Domain Representation Research Articles

Evaluation of the Use of the Angular Domain and Order Domain in a Bearing Fault Detection Framework using Deep Learning

Bearing failures are very common in the industrial environment, requiring effective fault detection methods, which can be categorized into physics-based, knowledge-based and data-driven types. Data-driven methods are efficient in differentiating healthy conditions from faulty conditions by characterizing machine signals, involving stages of data acquisition, feature extraction, and condition determination. Traditionally, feature extraction and condition determination were manual, but advances in artificial intelligence and machine learning, especially deep learning, have automated this process. Although deep learning automatically learns the best features from the input data, the signal domain can influence the model's performance. Time and frequency domain representations are widely used in fault detection methodologies using vibration signals, while angular and order domains are more common in variable operating conditions, but direct use of these domains with deep learning is still rare in the literature. Considering this, this study evaluates a bearing fault detection methodology using vibration signals in different domains (time, frequency, angular, and order) under various rotational conditions. Three distinct approaches were tested to assess the effectiveness of these representations. The results indicated that the frequency domain representation had the best overall performance and the study concluded that the angular and order domains do not offer significant advantages compared to the frequency domain. Nonetheless, it is recommended to conduct a more in-depth analysis with more diverse datasets, especially those containing early-stage bearing fault signals.

Phase Space Formulation of Light Propagation on Tilted Planes

The solution of the Helmholtz equation describing the propagation of light in free space from a plane to another can be described by the angular spectrum operator, which acts in the frequency domain. Many applications require this operator to be generalized to handle tilted source and target planes, which has led to research investigating the implications of these adaptations. However, the frequency domain representation intrinsically limits the understanding the way the signal is transformed through propagation. Instead, studying how the operator maps the space–frequency components of the wavefield provides essential information that is not available in the frequency domain. In this work, we highlight and exploit the deep relation between wave optics and quantum mechanics to explicitly describe the symplectic action of the tilted angular spectrum in phase space, using mathematical tools that have proven their efficiency for quantum particle physics. These derivations lead to new algorithms that open unprecedented perspectives in various domains involving the propagation of coherent light.

FSH3D: 3D Representation via Fibonacci Spherical Harmonics

AbstractSpherical harmonics are a favorable technique for 3D representation, employing a frequency‐based approach through the spherical harmonic transform (SHT). Typically, SHT is performed using equiangular sampling grids. However, these grids are non‐uniform on spherical surfaces and exhibit local anisotropy, a common limitation in existing spherical harmonic decomposition methods. This paper proposes a 3D representation method using Fibonacci Spherical Harmonics (FSH3D). We introduce a spherical Fibonacci grid (SFG), which is more uniform than equiangular grids for SHT in the frequency domain. Our method employs analytical weights for SHT on SFG, effectively assigning sampling errors to spherical harmonic degrees higher than the recovered band‐limited function. This provides a novel solution for spherical harmonic transformation on non‐equiangular grids. The key advantages of our FSH3D method include: 1) With the same number of sampling points, SFG captures more features without bias compared to equiangular grids; 2) The root mean square error of 32‐degree spherical harmonic coefficients is reduced by approximately 34.6% for SFG compared to equiangular grids; and 3) FSH3D offers more stable frequency domain representations, especially for rotating functions. FSH3D enhances the stability of frequency domain representations under rotational transformations. Its application in 3D shape reconstruction and 3D shape classification results in more accurate and robust representations. Our code is publicly available at https://github.com/Miraclelzk/Fibonacci-Spherical-Harmonics.

RSBagging: An ensemble classifier detecting the after-effects of ischemic stroke through EEG connectivity and microstates.

