Class Boundaries Research Articles

Cross-Category Mechanical Fault Diagnosis Based on Deep Few-Shot Learning

Industrial fault diagnosis often faces challenges from insufficient examples. Methods leveraging Generative Adversarial Network or transfer learning address this problem. However, the model trained by the labeled examples of one component is not applicable to classify the new fault categories of other components. This problem aggravates when there exist very few examples. In this paper, we propose a cross-category fault diagnosis method (CFDM) based on few-shot learning. Our method constructs a convolutional Siamese neural network to extract fault features from example pairs. A cross-entropy based loss function is used that includes parameters for feature discrepancy to maximize the inter-category distances and minimize the intra-category distances. This enables the proposed method to learn the accurate classification boundaries between fault features of the example pairs. We conduct experiments on two public benchmark datasets and one lab-built dataset. Our evaluation includes analysis of the proposed method to classify fault types with one or five examples in each category of the target component. Our results demonstrate that the proposed method improves the fault diagnosis accuracy and robustness in comparison to the state-of-the-art methods.

Racial and Class Inequality in US Incarceration in the Early Twenty-First Century

Abstract The relative importance of racial and class inequality in incarceration in the United States has recently become the subject of much debate. In this paper, we seek to give this debate a stronger empirical foundation. First, we update previous research on racial and class inequality in people’s likelihood of being imprisoned. Then, we examine racial and class inequality in people’s risk of having a family member imprisoned or living in a high-imprisonment neighborhood. We find that racial inequality in prison admissions has fallen in the twenty-first century, while class inequality has surged. However, in recent years, Black people with high levels of education and income were more likely than white people with low levels of education and income to experience the imprisonment of a family member or to live in a neighborhood with a high imprisonment rate. These seemingly contradictory conclusions can be reconciled by the fact that enduring structures of racial domination have made class boundaries among Black people more permeable than they are among white people. Imprisonment in the United States is increasingly reserved for the poor. But because Black Americans are disproportionately connected to the poor through their families and neighborhoods, racial inequality exceeds class inequality in people’s indirect experiences with imprisonment.

Boundary‐based Fuzzy‐SVDD for one‐class classification

Support Vector Data Description (SVDD) is an extremely hot topic issue in One-Class Classification (OCC), which has displayed outstanding performance in dealing with many novelty detection problems. However, SVDD just takes the data description by the kernel-based distance among each instance into consideration rather than considering the distribution of the data. Therefore, Fuzzy Support Vector Data Description (Fuzzy-SVDD) has been developed to distribute a fuzzy membership to each input sample so that different samples cause different contributions to classification boundary. The majority of the methods in Fuzzy-SVDD are based on the sample density, but there are remaining two problems. These density-based Fuzzy-SVDD methods would decrease the contribution of support vectors (SVs) in low densities. What is more, these methods cannot get a precise density when there are few target samples. These two problems would lead to a poor classification boundary. To overcome these drawbacks, a novel method called Boundary-based Fuzzy-SVDD (BF-SVDD) is proposed in this paper. BF-SVDD uses a new definition called local–global center distance to search for the samples near the boundary. Then, it enhances fuzzy memberships of these samples because they carry more significant information for the decision boundary than other data. The contribution of this paper can be summarized into three main points. First a novel concept called local–global center distances is proposed to find the SVs better. Second, fuzzy memberships with local–global center distance make SVs more informative to create the decision boundary. Furthermore, the experiments based on University of California, Irvine and Knowledge Extraction based on Evolutionary Learning also show that the proposed method has excellent performances. Even for the minority class in imbalance data sets, the proposed method can also have a good classification.

EEG fading data classification based on improved manifold learning with adaptive neighborhood selection

In electroencephalogram (EEG) signal analysis, data fading problem exists from signal production to collection by brain-computer interface (BCI) device, which can be raised by BCI device deficiency, dynamic network limitation and subject issue. EEG data fading problem changes the distribution of data, which results in the movement of the cluster center and fuzzy class boundary after feature extraction with negative effects in EEG classification results. To decrease the adverse influence of data fading, a novel fading data classification method based on manifold learning and adaptive neighborhood selection is proposed in this paper to mitigate this adverse effect of data fading. In the proposed method, after neighborhood selection according to local linearity, data are mapped into manifold space through local tangent space alignment (LTSA) for dimensionality reduction. The method is carried out on BCI Competition 2008 – Graz data set A of four-class EEG data of motor imagery (MI) experiments. The experimental results are compared with conventional LTSA and indicate that the proposed method effectively improves the classification accuracy of fading data.

