Cross Domain Research Articles

Fault migration diagnosis method for rolling bearing based on 2D convolutional neural network

ABSTRACT In recent years, the development of mechanical systems has gradually become larger and more complex. As one of the most critical components of mechanical systems, the health status of rolling bearings is crucial for the safe and orderly operation of the entire mechanical system. Therefore, this paper constructs a transfer diagnosis model based on two-dimensional convolutional neural networks, achieving efficient and fast cross working condition fault transfer diagnosis of rolling bearings. In summary, this article takes rolling bearings as the research object and constructs a fault diagnosis model under working condition migration by combining two-dimensional convolutional neural networks with maximum mean difference. Based on the constructed model, experiments are designed and signal data is collected for model training, validation, and testing. This article aims to achieve cross working condition transfer diagnosis of rolling bearings by combining the constructed model with real data from the test bench, providing reference and guidance for cross domain fault diagnosis of rolling bearings in practical engineering. The research results indicate that the constructed transfer diagnosis model based on two-dimensional convolutional neural network has achieved efficient and fast fault transfer diagnosis of rolling bearings across working conditions. The accuracy of the model in the frequency domain of transfer under 6 working conditions is higher than 98.15%.

Novel sparse auto-encoder framework with pseudo-labeled reinforcement for cross domain fault diagnosis with imbalanced samples

Abstract By applying diagnostic expertise from one area to another that is closely related, transfer fault diagnosis is an efficient strategy for guaranteeing the secure and dependable operation of mechanical equipment. However, the majority of rotating machinery monitoring data are gathered in industrial applications under normal operating settings, which leads to an imbalance between positive and negative samples. Consequently, performing high-precision fault diagnosis with imbalanced data and different working conditions becomes challenging due to the escalating difficulty and cost of acquiring labeled fault samples. For cross domain fault diagnosis, an enhanced deep transfer sparse auto-encoder (SAE) framework is provided. This approach leverages a SAE to delve deeper into fault features within imbalanced data and reconstruct the samples accordingly. Furthermore, the research proposes a feature domain penalty term to facilitate cross-domain training by aligning the distribution of the source and target domain data which can reduce data distribution deviation. A pseudo-labeled reinforcement training method is presented to further improve cross-domain classification accuracy with imbalanced samples. Extensive experiments were conducted on two datasets to assess the proposed method. The results were compared with other algorithms, demonstrating the effectiveness and superiority of the proposed approach.

The Framework of GeoSOT-3D Grid Modeling for Spatial Artificial Intelligence

Abstract. With the development of society, spatial artificial intelligence (spatial AI) research is gradually able to play a greater role. However, spatial AI has problems such as data alignment, poor interpretability, and cross domain learning. Therefore, this paper proposes an innovative GeoSOT-3D grid modeling framework for spatial AI research, which enhances the application capabilities of spatial AI. Grid modeling will be able to run through the upstream and downstream of spatial AI research, providing encoding calculations and spatial neighborhood embedding matrices for spatial data. This paper also uses task examples to demonstrate how to effectively organize and index spatial data using GeoSOT-3D grids and conduct spatial AI research. The use of GeoSOT-3D grids for spatial AI analysis has enormous potential and broad application prospects, which will help promote the further development and application of spatial AI.

Test time adaptation for cross-domain sleep stage classification

Domain shift is a serious problem with existing cross-domain sleep stage classification methods. However, most existing domain adaptation methods require access to a large amount of source domain data containing patient information, which may lead to infringement of patient privacy. At the same time, existing methods require collecting all information in advance when processing target data, which cannot meet the situation where test data arrives in batches or in order in actual scenarios. To this end, we propose a test time adaptation framework based on knowledge distillation for cross-domain sleep stage classification. This teacher-student network framework uses pre-trained model to learn variant features and robust representations. We evaluate our framework in the cross domain scenario composed of three datasets and validate its superiority, real time performance and privacy protection capability.

