Clipped multiscale spatial processes for multivariate plant cover data

Modeling risk characterization networks for chemical processes based on multi-variate data

Plant cover is measured by different methods and it is important to be able to estimate mean cover and to compare estimates of plant cover across different sampling methods in a coherent statistical framework. Here, a framework that incorporates (1) pin‐point cover data, (2) visually determined cover data, and (3) ordinal cover classification systems (e.g., Braun‐Blanquet cover data) is presented and tested on simulated plant cover data. The effect of measurement error when applying a visual determination of plant cover is considered. Generally, the estimation of the mean plant cover was well‐behaved and unbiased for all the three methods, whereas the estimate of the intra‐plot correlation tended to be upward biased and especially so if the plant cover data was collected using the Braun‐Blanquet method. It was surprising that the Braun‐Blanquet sampling procedure provided mean plant cover estimates that were comparable to the other sampling schemes. This method shows promise in the attempt to use the large amount of historic Braun‐Blanquet plant cover data in the investigation of the underlying causes for observed vegetation changes.

In real-world applications, data streams are gener-ated all the time. Real-time data processing of complex multi-variate data becomes essential for many downstream analysis tasks. However, real-world data is not bound to be of the same distribution - the environment where it is recorded could be rapidly evolving, making it a challenge to apply a stationary model throughout the whole flow of data. Moreover, labels are often expensive to acquire or delayed in such scenarios. This paper considers the severe problem in an unsupervised setting, where we detect the distributional drifts in the input data stream without considering the data labels or specific classifiers. We propose AECDD (Autoencoder-based Concept Drift Detec-tor), a reconstruction-based unsupervised drift detection model using an Autoencoder to track changes in data distribution. More specifically, instead of detecting drifts by tracking the classifi-cation error change as in many existing approaches, we track the reconstruction error of the Autoencoder in an unsupervised manner. Our empirical evaluation shows that AECDD captures the drifts well in multivariate data streams. Finally, we also demonstrate the drift in the reconstruction error space by an intuitive visualization.

Time series and multivariate data are required to accommodate more complex decision making. Data are processed using data mining techniques in order to obtain valuable trends in the data that can be used to support in decision making processes. Unfortunately, we often encounter a lot of problems in preparing the data for data mining process. One of the problem is missing values. Missing values in data may causes inaccurate results of data processing. Imputation are used to handle missing values. In this thesis missing value are handled using Dynamic Bayesian Network (DBN). DBN is a useful technique to maintain the relationships between attributes of data. The results of the prediction are used to fill in the missing values in the data. Support Vector Regression (SVR) algorithm is used for predicting the missing values. It is chosen for its good performance in comparison to other similar algorithms. Validation of the technique is carried out by using Symmetric Mean Absolute Percentage Error (SMAPE). SMAPE used to count an error rate for prediction model. The use of the DBN of feature selection for SVR can't decrease the error rate of the model.

Background This article proposes an extension of empirical wavelet transform (EWT) algorithm for multivariate signals specifically applied to cardiovascular physiological signals. Materials and methods EWT is a newly proposed algorithm for extracting the modes in a signal and is based on the design of an adaptive wavelet filter bank. The proposed algorithm finds an optimum signal in the multivariate data set based on mode estimation strategy and then its corresponding spectra is segmented and utilized for extracting the modes across all the channels of the data set. Results The proposed algorithm is able to find the common oscillatory modes within the multivariate data and can be applied for multichannel heterogeneous data analysis having unequal number of samples in different channels. The proposed algorithm was tested on different synthetic multivariate data and a real physiological trivariate data series of electrocardiogram, respiration, and blood pressure to justify its validation. Conclusions In this article, the EWT is extended for multivariate signals and it was demonstrated that the component-wise processing of multivariate data leads to the alignment of common oscillating modes across the components.

Modern industrial mining and mineral processing applications are characterized by large volumes of historical process data. Hazardous events occurring in these processes compromise process safety and therefore overall viability. These events are recorded in historical data and are often preceded by characteristic patterns. Reconstruction-based data-driven models are trained to reconstruct the characteristic patterns of hazardous event-preceding process data with minimal residuals, facilitating effective event prediction based on reconstruction residuals. This investigation evaluated one-dimensional convolutional auto-encoders as reconstruction-based data-driven models for predicting positive pressure events in industrial furnaces. A simple furnace model was used to generate dynamic multivariate process data with simulated positive pressure events to use as a case study. A one-dimensional convolutional auto-encoder was trained as a reconstruction-based model to recognize the data preceding the hazardous events, and its performance was evaluated by comparing it to a fully-connected auto-encoder as well as a principal component analysis reconstruction model. This investigation found that one-dimensional convolutional auto-encoders recognized event-preceding patterns with lower detection delays, higher specificities, and lower missed alarm rates, suggesting that the one-dimensional convolutional auto-encoder layout is superior to the fully connected auto-encoder layout for use as a reconstruction-based event prediction model. This investigation also found that the nonlinear auto-encoder models outperformed the linear principal component model investigated. While the one-dimensional auto-encoder was evaluated comparatively on a simulated furnace case study, the methodology used in this evaluation can be applied to industrial furnaces and other mineral processing applications. Further investigation using industrial data will allow for a view of the convolutional auto-encoder’s absolute performance as a reconstruction-based hazardous event prediction model.