The Master Equation in a bounded domain with Neumann conditions

In this article, we study the well-posedness of the Master Equation of Mean Field Games in a framework of Neumann boundary condition. The definition of solution is closely related to the classical one of the Mean Field Games system, but the boundary condition here leads to two Neumann conditions in the Master Equation formulation, for both space and measure. The global regularity of the linearized system, which is crucial in order to prove the existence of solutions, is obtained with a deep study of the boundary conditions and the global regularity at the boundary of a suitable class of parabolic equations.

Positioning self and other: building equity literacy in collaboration

AbstractCollaborative meaning‐making across difference is often undertaken in pursuit of equity, but too often socially constructed power differentials between collaborators on the basis of social class, race, gender, ability, age or other markers are reified. This article examines the ripples produced by one literacy collaboration that took place across public, private and charter schools, nested within urban, suburban and rural districts, traversing cultural, racial and class boundaries. Specifically, we examine retrospective interview data from youth and teachers reflecting on a collaborative project that asked youth to work together with young people from other schools to compose dramatic performances together. Our findings reveal limitations to equitable outcomes across disparate groups working together, particularly around identity markers like race or neurological difference. After juxtaposing a range of positionalities that youth took up when describing the experience of this field trip after the fact, we suggest a set of equity literacy tools for teachers and researchers interested in facilitating more equitable collaborations.

Identifying Factors That Influence Accuracy of Riparian Vegetation Classification and River Channel Delineation Mapped Using 1 m Data

Riparian vegetation delineation includes both the process of delineating the riparian zone and classifying vegetation within that zone. We developed a holistic framework to assess riparian vegetation delineation that includes evaluating channel boundary delineation accuracy using a combination of pixel- and object-based metrics. We also identified how stream order, riparian zone width, riparian land use, and image shadow influenced the accuracy of delineation and classification. We tested the framework by evaluating vegetation vs. non-vegetation riparian zone maps produced by applying random forest classification to aerial photographs with a 1 m pixel size. We assessed accuracy of the riparian vegetation classification and channel boundary delineation for two rivers in the northeastern United States. Overall accuracy for the channel boundary delineation was generally above 80% for both sites, while object-based accuracy revealed that 50% of delineated channel was less than 5 m away from the reference channel. Stream order affected channel boundary delineation accuracy while land use and image shadows influenced riparian vegetation classification accuracy; riparian zone width had little impact on observed accuracy. The holistic approach to quantification of accuracy that considers both channel boundary delineation and vegetation classification developed in this study provides an important tool to inform riparian management.

Structural Damage Detection Using Supervised Nonlinear Support Vector Machine

Damage detection, using vibrational properties, such as eigenfrequencies, is an efficient and straightforward method for detecting damage in structures, components, and machines. The method, however, is very inefficient when the values of the natural frequencies of damaged and undamaged specimens exhibit slight differences. This is particularly the case with lightweight structures, such as fiber-reinforced composites. The nonlinear support vector machine (SVM) provides enhanced results under such conditions by transforming the original features into a new space or applying a kernel trick. In this work, the natural frequencies of damaged and undamaged components are used for classification, employing the nonlinear SVM. The proposed methodology assumes that the frequencies are identified sequentially from an experimental modal analysis; for the study propose, however, the training data are generated from the FEM simulations for damaged and undamaged samples. It is shown that nonlinear SVM using kernel function yields in a clear classification boundary between damaged and undamaged specimens, even for minor variations in natural frequencies.

Generating decision support for alarm processing in cold supply chains using a hybrid k-NN algorithm

Real-time temperature monitoring is necessary in cold pharmaceutical supply chains (SCs), where exposures to extreme temperatures can lead to product quality deterioration. Temperature alarms (TAs) triggered by the current rule-based systems still require lengthy examinations before a suitable corrective measure (CM) can be chosen. However, provision of additional information relevant to TAs can expedite the examination process.In the related areas of recommender systems and false alarm/anomaly detection, k-nearest neighbors (k-NN) algorithm has proven to be successful because of its interpretability and ease of use. However, in the context of TA processing, it may suffer from some inherent limitations (i.e., varying neighborhood radius, unreliable classifications in sparse and noisy regions, and blindness to natural class boundaries). To overcome these limitations, we propose a hybrid k-NN (Hk-NN) algorithm based on the principles of local similarity and neighborhood homogeneity. It incorporates a two-step voting procedure with an entropy-optimized k-NN radius, decision trees with k-constrained leaves, and nearest neighbor predictions.We investigate 16,525 comments by alarm personnel for TAs in a pharmaceutical SC and encode them in terms of deviation causes and CMs (target features). We use SC data on cargo location, SC phase, sensor role, and temperature characteristics as predictor features for TA similarity estimation. In eight experimental setups, Hk-NN consistently outperforms k-NN with an optimized k in terms of accuracy, balanced accuracy, macro-average precision, recall, and specificity. At the same time, Hk-NN refrains from predicting observations, for which k-NN’s accuracy is close to a random guess.

