimation technique is available. In order to automatically estimate the parameters efficiently, the present work proposes a method, based on the differential evolution algorithm, aimed at the estimation of the electrical and mechanical parameters of three-phase induction motors. Such algorithm is capable of estimating the parameters of the equivalent electrical circuit, such as stator and rotor resistances and leakage inductances, the magnetizing inductance, and also mechanical parameters, such as moment of inertia and the friction coefficient. The performance of the proposed parameter estimation technique is evaluated for three different input signals: (i) current signal of a phase associated with the speed measured from a tachogenerator, (ii) current signal of a phase associated with the speed acquired from a torquemeter, and (iii) only the current signal of one phase. Finally, a series of simulated and experimental results are presented to validate the proposed technique, and the results show the good performance of the proposed strategies. [ABSTRACT FROM AUTHOR]

This paper presents a self-learning decision making procedure for robust real-time train rescheduling in case of disturbances. The procedure is applicable to aperiodic timetables of mixed-tracked networks and it consists of three steps. The first two are executed in real-time and provide the rescheduled timetable, while the third one is executed offline and guarantees the self-learning part of the method. In particular, in the first step, a robust timetable is determined, which is valid for a finite time horizon . This robust timetable is obtained solving a mixed integer linear programming problem aimed at finding the optimal compromise between two objectives: the minimization of the delays of the trains and the maximization of the robustness of the timetable. In the second step, a merging procedure is first used to join the obtained timetable with the nominal one. Then, a heuristics is applied to identify and solve all conflicts eventually arising after the merging procedure. Finally, in the third step an offline cross-efficiency fuzzy Data Envelopment Analysis technique is applied to evaluate the efficiency of the rescheduled timetable in terms of delays minimization and robustness maximization when different relevance weights (defining the compromise between the two optimization objectives) are used in the first step. The procedure is thus able to determine appropriate relevance weights to employ when disturbances of the same type affect again the network. The railway service provider can take advantage of this procedure to automate, optimize, and expedite the rescheduling process. Moreover, thanks to the self-learning capability of the procedure, the quality of the rescheduling is improved at each reapplication of the method. The technique is applied to a real data set related to a regional railway network in Southern Italy to test its effectiveness. [ABSTRACT FROM AUTHOR]

Extracellular neural recordings have become an essential technique for studying and monitoring neural activity, which is of vital importance in understanding brain functions. However, how to accurately and effectively detect spikes from the extracellular recording signals is still a major related challenge. The existing methods for spike detection have achieved much progress while they are vulnerable to the background noise. In this paper, we develop an object-dependent sparse representation framework for high accuracy and robust extracellular spike detection. Specifically, by exploiting the structural similarities of spikes, we construct an object-dependent dictionary to achieve a sparse and comprehensive representation of the recorded signals. Thus, the problem of spike detection can be formulated as a convex sparse optimization problem. Through systematically analyzing the optimal solution, the number and locations of spikes in the recorded signal are finally determined. In addition, singular value decomposition (SVD) is introduced to further improve the flexibility and robustness of the proposed method. Experimental results on both synthesized extracellular neural recordings and real data show that the proposed method outperforms the existing methods. [ABSTRACT FROM AUTHOR]

Mixture of experts (MoE) is a popular framework in the fields of statistics and machine learning for modeling heterogeneity in data for regression, classification and clustering. MoE for continuous data are usually based on the normal distribution. However, it is known that for data with asymmetric behavior, heavy tails and atypical observations, the use of the normal distribution is unsuitable. We introduce a new robust non-normal mixture of experts modeling using the skew t distribution. The proposed skew t mixture of experts, named STMoE, handles these issues of the normal mixtures experts regarding possibly skewed, heavy-tailed and noisy data. We develop a dedicated expectation conditional maximization (ECM) algorithm to estimate the model parameters by monotonically maximizing the observed data log-likelihood. We describe how the presented model can be used in prediction and in model-based clustering of regression data. Numerical experiments carried out on simulated data show the effectiveness and the robustness of the proposed model in fitting non-linear regression functions as well as in model-based clustering. Then, the proposed model is applied to the real-world data of tone perception for musical data analysis, and the one of temperature anomalies for the analysis of climate change data. The obtained results confirm the usefulness of the model for practical data analysis applications. [ABSTRACT FROM AUTHOR]

