Source Domain Research Articles

Study on Image Classification Algorithm Based on Multi-Scale Feature Fusion and Domain Adaptation

This paper introduces the MMTADAN, an innovative algorithm designed to enhance cross-domain image classification. By integrating multi-scale feature extraction with Taylor series-based detail enhancement and adversarial domain adaptation, the MMTADAN effectively aligns features between the source and target domains. The proposed approach addresses the critical challenge of generalizing classification models across diverse datasets, demonstrating significant improvements in performance. The findings suggest that retaining essential image details through multi-scale extraction and Taylor series enhancement can lead to better classification outcomes, making the MMTADAN a valuable contribution to the field of image classification.

Shedding light on the ‘invisible load’: an analysis of sight metaphors in parenthood podcasts

ABSTRACT This paper intends to establish which sight metaphors are preferably utilised in parenthood podcast discourse when the division of family responsibilities within heterosexual dual-income couples is discussed. The study examines a sample of podcast episodes about this topic aired during the COVID-19 pandemic and produced in a number of English-speaking countries. Starting from the assumption that work performed within the home is conventionally conceptualised as something heavy (DOMESTIC WORK IS A LOAD), the research relies on Conceptual Metaphor Theory and Critical Metaphor Analysis to explore the ways in which the ‘load’ source domains combines with that of ‘vision’. Results indicate the widespread presence of invisibility metaphors in relation to women's work within their households. The adoption of such rhetorical figures has noteworthy ideological repercussions: labelling mothers’ contributions to their families as ‘invisible’ produces the paradoxical effect of making them very noticeable, thus validating women's efforts and highlighting their crucial importance. The use of metaphorical patterns involving the sense of sight thus represents an instance of counter discourse that spreads awareness about the devaluation of housework and childcare and might ultimately contribute to family and societal transformation.

Remaining Useful Life Prediction based on Multisource Domain Transfer and Unsupervised Alignment

Transfer learning （TL） enhances remaining useful life (RUL) predictions by addressing data scarcity and operational challenges. Nonetheless, when a significant disparity in degradation data distribution exists between source and target domains, single-source domain TL may lead to misleading or negative transfer. Multisource domain TL partially mitigates these issues but fails to account for substantial discrepancies in feature-label correlations, impairing RUL prediction accuracy. To cope with this problem, we propose a multisource domain unsupervised adaptive learning method powered by a temporal convolutional network. Using a multilinear conditioning strategy, we combine degradation data and subregion labels to construct input characteristics for the domain discriminator. Additionally, we design a feature extractor that produces label-related features invariant across domains, thereby enhancing prediction precision. We evaluate our method using the publicly available C-MAPSS degradation dataset, demonstrating its effectiveness through a case study and ablation experiments.

Target Structure Learning Framework for Unsupervised Multi-Class Domain Adaptation

Unsupervised multi-class domain adaptation (multi-class UDA) has recently been proposed to fill the gap between empirically practical methods for multi-class classification and well-founded theory with the setting of binary classification. Nevertheless, the multi-class UDA methods use model predictions to characterize the disagreement of multi-class scoring hypotheses, which is used to optimize the divergence between domain distributions. Such self-training manner may bring inaccurate model predictions, which would damage the target structure due to the absence of labels of the target domain, leading to sub-optimal performance. On the other hand, this disagreement between multi-class scoring hypotheses does not involve the relationships among all of the multiple classes. It causes that multi-class UDA cannot properly connect the advanced practical UDA methods that consider class-conditional distribution alignment. Thus, we propose to exploit the target structure information and then incorporate it into multi-class UDA to achieve class-conditional distribution alignment. We theoretically and experimentally explain the importance of accurate target structure information to reduce the expected error on the target domain. Notably, our method achieves state-of-the-art results on three commonly-used benchmarks with different scales. In addition, using the target structure information, we propose a variant to cope with noisy open-world source domains such as noisy labels and out-of-distribution samples, enhancing the robustness of our method. The source code is available at https://github.com/jingzhengli/Multi_Class_UDA .