Problems and suggestions on site classification

The physical meaning of site classification is not clear in the current seismic design code for buildings, at the same time, the boundary of site classification is easy to cause the divergence of design ground motion parameters. For the above problems and deficiencies, some suggestions are given. To solve the problem that the physical meaning of site classification is not clear, on the basis of the current site classification method, according to the site classification index such as the covering layer thickness and the equivalent shear wave velocity, the sites are classified by two-level: the first level classification is consistent with the current one, which classifies sites based on the fundamental period of the site and the thickness of the overburden layer; the second level classification further considers the degree of hardness of the geotechnical medium based on the first level classification, and sub-classification according to equivalent shear wave velocity. Based on the current research on seismic disaster and seismic motion characteristics of thick soft site, combined with the development of long-period constructions, the site classification is expanded from the original four categories to five categories, at the same time, the boundary of each classification, especially the boundary of class II, III and IV sites, is limited from the original open type, which can effectively avoid the problem of divergence of design ground motion parameters caused by site classification. The related research results can provide reference for site classification and determination of design ground motion parameters.

Feasibility Analysis in Batch Process: A Machine Learning Approach

Scheduling is a major issue in process operations, and it is essential for maximizing production output. Short-term scheduling is used in batch operations to allocate a set of restricted resources across time to manufacture one or more items according to a batch recipe. For such processes, a feasible design space can be described by the decision-maker as per the process constraints and objectives. A machine learning approach using support vector machines is implemented for the classification of the feasible region from a data set. An algebraic equation is obtained using support vectors (data points participating in creating classification boundary), which could be incorporated into the mathematical model. The equation will lead to attaining several objectives in the finite obtained region. In this paper, kernel-based support vector classification is tailored to a continuous-time formulation for the short-term scheduling of batch processes. First, using a classification SVC over a data set, it was observed that the mathematical model is infeasible for a set of production combination of two different products. Using the proposed methodology, a design space is presented graphically for feasible production targets. In the second case, the study is applied to perform optimization operations to target feasible region within a specified limit as a choice of decision-maker.

An oversampling method for multi-class imbalanced data based on composite weights.

To solve the oversampling problem of multi-class small samples and to improve their classification accuracy, we develop an oversampling method based on classification ranking and weight setting. The designed oversampling algorithm sorts the data within each class of dataset according to the distance from original data to the hyperplane. Furthermore, iterative sampling is performed within the class and inter-class sampling is adopted at the boundaries of adjacent classes according to the sampling weight composed of data density and data sorting. Finally, information assignment is performed on all newly generated sampling data. The training and testing experiments of the algorithm are conducted by using the UCI imbalanced datasets, and the established composite metrics are used to evaluate the performance of the proposed algorithm and other algorithms in comprehensive evaluation method. The results show that the proposed algorithm makes the multi-class imbalanced data balanced in terms of quantity, and the newly generated data maintain the distribution characteristics and information properties of the original samples. Moreover, compared with other algorithms such as SMOTE and SVMOM, the proposed algorithm has reached a higher classification accuracy of about 90%. It is concluded that this algorithm has high practicability and general characteristics for imbalanced multi-class samples.

Universality class and exact phase boundary in the superradiant phase transition

The Dicke model and Rabi model can undergo phase transitions from the normal phase to the superradiant phase at the same boundary, which can be accurately determined using some approximated approaches. The underlying mechanism for this coincidence is still unclear and the universality class of these two models is elusive. Here we prove this phase transition exactly using the path-integral approach based on the faithful Schwinger fermion representation, and give a unified phase boundary condition for these models. We demonstrate that at the phase boundary, the fluctuation of the bosonic field is vanished, thus it can be treated as a classical field, based on which a much simplified method to determine the phase boundary is developed. This explains why the approximated theories by treating the operators as classical variables can yield the exact boundary. We use this method to study several similar spin and boson models, showing its much wider applicability than the previously used approaches. Our results demonstrate that these phase transitions belong to the same universality by the classical Landau theory of phase transitions, which can be confirmed using the platforms in the recent experiments.

