Class Boundaries Research Articles

A Dual-Adversarial Model for Cross-time and Cross-subject Cognitive Workload Decoding.

Electroencephalogram (EEG) signals are widely utilized in the field of cognitive workload decoding (CWD). However, when the recognition scenario is shifted from subject-dependent to subject-independent or spans a long period, the accuracy of CWD deteriorates significantly. Current solutions are either dependent on extensive training datasets or fail to maintain clear distinctions between categories, additionally lacking a robust feature extraction mechanism. In this paper, we tackle these issues by proposing a Bi-Classifier Joint Domain Adaptation (BCJDA) model for EEG-based cross-time and cross-subject CWD. Specifically, the model consists of a feature extractor, a domain discriminator, and a Bi-Classifier, containing two sets of adversarial processes for domain-wise alignment and class-wise alignment. In the adversarial domain adaptation, the feature extractor is forced to learn the common domain features deliberately. The Bi-Classifier also fosters the feature extractor to retain the category discrepancies of the unlabeled domain, so that its classification boundary is consistent with the labeled domain. Furthermore, different adversarial distance functions of the Bi-Classifier are adopted and evaluated in this model. We conduct classification experiments on a publicly available BCI competition dataset for recognizing low, medium, and high cognitive workload levels. The experimental results demonstrate that our proposed BCJDA model based on cross-gradient difference maximization achieves the best performance.

"Noise and Fury Signifying Nothing": Music, Sound, and Class in Covent Garden

Abstract: In the mid-eighteenth century, Covent Garden played host to a variety of different types and classes of people. It was the site of the Theatre Royal, Covent Garden, the Shakespeare's Head tavern, and numerous brothels. It also included the residences and shops of famed writers and artists. Yet despite its reputation as a meeting place for all ranks, the square had clear class divisions between those who lived in the fashionable houses on the northern side and the working people of the street market further south. This essay examines the different sonic territories within Covent Garden and how they were marked by gender and class. Starting with sites of musical performance, I propose that music can tell us much about the aural experiences of the time. An examination of maps and images of the market illustrates how sound helped to reproduce and reinforce elite attitudes toward lower-class people. Music also relegated women to certain roles within that environment and tells us much about attitudes toward female labor. Finally, the history of musical culture in Covent Garden Market demonstrates how permeable class boundaries could be even when there was an interest in resisting change and upholding a strict class hierarchy.

An early detection indicator of combustion instability for an industrial gas turbine combustor

Detection of combustion instability is crucial for the safety and reliability of gas turbines. In this paper, the recurrence quantification analysis (RQA) and multi-fractal analysis (MFA) methods are applied to investigate the transition process from combustion noise to combustion instability in an industrial-scale combustor. Based on the dynamic pressure (DP) obtained from high pressure and high temperature tests, a novel method is proposed to construct early detection indicators (EDI) of combustion instability. The method is mainly based on the three-dimensional map of the recurrence rate, Hurst exponent, and root mean square ratio. A regression method and SVM are applied to define the classification boundary. For three test cases, the results showed that the proposed EDI can effectively detect the onset of combustion instability. Compared to the conventional method based on the root mean square levels of dynamic pressure, the EDI has capability to forecast the onset of combustion instability approximately a few hundred milliseconds in advance.

ConCPDP: A Cross‐Project Defect Prediction Method Integrating Contrastive Pretraining and Category Boundary Adjustment