Conceptual Metaphor BUSINESS IS A JOURNEY in Business Terminology

Departing from the conventional understanding that metaphor is merely a component of rhetorical and poetic expression, the Theory of Conceptual Metaphor provides linguistic evidence that metaphor plays a crucial role in creating new specialized vocabulary. The present study attempts to apply the Conceptual Metaphor Theory to analyze the metaphor BUSINESS IS A JOURNEY in nominating business terminology. The corpus of the study comprises 179 metaphorical business terms collected from business dictionaries and textbooks. It is discovered in the study that certain attributes of the “journey” source domain are mapped onto those of the “business” target domain, resulting in four derivative metaphors in business terms, namely companies are conventionally viewed as travelers, business tools are metaphorically described as vehicles, business growth is conceptually viewed as the roadmap and distance covered, and business challenges are metaphorically described as obstacles encountered. The research findings highlight metaphorization as an effective method of business term nomination.

Metaphorical framing of political events through ENTERTAINMENT scenarios

Abstract The article sets out to examine the entertainment source domain and its scenarios as realised in the media discourse surrounding political events in Belarus in 2021. Metaphorical scenarios are investigated considering different viewpoints, such as those presented in Lithuanian, German, and Russian media. The methodological framework is a blend of Cognitive Linguistics and Critical Discourse Studies, embracing the viewpoint (Sweetser, 2012), Critical Metaphor Analysis (Charteris-Black, 2005), metaphorical scenarios (Musolff, 2016), and framing (Hart, 2014). The results demonstrate that the entertainment domain acquires multiple scenarios depending on the viewpoint. The evaluation attached to the scenarios is mostly negative; however, the viewpoint adopted in Lithuanian and German discourses is very different from Russian discourse. The former is based on Western values and targets the authoritarian regime, whereas the latter is Russian-centric, with the Western world posited as a major threat to the Belarusian and Russian societies.

Improved Prototypical Network Model for Classification of Farmland Shelterbelt Using Sentinel-2 Imagery

Farmland shelterbelt plays an important role in protecting farmland and ensuring stable crop yields, and it is mainly distributed in the form of bands and patches; different forms of distribution have different impacts on farmland, which is an important factor affecting crop yields. Therefore, high-precision classification of banded and patch farmland shelterbelt is a prerequisite for analyzing its impact on crop yield. In this study, we explored the effectiveness and transferability of an improved Prototypical Network model incorporating data augmentation and a convolutional block attention module for extracting banded and patch farmland shelterbelt in Northeast China, and we analyzed the potential of applying it to the production of large-scale farmland shelterbelt products. Firstly, we classified banded and patch farmland shelterbelt under different sample window sizes using the improved Prototypical Network in the source domain study area to obtain the optimal sample window size and the optimal classification model. Secondly, fine-tuning transfer learning and learning from scratch directly were used to classify the banded and patch farmland shelterbelt in the target domain study area, respectively, to evaluate the extraction model’s migratability. The results showed that classification of farmland shelterbelt using the improved Prototypical Network is very effective, with the highest extraction accuracy under the 5 × 5 sample window; the accuracies of the banded and patch farmland shelterbelt are 92.16% and 90.91%, respectively. Using the fine-tuning transfer learning method in the target domain can classify the banded and patch farmland shelterbelt with high accuracy, above 95% and 89%, respectively. The proposed approach can provide new insight into farmland shelterbelt classification and farmland shelterbelt products obtained from freely accessible Sentinel-2 multispectral images.

Theory and algorithm for domain adaptation

Domain adaptation is an important subfield of transfer learning, it has been successfully applied in many applications of machine learning. Recently, significant theoretical and algorithmic advances have been achieved in domain adaptation. The theoretical analyses for domain adaptation are based on VC dimension and Rademacher complexity. There are also some covering number-based results, but most of these bounds are based on the results of Rademacher complexity, indirectly given by the relationship between covering number and Rademacher complexity. In this paper, we propose a theoretical analysis framework for domain adaptation, thus the error bound can be derived directly by covering number, which is an effective method for analyzing the generalization error in statistical learning theory. We derive generalization error bound for domain adaptation with a class of loss functions satisfying the assumptions. We also propose a mixup contrastive adversarial network for domain adaptation by introducing a mixup module for enhancing the alignment of the source and target domains during domain transfer, and a contrastive learning module for solving class-level alignment after domain transfer. Experimental results demonstrate the effectiveness of the proposed algorithm and the property of the theoretical results.