The study was conducted to characterize previously unexplored wetland vegetation in lower montane areas of the Himalaya (1597–2538 m above sea level) of Jigme Dorji National Park, Gasa District, Northern Bhutan. A random quadrat sampling method was employed to assess percent plant cover and environmental data were collected following standard procedures. Cluster and indicator species analyses using plant cover data were used to define the species composition of plant communities. Differences in community composition along gradients of elevation, slope, soil pH, available phosphorus, and peat/soil depth were analyzed using Canonical Correspondence Analysis (CCA). The wetlands supported 120 vascular plant species from 84 genera and 51 families. Analyses identified four plant communities, I to IV, each named from the three most prominent species. The key indicator species of four plant communities, Acorus calamus, Carex diandra, Equisetum ramosissimum, and Carex capillacea, dominate shallow fresh marsh, seasonally flooded basin of flat, fresh water meadow, and poor fen, respectively. Elevation and soil phosphorus were the most important environmental variables in explaining the variation in wetland vegetation. The findings can be used to support the work of conservation agencies to identify and conserve these plant communities and their habitats in the Himalaya.

Multidisciplinary marine environmental database for the Aral Sea

Multidisciplinary marine environmental database for the Aral Sea

Batch process performance monitoring has been achieved primarily using process measurements with the extracted information being associated with the physical parameters of the process. With increasing attention now being paid to the application of on‐line real‐time process analytics through spectrometry, together with the FDA Process Analytical Technologies (PAT) initiative, the use of spectroscopic information for enhanced monitoring of reactions is gaining impetus. The harmonious integration of process data and spectroscopic data then becomes a major challenge. By integrating the process and spectroscopic measurements for multivariate statistical data modelling and analysis, it is conjectured that improved process understanding and fault diagnosis can be achieved. An investigation into combining process and spectral data using multiblock and multiresolution analysis is proposed and the results from the analysis of experimental data from two industrial application studies are presented to demonstrate the improvements achievable in terms of process performance monitoring and fault diagnosis.

Over the last few years, the development of multi-channel sensors motivated interest in methods for the coherent processing of multivariate data. From blind source separation (BSS) to multi/hyper-spectral data restoration, an extensive work has already been dedicated to multivariate data processing. Previous work has emphasized on the fundamental role played by sparsity and morphological diversity to enhance multichannel signal processing. Morphological diversity has been first introduced in the mono-channel case to deal with contour/texture extraction. The morphological diversity concept states that the data are the linear combination of several so-called morphological components which are sparse in different incoherent representations. In that setting, piecewise smooth features (contours) and oscillating components (textures) are separated based on their morphological differences assuming that contours (respectively textures) are sparse in the Curvelet representation (respectively Local Discrete Cosine representation). In the present paper, we define a multichannel-based framework for sparse multivariate data representation. We introduce an extension of morphological diversity to the multichannel case which boils down to assuming that each multichannel morphological component is diversely sparse spectrally and/or spatially. We propose the Generalized Morphological Component Analysis algorithm (GMCA) which aims at recovering the so-called multichannel morphological components. Hereafter, we apply the GMCA framework to two distinct multivariate inverse problems : blind source separation (BSS) and multichannel data restoration. In the two aforementioned applications, we show that GMCA provides new and essential insights into the use of morphological diversity and sparsity for multivariate data processing. Further details and numerical results in multivariate image and signal processing will be given illustrating the good performance of GMCA in those distinct applications.

Multivariate data is collected in many fields, such as chemometrics, econometrics, financial engineering and genetics. In multivariate data, heteroscedasticity and collinearity occur frequently. And selecting material predictors is also a key issue when analyzing multivariate data. To accomplish these tasks, multivariate linear regression model is often constructed. We thus propose row-sparse elastic-net regularized multivariate Huber regression model in this paper. For this new model, we proof its grouping effect property and the property of resisting sample outliers. Based on the KKT condition, an accelerated proximal sub-gradient algorithm is designed to solve the proposed model and its convergency is also established. To demonstrate the accuracy and efficiency, simulation and real data experiments are carried out. The numerical results show that the new model can deal with heteroscedasticity and collinearity well.

The present study investigates the hydrogeochemical regime of a complex aquifer system in a highly cultivated area of Thessaly, central Greece. To do so, totally forty (40) groundwater samples were collected for three aquifer units with diverse geological and hydrogeological attributes and analyzed for 77 parameters. Data processing was accomplished with the joint use of classic hydrogeochemical techniques including major ion molar ratios and graphical interpretation, as well as multivariate statistical methods including R-mode factor (FA) and hierarchical cluster analysis (HCA). Results showed that major ion hydrogeochemistry is characterized by the prevalence of calcium (median = 81 mg/L) and bicarbonates (median = 308 mg/L) in the following descending order of concentrations for cations Ca2+>Mg2+>Na+>K+ and anions HCO3−>NO3−>SO42−>Cl−, respectively. Nitrate values are elevated (median = 23 mg/L), especially in the porous quaternary aquifer, indicating the ongoing agricultural impact from the excessive use of nitrogen fertilizers and manure. The results of multivariate statistics highlighted four factors that chiefly control 81.4 % of overall hydrogeochemistry, related with both geogenic and anthropogenic impacts. The geogenic impact is mainly attributed to the geological substrate and secondarily to the ongoing geochemical (redox) conditions which in turn enrich or deplete groundwater solution with different ions; anthropogenic impact is mainly related with the extensive agricultural practices which favor nitrate enrichment and salinization due to irrigation water return flow.

Application of multivariate statistics to ecotoxicological field studies

Multivariate statistical technologies, the principal components analysis and projection to latent structures, are data modeling technologies based on advanced multivariable statistical methods. These methods are capable of: analyzing process data; building predictive models and providing SPC functionality by extracting information from all process and quality data from an operation simultaneously. Multivariate statistical methods are especially powerful techniques for analyzing industrial data sets that have the following characteristics: higher dimensionality; high collinearity; noisy; and with some missing data. The application of these methods have been successfully done at Dofasco since 1993 to analyze data for a variety of purposes, develop online predictive models, and develop online process monitoring systems. An online application is described to illustrate the advantages of this technology.