Software defect prediction (SDP) is a crucial phase preceding the launch of software products. Cross‐project defect prediction (CPDP) is introduced for the anticipation of defects in novel projects lacking defect labels. CPDP can use defect information of mature projects to speed up defect prediction for new projects. So that developers can quickly get the defect information of the new project, so that they can test the software project pertinently. At present, the predominant approaches in CPDP rely on deep learning, and the performance of the ultimate model is notably affected by the quality of the training dataset. However, the dataset of CPDP not only has few samples but also has almost no label information in new projects, which makes the general deep‐learning‐based CPDP model not ideal. In addition, most of the current CPDP models do not fully consider the enrichment of classification boundary samples after cross‐domain, leading to suboptimal predictive capabilities of the model. To overcome these obstacles, we present contrastive learning pretraining for CPDP (ConCPDP), a CPDP method integrating contrastive pretraining and category boundary adjustment. We first perform data augmentation on the source and target domain code files and then extract the enhanced data as an abstract syntax tree (AST). The AST is then transformed into an integer sequence using specific mapping rules, serving as input for the subsequent neural network. A neural network based on bidirectional long short‐term memory (Bi‐LSTM) will receive an integer sequence and output a feature vector. Then, the feature vectors are input into the contrastive module to optimise the feature extraction network. The pretrained feature extractor can be fine‐tuned by the maximum mean discrepancy (MMD) between the feature distribution of the source domain and the target domain and the binary classification loss on the source domain. This paper conducts a large number of experiments on the PROMISE dataset, which is commonly used for CPDP, to validate ConCPDP’s efficacy, achieving superior results in terms of F1 measure, area under curve (AUC), and Matthew’s correlation coefficient (MCC).

Microscopic pore-throat classification and reservoir grading evaluation of the Fengcheng formation in shale oil reservoir

Different basins in China have proposed various reservoir grading standards for shale oil. Based on a comprehensive understanding of the basic characteristics of the shale oil reservoir in the Mahu Depression, this paper uses data from high-pressure mercury injection, physical properties, nuclear magnetic resonance, depletion development, and CO2 displacement development tests to analyze the microscopic pore structure features of the Fengcheng Formation shale oil reservoir. On this basis, the classification boundaries of the pore throats in the shale oil reservoir were analyzed, and a reservoir grading standard suitable for the Fengcheng Formation shale was proposed: large pore throats (greater than 1000 nm), medium pore throats(100∼1000 nm), small pore throats (20∼100 nm), and ultra-small pore throats (less than 20 nm). The medium pore throat is the lower limit for depletion development, the small pore throat is the lower limit under CO2 displacement conditions, and the ultra-small pore throat cannot be utilized under current conditions. The classification effect of the shale oil reservoir is verified using the production characteristics of Well MY1, the liquid production profile, and the results of geological "sweet spots" studies. The results show that the classification scheme for the microscopic pore throats of the Fengcheng Formation shale oil is reliable and feasible.

Monitoring and Fault Diagnosis of Breathing Valves in Atmospheric Storage Tank under Fuzzy PID

The atmospheric storage tank breathing valve relies too much on manual experience and simple monitoring methods in monitoring and fault diagnosis, and cannot provide high-precision fault diagnosis and prediction. Therefore, this article introduces a monitoring and fault diagnosis system for atmospheric storage tank breathing valves based on Fuzzy PID (Proportional-Integrated-Derivative). The research aims to design the atmospheric storage tank breathing valve system into three modules. The monitoring module uses sensors for data collection, while the early warning module classifies the data based on the monitoring module to find the optimal classification boundary and achieve abnormal state recognition. The fault diagnosis module uses the fuzzy PID algorithm to thoroughly inspect and evaluate the abnormal conditions detected in the atmospheric storage tank, and finally evaluates the monitoring and fault diagnosis of the atmospheric storage tank breathing valve before and after improvement. The results showed that the diagnostic accuracy improved by using fuzzy PID was 35.2% higher than before. In summary, the diagnostic method proposed in this paper is superior to the traditional method and improves the reliability and performance of the system.

Alignment-Based Adversarial Training (ABAT) for Improving the Robustness and Accuracy of EEG-Based BCIs.

Machine learning has achieved great success in electroencephalogram (EEG) based brain-computer interfaces (BCIs). Most existing BCI studies focused on improving the decoding accuracy, with only a few considering the adversarial security. Although many adversarial defense approaches have been proposed in other application domains such as computer vision, previous research showed that their direct extensions to BCIs degrade the classification accuracy on benign samples. This phenomenon greatly affects the applicability of adversarial defense approaches to EEG-based BCIs. To mitigate this problem, we propose alignment-based adversarial training (ABAT), which performs EEG data alignment before adversarial training. Data alignment aligns EEG trials from different domains to reduce their distribution discrepancies, and adversarial training further robustifies the classification boundary. The integration of data alignment and adversarial training can make the trained EEG classifiers simultaneously more accurate and more robust. Experiments on five EEG datasets from two different BCI paradigms (motor imagery classification, and event related potential recognition), three convolutional neural network classifiers (EEGNet, ShallowCNN and DeepCNN) and three different experimental settings (offline within-subject cross-block/-session classification, online cross-session classification, and pre-trained classifiers) demonstrated its effectiveness. It is very intriguing that adversarial attacks, which are usually used to damage BCI systems, can be used in ABAT to simultaneously improve the model accuracy and robustness.

