SVM-Based Data Editing for Enhanced One-Class Classification of Remotely Sensed Imagery

<p>In one-class classification, the low variance directions in the training data carry crucial information to build a good model of the target class. Boundary-based methods like One-Class Support Vector Machine (OSVM) preferentially separates the data from outliers along the large variance directions. On the other hand, retaining only the low variance directions can result in sacrificing some initial properties of the original data and is not desirable, specially in case of limited training samples. This paper introduces a Covariance-guided One-Class Support Vector Machine (COSVM) classification method which emphasizes the low variance projectional directions of the training data without compromising any important characteristics. COSVM improves upon the OSVM method by controlling the direction of the separating hyperplane through incorporation of the estimated covariance matrix from the training data. Our proposed method is a convex optimization problem resulting in one global optimum solution which can be solved efficiently with the help of existing numerical methods. The method also keeps the principal structure of the OSVM method intact, and can be implemented easily with the existing OSVM libraries. Comparative experimental results with contemporary one-class classifiers on numerous artificial and benchmark datasets demonstrate that our method results in significantly better classification performance.</p>

Huberized one-class support vector machine with truncated loss function in the primal space

In this paper, we propose a method by engaging the One Class Support Vector Machine (OC-SVM) in the identification of Diffractive Optically Variable Images (DOVIs). OC-SVM, as a special SVM, can solve the problems of high-dimensional data sets and small sample size (SSS) with positive and negative unbalance training data. Image feature matrix is built by extracting image features from texture aspects. OC-SVM can be trained with the high-dimensional matrix directly, and does not have to reduce the dimensionality of feature matrix as the usual methods. The experiment results show the effectiveness of the proposed approach against Linear Discriminant Analysis. Considering time cost and correct classification rate, OC-SVM is suitable for the identification of DOVIs.

This article proposes an unsupervised deep learning–based approach to detect structural damage. Supervised deep learning methods have been proposed in recent years, but they require data from an intact structure and various damage scenarios of monitored structures for their training processes. However, the labeling work on the training data is typically time-consuming and costly, and sometimes collecting sufficient training data from various damage scenarios of infrastructures in service is impractical. In this article, the proposed unsupervised deep learning method based on a deep auto-encoder with an one-class support vector machine only uses the measured acceleration response data acquired from intact or baseline structures as training data, which enables future structural damage to be detected. The major contributions and novelties of the proposed method are as follows. First, an appropriate deep auto-encoder is carefully designed through comparative studies on the depth of neural networks. Second, the designed deep auto-encoder is taken as an extractor to obtain damage-sensitive features from the measured acceleration response data, and an one-class support vector machine is used as a damage detector. Third, experimental and numerical studies validate the high accuracy of the proposed method for damage detection: a 97.4% mean average for a 12-story numerical building model and a 91.0% accuracy for a laboratory-scaled steel bridge. Fourth, the proposed method also detects light damage (i.e. a 10% reduction in stiffness) with 96.9% to 99.0% accuracy, which shows its superior performance compared with the current state of the art. Fifth, it provides stable and more robust damage detection performance with reduced tuning parameters.

A comparative investigation of data-driven approaches based on one-class classifiers for condition monitoring of marine machinery system

One-class support vector machine (OCSVM) is one of the most popular algorithms in the one-class classification problem, but it has one obvious disadvantage: it is sensitive to noise. In order to solve this problem, the fuzzy membership degree is introduced into OCSVM, which makes the samples with different importance have different influences on the determination of classification hyperplane and enhances the robustness. In this paper, a new calculation method of membership degree is proposed and introduced into the fuzzy multiple kernel OCSVM (FMKOCSVM). The combined kernel is used to measure the local similarity between samples, and then, the importance of samples is determined based on the local similarity between training samples, so as to determine the membership degree and reduce the impact of noise. The proposed membership requires only positive data in the calculation process, which is consistent with the training set of OCSVM. In this method, the noise has a smaller membership value, which can reduce the negative impact of noise on the classification boundary. Simultaneously, this method of calculating membership has a higher efficiency. The experimental results show that FMKOCSVM based on proposed local similarity membership is efficient and more robust to outliers than the ordinary multiple kernel OCSVMs.