In this paper, an innovative robust prediction algorithm for performance degradation of proton exchange membrane fuel cell (PEMFC) is proposed based on a combination of model-based and data-driven prognostic method. A novel approach using the moving window method is applied, in order to 1) train the developed models; 2) update the weight factors of each method and 3) further fuse the predicted results iteratively. In the proposed approach, both model-based and data-driven methods are simultaneously used to achieve a better accuracy. During the prediction process, each dataset in the proposed moving window are divided into three sections respectively: training, evaluation and prediction. The training data are used first to identify the models parameters. The evaluation data are then used to measure the weight of each method, which represents the degree of confidence of each method in the actual state. Based on these dynamically adjusting weight factors, the prediction results from different methods are then fused using weighted average methodology to calculate the final prediction results. In order to verify the proposed method, three experimental validations with different aging testing profiles have been performed. The results demonstrate that the proposed hybrid prognostic approach can achieve a higher accuracy than conventional prediction methods. In addition, in order to find the satisfactory trade-off between the prediction accuracy and forecast time for optimizing on-line prognostic, the performance variation of proposed approach with different moving window length is further showed and discussed. [ABSTRACT FROM AUTHOR]

Multidimensional scaling (MDS) is an efficient technique for data analysis, and has been successfully applied in data visualization, object retrieval, data clustering, and so on. However, its use in image hashing is rarely discussed yet. In this study, we investigate the use of MDS in image hashing and propose an MDS-based hashing algorithm resistant to any-angle rotation. The proposed algorithm extracts a rotation-invariant feature matrix with log-polar transform and discrete Fourier transform from the normalized image, and learns a compact and discriminative representation from the feature matrix by MDS. Experiments with 3845 images are carried out and the results demonstrate that the proposed algorithm is robust to many content-preserving operations, including any-angle rotation, and reaches good discrimination. Receiver operating characteristics (ROC) curve comparisons illustrate that the proposed algorithm outperforms some state-of-the-art algorithms in classification with respect to robustness and discrimination. [ABSTRACT FROM AUTHOR]

Terrestrial Laser Scanning (TLS) efficiently collects 3D information based on lidar (light detection and ranging) technology. TLS has been widely used in topographic mapping, engineering surveying, forestry, industrial facilities, cultural heritage, and so on. Ground filtering is a common procedure in lidar data processing, which separates the point cloud data into ground points and non-ground points. Effective ground filtering is helpful for subsequent procedures such as segmentation, classification, and modeling. Numerous ground filtering algorithms have been developed for Airborne Laser Scanning (ALS) data. However, many of these are error prone in application to TLS data because of its different angle of view and highly variable resolution. Further, many ground filtering techniques are limited in application within challenging topography and experience difficulty coping with some objects such as short vegetation, steep slopes, and so forth. Lastly, due to the large size of point cloud data, operations such as data traversing, multiple iterations, and neighbor searching significantly affect the computation efficiency. In order to overcome these challenges, we present an efficient ground filtering method for TLS data via a Scanline Density Analysis, which is very fast because it exploits the grid structure storing TLS data. The process first separates the ground candidates, density features, and unidentified points based on an analysis of point density within each scanline. Second, a region growth using the scan pattern is performed to cluster the ground candidates and further refine the ground points (clusters). In the experiment, the effectiveness, parameter robustness, and efficiency of the proposed method is demonstrated with datasets collected from an urban scene and a natural scene, respectively. [ABSTRACT FROM AUTHOR]

The modification of an energy-based approach called the dissipating energy flow (DEF) method is proposed, which uses data from phasor measurement units (PMUs) to trace the source of poorly damped natural and forced oscillations in power systems. The original energy-based approach (Chen et al., 2013) assumes the ability to determine steady-state values of variables measured by PMU during the transient process and that prevents the reliable use of the original method with actual PMU data. PMU data processing, proposed in the DEF method, is a key step in converting the energy-based method into a robust and automated tool for use with actual PMU data. The effectiveness of the proposed DEF method is demonstrated by testing multiple simulated cases of sustained oscillations, including both poorly damped natural and forced oscillations and more than 30 actual events in ISO New England (ISO-NE) and two events in Western Electricity Coordination Council (WECC) systems. The study also demonstrates the potential for using the DEF method to estimate the contribution of any generator to the damping of a specific oscillation mode. [ABSTRACT FROM AUTHOR]

