Class Boundaries Research Articles

The stakes of (not) knowing

This article draws on the concept of subjunctivity to explore how conditions of uncertainty, experimentation, and refusal shape the lives of women raising children with Down syndrome in Amman, Jordan. The connections that women forge – as mothers of children with Down syndrome – enable them to imagine new possibilities for their families and their futures across boundaries of class and circumstance. Prenatal diagnosis, however, invites possibilities of a different kind, challenging established models for divine creation, human agency, and moral accountability. As women reflect on what they would have done if they had known about their child’s Down syndrome in utero, they reason themselves to different conclusions. Yet their interest in the question itself reveals how, even in its absence, prenatal diagnosis circulates as a technology of subjunctivity, conjuring multiple possible pasts, presents, and futures.

Thematic Classification Accuracy Assessment with Inherently Uncertain Boundaries: An Argument for Center-Weighted Accuracy Assessment Metrics

Accuracy assessment is one of the most important components of both applied and research-oriented remote sensing projects. For mapped classes that have sharp and easily identified boundaries, a broad array of accuracy assessment methods has been developed. However, accuracy assessment is in many cases complicated by classes that have fuzzy, indeterminate, or gradational boundaries, a condition which is common in real landscapes; for example, the boundaries of wetlands, many soil map units, and tree crowns. In such circumstances, the conventional approach of treating all reference pixels as equally important, whether located on the map close to the boundary of a class, or in the class center, can lead to misleading results. We therefore propose an accuracy assessment approach that relies on center-weighting map segment area to calculate a variety of common classification metrics including overall accuracy, class user’s and producer’s accuracy, precision, recall, specificity, and the F1 score. This method offers an augmentation of traditional assessment methods, can be used for both binary and multiclass assessment, allows for the calculation of count- and area-based measures, and permits the user to define the impact of distance from map segment edges based on a distance weighting exponent and a saturation threshold distance, after which the weighting ceases to grow. The method is demonstrated using synthetic and real examples, highlighting its use when the accuracy of maps with inherently uncertain class boundaries is evaluated.

Design of Reinforced Fuzzy Radial Basis Function Neural Network Classifier Driven With the Aid of Iterative Learning Techniques and Support Vector-Based Clustering

In this article, a reinforced fuzzy radial basis function neural network (R-FRBFNN) classifier is proposed. It focuses on the development of methodologies of reinforced architecture to improve classification accuracy and enhance the robust capability based on two learning strategies. The two learning strategies are summarized: 1) R-FRBFNN designed via support vector (SV)-based fuzzy C-means (FCM) clustering and softmax-based iterative reweighted least square (IRLS), which concentrate on improving the classification performance of R-FRBFNN; and 2) R-FRBFNN designed via SV-based FCM and softmax-based iterative quadratic programming (IQP), which focus on improving the robust abilities of the R-FRBFNN and reducing the effects of noise and outliers. The essential points of the proposed R-FRBFNN classifier are summarized as follows. a) The proposed R-FRBFNN consists of three phases: condition, conclusion, and inference. b) An SV-based FCM is considered for prioritizing the classification boundary and improving the classification performance of the proposed classifier. c) Three types of polynomials construct the conclusion phase. Two learning techniques are designed to update the coefficients of the polynomials. Softmax-based IRLS is a type of iterative learning technique based on Newton's method. Softmax-based IQP is more robust and avoids the degradation of generalization capabilities caused by outliers and noisy data. d) In the concept of reinforced architecture, SV-based FCM imposes compensation (membership degrees) on learning techniques according to the data characteristics encountered in the inference phase. Experimental results reported for benchmark data and outliers/noisy datasets demonstrate that the proposed classifier shows improved classification performance compared with other previously studied methods.