Stroke can lead to significant after-effects, including motor function impairments, language impairments (aphasia), disorders of consciousness (DoC), and cognitive deficits. Computer-aided analysis of EEG connectivity matrices and microstates from bedside EEG monitoring can replace traditional clinical observation methods, offering an automatic approach to monitoring the progression of these after-effects. This EEG-based method also enables quicker and more efficient assessments for medical practitioners. In this study, we employed Functional Connectivity features that extract spatial representation and Microstate features that focus on the time domain representation to monitor the after-effects of ischemic stroke patients. As the dataset from stroke patients is heavily imbalanced across various clinical after-effects conditions, we designed an ensemble classifier, RSBagging, to address the issue of classifiers often favoring the majority classes in the classification of imbalanced datasets. The experimental results demonstrate that different connectivity matrices are effective for three classification tasks: consciousness level, motor disturbance, and stroke location. Using our RSBagging model, all three tasks achieve over 98% accuracy, sensitivity, specificity, and F1-score, significantly outperforming the existing classifiers SVM, XGBoost, and Random Forest. Therefore, the RSBagging classifier based on connectivity matrices offers an effective method for monitoring the after-effects in stroke patients.

Perceptual representations in L1 and L2 spatial and abstract language processing: applying an innovative sentence-diagram verification paradigm.

Perceptual representations in language comprehension were examined using sentence-picture verification tasks. However, concerns have been raised regarding the suitability of concrete pictures for representing abstract concepts compared to image-schematic diagrams. To assess the perceptual representations of spatial and abstract domains in both first language (L1) and second language (L2) processing, the study tests bilingual speakers' mental imagery on the basis of the simulation-based L1 comprehension model and proposes a simulation-based L2 comprehension model, supported by empirical evidence from an innovative sentence-diagram verification paradigm. 41 adult L1 Mandarin Chinese speakers participated in the study. 21 participants completed the Chinese sentence-diagram verification task (Experiment 1), while 20 participants completed the translation-equivalent version in L2 English (Experiment 2). Participants read a sentence [e.g., A diligent worker walked into the office (spatial sense); A strong team headed into the final (abstract sense)] at their self-paced speed, followed by a congruent (e.g., into diagram) or incongruent diagram (e.g., out-of diagram), and made binary judgments to verify spatial configurations between the sentence and diagram. Semantic rating tasks in both Chinese and English were also conducted to validate congruency between diagrams and sentences in both languages. Results from Experiment 1 indicate overall compatibility effects on L1 Chinese processing, unaffected by directional verbs or abstractness of sense. Results from Experiment 2 reveal interference effects on L2 English processing, with interference observed only after reading sentences encoding spatial senses, not abstract senses. Aligning with previous findings using sentence-picture verification tasks, the current findings confirm the weaker mental simulation effects in L2 processing compared to L1 processing. These findings extend the existing simulation-based L1 comprehension model, provide empirical support for the proposed simulation-based L2 comprehension model, and validate the innovative sentence-diagram verification paradigm for examining image-schematic representations in spatial and abstract language processing among Chinese-English bilinguals. The paradigm holds significant potential for research on perceptual representations in processing a broader range of grammatical and semantic properties during both online and offline L1 and L2 comprehension.

Quantifying the frequency modulation in electrograms during simulated atrial fibrillation in 2D domains

Atrial fibrillation (AF) affects millions of people in the world, causing increased morbidity and mortality. Treatment involves antiarrhythmic drugs and catheter ablation, showing high success for paroxysmal AF but challenges for persistent AF. Experimental evidence suggests reentrant waves and rotors contribute to AF substrates. Ablation procedures rely on electroanatomical maps and electrogram (EGM) signals; however, current methods used in clinical practice lack consideration for time–frequency varying EGM components. The fractional Fourier transform (FrFT) can be adopted to capture time-varying frequency components, thereby enhancing the comprehension of arrhythmogenic substrates during AF for improved ablation strategies. To this end, a FrFT-based algorithm is developed to characterize non-stationary components in EGM signals from simulated AF episodes. The proposed algorithm comprises a pre-processing step to enhance the coarser features of the EGM waveform, a windowing process for dynamic assessment of the EGM, and a FrFT order optimization stage that seeks compact signal representations in fractional Fourier domains. The resulting order is related to the rate of frequency change in the signal, making it a useful indicator for frequency-modulated components. The FrFT-based algorithm is implemented on EGM signals from AF simulations in 2D domains representing a region of the atrial tissue. Consequently, the computed optimum FrFT orders are used to build maps that are spatially correlated to the underlying propagation dynamics of the simulated AF episode. The results evince that the extreme values in the optimum orders map pinpoint the localization of fibrillatory mechanisms, generating EGM activation waveforms with varying frequency content over time.