This paper proposes a new non-fragile stochastic control method to investigate the robust sampled-data synchronization problem for uncertain chaotic Lurie systems (CLSs) with time-varying delays. The controller gain fluctuation and time-varying uncertain parameters are supposed to be random and satisfy certain Bernoulli distributed white noise sequences. Moreover, by choosing an appropriate Lyapunov-Krasovskii functional (LKF), which takes full advantage of the available information about the actual sampling pattern and the nonlinear condition, a novel synchronization criterion is developed for analyzing the corresponding synchronization error system. Furthermore, based on the most powerful free-matrix-based integral inequality (FMBII), the desired non-fragile sampled-data estimator controller is obtained in terms of the solution of linear matrix inequalities. Finally, three numerical simulation examples of Chua's circuit and neural network are provided to show the effectiveness and superiorities of the proposed theoretical results. [ABSTRACT FROM AUTHOR]

This paper introduces an application of simultaneous nonlinear data reconciliation and gross error detection for power plants utilizing a complex but computationally light first principle combustion model. Element and energy balances and robust techniques introduce nonlinearity and the consequent optimization problem is solved using nonlinear optimization. Data reconciliation improves estimation of process variables and enables improved sensor quality control and identification of process anomalies. The approach was applied to an industrial 200 MW th fluidized bed boiler combusting wood, peat, bark, and slurry. The results indicate that the approach is valid and is able to perform in various process conditions. As the combustion model is generic, the method is applicable in any boiler environment. [ABSTRACT FROM AUTHOR]

Face alignment is a key component of face recognition system, and facial landmark points are widely used for face alignment by a number of face recognition systems. However, inaccurate locations of landmark points bring about spatial misalignment which degrades the performance of face recognition systems. In order to alleviate this problem, we propose a simple and efficient data augmentation approach, which uses artificial landmark perturbation to generate a huge number of misaligned face images, to train Deep Convolutional Neural Networks (DCNN) models robust to landmark misalignment. In our experiments, three types of facial landmark-based face alignment methods are applied to train DCNN models on CASIA-WebFace training database. Experimental results on Labeled Faces in the wild database (LFW) and YouTube Faces database (YTF) verify the effectiveness of our approach. [ABSTRACT FROM AUTHOR]

Planar nearfield acoustic holography (PNAH) is usually based on narrow-band, single frequency analysis, which is time consuming when the source behavior over a broad frequency range is of interest, as is the case with many industrial sources. In this paper a method, broadband planar nearfield acoustic holography based on one-third-octave band analysis (BPNAH), is described. Data relating to the complex band pressure on the hologram is obtained by combining the root-mean-square pressure corresponding to a one-third-octave band with the phase of the pressure corresponding to a single frequency line. Numerical simulations and measurements show that the BPNAH method allows a significant reduction in processing time, while keeping a similar accuracy to the conventional reconstruction, which is based on the summation of frequency by frequency in the corresponding band. As a simple, time-saving and robust technique, the BPNAH method is particularly well adapted to industrial studies. [ABSTRACT FROM AUTHOR]

The local binary pattern with H function (H-LBP) technique enables fast and efficient edge extraction in digital radiography. In this paper, we reformulate the model of H-LBP and propose a novel sparsity-based shrinkage approach, in which the threshold can be adapted to the data sparsity. Using this model, we upgrade fast H-LBP framework and apply it to real digital radiography. The experiments show that the method improved using the new shrinkage approach can avoid elaborately artificial modulation of parameters and possess greater robustness in edge extraction compared with the other current methods without increasing processing time. [ABSTRACT FROM AUTHOR]

Image quality assessment (IQA) aims at developing computational models that can precisely and automatically estimate human perceived image quality. To date, various IQA methods have been proposed to mimic the processing of the human visual system, with limited success. Here, we present a novel IQA approach named biologically inspired feature similarity (BIFS), which is demonstrated to be highly consistent with the human perception. In the proposed approach, biologically inspired features (BIFs) of the test image and the relevant reference image are first extracted. Afterwards, local similarities between the reference BIFs and the distorted ones are calculated and then combined to obtain a final quality index. Thorough experiments on a number of IQA databases demonstrate that the proposed method is highly effective and robust, and outperform state-of-the-art FR-IQA methods across various datasets. [ABSTRACT FROM AUTHOR]