Transgression of Race, Gender, and Class:

This paper aims to explore Mary Ann Shadd’s transgression of race, gender, and class boundaries by employing a close reading of the text, A Plea for Emigration. I will explore the triangular relationship between race, class, and gender seen in the text from intersectional feminist perspectives. My contention is that, through her activism by pen, especially in A Plea for Emigration, Shadd exposes the feminist voice that enables her to protest against racism, slavery, gender stratification, and marginalization based on class hierarchy. In other words, I claim that Shadd’s transgression of the borders of race, gender, and class lies in her activism and ideology as a woman, black, and marginalized. This paper will, therefore, show that Mary Ann Shadd strongly transgresses the borders of race, gender, and class as the first black woman who owned and edited a newspaper, inspired American blacks towards freedom, confronted her contemporary male leaders, exposed the female gaze during a period of history when the male gaze was predominant and authoritative, became a public speaker making the world listen to her while working with the so-called socially aesthetic people despite being a “negro”.

DPD-Net: Dual-path Proposal Discriminative Network for abnormal cell detection in cervical cytology images

Cytology inspection is a basic examination for the prevention of cervical cancer, which is still done manually and is a labor-intensive and time-consuming process with high inter-observer variability. With the rapid development of deep learning, automatic cytology inspection methods have achieved gratifying results, but the research on the effective detection of abnormal cells remains insufficient. In this paper, we propose a novel Dual-path Proposal Discriminative detection Network (DPD-Net) for abnormal cell detection in cervical cytology images. Specifically, considering the distinctive characteristics of abnormal nuclei such as increased sizes and unclear boundaries, we first design a dual-path architecture, where the cell path acts as the primary detector and the nucleus path serves as the auxiliary detector to provide supplementary information. In addition, the proposal information isolation may result in ambiguous classification boundaries. To transcend individual features and delve deeper into cellular relationships as implicit features, the proposal relation modules are added to explore relation information and refine features adaptively. Finally, to tackle problems of intra-class variation and inter-class similarity, we calculate the proposal contrastive losses in two paths respectively to guide a better distinction between the features of normal and abnormal cells. The proposed method is evaluated on our in-house cervical liquid-based cytology dataset (CLBC) and a public pap smear cytology dataset (CRIC) and gains satisfactory results, outperforming other state-of-the-art methods. Comprehensive experiments demonstrate the superiority of the proposed DPD-Net and the effectiveness of each proposed component. Our code is available at https://github.com/chaisiyii/DPD-Net.

Taxonomical lives: The making of social divisions in the Swedish press during the golden age of social democracy, 1945–76

This article investigates the media lives of a particular class taxonomy in the Swedish press from 1945 to 1976. Invented by the Central Bureau of Statistics in 1911, the ‘social group division’ system was abandoned in the early post-war period. Around the same time, however, it gained popularity in Swedish culture and political debate. While earlier research has noted that such bureaucratic class taxonomies – as in several other Western countries – conditioned how actors understood and created new knowledge about the population, this process of wider circulation remains understudied. Using insights from literature on ‘the social life of methods’ and the history of knowledge, which underline that knowledge is transformed by and transforms the contexts it circulates in, I show that print media was an arena for circulating and producing new meaning around class taxonomies. Although editorials shunned the social group division for incorrectly representing Swedish society and creating artificial class boundaries, journalists used the taxonomy to explain social structures. Furthermore, by interviewing ‘typical’ members of the different social groups, journalists made the system relatable and personal for their readers. In this context, the social groups were imagined as cultural communities, sharing cultural behaviours and preferences. Lastly, I analyse usages of the social group division in letters to the editor, which reveal that people felt they were being classified and wanted to offer their views of society, using the taxonomy in ways the experts had not intended. This study thereby contributes to the history of social taxonomies and class languages in the post-war period.

