Develop an Ensemble Support Vector Data Description method for improving invasive tamarisk mapping at regional scale

Anomaly detection using improved deep SVDD model with data structure preservation

The paper aims to solve the problem of insufficient high risk data in risk assessment of R&D projects. A one-class classification method called support vector data description (SVDD) is studied, and an intelligent risk assessment model based on SVDD with fuzzy regression information is also proposed. The model comes into being a new approach. Applying this approach, firstly verify the conversional risk evaluation indexes by fuzzy regression technique to develop a sensitive index system. Secondly the study uses the historical risk data referring to these indexes to train the SVDD one-class classifier. Unlike previously proposed intelligent methods of risk assessment, with this model the risk level can be distinguished only by training of low risk data. The results of its application on an example show that the method is feasible for risk assessment with the fuzzy high risk data.

Fault signal is always a problem that interferes with the operation of fiber board gluing control system. This paper proposes a Possibilistic C-Means (PCM) improved support vector data description (SVDD) method to construct a multi-classifier for the fault diagnosis of fiber gluing control system. In the proposed method, SVDD is employed to construct a multi-classifier for the fault diagnosis in the gluing system. Because the original SVDD is sensitive to the noises and outliers, we use PCM to improve the accuracy of classifier and then conduct a series of experiments. The results of the experiments show that the method proposed can identify the actual situation accurately and provide a high identification rate up to 97%, which is better than original SVDD.

Support Vector Data Description (SVDD) methods have been successfully applied to hyperspectral anomaly detection. Unfortunately, the performance of SVDD methods suffers when noisy or non-informative bands are present in the data. If a set of sparse features could be identified for these techniques, the resulting data may improve SVDD performance while enjoying the benefits of decreased processing overhead. Although band selection has been investigated in previous efforts, this work builds on recent research that has resulted in the development of a theoretical framework for signal classification with sparse representation using L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> measures.

Aim We explore the utility of newly available optical and microwave remote sensing data from the Moderate Resolution Imaging Spectroradiometer (MODIS) and QuikSCAT (QSCAT) instruments for species distribution modelling at regional to continental scales. Using eight Neotropical species from three taxonomic groups, we assess the extent to which remote sensing data can improve predictions of their geographic distributions. For two bird species, we investigate the specific contributions of different types of remote sensing variables to the predictions and model accuracy at the regional scale, where the benefits of the MODIS and QSCAT satellite data are expected to be most significant.Location South America, with a focus on the tropical and subtropical Andes and the Amazon Basin.Methods Potential geographic distributions of eight species, namely two birds, two mammals and four trees, were modelled with the maxent algorithm at 1‐km resolution over the South American continent using climatic and remote sensing data separately and combined. For each species and model scenario, we assess model performance by testing the agreement between observed and simulated distributions across all thresholds and, in the case of the two focal bird species, at selected thresholds.Results Quantitative performance tests showed that models built with remote sensing and climatic layers in isolation performed well in predicting species distributions, suggesting that each of these data sets contains useful information. However, predictions created with a combination of remote sensing and climatic layers generally resulted in the best model performance across the three taxonomic groups. In Ecuador, the inclusion of remote sensing data was critical in resolving the known geographically isolated populations of the two focal bird species along the steep Amazonian–Andean elevational gradients. Within remote sensing subsets, microwave‐based data were more important than optical data in the predictions of the two bird species.Main conclusions Our results suggest that the newly available remote sensing data (MODIS and QSCAT) have considerable utility in modelling the contemporary geographical distributions of species at both regional and continental scales and in predicting range shifts as a result of large‐scale land‐use change.

The effective extraction of impervious surfaces is critical to monitor their expansion and ensure the sustainable development of cities. Open geographic data can provide a large number of training samples for machine learning methods based on remote-sensed images to extract impervious surfaces due to their advantages of low acquisition cost and large coverage. However, training samples generated from open geographic data suffer from severe sample imbalance. Although one-class methods can effectively extract an impervious surface based on imbalanced samples, most of the current one-class methods ignore the fact that an impervious surface comprises varied geographic objects, such as roads and buildings. Therefore, this paper proposes an object-oriented deep multi-sphere support vector data description (OODMSVDD) method, which takes into account the diversity of impervious surfaces and incorporates a variety of open geographic data involving OpenStreetMap (OSM), Points of Interest (POIs), and trajectory GPS points to automatically generate massive samples for model learning, thereby improving the extraction of impervious surfaces with varied types. The feasibility of the proposed method is experimentally verified with an overall accuracy of 87.43%, and its superior impervious surface classification performance is shown via comparative experiments. This provides a new, accurate, and more suitable extraction method for complex impervious surfaces.