Amid the literature on members of political parties, surprisingly little has been written on the potential or actual impacts that can be made upon party strategy or policies by a rapid influx of new members. New joiners may have different outlooks and desires than long-standing members. Although already sympathetic to the party they are joining, new arrivals, if signing up in large numbers, may hold sufficiently revisionist views to be able to re-orientate a political party in a direction not previously taken. Using data from the first-ever membership survey of the Democratic Unionist Party (DUP) in Northern Ireland, the largest party in the Northern Ireland Assembly since 2003 and the fourth largest UK parliamentary party since 2005, this article analyses whether more recent joiners of the Party have brought greater pragmatism and moderation to an organisation previously dominated by hardline political, religious and ethnic attitudes. Modernisation from outsiders who become insiders can be a key aspect of party development. The DUP offers one of the stiffest tests of modernisation, given its history of opposition to moderation. This article shows that newer members have tempered beliefs in one of the most robustly ethno-religious parties in Europe. [ABSTRACT FROM AUTHOR]

In the past, electric distribution systems have lacked measurement points, and equipment is often operated to its failure point, resulting in customer outages. The widespread deployment of sensors improves distribution level observability. This paper presents an off-line parameter tracking procedure that leverages the increased deployment of distribution level measurement devices to estimate changes in impedance parameters over time. Parameter tracking enables the discovery of non-diurnal and non-seasonal changes, which can be flagged for investigation. The presented method uses an unbalanced distribution-system state-estimator and a measurement-residual based parameter-estimation procedure. Measurement residuals from multiple measurement snapshots are combined to increase effective local redundancy and improve robustness to measurement noise. The input data used in the experiments consists of data from devices on the primary distribution system and from customer meters, via an AMI system. Results of simulations on the IEEE 13-Node Test Feeder with 307 measurements and 246 parameters are presented to illustrate the proposed approach applied to changes in series impedance parameters. The proposed approach can detect a 5% change in series resistance elements with 2% measurement error using less than 1 day of measurement snapshots for a single estimate. [ABSTRACT FROM AUTHOR]

Scenario discovery is a novel model-based approach to scenario development in the presence of deep uncertainty. Scenario discovery frequently relies on the Patient Rule Induction Method (PRIM). PRIM identifies regions in the model input space that are highly predictive of producing model outcomes that are of interest. To identify these, PRIM uses a lenient hill climbing optimization procedure. PRIM struggles when confronted with cases where the uncertain factors are a mix of data types, and can be used only for binary classifications. We compare two more lenient objective functions which both address the first problem, and an alternative objective function using Gini impurity which addresses the second problem. We assess the efficacy of the modification using previously published cases. Both modifications are effective. The more lenient objective functions produce better descriptions of the data, while the Gini impurity objective function allows PRIM to be used when handling multinomial classified data. [ABSTRACT FROM AUTHOR]

Citation is perhaps the mostly used metric to evaluate the scientific impact of papers. Various measures of the scientific impact of researchers and journals rely heavily on the citations of papers. Furthermore, in many practical applications, people may need to know not only the current citations of a paper, but also a prediction of its future citations. However, the complex heterogeneous temporal patterns of the citation dynamics make the predictions of future citations rather difficult. The existing state-of-the-art approaches used parametric methods that require long period of data and have poor performance on some scientific disciplines. In this paper, we present a simple yet effective and robust data analytic method to predict future citations of papers from a variety of disciplines. With rather short-term (e.g., 3 years after the paper is published) citation data, the proposed approach can give accurate estimate of future citations, outperforming state-of-the-art prediction methods significantly. Extensive experiments confirm the robustness of the proposed approach across various journals of different disciplines. [ABSTRACT FROM AUTHOR]

The Directional Median Analysis is a new proposal of robust data exploration. It can be treated as a multivariate extension of the idea similar to Theil–Sen estimator, where one finds a direction which minimizes the sum of angles to all observations. Theoretical analysis of this problem reveals that this analysis can be perceived as a special case of Spherical PCA and further robustifies the Spherical PCA analysis. Data decomposition can be done sequentially and each direction can be obtained by iterative reweighting. The idea is compared with classical PCA and Spherical PCA. A comparison on two artificial datasets shows that this method works more robust than Spherical PCA and could be promising alternative (or additive) to known robust data analysis methods. [ABSTRACT FROM AUTHOR]