PAST AND PRESENT OF WOMEN'S RIGHTS AND VIOLENCE AGAINST WOMEN

In history, the greatest aspiration of people is that all humanity has equal rights regardless of race, language, religion or gender. Gender inequality seen in communities where patriarchal structure prevails has caused women to be deprived of their rights. The exclusion of women who have been deprived of their rights due to their gender and even exposure to violence is a global problem that continues from past to present.
 Violence against women, which is as old as the history of humanity, is a phenomenon that affects all societies deeply and negatively. As a fundamental human rights and freedom problem, it continues to exist all over the World as a universal public health problem, regardless of ethnic origin, class, religion, social status, culture, economic and geographical boundaries. Domestic violence is the most common form of violence against women. 
 In this study, the historical process of women and their rights, the place of women in society today, the historical process of violence against women, the causes and types of violence against women, femicides, the end point of violence against women, the effects of violence on public health, violence in our country will be discussed. Furthermore, institutions and organizations that women victims of violence can apply to, and suggestions against violence towards women are mentioned.

PREDICTING 10 YEAR MORTALITY WITH MACHINE LEARNING: EVIDENCE FROM NATIONAL SOCIAL LIFE, HEALTH, AND AGING PROJECT

Abstract The current academic literature extensively used linear logistic models with social, behavioral, and psychological status to predict mortality. However, few address the interdependency of predictors and the imbalance of targets that adversely bias the results. Using the National Social Life Health and Aging Project (NSHAP), we developed two machine learning models predicting the 10-year mortality of older adults in the US. We first used tree-based algorithms of Decision Tree (DT) that account for the interdependency of the social features and decide the splitting nodes and thresholds using entropy gain conditional on the previous splitting predictor to discern disposition status. Second, we used the Fuzzy Support Vector Machine (FSVM) that regards every sample as a node in high-dimensional vector space and splits the nodes with an optimum plane by finding the best linear combination of features to get an optimum prediction accuracy. Additionally, FSVM addresses the target imbalance problem by conducting a more delicate classification of samples with close predicted probabilities of being alive and deceased. Compared to the accuracy rates achieved by the Logistic Regression, our algorithms perform better on the entire population and the population near the class boundary. We also discussed the social and demographic characteristics of the cases whose disposition statuses were either wrongly predicted as deceased or alive by our algorithms. The findings serve important purposes for public health practitioners in accurately understanding the risk and protective factors of mortality in aging.

Uncertainty Evaluation of Soil Heavy Metal(loid) Pollution and Health Risk in Hunan Province: A Geographic Detector with Monte Carlo Simulation.

Research on soil heavy metal(loid) pollution and health risk assessment is extensive, but a notable gap exists in systematically examining uncertainty in this process. We employ the Nemerow index, the health risk assessment model, and the geographic detector model (GDM) to analyze soil heavy metal(loid) pollution, assess health risks, and identify driving factors in Hunan Province, China. Furthermore, the Monte Carlo simulation (MCS) method is utilized to quantitatively evaluate the uncertainties associated with the sampling point positions, model parameters, and classification boundaries of the driving factors in these processes. The experimental findings reveal the following key insights: (1) Regions with high levels of heavy metal(loid) pollution, accompanied by low uncertainty, are identified in Chenzhou and Hengyang Cities in Hunan Province. (2) Arsenic (As) and chromium (Cr) are identified as the primary contributors to health risks. (3) The GDM results highlight strong nonlinear enhanced interactions among lithology and other factors. (4) The input GDM factors, such as temperature, river distance, and gross domestic product (GDP), show high uncertainty on the influencing degree of soil heavy metal(loid) pollution. This study thoroughly assesses high heavy metal(loid) pollution in Hunan Province, China, emphasizing uncertainty and offering a scientific foundation for land management and pollution remediation.

A Fault Detection Approach Based on One-Sided Domain Adaptation and Generative Adversarial Networks for Railway Door Systems.