Content-Based Image Retrieval and Feature Extraction: Analysing the Literature

A significant amount of multimedia data consists of digital images, and multimedia content analysis is used in many real-world computer vision applications. Multimedia information, especially photos, has become much more complicated in the last several years. Every day, millions of photos are posted to various websites, such as Instagram, Facebook, and Twitter. Finding a suitable image in an archive is a difficult research subject for the field of computer vision. Most search engines use standard text-based techniques that depend on metadata and captions in order to fetch photos. Over the past 20 years, a great deal of research has been conducted on content-based image retrieval (CBIR), picture categorization, and analysis. In image classification models and CBIR, high-level picture representations are represented as feature vectors made up of numerical values. Empirical evidence indicates a considerable disparity between picture feature representation and human visual understanding. Reducing the semantic gap between human visual understanding and picture feature representation is the aim of this study. This study aims to do a thorough analysis of the latest advancements in the domains of Content-Based picture Retrieval and picture representation. We performed a comprehensive analysis of many models for image retrieval and picture representation, encompassing the most recent advancements in semantic deep-learning methods and feature extraction. This paper provides an in-depth analysis of the key ideas and important studies related to image representation and content-based picture retrieval. In an effort to stimulate more research in this field, it also offers a preview of potential future study topics.

Revisiting block deordering in finite-domain state variable planning

Plan deordering removes unnecessary ordering constraints between actions in a plan, facilitating plan execution flexibility and several other tasks, such as plan reuse, modification, and decomposition. Block deordering is a variant of plan deordering that encapsulates coherent actions into blocks to eliminate further ordering constraints from a partial-order plan (POP) and is useful in many applications (e.g., generating macro-actions and improving the overall plan quality). The existing block deordering strategy is formulated in propositional encodings. Finite-domain state variable encodings (e.g., SAS+ representation), in contrast with propositional encodings, can capture the internal structure and the behavior of state variables of a planning instance through concise constructs such as causal graphs (CGs) and domain transition graphs (DTGs). This work redefines the semantics of block deordering terminologies and related plan deordering concepts in finite domain representation (FDR). Our proposed semantics also resolves some limitations of the existing block semantics and further enhance plan flexibility. In addition, this work exploits block deordering to eliminate redundant actions from a POP. A comparative analysis is also performed on block deordering with various deordering/reordering techniques using explanation-based order generalization (EOG) and MaxSAT. Our experiments on the benchmark problems from International Planning Competitions (IPC) show that our FDR formalism of block deordering significantly improves the plan execution flexibility while maintaining good coverage and execution time.

Unsupervised domain adaptation bearing fault diagnosis method based on joint feature alignment

In this paper, the issue of cross-condition fault diagnosis of bearing is studied. During actual operation, the conditions of bearing vary due to changes in factors such as rotation speed and load, and the data distribution between different working conditions varies. Deep learning models that perform well in one condition are not ideal when applied to another condition directly. To address this problem, a novel unsupervised domain adaptation fault diagnosis method based on joint feature alignment is proposed in this paper. 1D-CNN is used as a weight-shared feature extractor to extract the features from both the source and target domains. The discrepancies in marginal and conditional distributions between the source and target domains are comprehensively considered by multi-layer multi-bandwidth Cauchy kernel maximum mean discrepancy (MB-CMMD) and mutual information (MI). The domain drift is reduced by aligning the feature representations of source and target domains. The network after feature alignment demonstrates a notable enhancement in the diagnostic accuracy of unlabeled samples within the target domain. The experimental results demonstrate that, in comparison to other domain adaptation approaches, The proposed approach can significantly enhance the accuracy of fault diagnosis while realizing feature alignment.

Towards the Automation of Non-destructive Fault Recognition: Enhancement of Robustness and Accuracy Through AI Powered Acoustic and Thermal Signal Analysis in Time, Frequency- and Time-Frequency Domains

AbstractNon-destructive inspection and analysis techniques are crucial for quality assessment and defect analysis in various industries. They enable for screening and monitoring of parts and products without alteration or impact, facilitating the exploration of material interactions and defect formation. With increasing complexity in microelectronic technologies, high reliability, robustness and thus, successful failure analysis is essential. Machine learning (ML) approaches have been developed and evaluated for the analysis of acoustic echo signals and time-resolved thermal responses for assessing their ability for defect detection. In the present paper different ML architectures were evaluated, including 1D and 2D convolutional neural networks (CNNs) after transforming time domain data into the spectral- and wavelet domains. Results showed that 2D CNNs processing data in wavelet domain representation performed best, however at the expense of additional computational effort. Furthermore, ML-based analysis was explored for lock-in thermography to detect and locate defects in the axial dimension based on thermal emissions. While promising, further research is needed to fully realize its potential.