Despite significant advances in neuroscience, the neural bases of intelligence remain poorly understood. Arguably the most elusive aspect of intelligence is the ability to make robust inferences that go far beyond one's experience. Animals categorize objects, learn to vocalize and may even estimate causal relationships — all in the face of data that is often ambiguous and sparse. Such inductive leaps are thought to result from the brain's ability to infer latent structure that governs the environment. However, we know little about the neural computations that underlie this ability. Recent advances in developing computational frameworks that can support efficient structure learning and inductive inference may provide insight into the underlying component processes and help pave the path for uncovering their neural implementation. [ABSTRACT FROM AUTHOR]

Many studies have confirmed gait as a robust biometric feature for identification of individuals. However, direction changes cause difficulties for most of the gait recognition systems, due to appearance changes. This study presents an efficient multi-view gait recognition method that allows curved trajectories on unconstrained paths in indoor environments. The recognition is based on volumetric analysis of the human gait, to exploit most of the 3D information enclosed in it. Appearance-based gait descriptors are extracted from 3D gait volumes and temporal patterns of them are classified using a Support Vector Machine with a sliding temporal window for majority voting. The proposed approach is experimentally validated on the “AVA Multi-View Dataset (AVAMVG)” and on the “Kyushu University 4D Gait Database (KY4D)”. The results show that this new approach is able to identify people walking on curved paths. [ABSTRACT FROM AUTHOR]

Recently Smartphones have become more robust tools in terms of storage capacity and computing power, effective tools for business to improve productivity, and daily tools for many people due to the various services they offer and allow to end users to perform multiple tasks and be always updated on the move. This has made it a favorite target for malicious applications that specifically attack their personal and professional data. To overcome this problem, mobile platforms have set up a security system based on the permissions model; the user decides whether to validate the permissions requested by an application before installation, or to abort the installation. In case the user needs to install an application, and that application requests unjustified permissions, this represents a particularly troublesome weakness. In this paper, we propose a firewall Anti-Leak of Sensitive Data (ALSD), allowing reliable protection against leakage of sensitive personal and professional data. This integrated solution to the mobile operating system is based on automated analysis of markets; it allows blocking applications query on the sensitive data while ensuring their proper functioning. [ABSTRACT FROM AUTHOR]

In this paper, we propose a design method of digital repetitive controllers to track continuous-time periodic references based on sampled-data H ∞ delayed signal reconstruction. It is well known that perfect tracking is not possible for arbitrary periodic signals with a fixed period if the plant to be controlled is strictly proper. For this reason, we adopt the internal model control (IMC), with which the repetitive control is cast into the framework of sampled-data H ∞ delayed signal reconstruction problem. We also extend this formulation to multi-rate and robust control. Design examples show the effectiveness of our method. [ABSTRACT FROM AUTHOR]

In the present paper the link between renewable energy generation and imports dynamics is explored in import demand equations. We find that renewable energy generation reduces import growth. The results display a considerable robustness across estimation methods and model specifications. [ABSTRACT FROM AUTHOR]

We present a histogram-based image retrieval method which is designed specifically for noisy query images. The images are retrieved according to histogram similarity. To reach high robustness to noise, the histograms are described by newly proposed features which are insensitive to a Gaussian additive noise in the original images. The advantage of the new method is proved theoretically and demonstrated experimentally on real data. [ABSTRACT FROM AUTHOR]

Many multiple-criteria decision-making (MCDM) methods have been proposed for decision-making environments. However, the performance of these methods is degraded by the uncertainty and inaccuracy which characterizes most practical decision-making environments as a result of the inherent prejudices and preferences of the decision-makers or experts and an insufficient volume of multiple inputs and outputs (MIO) information. Accordingly, the present study proposes an enhanced MIO classification method to address these limitations of existing MCDM methods. The proposed MIO classification method designated as the FVM-index method integrates fuzzy set theory ( F ST), variable precision rough set ( V PRS) theory, and a modified cluster validity index ( M CVI) function, and is designed specifically to filter out the uncertainty and inaccuracy inherent in the surveyed MIO real-valued dataset; thereby improving the classification performance. The effectiveness of the proposed approach is first demonstrated by comparing the MIO classification results obtained for three relating UCI datasets: (1) the original dataset; (2) a dataset with a large amount of inaccurate instances; and (3) an FVM-index filtered dataset extracted from the original dataset using a statistical approach. Then, the validity of the proposed approach is illustrated by using an Augmented Reality product design and a hospital related datasets. The results confirm that the proposed FVM-index method provides a good classification performance even in the presence of inaccuracy and uncertainty. As a result, it provides a robust approach for the extraction of reliable decision-making rules. [ABSTRACT FROM AUTHOR]