Fault detection using the domain adaptation technique is one of the more promising methods of solving the domain shift problem, and has therefore been intensively investigated in recent years. However, the domain adaptation method still has elements of impracticality: firstly, domain-specific decision boundaries are not taken into consideration, which often results in poor performance near the class boundary; and secondly, information on the source domain needs to be exploited with priority over information on the target domain, as the source domain can provide a rich dataset. Thus, the real-world implementations of this approach are still scarce. In order to address these issues, a novel fault detection approach based on one-sided domain adaptation for real-world railway door systems is proposed. An anomaly detector created using label-rich source domain data is used to generate distinctive source latent features, and the target domain features are then aligned toward the source latent features in a one-sided way. The performance and sensitivity analyses show that the proposed method is more accurate than alternative methods, with an F1 score of 97.9%, and is the most robust against variation in the input features. The proposed method also bridges the gap between theoretical domain adaptation research and tangible industrial applications. Furthermore, the proposed approach can be applied to conventional railway components and various electro-mechanical actuators. This is because the motor current signals used in this study are primarily obtained from the controller or motor drive, which eliminates the need for extra sensors.

A robust class decomposition-based approach for detecting Alzheimer's progression.

Computer-aided diagnosis of Alzheimer's disease (AD) is a rapidly growing field with the possibility to be utilized in practice. Deep learning has received much attention in detecting AD from structural magnetic resonance imaging (sMRI). However, training a convolutional neural network from scratch is problematic because it requires a lot of annotated data and additional computational time. Transfer learning can offer a promising and practical solution by transferring information learned from other image recognition tasks to medical image classification. Another issue is the dataset distribution's irregularities. A common classification issue in datasets is a class imbalance, where the distribution of samples among the classes is biased. For example, a dataset may contain more instances of some classes than others. Class imbalance is challenging because most machine learning algorithms assume that each class should have an equal number of samples. Models consequently perform poorly in prediction. Class decomposition can address this problem by making learning a dataset's class boundaries easier. Motivated by these approaches, we propose a class decomposition transfer learning (CDTL) approach that employs VGG19, AlexNet, and an entropy-based technique to detect AD from sMRI. This study aims to assess the robustness of the CDTL approach in detecting the cognitive decline of AD using data from various ADNI cohorts to determine whether comparable classification accuracy for the two or more cohorts would be obtained. Furthermore, the proposed model achieved state-of-the-art performance in predicting mild cognitive impairment (MCI)-to-AD conversion with an accuracy of 91.45%.

Joint Learning of Image Deblurring and Depth Estimation Through Adversarial Multi-Task Network

Self-supervised monocular depth estimation methods have achieved remarkable results on natural clear images. However, it is still a serious challenge to directly recover depth information from blurred images caused by long-time exposure while camera fast moving. To address this issue, we propose a unified framework for simultaneous deblurring and depth estimation (SDDE), which has higher coupling performance and flexibility compared with the simple concatenation strategy of deblurring model and depth estimation model. This framework mainly benefits from three features: (1) a novel Task-aware Fusion Module (TFM) to adaptively select the most relevant intermediate shared features for the dual decoder network by aggregating multi-scale features, (2) a unique Spatial Interaction Module (SIM) to learn higher-order representation in the encoder stage to better describe complex boundaries of different classes in high-dimensional space, and focuses on the task-related region by modeling the pairwise spatial correlation of the holistic tensor, (3) a Priors-Based Composite Regularization term to jointly optimize the shared encoder-dual decoder network. This work was evaluated on multiple datasets, including: Stereo blur [1], KITTI [2],NYUv2 [3], REDS [4] and our own large-scale stereo blur dataset, resulting in state-of-the-art results for depth estimation and image deblurring, respectively.

A Data-Driven Approach to Rapidly Identify the Critical Current of Fast-Charging Lithium-Ion Batteries

Traditional evaluation of battery charging protocols typically requires hundreds of electrochemical cycles and months of experimentation to select charging schemes that maximize the battery performance without compromising the cycle life. In this work, by nesting clustering and classification algorithms, a data-driven method using only data within a few tens of cycles is proposed to accurately classify constant-current charging protocols and rapidly identify the critical current, beyond which rapid degradation tends to occur within a specified lifetime. Specifically, by utilizing unsupervised clustering to process early-stage features and generate prediction labels, a model for early-stage prediction of the rapid degradation is established with an accuracy higher than 92.75%. Subsequently, the critical current is determined by intersecting the classification boundary with the physical distribution domain of the features. The reliability and generalizability of the proposed method is also discussed, which suggests that only ∼30 cycles and ∼40 samples are required to accomplish acceptable identification. The method is also proven to suitable for different battery systems. Therefore, the data-driven method proposed in this work provides a novel pathway to rapidly evaluate fast-charging batteries and charging protocols.