Combined Duval Pentagons: A Simplified Approach

The paper describes a newly proposed combination of the two existing Duval Pentagons method utilized for the identification of mineral oil-insulated transformers. The aim of the combination is to facilitate automatic fault identification through computer programs, and at the same time, apply the full capability of both original Pentagons, now reduced to a single geometry. The thorough classification of a given fault (say, of the electrical or thermal kind), employing individual Pentagons 1 and 2, as originally defined, involves a complex geometrical problem that requires the build-up of a convoluted geometry (a regular Pentagon whose axes represent each of five possible combustible gases) to be constructed using computer language code and programming, followed by the logical localization of the geometrical centroid of an irregular pentagon, formed by the partial contribution of individual combustibles, inside two similar structures (Pentagons 1 and 2) that, nonetheless, have different classification zones and boundaries, as more thoroughly explained and exemplified in the main body of this article. The proposed combined approach results in a lower number of total fault zones (10 in the combined Pentagons against 14 when considering Pentagons 1 and 2 separately, although zones PD, S, D1 and D2 are common to both Pentagons 1 and 2), and therefore eliminates the need to solve for two separate Pentagons.

Persistence of Delayed Complex Balanced Chemical Reaction Networks

In this article, we mainly focus on the persistence of delayed complex balanced systems. We first give the ω-limit set theorem for this kind of system which says that ω-limit set can be the single constant positive equilibrium or the set of constant equilibria on the boundaries. In addition, we derive several sufficient conditions to diagnose the persistence of delayed complex balanced chemical reaction network systems equipped with mass-action kinetics based on the situation of the boundary of stoichiometric compatibility class. Then, we can directly obtain that delayed complex balanced systems with two-dimensional stoichiometric subspace are persistent. Furthermore, we prove the abovementioned systems are globally asymptotically stable at the corresponding positive equilibrium if the trajectory starts from a positive initial function. We illustrate the analysis by two numerical examples.

Optimal Margin Distribution Machine

Support Vector Machine (SVM) has always been one of the most successful learning algorithms, with the central idea of maximizing the minimum margin , i.e., the smallest distance from the instances to the classification boundary. However, recent theoretical results disclosed that maximizing the minimum margin does not necessarily lead to better generalization performance, and instead, the margin distribution has been proven to be more crucial. Based on this idea, we propose the Optimal margin Distribution Machine (ODM), which can achieve a better generalization performance by optimizing the margin distribution explicitly. We characterize the margin distribution by the first- and second-order statistics, i.e., the margin mean and variance. The proposed method is a general learning approach which can be applied in any place where SVMs are used, and its superiority is verified both theoretically and empirically in this paper.

Hyperspectral Image Classification With Context-Aware Dynamic Graph Convolutional Network

In hyperspectral image (HSI) classification, spatial context has demonstrated its significance in achieving promising performance. However, conventional spatial context-based methods simply assume that spatially neighboring pixels should correspond to the same land-cover class, so they often fail to correctly discover the contextual relations among pixels in complex situations, and thus leading to imperfect classification results on some irregular or inhomogeneous regions such as class boundaries. To address this deficiency, we develop a new HSI classification method based on the recently proposed Graph Convolutional Network (GCN), as it can flexibly encode the relations among arbitrarily structured non-Euclidean data. Different from traditional GCN, there are two novel strategies adopted by our method to further exploit the contextual relations for accurate HSI classification. First, since the receptive field of traditional GCN is often limited to fairly small neighborhood, we proposed to capture long range contextual relations in HSI by performing successive graph convolutions on a learned region-induced graph which is transformed from the original 2D image grids. Second, we refine the graph edge weight and the connective relationships among image regions by learning the improved adjacency matrix and the 'edge filter', so that the graph can be gradually refined to adapt to the representations generated by each graph convolutional layer. Such updated graph will in turn result in accurate region representations, and vice versa. The experiments carried out on three real-world benchmark datasets demonstrate that the proposed method yields significant improvement in the classification performance when compared with some state-of-the-art approaches.

Mechanical fault diagnosis of high-voltage circuit breakers using multi-segment permutation entropy and a density-weighted one-class extreme learning machine

Condition monitoring for high-voltage circuit breakers (HVCBs) is of great significance for the safety of power grids. Based on machine-learning methods, most relevant studies have contributed significantly to improving the classification accuracy of known states. However, these studies have neglected the detection of unknown faults. In this study, a new one-class classifier, called a density-weighted one-class extreme learning machine (DW-OCELM), was proposed to detect unknown faults of HVCBs. The DW-OCELM determines the classification boundary considering data distribution by introducing the notion of density weight, such that samples located in low-density regions are more likely to be separated, improving detection performance. On this basis, a multi-class classifier was developed based on the homogeneous combination of multiple DW-OCELMs to classify known states. In addition, the proposed classifiers were trained based on multi-segment permutation entropy calculated from vibration signals. Experiments on a 35 kV HVCB demonstrated that the proposed methods outperformed other state-of-the-art techniques.