Due to the fact that limited amounts of labeled data are normally available in real-world, semi-supervised learning has become a popular option, where we expect to use unlabeled data information to improve the learning performance. However, how to use such unlabeled information to make the predicted labels more reliable remains to be a key for any successful learning. In this paper, we propose a semi-supervised learning framework via combination of semi-supervised clustering and semi-supervised classification. In our approach, the predicted labels are selected by both the constrained k -means and safe semi-supervised SVM (S4VMs) to improve the reliability of the predicted labels. Extensive evaluations on collection of benchmarks and real-world action recognition datasets show that the proposed technique outperforms the others. [ABSTRACT FROM AUTHOR]

In this letter, a robust kernel adaptive algorithm, called the kernel recursive maximum correntropy (KRMC), is derived in kernel space and under the maximum correntropy criterion (MCC). The proposed algorithm is particularly useful for nonlinear and non-Gaussian signal processing, especially when data contain large outliers or disturbed by impulsive noises. The superior performance of KRMC is confirmed by simulation results about short-term chaotic time series prediction in alpha-stable noise environments. [ABSTRACT FROM AUTHOR]

Atom probe tomography (APT) is a valuable near-atomic scale imaging technique, which yields mass spectrographic data. Experimental correctness can often pivot on the identification of peaks within a dataset, this is a manual process where subjectivity and errors can arise. The limitations of manual procedures complicate APT experiments for the operator and furthermore are a barrier to technique standardisation. In this work we explore the capabilities of computer-guided ranging to aid identification and analysis of mass spectra. We propose a fully robust algorithm for enumeration of the possible identities of detected peak positions, which assists labelling. Furthermore, a simple ranking scheme is developed to allow for evaluation of the likelihood of each possible identity being the likely assignment from the enumerated set. We demonstrate a simple, yet complete work-chain that allows for the conversion of mass-spectra to fully identified APT spectra, with the goal of minimising identification errors, and the inter-operator variance within APT experiments. This work chain is compared to current procedures via experimental trials with different APT operators, to determine the relative effectiveness and precision of the two approaches. It is found that there is little loss of precision (and occasionally gain) when participants are given computer assistance. We find that in either case, inter-operator precision for ranging varies between 0 and 2 “significant figures” (2 σ confidence in the first n digits of the reported value) when reporting compositions. Intra-operator precision is weakly tested and found to vary between 1 and 3 significant figures, depending upon species composition levels. Finally it is suggested that inconsistencies in inter-operator peak labelling may be the largest source of scatter when reporting composition data in APT. [ABSTRACT FROM AUTHOR]

Early identification and detection of abnormal patterns is vital for a number of applications. In manufacturing for example, slide shifts and alterations of patterns might be indicative of some production process anomaly, such as machinery malfunction. Usually due to the continuous flow of data, monitoring of manufacturing processes and other types of applications requires automated control chart pattern recognition (CCPR) algorithms. Most of the CCPR literature consists of supervised classification algorithms. Fewer studies consider unsupervised versions of the problem. Despite the profound advantage of unsupervised methodology for less manual data labeling their use is limited due to the fact that their performance is not robust enough and might vary significantly from one algorithm to another. In this paper, we propose the use of a consensus clustering framework that takes care of this shortcoming and produces results that are robust with respect to the chosen pool of algorithms. Computational results show that the proposed method achieves not less than 79.10% G -mean with most of test instances achieving higher than 90%. This happens even when in the algorithmic pool are included algorithms with performance less than 15%. To our knowledge, this is the first paper proposing an unsupervised consensus learning approach in CCPR. The proposed approach is promising and provides a new research direction in unsupervised CCPR literature. [ABSTRACT FROM AUTHOR]