Spider Silk: Rapid, Bottom‐Up Self‐Assembly of MaSp1 into Hierarchically Structured Fibers Through Biomimetic Processing

AbstractSpider dragline silk's exceptional mechanical performance, coupled with its benign production pathway, have inspired the design of diverse smart materials. Remarkably, relatively little is known about the self‐assembly process of major ampullate spidroin 1 (MaSp1) – the main protein constituent of dragline fiber – during its rapid conversion from soluble precursor protein into hierarchically structured mature silk fibers. Herein, the biomimetic potential of MaSp1 is explored using a new recombinant platform with full domain representation. MaSp1 is found to undergo efficient liquid‐liquid phase separation (LLPS) in response to kosmotropic ions, with notably higher propensity compared to MaSp2, and with MaSp1 exhibiting a more complex solubility profile relative to levels of sodium chloride. To further the understanding of silk spinning, the rapid assembly of mesoscale structures is monitored in real‐time in response to ion and pH gradients, revealing a progression from LLPS droplets toward aligned hierarchical fibers. Furthermore, using this biomimetic system, insoluble macroscopic MaSp1 fibers can be readily generated, wherein the application of mechanical deformation triggers the emergence of β‐sheet secondary structures. The insights gained from this study can have broader application in efforts to mimic the formation of biomaterials with spatially organized features across multiple length scales.

GNN-based multi-source domain prototype representation for cross-subject EEG emotion recognition

Emotion recognition based on electroencephalography (EEG) signals is a major area of affective computing. However, the existence of distributional differences between subjects has greatly hindered the large-scale application of EEG emotion recognition techniques. Most of the existing cross-subject methods primarily concentrate on treating multiple subjects as a single source domain. These methods lead to significant distributional differences within the source domain, which hinder the model’s ability to generalise effectively to target subjects. In this paper, we propose a new method that combines graph neural network-based prototype representation of multiple source domains with clustering similarity loss. It consists of three parts: multi-source domain prototype representation, graph neural network and loss. Multi-source domain prototype representation treats different subjects in the source domain as sub-source domains and extracts prototype features, which learns a more fine-grained feature representation. Graph neural network can better model the association properties between prototypes and samples. In addition, we propose a similarity loss based on clustering idea. The loss makes maximum use of similarity between samples in the target domain while ensuring that the classification performance does not degrade. We conduct extensive experiments on two benchmark datasets, SEED and SEED IV. The experimental results validate the effectiveness of the proposed multi-source domain fusion approach and indicate its superiority over existing methods in cross-subject classification tasks.

South Sudanese Refugee Higher Education Access in Uganda: An Intersectionality Enquiry

This study was guided by the intersectionality theory, originally developed by Kimberlé Crenshaw. According to Crenshaw, the theory assumes that people have multiple biological, social and cultural identity markers that intersect, resulting in experiences of privilege or disadvantage, inclusion or discrimination. However, the theory maintains that marginalized individuals are not homogeneous and they experience discrimination and inclusion in different ways. The intersectionality theory also recognizes power dynamics and how structural, political and representational domains, intersect and produce complex patterns of discrimination, inequality and disadvantage. Ultimately, the intersectionality theory asserts that effective activism and social change require recognizing and addressing the intersections of various forms of oppression, and advocating for justice across multiple fronts. This exposes discrimination and exclusion that would have otherwise gone unnoticed, also giving voice to the disadvantaged and excluded. The study adopted a qualitative approach, an exploratory case study design, and an advocacy/ participatory philosophical lens. Twenty-seven purposively sampled participants took part in the study. They included 12 undergraduates from two private Ugandan universities, 13 government and non-governmental organization (NGO) officials, two officials from public and private universities, all involved in refugee higher education. Data was collected through a literature review, in-depth interviews with key informants and students, and a students’ focus group discussion. The study established that higher education access for South Sudanese refugees in Uganda involves multiple intersectional prohibitive and also supportive factors. The study therefore recommends that through situational analysis and needs assessment, Uganda develops clear objectives, activities and outcomes in the Education Response Plan, to establish the divergent supportive and prohibitive factors and cater for the various refugee student needs. The study also designed the refugee access and resilience (RARE) model to assist in the aforementioned regard