It has never been “normal”: queer pop in post-2000 China

ABSTRACT Since public access to the Internet in Mainland China increased in the early 2000s, pop-cultural (re)productions and imaginings that interrogate the rigid boundaries of gender, sexuality, ethnicity, class, and other sociocultural registers have thrived and diversified. As an introductory piece to the special issue of Feminist Media Studies, “Queer Pop in Post-2000 China,” this paper explores this “queer pop” phenomenon as a proliferation of non-normatively gendered and/or sexualized narratives, performances, cultural productions, inventions, interpretations, artistic expressions, gestures, sociocultural relations, imaginations, and significations, especially in China’s mainstream media and public spaces. By mapping out various manifestations of this phenomenon in this digital, globalist age, as well as its potential and the challenges it faces, the case studies presented in this special issue, such as those that address queer fandom, livestreaming, online video and digital documentary making, cross-cultural translation, and the making and broadcasting of online TV programs, excavate its substantial norm-defying power. The essays reveal the negotiative spaces made possible by the development and transformation of media cultures and practices by and for gender, sexual, and sociocultural minorities in an authoritarian, heteropatriarchal society where media portrayals of LGBTQ groups and lives have been subject to ambiguous, yet persistent, censorship.

Mitigating Domestic Violence and the Role of Protection Officers Under Domestic Violence Act: A Case of National Capital of India

Cutting across boundaries of culture, class, education, income and age, violence against women exists. The paper examines the impact of Domestic Violence, challenges faced in reporting and seeking legal support. In-depth interviews were conducted with 30 aggrieved women to understand the problem of domestic violence, associated reasons of abuse and how the victims dealt with it. Results show that majority faced physical, emotional and economic violence affecting their physical and mental health. Alcoholism and absolute financial dependence on husband were the factors that lead to abuse. Lack of information and logistical issues in using the provisions made available under the DV Act were found as the weak links. The findings highlight the importance of generating awareness about the provisions of DV Act and strengthen its implementation.

Development of Computer-Aided Semi-Automatic Diagnosis System for Chronic Post-Stroke Aphasia Classification with Temporal and Parietal Lesions: A Pilot Study

Survivors of either a hemorrhagic or ischemic stroke tend to acquire aphasia and experience spontaneous recovery during the first six months. Nevertheless, a considerable number of patients sustain aphasia and require speech and language therapy to overcome the difficulties. As a preliminary study, this article aims to distinguish aphasia caused from a temporoparietal lesion. Typically, temporal and parietal lesions cause Wernicke’s aphasia and Anomic aphasia. Differential diagnosis between Anomic and Wernicke’s has become controversial and subjective due to the close resemblance of Wernicke’s to Anomic aphasia when recovering. Hence, this article proposes a clinical diagnosis system that incorporates normal coupling between the acoustic frequencies of speech signals and the language ability of temporoparietal aphasias to delineate classification boundary lines. The proposed inspection system is a hybrid scheme consisting of automated components, such as confrontation naming, repetition, and a manual component, such as comprehension. The study was conducted involving 30 participants clinically diagnosed with temporoparietal aphasias after a stroke and 30 participants who had experienced a stroke without aphasia. The plausibility of accurate classification of Wernicke’s and Anomic aphasia was confirmed using the distinctive acoustic frequency profiles of selected controls. Accuracy of the proposed system and algorithm was confirmed by comparing the obtained diagnosis with the conventional manual diagnosis. Though this preliminary work distinguishes between Anomic and Wernicke’s aphasia, we can claim that the developed algorithm-based inspection model could be a worthwhile solution towards objective classification of other aphasia types.

In their shoes: using fashion objects to explore the duration and complexity of wartime experiences

ABSTRACT Experiences of conflict rarely adhere to the historical confines of defined dates. Although the Second World War was officially brought to a close on 2 September 1945, the emotional legacy of the conflict lingered. Drawing on objects from the Museum of London, this article investigates how fashion objects can be used to highlight the long-term impacts of conflict. By looking at how people reused, saved, and fetishized wartime objects in peacetime, it shows how emotional reactions of hope, disappointment, and lingering resentment manifested themselves through practices of dressing, as well as demonstrating the uneven impact of conflict across class and gender boundaries.