Generative Data Free Model Quantization With Knowledge Matching for Classification

Neural network quantization aims to reduce the model size, computational complexity, and memory consumption by mapping weights and activations from full-precision to low-precision. However, many existing quantization methods, either post-training with calibration or quantization-aware training with fine-tuning, require original data for better performance, which may not be available due to confidentiality or privacy constraints. This lack of data can lead to a significant decline in performance. In this paper, we propose a universal and effective method called Generative Data Free Model Quantization with Knowledge Matching for Classification (KMDFQ) that removes the dependence on data for neural network quantization. To achieve this, we propose a knowledge matching generator that produces meaningful fake data based on the latent knowledge in the pre-trained model, including classification boundary knowledge and data distribution information. Based on this generator, we propose a fake-data driven data free quantization method that uses the generated data to take advantage of the latent knowledge for quantization. Furthermore, we introduce Mean Square Error alignment during the fine-tuning of the quantized model to more strictly and directly learn knowledge, making it more suitable for data free quantization. Extensive experiments on image classification demonstrate the effectiveness of our method, achieving higher accuracy than existing data free quantization methods, particularly as the quantization bit decreases. For example, on ImageNet, the 4-bit data free quantized ResNet-18 has less than a 1.2% accuracy decline compared to quantization with real data. The source code is available at https://github.com/ZSHsh98/KMDFQ.

An adaptive classification and updating method for unknown network traffic in open environments

In recent years, to address the classification problem of unknown traffic in open network environments, numerous deep learning (DL)-based classification techniques have been proposed. Among these techniques, the single threshold-based DL method has gained significant popularity. However, the classification boundary constructed by this method is inaccurate, thus leading to the misclassification of known and unknown traffic. In this paper, we propose an adaptive classification and updating method for accurate application-level classification of known and unknown traffic in open environments. We adaptively construct individualized and accurate decision boundaries for each class of known traffic, which avoids misclassification cases caused by a single threshold and achieves accurate separation of known and unknown traffic. To provide a more accurate feature representation for the construction of the decision boundary, we also introduce an additional angular loss function to guide the model in learning more accurate flow features. In addition, to cope with the constant emergence of new classes of traffic in real network environments, our proposed method adaptively updates the model to respond to changes in network traffic classes. The proposed method is evaluated on two datasets, and the experimental results show that our proposed method has excellent classification accuracy and outperforms the state-of-the-art unknown traffic classification methods.

Eco-cultural identity building through tattoos: a conversational approach

While in the not-too-distant past, tattoos were often perceived as representing non-conformity or even deviance, tattoos now increasingly transcend class, gender, and age boundaries and are more acceptable than ever. Tattoos are created by artists and are an interpretation of a story that the client wants to tell, re-created in interpersonal communication situations—before, during, and after the actual tattooing. The project at hand conceptualizes and critically examines the ways in which tattoos alter people's sense of being not only in a semiotic way but also in a conversational way. Our guiding research question is how (much) tattooed images, ornaments, and symbols of nature (re)create the eco-cultural identity of the person wearing it and what role storytelling plays in restoring human–nature relationships. The insights were gained with a series of explorative interviews with (N =) 12 tattoo artists in Oceania (Australia and New Zealand) and Europe (Germany, Austria, and France), analyzed with an inductive categorization supported by QCAmap. The findings show that tattoos are both a device and signifier and a storytelling method. Bodies are described as landscapes where individual stories are carved out through a process of tattooing and ritual interactions and conversations tattooed bodies have with others. Tattoos have the potential to re-story the body and shape it in ways that create meaning for the tattooer, the wearer, and the society, and to create eco-cultural identities, thus regenerating or restoring human–nature relationships. This project opens a new field for communication research that helps to strengthen a conversational understanding of communication beyond the ritual perspective. The conceptualization of tattooing as a conversational process where meaning is created, common beliefs are (re)produced, new norms are cultivated, and meaningful human–nature relationships are forged stimulates further research studying other rituals and their potential to communicatively re-create a more sustainable society.