Capitalizing on desire: (re)producing and consuming class in Indian ‘gay’ pornography

ABSTRACT This article investigates the emerging popularity of same-sex pornographic content in India featuring fitness trainers and bodybuilders. The article argues that its production and consumption is governed by socio-economic difference that is revealing for the resilience of (middle-)class boundaries. Drawing on long-term ethnographic research, the analysis is complemented by engaging with informants’ social media updates and the un/intentionality of their homoerotic layering. By focusing on the trajectory of one trainer who now provides escort services and features in pornographic movies, the article shows that such productions need to be understood as amalgamated with and indivisible from non-pornographic content depicting near-naked muscular men. It treats homoerotically suggestive social media updates, YouTube productions that warn men against the pitfalls of male modelling and the risk of sexual abuse and exploitation, and actual same-sex ‘porn’ as existing within a shared continuum through which we can understand different productions of desire and desirability.

Robust CSI-Based Human Activity Recognition With Augment Few Shot Learning

With the development of Internet of Things technology, Channel State Information (CSI) based human activity recognition (HAR) plays an important role in Human-Computer Interaction and achieves considerable advancements over recent years. However, when the trained model is applied to recognize new activity categories or recognizing new users in new scenarios, the recognition performance of general methods will dramatically decline. And re-collecting adequate new activity categories’ samples to train the HAR model to adapt to the new situation will consume a lot of time and human effort. To overcome this challenge, we propose a framework, Augment Few Shot Learning-based Human Activity Recognition (AFSL-HAR), which can achieve significant performance in recognizing new categories through a small amount of samples to fine-tune the model parameters and avoid retraining the network from scratch again. And besides, in order to improve the robustness of AFSL-HAR, we design a Feature Wasserstein Generative Adversarial Network (FWGAN) module, which can synthesize diverse samples to help the recognition model learn more sharper classification boundaries. Specifically, the FWGAN module incorporates a feature extractor to realize converging with a fewer number of training samples, and takes an improved discriminator to enhance system performance. The experimental results demonstrate that AFSL-HAR can achieve accuracy of 98.9% and 94.7% when recognizing new activities using few samples for each category on the public data set and self-made data set, respectively.

Clustering Analysis Methods for GNSS Observations: A Data-Driven Approach to Identifying California's Major Faults.

We present a data‐driven approach to clustering or grouping Global Navigation Satellite System (GNSS) stations according to observed velocities, displacements or other selected characteristics. Clustering GNSS stations provides useful scientific information, and is a necessary initial step in other analysis, such as detecting aseismic transient signals (Granat et al., 2013, https://doi.org/10.1785/0220130039). Desired features of the data can be selected for clustering, including some subset of displacement or velocity components, uncertainty estimates, station location, and other relevant information. Based on those selections, the clustering procedure autonomously groups the GNSS stations according to a selected clustering method. We have implemented this approach as a Python application, allowing us to draw upon the full range of open source clustering methods available in Python's scikit‐learn package (Pedregosa et al., 2011, https://doi.org/10.5555/1953048.2078195). The application returns the stations labeled by group as a table and color coded KML file and is designed to work with the GNSS information available from GeoGateway (Donnellan et al., 2021, https://doi.org/10.1007/s12145-020-00561-7; Heflin et al., 2020, https://doi.org/10.1029/2019ea000644) but is easily extensible. We demonstrate the methodology on California and western Nevada. The results show partitions that follow faults or geologic boundaries, including for recent large earthquakes and post‐seismic motion. The San Andreas fault system is most prominent, reflecting Pacific‐North American plate boundary motion. Deformation reflected as class boundaries is distributed north and south of the central California creeping section. For most models a cluster boundary connects the southernmost San Andreas fault with the Eastern California Shear Zone (ECSZ) rather than continuing through the San Gorgonio Pass.

A new WFD\u2014compliant littoral macroinvertebrate index for monitoring and assessment of Mediterranean lakes (HeLLBI)