The U.S. Department of Agriculture's Conservation Reserve Program (CRP) was established by the Food Security Act of 1985. Since its inception, thousands of acres of cropland in stream riparian zones have been converted to conservation buffers through the planting of trees and native grasses. The objectives of this study were to determine the phosphorus (P)–sorption characteristics of the surface soil in a 13‐year‐old CRP buffer and an adjacent continuously cropped production area from which the buffer was created and to assess differences in P‐sorption maxima and P‐buffering capacity between the sites. Phosphorus sorption was modeled with both the simple Langmuir and the two‐surface Langmuir equations. There were significant differences in all P‐sorption parameters between the cropped area and the buffer over most of the depth increments studied. The cropped area soil had higher sorption max (Smax), binding energy (k), and P equilibrium buffering capacity (PEBC) than the buffer soil. However, the buffer had higher equilibrium P concentration (EPC). These findings imply that it may not be appropriate to assume that a buffer will act as a P sink simply because it is not receiving P fertilization. Any assessment of buffer or filter strip effectiveness for P retention should include an examination of the P‐sorption properties of the soils present.

Spatiotemporal information on crops and cropping systems can provide useful insights into disease outbreak mechanisms in croplands. In September 2011, a severe outbreak of Maize Lethal Necrosis (MLN) disease was reported in Bomet County, Kenya. We aimed to detect severely MLN-infected fields and discriminate mono, inter, and continuous maize cropping systems. We collected in-situ MLN severity observations and acquired multi-date and multi-sensor data viz., RapidEye (RE), Sentinel-1 (S1), digital elevation model (DEM), and Landsat-8 (L8) imagery. A hierarchical classification approach was used to map the cropping systems and severely MLN-infected fields during the short rainy season (September 2014–February 2015) using the random forest (RF), one-class support vector machine (OCSVM) and biased SVM (BSVM) classifiers. RF showed better performance when a balanced multi-class dataset was available. Both OCSVM and BSVM did not lead to an accurate high severity MLN class separation. Moreover, the BSVM classifier was able to separate the mono and intercropping systems. During the long rainy season (March–August 2015), only maize crop data were available, hence the BSVM as one class classifiers (OCC) was used and maize fields were successfully mapped even with high confusion rate. Furthermore, the distribution of maize intercropping system increased in low rainfall sites, and the continuous cropping system limited to only 31% of total maize cropland.

Stable night-time light data from the Defense Meteorological Satellite Program (DMSP) Operational Line-scan System (OLS) provide a unique proxy for anthropogenic development. This paper presents a regional urban extent extraction method using a one-class classifier and combinations of DMSP/OLS stable night-time light (NTL) data, MODIS normalized difference vegetation index (NDVI) data, and land surface temperature (LST) data. We first analyzed how well MODIS NDVI and LST data quantify the properties of urban areas. Considering that urban area is the only class of interest, we applied the one-class support vector machine (OCSVM) to classify different combinations of the three datasets. We evaluated the effectiveness of the proposed method and compared with the locally optimized threshold method in regional urban extent mapping in China. The experimental results demonstrate that DMSP/OLS NTL data, MODIS NDVI and LST data provide different but complementary information sources to quantify the urban extent at a regional scale. The results also indicate that the OCSVM classification of the combination of all three datasets generally outperformed the locally optimized threshold method. The proposed method effectively and efficiently extracted the urban extent at a regional scale, and is applicable to other study areas.