RGB-D cameras like PrimeSense and Microsoft Kinect are popular sensors in the simultaneous localization and mapping researches on mobile robots because they can provide both vision and depth information. Most of the state-of-the-art RGB-D SLAM systems employ the Iterative Closest Point (ICP) algorithm to align point features, whose spatial positions are computed by the corresponding depth data of the sensors. However, the depth measurements of features are often disturbed by noise because visual features tend to lie at the margins of real objects. In order to reduce the estimation error, we propose a method that extracts and selects the features with reliable depth values, i.e. planar point features. The planar features can benefit the accuracy and robustness of traditional ICP, while holding a reasonable computation cost for real-time applications. An efficient RGB-D SLAM system based on planar features is also demonstrated, with trajectory and map results from open datasets and a physical robot in real-world experiments. [ABSTRACT FROM AUTHOR]

In this paper, a new robust data clustering algorithm inspired by Newtonian law of gravity is proposed. The proposed algorithm not only reduces the effects of noise and outliers but also, it is not sensible to the initial positions of the centroids. In the proposed method, data points and the cluster centroids are considered as fixed celestial objects and movable objects, respectively. The celestial objects apply a gravity force to the movable objects and change their positions in the feature space and therefore, the best positions of the cluster centroids are determined by employing the law of gravity. To evaluate the performance of the proposed algorithm, a comparative experimental study with some well-known clustering algorithms, using three visual datasets as well as several benchmark datasets from UCI, is performed. The experimental results confirm the effectiveness and the efficiency of the proposed clustering algorithm. [ABSTRACT FROM AUTHOR]

We mainly study the low-rank image recovery problem by proposing a bilinear low-rank coding framework called Tensor Low-Rank Representation. For enhanced low-rank recovery and error correction, our method constructs a low-rank tensor subspace to reconstruct given images along row and column directions simultaneously by computing two low-rank matrices alternately from a nuclear norm minimization problem, so both column and row information of data can be effectively preserved. Our bilinear approach seamlessly integrates the low-rank coding and dictionary learning into a unified framework. Thus, our formulation can be treated as enhanced Inductive Robust Principal Component Analysis with noise removed by low-rank representation, and can also be considered as the enhanced low-rank representation with a clean informative dictionary via low-rank embedding. To enable our method to include outside images, the out-of-sample extension is also presented by regularizing the model to correlate image features with the low-rank recovery of the images. Comparison with other criteria shows that our model exhibits stronger robustness and enhanced performance. We also use the outputted bilinear low-rank codes for feature learning. Two unsupervised local and global low-rank subspace learning methods are proposed for extracting image features for classification. Simulations verified the validity of our techniques for image recovery, representation and classification. [ABSTRACT FROM AUTHOR]

The effect of corruption on airport productive efficiency is analyzed using an unbalanced panel data of major European airports from 2003 to 2009. We first compute the residual (or net) variable factor productivity using the multilateral index number method and then apply robust cluster random effects model in order to evaluate the importance of corruption. We find strong evidence that corruption has negative impacts on airport operating efficiency; and the effects depend on the ownership form of the airport. The results suggest that airports under mixed public–private ownership with private majority achieve lower levels of efficiency when located in more corrupt countries. They even operate less efficiently than fully and/or majority government owned airports in high corruption environment. We control for economic regulation, competition level and other airports’ characteristics. Our empirical results survive several robustness checks including different control variables, three alternative corruption measures: International Country Risk Guide (ICRG) corruption index, Corruption Perception Index (CPI) and Control of Corruption Index (CCI). The empirical findings have important policy implications for management and ownership structuring of airports operating in countries that suffer from higher levels of corruption. [ABSTRACT FROM AUTHOR]

Cycling, as a mode share of urban travel, is widely desired to be increased. To support the delivery of improved infrastructure, robust modelling is desired and modelling such agents demands real-world calibration. Data to enable this is expensive to obtain by conventional means. This paper presents and demonstrates a process for the analysis of video to provide such data. This analysis yields spatiotemporal data for experimentally-observed cyclists from which velocity information (amongst other things) can be derived. With further refinement, this process can be used in the analysis of existing and future highway video data. [ABSTRACT FROM AUTHOR]