Efficient Cross-Domain Fault Diagnosis via Distributed Multi-Source Domain Deep Transfer Learning

Abstract In the actual industrial production, the working conditions of rotating machinery are complex and changeable, and the health-state monitoring data are increasingly large and difficult to be labeled, which will seriously restrict the accuracy and efficiency of cross-domain fault diagnosis (CDFD) of rotating machinery. Therefore, an efficient multi-source domain deep transfer learning (MDDTL) method for CDFD of rotating machinery is proposed. Firstly, a MDDTL model is constructed to improve the accuracy of CDFD. In the model, a dual-phase domain alignment strategy is designed, which considers the alignment of feature distributions between each source and target domain pair in the feature space and that of prediction probabilities between domain-specific fault classifiers in the output space. The fault prediction results from multiple different fault classifiers are merged dynamically by the proposed imbalanced adaptive prediction strategy. Secondly, a data-parallel distributed training scheme for MDDTL model is proposed. Based on the idea of data parallelism, the distributed parallel training of MDDTL model is performed with Horovod-GPU platform, and the parameters are synchronously updated with the bandwidth-optimal Ring-AllReduce architecture. Under the premise of ensuring the accuracy of fault diagnosis (FD), the training time of MDDTL model is significantly reduced. Finally, extensive experiments are conducted to verify the effectiveness of the proposed MDDTL method. The results demonstrate that the proposed method not only effectively improves the accuracy of CDFD of rotating machinery, but also significantly improves the training efficiency of MDDTL model. After adopting the proposed method, the diagnosis accuracies achieved under two different cross-working condition scenarios reach 97.09% and 97.87% respectively, and the model training time is reduced by 73.62% when facing a large-scale rotating machinery training set.

CONCEPTUAL METAPHOR IN FOOTBALL NEWS ON GOAL.COM

This research examines conceptual metaphors as defined by Lakoff and Johnson, focusing on three types: structural, ontological, and orientational. The study analyzes an editorial from Goal.com titled, "Arsenal have no margin for error! Gunners told Liverpool showdown is 'must-win' in title race just eight games into 2024-25 season," using a qualitative approach grounded in cognitive semantic theory to explore the nuanced meanings conveyed through metaphor in sports commentary. Known for its in-depth and timely football analysis, Goal.com offers insights into how metaphors enhance fans' understanding of competitive sports narratives. Data collection involved close reading and note-taking, identifying instances of structural, ontological, and orientational metaphors, along with their source and target domains and image schemas. Findings reveal five structural metaphors, which use schemas such as Scale and Force to emphasize competitive intensity; four ontological metaphors, drawing on Container, Force, and Existence schemas to illustrate team pressures; and one orientational metaphor, using the Container schema to deepen spatial and relational context in the text. This study highlights the role of sports media metaphors in shaping public perception, making abstract concepts like competition and resilience more tangible. By framing sports challenges in relatable, high-stakes terms, these metaphors foster emotional engagement among fans, creating a shared understanding of a team's journey and pressures and underscoring the powerful influence of metaphor in sports narratives.