A new multimetric index (HeLLBI) based on littoral benthic macroinvertebrates is presented in this paper for classification of Greek natural lakes, in compliance with the requirements of Water Framework Directive (WFD). The method was developed based on the collection of littoral benthic invertebrate fauna and environmental data from 109 sampling sites in 21 natural lakes of the Greek National Water Monitoring Network. We focused the analysis on the effects of shore morphological alterations and eutrophication to the littoral invertebrate fauna, identified to family level, except oligochaetes, which were identified as a class, and more particularly to taxonomic composition and abundance, to taxa sensitivity, and to richness/diversity. Three metrics were included in the multimeric index: the relative abundance of Odonata classes, the Average Score per Taxon, and the Simpson’s diversity index. The metrics were converted to ecological quality ratios and ecological class boundaries were defined. The final multimetric index HeLLBI is expressed as an arithmetic average of normalized ecological quality ratios of the above metrics and a final score was assigned to each lake. Pressure-response relationships of HeLLBI scores were statistically tested for morphological alterations, expressed as percentage of artificial shoreline, and eutrophication, expressed as total phosphorus. The HeLLBI scores correspond to ecological classes, according to WFD, and sampling sites with different ecological status contained distinct biological communities; those at high status where more diverse and with sensitive taxa and as the water quality deteriorated, macroinvertebrate assemblages consisted of fewer and more tolerant to degradation taxa. The HeLLBI method gave a reliable assessment of littoral benthic invertebrate fauna of Greek natural lakes and could be a useful tool for the classification of ecological status of other Mediterranean lakes.

SVDD boundary and DPC clustering technique-based oversampling approach for handling imbalanced and overlapped data

Imbalanced datasets classification remains an important domain in machine learning. Conventional supervised learning algorithms tend to be biased towards the majority class when addressing imbalanced datasets, thus providing poor classification results on the minority class. The learning task would become more challenging when there are overlapping and within-imbalance issues in imbalanced datasets, which are often the case and have been proven to play more negative impact on the classification performance than between-class imbalance. In this paper, we propose a novel SVDD (Support Vector Data Description) boundary and DPC (Density Peaks Clustering) clustering technique-based oversampling approach (SVDDDPCO) for handling imbalanced and overlapped data. The proposed approach first utilizes support vector data description (SVDD) model with greater penalty constant for the minority class than the majority class to generate the class boundary, and then identifies those misclassified majority or few minority instances by the boundary as potential overlapped or noisy ones and eliminates them. To address the within-balance issues, density peaks clustering (DPC) is used to cluster the minority instances due to its advantage of accurately identifying sub-clusters with different sizes and densities, which facilitates simultaneously combating between-class and within-class imbalance issues caused by various reasons. The minority instances are assigned with different weights inversely proportional to their local densities and their distances to the boundary and then the size for each identified sub-cluster to be oversampled is adaptively determined according to its own size and the weights of its elements. Such strategy aims to generate more synthetic minority instances for borderline and sparser small sub-clusters which are usually informative to the later learning tasks. Finally, oversampling is performed within each sub-cluster with different sizes to not only counteract the within imbalance but also avoid the generation of any noisy or overlapped synthetic instance. Extensive comparison results on various datasets showed the proposed method achieves statistically significant improvements in classification performance relative to state-of-the-art ones.

Fuzzy Overclustering: Semi-Supervised Classification of Fuzzy Labels with Overclustering and Inverse Cross-Entropy.

Deep learning has been successfully applied to many classification problems including underwater challenges. However, a long-standing issue with deep learning is the need for large and consistently labeled datasets. Although current approaches in semi-supervised learning can decrease the required amount of annotated data by a factor of 10 or even more, this line of research still uses distinct classes. For underwater classification, and uncurated real-world datasets in general, clean class boundaries can often not be given due to a limited information content in the images and transitional stages of the depicted objects. This leads to different experts having different opinions and thus producing fuzzy labels which could also be considered ambiguous or divergent. We propose a novel framework for handling semi-supervised classifications of such fuzzy labels. It is based on the idea of overclustering to detect substructures in these fuzzy labels. We propose a novel loss to improve the overclustering capability of our framework and show the benefit of overclustering for fuzzy labels. We show that our framework is superior to previous state-of-the-art semi-supervised methods when applied to real-world plankton data with fuzzy labels. Moreover, we acquire 5 to 10% more consistent predictions of substructures.

Interpretation of the results of particle-size distribution determination using various soil texture classifications

An analysis of discrepancies in methodological approaches as well as in determination of the boundaries of the main textural classes classified according to classifications of N.A. Kachinsky (Russia), US Department of Agriculture (USDA) and World Soil Reference Base (WRB) soil texture classification was made. A comparative analysis of the obtained data showed that the differences in the dimensions of the clay fraction in the classifications lead to a seeming increase in the content of this fraction by 1.5–2 times, and therefore, to a shift to heavier textural class according to USDA and WRB classifications. This circumstance inevitably affects the content of the silt fraction. Due to discrepancies in determination of the boundaries of the main textural classes in the classifications of Kachinsky, USDA, WRB, the distinctions in the diagnosis of soil on its textural composition are reflected in the name, while the real number of soil primary particles of various sizes in the sample does not change.