A central issue in biological data analysis is that uncertainty, resulting from different factors of variability, may change the effect of the events being investigated. Therefore, robustness is a fundamental step to be considered. Robustness refers to the ability of a process to cope well with uncertainties, but the different ways to model both the processes and the uncertainties lead to many alternative conclusions in the robustness analysis. In this paper we apply a framework allowing to deal with such questions for mass spectrometry data. Specifically, we provide robust decisions when testing hypothesis over a case/control population of subject measurements (i.e. proteomic profiles). To this concern, we formulate (i) a reference model for the observed data (i.e., graphs), (ii) a reference method to provide decisions (i.e., test of hypotheses over graph properties) and (iii) a reference model of variability to employ sources of uncertainties (i.e., random graphs). We apply these models to a realcase study, analyzing the mass spectrometry profiles of the most common type of Renal Cell Carcinoma; the Clear Cell variant. [ABSTRACT FROM AUTHOR]

We present a novel approach to learn binary classifiers when only positive and unlabeled instances are available (PU learning). This problem is routinely cast as a supervised task with label noise in the negative set. We use an ensemble of SVM models trained on bootstrap resamples of the training data for increased robustness against label noise. The approach can be considered in a bagging framework which provides an intuitive explanation for its mechanics in a semi-supervised setting. We compared our method to state-of-the-art approaches in simulations using multiple public benchmark data sets. The included benchmark comprises three settings with increasing label noise: (i) fully supervised, (ii) PU learning and (iii) PU learning with false positives. Our approach shows a marginal improvement over existing methods in the second setting and a significant improvement in the third. [ABSTRACT FROM AUTHOR]

In this paper, we present a robust real-time hand tracking system via multi-cue integration. In practice, the motion information of the hand, such as optical flow, is hard to exploit, because images of hands lack texture. As a result, the integration of the color and motion cues using conventional integration algorithms is difficult. Here, we integrate the motion and color cues from a novel feature point selection view. The hand is tracked using feature points, and the integration is realized during the feature points generation and selection process. In the generation process, a bounding box estimated by the color cue is used to provide a region for the feature points generation. Then, the RCD ( Representative , Compact and Diverse ) criteria are proposed to control the feature point selection process. After the selection process, the feature points are tracked using estimates of the motion of each feature point. The centroid of the feature points in each frame is adopted as the position of the hand. The experimental results show that our integration algorithm outperforms tracking algorithms that only use a single cue. Also the proposed tracking algorithm is more robust in complex environments than other state-of-art algorithms. [ABSTRACT FROM AUTHOR]

Attribution studies investigate the causes of recent global warming. For a few decades the scientific community generally adopted dynamical models – the so-called Global Climate Models (GCMs) – for such an investigation. These models show the essential role of anthropogenic forcings in driving the temperature behaviour of the last half century. In the last period even other (data-driven) methodological approaches were adopted for attribution studies. This allows the scientific community to compare the results coming from these different approaches and to possibly increase their robustness. For such a purpose, the paper explores the possibility of applying a robustness framework, so far used only in the case of multi-model GCM ensembles, to a strategy including models from different methodological orientations, assessing such an application especially in the light of the independence issue. [ABSTRACT FROM AUTHOR]

The class imbalance problem has attracted a lot of attention from the data mining community recently, becoming a current trend in machine learning research. The Consolidated Tree Construction (CTC) algorithm was proposed as an algorithm to solve a classification problem involving a high degree of class imbalance without losing the explaining capacity, a desirable characteristic of single decision trees and rule sets. CTC works by resampling the training sample and building a tree from each subsample, in a similar manner to ensemble classifiers, but applying the ensemble process during the tree construction phase, resulting in a unique final tree. In the ECML/PKDD 2013 conference the term “Inner Ensembles” was coined to refer to such methodologies. In this paper we propose a resampling strategy for classification algorithms that use multiple subsamples. This strategy is based on the class distribution of the training sample to ensure a minimum representation of all classes when resampling. This strategy has been applied to CTC over different classification contexts. A robust classification algorithm should not just be able to rank in the top positions for certain classification problems but should be able to excel when faced with a broad range of problems. In this paper we establish the robustness of the CTC algorithm against a wide set of classification algorithms with explaining capacity. [ABSTRACT FROM AUTHOR]