A Transfer Learning Model for Rolling Bearing Fault Diagnosis Based on Texture Loss Strategy and Nuclear Norm Regularization

Abstract In recent years, transfer learning (TL) approaches have seen extensive application in diagnosing bearing faults due to their exceptional performance. However, mechanical noise, equipment aging, and wear lead to notable disparities and differences in the multi-level feature distributions across the source and target domain signals. The issue is addressed by proposing a transfer learning model based on a texture loss strategy and nuclear norm regularization method. First, a Feature-Enhanced Network (MSRnet) is designed, which significantly improves the ability to capture local details and long-range dependencies by combining a multi-scale feature extraction module with a dilated residual module. Next, a texture loss strategy is proposed to align multi-scale features across domains by minimizing the Gram matrix of signal features. Finally, a nuclear norm regularization method is proposed to perform low-rank approximation on the signal matrix, facilitating the extraction of more robust feature data and mitigating the risk of overfitting. The experimental results demonstrate that the proposed method achieved an average accuracy of 98.58% on the University of Ottawa bearing fault dataset and 98.11% on the Jiangnan University (JNU) bearing dataset, surpassing eight other algorithms in bearing fault diagnosis.

Metaphorical meaning dynamics: Identifying patterns in the metaphorical evolution of English words using mathematical modeling techniques

Abstract Conceptual metaphor theory has been criticized due to its emphasis on concepts instead of words and its top-down direction of analysis. In response to these criticisms, this paper employs a new strategy, utilizing established mathematical modeling methods to allow a systematic, quantitative analysis of the entire dataset produced by the Mapping Metaphor project at the University of Glasgow. This dataset consists of 9609 words performing 18916 metaphorical mappings between 414 domains. The data is represented as a network consisting of 414 nodes, the domains, connected by shared words. Words are represented by groups of directed mappings between all domains in which they occur. This is made possible by the use of a directed hypergraph representation, a tool commonly used in discrete mathematics and various areas of computer science but not previously applied to the metaphorical meanings of words. Examining the dataset as a whole, rather than focusing on individual words or metaphors, allows global patterns of behavior to emerge from the data without pre-filtering or selection by the authors. Outcomes of the analysis relating to the distributions of source and target domains within the network, the growth mechanisms at work in the spread of metaphorical meanings and how these relate to existing concepts in CMT are discussed.

CycleGAN-based Data Augmentation for Enhanced Remaining Useful Life Prediction Under Unsupervised Domain Adaptation

Predictive maintenance is crucial for enhancing operational efficiency and reducing costs in Prognostics and Health Management (PHM). One of the key tasks in predictive maintenance is the estimation of Remaining Useful Life (RUL) of machinery. In practice, the data for different machines is not always accessible in sufficient quantity or quality, therefore the machine learning models trained on machines in one domain often perform poorly when applied to other domains due to covariate shifts. As a solution, Domain Adaptation (DA) aims to tackle domain shifts by extracting domain-invariant features. However, traditional methods often fail to adequately address the complexity and variability of real-world data. We propose to address this challenge, using a Wasserstein CycleGAN with Gradient Penalty (W-CycleGAN-GP) to learn mappings between domains and generate augmented data in the target domain from data in the source domain. We use our approach to generate realistic augmented data that bridge domain gap coupled with recent work on adversarial-based and correlation alignment-based DA models to improve the performance of RUL prediction models in target domains without having access to labeled data. The experimental results on the C-MAPSS dataset demonstrate a significant improvement in the RUL prediction score and accuracy within the target domain.

SAFENet: Semantic-Aware Feature Enhancement Network for unsupervised cross-domain road scene segmentation

Unsupervised cross-domain road scene segmentation has attracted substantial interest because of its capability to perform segmentation on new and unlabeled domains, thereby reducing the dependence on expensive manual annotations. This is achieved by leveraging networks trained on labeled source domains to classify images on unlabeled target domains. Conventional techniques usually use adversarial networks to align inputs from the source and the target in either of their domains. However, these approaches often fall short in effectively integrating information from both domains due to Alignment in each space usually leads to bias problems during feature learning. To overcome these limitations and enhance cross-domain interaction while mitigating overfitting to the source domain, we introduce a novel framework called Semantic-Aware Feature Enhancement Network (SAFENet) for Unsupervised Cross-domain Road Scene Segmentation. SAFENet incorporates the Semantic-Aware Enhancement (SAE) module to amplify the importance of class information in segmentation tasks and uses the semantic space as a new domain to guide the alignment of the source and target domains. Additionally, we integrate Adaptive Instance Normalization with Momentum (AdaIN-M) techniques, which convert the source domain image style to the target domain image style, thereby reducing the adverse effects of source domain overfitting on target domain segmentation performance. Moreover, SAFENet employs a Knowledge Transfer (KT) module to optimize network architecture, enhancing computational efficiency during testing while maintaining the robust inference capabilities developed during training. To further improve the segmentation performance, we further employ Curriculum Learning, a self-training mechanism that uses pseudo-labels derived from the target domain to iteratively refine the network. Comprehensive experiments on three well-known datasets, “Synthia→Cityscapes” and “GTA5→Cityscapes”, demonstrate the superior performance of our method. In-depth examinations and ablation studies verify the efficacy of each module within the proposed method.