Human-Leg Detection in 3D Feature Space for a Person-Following Mobile Robot Using 2D LiDARs

People detection is an essential technique for person-following mobile robots in applications of human-friendly services and collaborative tasks. 2D light detection and ranging (LiDAR) sensors are useful for these applications, especially for applications that detect and follow people while maintaining a suitable distance, at a close range, using accurate range measurements. In this study, we propose a method of human-leg detection in 3D feature space for a person-following mobile robot equipped with a 2D LiDAR sensor. We also propose an improved LiDAR scan segmentation technique to extract segments of human leg candidates. The newly proposed method generates a feature vector with the attributes of leg shapes and learns a classification boundary in 3D feature space. Experimental results indicate that the proposed method successfully describes the target dataset and provides accurate leg detection. This study demonstrates that human legs can be detected with improved accuracy by learning the classification boundary in 3D feature space.

Incremental one-class classifier based on convex–concave hull

One subject that has been considered less is a binary classification on data streams with concept drifting in which only information of one class (target class) is available for learning. Well-known methods such as SVDD and convex hull have tried to find the enclosed boundary around target class, but their high complexity makes them unsuitable for large data sets and also online tasks. This paper presents a novel online one-class classifier adapted to the streaming data. Considering time complexity, an incremental convex–concave hull classification method, called ICCHC, is proposed which can significantly reduce the computational time and expand the target class boundary. Also, it can be adapted to the gradual concept drift. Evaluations have been conducted on seventeen real-world data sets by hold-out validation. Also, noise analysis has been carried out. The results of the experiments have been compared with the state-of-the-art methods, which show the superiority of ICCHC regarding the accuracy, precision, and recall metrics.

Learning with Unsure Responses

Many annotation systems provide to add an unsure option in the labels, because the annotators have different expertise, and they may not have enough confidence to choose a label for some assigned instances. However, all the existing approaches only learn the labels with a clear class name and ignore the unsure responses. Due to the unsure response also account for a proportion of the dataset (e.g., about 10-30% in real datasets), existing approaches lead to high costs such as paying more money or taking more time to collect enough size of labeled data. Therefore, it is a significant issue to make use of these unsure.In this paper, we make the unsure responses contribute to training classifiers. We found a property that the instances corresponding to the unsure responses always appear close to the decision boundary of classification. We design a loss function called unsure loss based on this property. We extend the conventional methods for classification and learning from crowds with this unsure loss. Experimental results on realworld and synthetic data demonstrate the performance of our method and its superiority over baseline methods.

Uncertainty-Aware Deep Classifiers Using Generative Models

Deep neural networks are often ignorant about what they do not know and overconfident when they make uninformed predictions. Some recent approaches quantify classification uncertainty directly by training the model to output high uncertainty for the data samples close to class boundaries or from the outside of the training distribution. These approaches use an auxiliary data set during training to represent out-of-distribution samples. However, selection or creation of such an auxiliary data set is non-trivial, especially for high dimensional data such as images. In this work we develop a novel neural network model that is able to express both aleatoric and epistemic uncertainty to distinguish decision boundary and out-of-distribution regions of the feature space. To this end, variational autoencoders and generative adversarial networks are incorporated to automatically generate out-of-distribution exemplars for training. Through extensive analysis, we demonstrate that the proposed approach provides better estimates of uncertainty for in- and out-of-distribution samples, and adversarial examples on well-known data sets against state-of-the-art approaches including recent Bayesian approaches for neural networks and anomaly detection methods.

CPFNet: Context Pyramid Fusion Network for Medical Image Segmentation.

Accurate and automatic segmentation of medical images is a crucial step for clinical diagnosis and analysis. The convolutional neural network (CNN) approaches based on the U-shape structure have achieved remarkable performances in many different medical image segmentation tasks. However, the context information extraction capability of single stage is insufficient in this structure, due to the problems such as imbalanced class and blurred boundary. In this paper, we propose a novel Context Pyramid Fusion Network (named CPFNet) by combining two pyramidal modules to fuse global/multi-scale context information. Based on the U-shape structure, we first design multiple global pyramid guidance (GPG) modules between the encoder and the decoder, aiming at providing different levels of global context information for the decoder by reconstructing skip-connection. We further design a scale-aware pyramid fusion (SAPF) module to dynamically fuse multi-scale context information in high-level features. These two pyramidal modules can exploit and fuse rich context information progressively. Experimental results show that our proposed method is very competitive with other state-of-the-art methods on four different challenging tasks, including skin lesion segmentation, retinal linear lesion segmentation, multi-class segmentation of thoracic organs at risk and multi-class segmentation of retinal edema lesions.