This paper exposes automatic classification for wooden board according to its knot defects. A four-parameter-classification vector, which includes the knot size and red component pixels of interior and exterior and boundary part of the knot, is formed to recognize the knot type. A possibilistic c-means (PCM) improved support vector data description (SVDD) method was proposed to construct a multi-classifier to classify four types of wood knots. The results obtained with our method show a real improvement of the recognition rate, which is 94%, compared to the original SVDD classifier, which recognition rate is just 86%, and experiments also testify PCM can help SVDD overcome the shortage of being sensitive to the noises and outliers.

Power electronic circuits (PECs) are prone to various failures, whose classification is of paramount importance. This paper presents a data-driven based fault diagnosis technique, which employs a support vector data description (SVDD) method to perform fault classification of PECs. In the presented method, fault signals (e.g. currents, voltages, etc.) are collected from accessible nodes of circuits, and then signal processing techniques (e.g. Fourier analysis, wavelet transform, etc.) are adopted to extract feature samples, which are subsequently used to perform offline machine learning. Finally, the SVDD classifier is used to implement fault classification task. However, in some cases, the conventional SVDD cannot achieve good classification performance, because this classifier may generate some so-called refusal areas (RAs), and in our design these RAs are resolved with the one-against-one support vector machine (SVM) classifier. The obtained experiment results from simulated and actual circuits demonstrate that the improved SVDD has a classification performance close to the conventional one-against-one SVM, and can be applied to fault classification of PECs in practice.

In this paper, we describe a method for video summarization that operates on a video segment level. We formulate this problem as the one of automatic video segment selection based on a learning process that employs salient video segment paradigms. We design an hierarchical learning scheme that consists of two steps. At the first step, an unsupervised process is performed in order to determine salient video segment types. The second step is a supervised learning process that is performed for each of the salient video segment type independently. For the latter case, since only salient training examples are available, the problem is stated as an one-class classification problem. In order to take into account subclass information that may appear in the video segment types, we introduce a novel formulation of the Support Vector Data Description method that exploits subclass information in its optimization process. We evaluate the proposed approach in three Hollywood movies, where the performance of the proposed Subclass SVDD (SSVDD) algorithm is compared with that of related methods. Experimental results show that the adoption of both hierarchical learning and the proposed SSVDD method contribute to the final classification performance.

To improve the efficiency and usability of adaptive anomaly detection system, we propose a new framework based on Support Vector Data Description (SVDD) method. This framework includes two main techniques: online change detection and unsupervised anomaly detection. The first one enables automatically obtain model training data by measuring and distinguishing change caused by intensive attacks from normal behavior change and then filtering most intensive attacks. The second retrains model periodically and detects the forthcoming data. Results of experiments with the KDD’99 network data show that these techniques can handle intensive attacks effectively and adapt to the concept drift while still detecting attacks. As a result, false positive rate is reduced from 13.43% to 4.45%.

This article presents a comprehensive subpixel water mapping algorithm to automatically produce routinely open water fraction maps in the Tibetan Plateau (TP) with the Moderate Resolution Imaging Spectroradiometer (MODIS). A multi-index threshold endmember extraction method was applied to select the endmembers from MODIS images. To incorporate endmember variability, an endmember selection strategy, called the combined use of typical and neighboring endmembers, was adopted in multiple endmember spectral mixture analysis (MESMA), which can assure a robust subpixel water fractions estimation. The accuracy of the algorithm was assessed at both the local scale and regional scale. At the local scale, a comparison using the eight pairs of MODIS/Landsat 8 Operational Land Imager (OLI) water maps demonstrated that subpixels water fractions were well retrieved with a root mean square error (RMSE) of 7.86% and determination coefficient (R2) of 0.98. At the regional scale, the MODIS water fraction map in October 2014 matches well with the TP lake data set and the Global Lake and Wetland Database (GLWD) in both latitudinal and longitudinal distribution. The lake area estimation is more consistent with the reference TP lake data set (difference of −3.15%) than the MODIS Land Water Mask (MOD44W) (difference of −6.39%).