Contrastive learning with hard negative samples for chest X-ray multi-label classification

Contrastive learning has gained significant popularity and achieved remarkable success in learning meaningful representations in various domains. This study addresses the significant problem of dependency on labeled data in chest radiography (CXR) images, which are crucial for diagnosing respiratory diseases such as pneumonia but are both time-consuming and expensive to annotate. Despite extensive research, existing studies on CXR largely depend on labeled data. To overcome this challenge, we propose a framework named SURE (similarity, uncertainty, and representativeness) for multi-label classification with hard negatives in contrastive learning. The proposed framework incorporates these aspects when handling hard negatives and effectively combines contrastive learning and downstream tasks for robust representation learning and multi-label classification. Experimental validation using three distinct CXR datasets demonstrates that our approach significantly reduces the dependency on labeled data while achieving notable performance improvements over existing methods, highlighting its potential effectiveness and efficiency in the CXR domain.

Conceptualizing Symptom Invalidation as Experienced by Patients With Endometriosis.

The aim of this paper is to provide foundational work to standardize the conceptual definition of what I refer to as symptom invalidation by using invalidating environments and illness representations as guiding conceptual frameworks. Mixed deductive-inductive thematic analysis was used to analyze survey responses to an open-ended question gauging an invalidating interaction patients experienced with a clinician among 1038 patients with endometriosis. Dissimilarity in illness representations between patients and clinicians, as perceived by patients, occurred with feelings of invalidation. Invalidation was experienced in relationship to all identified domains of illness representations including how clinicians communicated the diagnosis (identity label), the internal (internal cause) and/or external (external cause) nature of the cause, clinicians' understanding of the timeline (timeline) and consequences (consequences), and clinicians' understanding of control over the symptoms via the efficacy of patients (self-efficacy) and coping procedures (response efficacy). Inductive analysis revealed invalidation can also be related to how clinicians communicate judgments of whether patients are presenting with ulterior motives (secondary gains). Clinicians' actions appear to compound experiences of invalidation by not having symptoms investigated (investigative experiences). Invalidating environments and illness representations serve as effective conceptual frameworks for providing a conceptual definition of symptom invalidation.

Discrimination of semantically similar verbal memory traces is affected in healthy aging

Mnemonic discrimination of highly similar memory traces is affected in healthy aging via changes in hippocampal pattern separation—i.e., the ability of the hippocampus to orthogonalize highly similar neural inputs. The decline of this process leads to a loss of episodic specificity. Because previous studies have almost exclusively tested mnemonic discrimination of visuospatial stimuli (e.g., objects or scenes), less is known about age-related effects on the episodic specificity of semantically similar traces. To address this gap, we designed a task to assess mnemonic discrimination of verbal stimuli as a function of semantic similarity based on word embeddings. Forty young (Mage = 21.7 years) and 40 old adults (Mage = 69.8 years) first incidentally encoded adjective-noun phrases, then performed a surprise recognition test involving exactly repeated and highly similar lure phrases. We found that increasing semantic similarity negatively affected mnemonic discrimination in both age groups, and that compared to young adults, older adults showed worse discrimination at medium levels of semantic similarity. These results indicate that episodic specificity of semantically similar memory traces is affected in aging via less efficient mnemonic operations and strengthen the notion that mnemonic discrimination is a modality-independent process supporting memory specificity across representational domains.