The Ultimate Challenge: Nationalism and Climate Change

AbstractClimate change has rapidly expanded as a key topic of research across disciplines, but it has remained virtually untouched in nationalism studies. Climate change is a boundless, uncontainable phenomenon that ignores class, geographic, and ethnonational boundaries. As such, it can hardly be comprehended within the limits of a nationalist world vision. This article reassesses this intuition by focusing on the situational and adaptive plasticity of nationalism, characterized by its notorious Janus-faced adaptability. I first identify and address a methodological stumbling block that precludes scholars in some areas of the humanities and social sciences—specifically nationalism studies—from conceptualizing and grappling with this unfolding reality. Second, I advance a typology that can work as a conceptual grid for studying similar problems that emerge at the intersection of environmental politics, climate change, and nationalism studies. I suggest two ways in which the nation and national narratives have been and are being mobilized to make sense of, contrast, reject, and incorporate new life-changing trends. I identify these, respectively, under the umbrella termsresource nationalismandgreen nationalism.I conclude by emphasizing the continuing relevance of nationalism in plans for ongoing global energy transitions.

Semi-supervised learning method based on predefined evenly-distributed class centroids

Compared to supervised learning, semi-supervised learning reduces the dependence of deep learning on a large number of labeled samples. In this work, we use a small number of labeled samples and perform data augmentation on unlabeled samples to achieve image classification. Our method constrains all samples to the predefined evenly-distributed class centroids (PEDCC) by the corresponding loss function. Specifically, the PEDCC-Loss for labeled samples, and the maximum mean discrepancy loss for unlabeled samples are used to make the feature distribution closer to the distribution of PEDCC. Our method ensures that the inter-class distance is large and the intra-class distance is small enough to make the classification boundaries between different classes clearer. Meanwhile, for unlabeled samples, we also use KL divergence to constrain the consistency of the network predictions between unlabeled and augmented samples. Our semi-supervised learning method achieves the state-of-the-art results, with 4000 labeled samples on CIFAR10 and 1000 labeled samples on SVHN, and the accuracy is 95.10% and 97.58% respectively. Code is available in https://github.com/sweetTT/semi-supervised-method-based-on-PEDCC.

An Efficient Hybrid Fuzzy-Clustering Driven 3D-Modeling of Magnetic Resonance Imagery for Enhanced Brain Tumor Diagnosis

Brain tumor detection and its analysis are essential in medical diagnosis. The proposed work focuses on segmenting abnormality of axial brain MR DICOM slices, as this format holds the advantage of conserving extensive metadata. The axial slices presume the left and right part of the brain is symmetric by a Line of Symmetry (LOS). A semi-automated system is designed to mine normal and abnormal structures from each brain MR slice in a DICOM study. In this work, Fuzzy clustering (FC) is applied to the DICOM slices to extract various clusters for different k. Then, the best-segmented image that has high inter-class rigidity is obtained using the silhouette fitness function. The clustered boundaries of the tissue classes further enhanced by morphological operations. The FC technique is hybridized with the standard image post-processing techniques such as marker controlled watershed segmentation (MCW), region growing (RG), and distance regularized level sets (DRLS). This procedure is implemented on renowned BRATS challenge dataset of different modalities and a clinical dataset containing axial T2 weighted MR images of a patient. The sequential analysis of the slices is performed using the metadata information present in the DICOM header. The validation of the segmentation procedures against the ground truth images authorizes that the segmented objects of DRLS through FC enhanced brain images attain maximum scores of Jaccard and Dice similarity coefficients. The average Jaccard and dice scores for segmenting tumor part for ten patient studies of the BRATS dataset are 0.79 and 0.88, also for the clinical study 0.78 and 0.86, respectively. Finally, 3D visualization and tumor volume estimation are done using accessible DICOM information.