Support vector data description (SVDD) is an effective algorithm for nonlinear process monitoring. However, the conventional SVDD method can't deal with the incipient faults well, which has the small fault amplitude and is easy to be overlapped by industrial noises. Aiming at this problem, an improved SVDD, called probability related SVDD in local variable field (LVPSVDD), is proposed to detect the incipient faults in nonlinear processes. Firstly, the method divides process variables into several local variable fields by hierarchical clustering, and the SVDD model of each variable field is built. Then the sliding window technology is applied to the SVDD distance statistics, and the probability distribution change in the sliding window is measured by Kullback Leibler divergence (KLD). For each local variable field, the corresponding probability related monitoring statistic is developed to replace the original distance statistic. Finally, the global monitoring statistic is obtained by integrating the monitoring results of all local variable fields with Bayesian inference strategy. The method is illustrated with simulation on the continuous stirred tank reactor (CSTR).

Host plant-mediated effects of climate change on the occurrence of the Alcon blue butterfly (Phengaris alcon)

An edge-pixels-based support vector data description (EPSVDD) method has been developed for improving one-class classification accuracy. The proposed method was validated in two experiments: a simulated experiment and an actual experiment. In the simulated experiment, a ring segmentation search method was performed to segment the wheat spectral feature for deriving training samples of different spectral responses. As the training data moved from the center to the edge of wheat distribution, the hypersphere expanded and the overall accuracy (OA) simultaneously increased, highlighting the potential advantage of edge pixels in SVDD classification. In the actual experiment, edge training samples were manually acquired from geographical parcel boundary and minimum noise fraction (MNF) scatterplots for both wheat and bare-land classes. For the wheat class, EPSVDD yielded an improved classification with an OA of 92.71% and a producer’s accuracy of 95.81%, which were higher than those of conventional SVDD method using typical training samples. Similarly, for the bare-land class, the OA of the EPSVDD was 92.53%, which was also significantly higher than traditional SVDD method. Then, SVDD classifications were carried out and repeated 10 times using different training set sizes. Mean OAs were almost higher than 0.9 with variance less than 0.03 using edge training samples, while highest OAs for wheat and bare land classes were 0.74 and 0.81, respectively, using random sampling method. The EPSVDD can effectively select the informative training sample for SVDD classifier to improve the accuracy of one-class classification.

As one classical anomaly detection technology, support vector data description (SVDD) has been successfully applied to nonlinear chemical process monitoring. However, the basic SVDD model cannot achieve a satisfactory fault detection performance in the complicated cases because of its intrinsic shallow learning structure. Motivated by the deep learning theory, one improved SVDD method, called ensemble deep SVDD (EDeSVDD), is proposed in order to monitor the process faults more effectively. In the proposed method, a deep support vector data description (DeSVDD) framework is firstly constructed by introducing the deep feature extraction procedure. Different to the traditional SVDD with only one feature extraction layer, DeSVDD is designed with multi-layer feature extraction structure and optimized by minimizing the data-enclosing hypersphere with the regularization of the deep network weights. Further considering the problem that DeSVDD monitoring performance is easily affected by the model structure and the initial weight parameters, an ensemble DeSVDD (EDeSVDD) is presented by applying the ensemble learning strategy based on Bayesian inference. A series of DeSVDD sub-models are generated at the parameter level and the structure level, respectively. These two levels of sub-models are integrated for a holistic monitoring model. To identify the cause variables for the detected faults, a fault isolation scheme is designed by applying the distance correlation coefficients to measure the nonlinear dependency between the original variables and the holistic monitoring index. The applications to the Tennessee Eastman process demonstrate that the proposed EDeSVDD model outperforms the traditional SVDD model and the DeSVDD model in terms of fault detection performance and can identify the fault cause variables effectively.