<p>Conservation agriculture has proved to be beneficial in terms of securing yield, sustainability of natural resources, and biodiversity of the natural and cultivated ecosystems. The effectiveness of existing and planned conservation practices in targeted watersheds in Tennessee, USA, were evaluated. Two watershed systems were selected in coordination with the U.S. Department of Agriculture - National Resources Conservation Service (NRCS) including four watersheds in Northern Middle Tennessee and six watersheds in West Tennessee.</p><p>Our objective was accomplished using the Annualized Agricultural Non-Point Source (AnnAGNPS) watershed pollution model to generate watershed simulations for our study areas. The main inputs databases needed include: (1) a 3-m LiDAR based Digital Elevation Model (DEM), (2) weather data from 23 NOAA stations and from AGNPS Climate Generator (agGEM), (3) soil data from the Web Soil Survey (WSS) and complementary soil description of physical and chemical properties from the USDA Soil Data Access website, (4) land use and land cover data describing crop type from 2009 to 2019 from the National Agricultural Statistics Service’s Cropland Data Layer (CDL), and (5) typical farming management practices that were generated by integrating spatiotemporal crop type information at raster grid cell scale (from CDL), average crop yield at county scale (from USDA-NASS), and one-year farming management schedule (from USDA-NRCS). In addition to the AnnAGNPS simulation representing existing conditions, 34 additional AnnAGNPS simulations representing alternative scenarios of conservation practices were evaluated. Eight scenarios depicting the effectiveness of sediment retention ponds under various stream order, stream length, and sediment yield conditions; 4 scenarios were run to depict the effectiveness of crop rotation under various sediment yield-based conditions; 4 scenarios were run to depict the effectiveness of the conservation reserve program (CRP) under various sediment yield-based conditions; and 18 scenarios were run to depict the effectiveness of riparian forest buffer under various buffer width, and sediment yield- based conditions.</p><p>Preliminary results indicate that the vegetative riparian buffer is a very effective practice that could eliminate up to 80% of the total watershed sediment yield if implemented in every stream of the watershed. Alternatively, creating and maintaining a riparian buffer in just agricultural fields could decrease the sediment yield by 42% to 50% depending on width and by 5 to 6% when implemented in the top sediment producing fields. The projected reduction from sediment retention ponds of sediment yield is 95% in the case of 233 ponds strategically placed across the Western TN watershed system. Crop rotation simulations show that this conservation practice could decrease sediment yield by up to 12% in the extreme scenario of applying it in every soybean agricultural field in the study area, making it less effective than the other simulated conservation practices. CRP decreases the sediment yield by more than 81% percent in the most optimistic scenario and by 10% in the least optimistic scenario.</p><p>Findings from this study support efforts in guiding future conservation strategies development contributing to water quality and sediment erosion improvement in the state of Tennessee and across the US.</p>

An one-class classification support vector machine model by interval-valued training data

In this work, we are interested in the extraction of areas of interest from satellite images by introducing a MOTRIBES/ OC-SVM approach. The One-Class Support Vector Machine (OC-SVM) is based on the estimation of a support that includes training data. It identifies areas of interest without including other classes from the scene. We propose generating optimal training data using the Multi-Objective TRIBES (MO-TRIBES) to improve the performances of the OC-SVM. The MO-TRIBES is a parameter-free optimization technique that manages the search space in tribes composed of agents. It makes different behavioral and structural adaptations to minimize the false positive and false negative rates of the OC-SVM. We have applied our proposed approach for the extraction of earthquakes and urban areas. The experimental results and comparisons with different state-of-the-art classifiers confirm the efficiency and the robustness of the proposed approach.

Comparison of Landsat TM and ERS-2 SAR data for discriminating among grassland types and treatments in eastern Kansas

Anomaly-based network intrusion detection systems (NIDSs) complement signature-based detection methods to identify unknown (zero-day) attacks. The integration of machine and deep learning enhanced the efficiency of such NIDSs. However, since anomaly-based NIDSs heavily depend on the quality of the training data, the presence of malicious traffic in the training set can significantly degrade the model’s performance. Purging the training data of such traffic is often impractical. This study investigates performance degradation caused by increasing amounts of malicious traffic in the training data. We introduced varying portions of malicious traffic into the training sets of machine and deep learning models to determine which approach is most resilient to unclean training data. Our experiments revealed that Autoencoders, using a byte frequency feature set, achieved the highest F2 score (0.8989), with only a minor decrease of 0.0009 when trained on the most contaminated dataset. This performance drop was the smallest compared to other algorithms tested, including an Isolation Forest, a Local Outlier Factor, a One-Class Support Vector Machine, and Long Short-Term Memory.

A novel incremental one-class support vector machine based on low variance direction