Explicit or implicit digital humanities? An examination of search strategies to retrieve digital humanities publications from large-scale scholarly databases

Abstract As a growing research field, digital humanities (DH) is receiving increasing attention from quantitative science studies using standardized scholarly databases. However, one of the challenges of this new line of research is how to select the query strategy to produce a representative sample of the field. In this research, we analyzed the differences between two publication samples acquired from the Dimensions database using two sampling approaches, namely, a keyword search and a DH journal list. We argue that these two samples offer distinct perspectives on the conceptual landscape of digital humanities, namely, implicit DH and explicit DH, and contribute to building a more comprehensive representation of the DH research domain. We identified notable differences between the publication samples from these two query strategies, especially the fact that these two samples have a very small overlap of publications, and they also have different disciplinary orientations. Our findings indicate that future quantitative studies analyzing DH publications should use more inclusive methods to cover both the implicit and explicit types of DH contributions. Moreover, we also discussed how our findings contribute to a deeper understanding of the disciplinary composition of DH, an interdisciplinary research field.

The Politics of Menstruation

Menstrual blood is still regarded as embarrassing and taboo in many places all over the world. This article focuses on the study of the Red Tent as an example of feminist-spiritual menstrual activism established in 2007 in the US because it represents an important form of breaking the menstrual taboo. Although contemporary spiritualities present themselves as nonhierarchical and gender equal, spirituality and well-being in the women's circles is predominantly practiced by cisgender, heterosexual, and white middle-class women, excluding lesbian, gay, bisexual, transgender, queer/questioning, and others (LGBTQ+). Constructs around the sacredness of female experiences (menstruation, menopause) are problematic for transgender women who do not share these experiences, and a lack of diversity may perpetuate systematic inequities and discrimination. This article discusses whether the Red Tent in Slovenia is open to include transgender and nonbinary people. By creating alternative domains of representation in which nonnormative bodies can exist, we disrupt the sex/gender system and dismantle normative femininity and masculinity. The article argues that in this way the Red Tent has the potential to subvert the dominant ideology of gender binary construction by providing alternative models for the embodiment of gender to challenge traditional conservative gender essentialisms in society. The methodology employed consists of ethnographic fieldwork, which was performed in the Red Tent gatherings and semistructured in-depth interviews with participants who host or participate in them. Because a part of the scope of the research “lives” in the cyber world, the ethnographic research methodology was integrated with the phenomena and data obtained from the internet in the form of netnography.

Detection and Segmentation of Glioma Tumors Utilizing a UNet Convolutional Neural Network Approach with Non-Subsampled Shearlet Transform.

The prompt and precise identification and delineation of tumor regions within glioma brain images are critical for mitigating the risks associated with this life-threatening ailment. In this study, we employ the UNet convolutional neural network (CNN) architecture for glioma tumor detection. Our proposed methodology comprises a transformation module, a feature extraction module, and a tumor segmentation module. The spatial domain representation of brain magnetic resonance imaging images undergoes decomposition into low- and high-frequency subbands via a non-subsampled shearlet transform. Leveraging the selective and directive characteristics of this transform enhances the classification efficacy of our proposed system. Shearlet features are extracted from both low- and high-frequency subbands and subsequently classified using the UNet-CNN architecture to identify tumor regions within glioma brain images. We validate our proposed glioma tumor detection methodology using publicly available datasets, namely Brain Tumor Segmentation (BRATS) 2019 and The Cancer Genome Atlas (TCGA). The mean classification rates achieved by our system are 99.1% for the BRATS 2019 dataset and 97.8% for the TCGA dataset. Furthermore, our system demonstrates notable performance metrics on the BRATS 2019 dataset, including 98.2% sensitivity, 98.7% specificity, 98.9% accuracy, 98.7% intersection over union, and 98.5% disc similarity coefficient. Similarly, on the TCGA dataset, our system achieves 97.7% sensitivity, 98.2% specificity, 98.7% accuracy, 98.6% intersection over union, and 98.4% disc similarity coefficient. Comparative analysis against state-of-the-art methods underscores the efficacy of our proposed glioma brain tumor detection approach.

FAQ: How do I estimate the output gap?

Abstract I investigate the properties of output gaps in New Keynesian DSGE models and study the relationship between theory-based quantities and the estimates obtained with standard approaches. Theoretical gaps display low frequency variations, have similar frequency domain representation as potentials and are generally correlated with them. Potentials have important business cycle variability. Existing statistical approaches fail to recognize these features and generate distorted estimates. Gaps are best estimated with a Polynomial filter. Explanations for the outcomes are given. I propose a statistical procedure reducing estimation biases.