Domain Adaptive Urban Garbage Detection Based on Attention and Confidence Fusion

To overcome the challenges posed by limited garbage datasets and the laborious nature of data labeling in urban garbage object detection, we propose an innovative unsupervised domain adaptation approach to detecting garbage objects in urban aerial images. The proposed method leverages a detector, initially trained on source domain images, to generate pseudo-labels for target domain images. By employing an attention and confidence fusion strategy, images from both source and target domains can be seamlessly integrated, thereby enabling the detector to incrementally adapt to target domain scenarios while preserving its detection efficacy in the source domain. This approach mitigates the performance degradation caused by domain discrepancies, significantly enhancing the model’s adaptability. The proposed method was validated on a self-constructed urban garbage dataset. Experimental results demonstrate its superior performance over baseline models. Furthermore, we extended the proposed mixing method to other typical scenarios and conducted comprehensive experiments on four well-known public datasets: Cityscapes, KITTI, Sim10k, and Foggy Cityscapes. The result shows that the proposed method exhibits remarkable effectiveness and adaptability across diverse datasets.

A hydraulic motor fault diagnosis method based on weighted multi-channel information fusion

Abstract In response to the limitations of the existing single-sensor hydraulic motor fault diagnosis model, which includes significant fluctuations in fault identification accuracy, low data utilization, poor reliability, and insufficient generalization ability under variable working conditions, a novel hydraulic motor fault diagnosis method based on weighted fusion of multi-channel data and migration learning is proposed. Firstly, in order to fully extract the information content in the multi-channel data set of the hydraulic motor, a multi channel-fusion method based on information entropy weighting is proposed. The information entropy method is employed to calculate the fusion weight of each channel of data, and the sampled data of each channel is weighted and fused. Subsequently, the fusion data from the source domain is employed to pre-train the depth transmission model, with the model parameters obtained from this pre-training serving as the initialization parameters for the target domain model. Subsequently, the parameters of the target domain model's feature extractor are fixed, and the parameters of its classifier are fine-tuned using the target domain's fusion data. The distance between the source and target domains is reduced by incorporating an attention mechanism and constructing a loss function. The migration from the source domain to the target domain is achieved, which enables the classifier to adapt to the novel target sample recognition task. Ultimately, the experimental results of hydraulic motor migration diagnosis under variable operating conditions demonstrate that the proposed method is an efficacious approach for hydraulic motor fault diagnosis. In comparison to conventional models such as
CNN and GRU, the proposed method exhibits superior migration diagnosis accuracy and enhanced generalization and robustness under variable operating conditions.

Optimizing Models and Data Denoising Algorithms for Power Load Forecasting

To handle the data imbalance and inaccurate prediction in power load forecasting, an integrated data denoising power load forecasting method is designed. This method divides data into administrative regions, industries, and load characteristics using a four-step method, extracts periodic features using Fourier transform, and uses Kmeans++ for clustering processing. On this basis, a Transformer model based on an adversarial adaptive mechanism is designed, which aligns the data distribution of the source domain and target domain through a domain discriminator and feature extractor, thereby reducing the impact of domain offset on prediction accuracy. The mean square error of the Fourier transform clustering method used in this study was 0.154, which was lower than other methods and had a better data denoising effect. In load forecasting, the mean square errors of the model in predicting long-term load, short-term load, and real-time load were 0.026, 0.107, and 0.107, respectively, all lower than the values of other comparative models. Therefore, the load forecasting model designed for research has accuracy and stability, and it can provide a foundation for the precise control of urban power systems. The contributions of this study include improving the accuracy and stability of the load forecasting model, which provides the basis for the precise control of urban power systems. The model tracks periodicity, short-term load stochasticity, and high-frequency fluctuations in long-term loads well, and possesses high accuracy in short-term, long-term, and real-time load forecasting.

A Cross-Attention-Based Class Alignment Network for Cross-Subject EEG Classification in a Heterogeneous Space.

Domain adaptation (DA) techniques have emerged as a pivotal strategy in addressing the challenges of cross-subject classification. However, traditional DA methods are inherently limited by the assumption of a homogeneous space, requiring that the source and target domains share identical feature dimensions and label sets, which is often impractical in real-world applications. Therefore, effectively addressing the challenge of EEG classification under heterogeneous spaces has emerged as a crucial research topic. We present a comprehensive framework that addresses the challenges of heterogeneous spaces by implementing a cross-domain class alignment strategy. We innovatively construct a cross-encoder to effectively capture the intricate dependencies between data across domains. We also introduce a tailored class discriminator accompanied by a corresponding loss function. By optimizing the loss function, we facilitate the aggregation of features with corresponding classes between the source and target domains, while ensuring that features from non-corresponding classes are dispersed. Extensive experiments were conducted on two publicly available EEG datasets. Compared to advanced methods that combine label alignment with transfer learning, our method demonstrated superior performance across five heterogeneous space scenarios. Notably, in four heterogeneous label space scenarios, our method outperformed the advanced methods by an average of 7.8%. Moreover, in complex scenarios involving both heterogeneous label spaces and heterogeneous feature spaces, our method outperformed the state-of-the-art methods by an average of 4.1%. This paper presents an efficient model for cross-subject EEG classification under heterogeneous spaces, which significantly addresses the challenges of EEG classification within heterogeneous spaces, thereby opening up new perspectives and avenues for research in related fields.

Pseudospin-polarized slow light waveguides with large delay-bandwidth product

Delay-bandwidth product (DBP) is a key metric in slow light waveguides, requiring a balance between a large group index and broad bandwidth—two parameters that often involve a trade-off. Here, we propose and demonstrate a slow light waveguide with large DBP using a pseudospin-polarized transverse electromagnetic mode. This waveguide features a folded edge configuration that supports a 200% relative bandwidth from quasistatic limit (zero frequency) and an arbitrarily large group index. Owing to the pseudospin-polarized design, the dense folding would not introduce backscattering and the associated group velocity dispersion (GVD). The resulting gapless linear dispersion and pulse transmission behavior in folded edge waveguide are observed in microwave experiments. Our scheme provides a way to overcome the trade-off between group index and working bandwidth in slow light waveguide, which has potential applications in broadband optical buffering, light-matter interaction enhancement, terahertz radiation source and time domain processing.

Time Prediction in Ship Block Manufacturing Based on Transfer Learning

Accurate time prediction is critical to the success of ship block manufacturing. However, the emergence of new ship types with limited historical data poses challenges to existing prediction methods. In response, this paper proposes a novel framework for ship block manufacturing time prediction, integrating clustering and the transfer learning algorithm. Firstly, the concept of distributed centroids was innovatively adopted to achieve the clustering of categorical attribute features. Secondly, abundant historical data from other types of blocks (source domain) were incorporated into the neural network model to explore the effects of block features on manufacturing time, and the model was further transferred to blocks with limited data (target domain). Leveraging the similarities and differences between source and target domain blocks, actions involving freezing and fine-tuning parameters were adopted for the predictive model development. Despite a small sample size of only 80, our proposed block time prediction method achieves an impressive mean absolute percentage error (MAPE) of 8.62%. In contrast, the MAPE for the predictive model without a transfer learning algorithm is notably higher at 14.97%. Experimental validation demonstrates the superior performance of our approach compared to alternative methods in scenarios with small sample datasets. This research addresses a critical gap in ship block manufacturing time prediction.