SPRout-DBN: a cross domain bearing fault diagnosis method based on spatial pyramid pooling residual network-DBN

Abstract Effectively leveraging the spatial features of time series signals to improve the accuracy of bearing fault classification in neural networks presents a significant challenge. To address this issue of different operating conditions, a novel model termed spatial pyramid pooling residual network-deep belief network (SPRout-DBN) is proposed. First and foremost, the Gramian angular difference fields (GADF) are utilized to encode original vibration signals of bearings. Secondly, two-dimensional images transformed by GADF from original signals are input to a novel designed residual network with spatial pyramid pooling to extract fixed-size temporal fusion feature vectors. Finally, a deep belief network is employed for classification and cross-domain learning, enabling the identification of fault samples under varying operating conditions. The proposed method is validated by two sets of datasets from Case Western Reserve University and Jiangnan University, achieving accuracies of 99.81% and 99.0% under identical operating conditions, and 99.41% and 98.43% under different operating conditions with 40 samples. Comparative analysis indicates that the proposed SPRout-DBN remains more robust and effective compared with other methods such as K-nearest neighbors, support vector machines, LeNet-5, ResNet-18, domain adaptation networks, and domain-adversarial neural networks in diverse operating environments.

A cross domain access control model for medical consortium based on DBSCAN and penalty function

BackgroundGraded diagnosis and treatment, referral, and expert consultations between medical institutions all require cross domain access to patient medical information to support doctors’ treatment decisions, leading to an increase in cross domain access among various medical institutions within the medical consortium. However, patient medical information is sensitive and private, and it is essential to control doctors’ cross domain access to reduce the risk of leakage. Access control is a continuous and long-term process, and it first requires verification of the legitimacy of user identities, while utilizing control policies for selection and management. After verifying user identity and access permissions, it is also necessary to monitor unauthorized operations. Therefore, the content of access control includes authentication, implementation of control policies, and security auditing. Unlike the existing focus on authentication and control strategy implementation in access control, this article focuses on the control based on access log security auditing for doctors who have obtained authorization to access medical resources. This paper designs a blockchain based doctor intelligent cross domain access log recording system, which is used to record, query and analyze the cross domain access behavior of doctors after authorization. Through DBSCAN clustering analysis of doctors’ cross domain access logs, we find the abnormal phenomenon of cross domain access, and build a penalty function to dynamically control doctors’ cross domain access process, so as to reduce the risk of Data breach. Finally, through comparative analysis and experiments, it is shown that the proposed cross domain access control model for medical consortia based on DBSCAN and penalty function has good control effect on the cross domain access behavior of doctors in various medical institutions of the medical consortia, and has certain feasibility for the cross domain access control of doctors.

Embracing imperfections: a predictive analysis of factors alleviating adult learners’ digital learning stress on Singapore’s lifelong learning journey

ABSTRACT This research paper examines the intersection of self-determination theory and its constructs of autonomy, competence and relatedness with the effects of learning support levers available to online educators. The learning support levers of social, technical and financial support are considered against their ability to impact online learning satisfaction and overall digital well-being. In surveying 246 adult learners, the research analysis uses structural equation modelling to yield results that highlight the opportunity for suitably planned social and technical support design to enhance the effectiveness of online teaching and learning. The overall findings add to understanding in the domain of digital learning effectiveness and possible strategies for improving online teaching and learning instructional design, including the surrounding environmental support variables. The paper further highlights the benefits of a cross domain approach to exploring learning effectiveness goals in a digital context. Given the increased prevalence of online education, the methodology and resultant findings of this paper are novel, reflecting the lack of research in the digital learning domain.

Semantic consistency knowledge transfer for unsupervised cross domain object detection

Semantic consistency knowledge transfer for unsupervised cross domain object detection

Kernel Extreme Learning Machine with Discriminative Transfer Feature and Instance Selection for Unsupervised Domain Adaptation

The goal of domain adaptation (DA) is to develop a robust decision model on the source domain effectively generalize to the target domain data. State-of-the-art domain adaptation methods typically focus on finding an optimal inter-domain invariant feature representation or helpful instances from the source domain. In this paper, we propose a kernel extreme learning machine with discriminative transfer features and instance selection (KELM-DTF-IS) for unsupervised domain adaptation tasks, which consists of two steps: discriminative transfer feature extraction and classification with instance selection. At the feature extraction stage, we extend cross domain mean approximation(CDMA) by incorporating a penalty term and develop discriminative cross domain mean approximation (d-CDMA) to optimize the category separability between instances. Subsequently, d-CDMA is integrated into kernel ELM-AutoEncoder(KELM-AE) for extracting inter-domain invariant features. During the classification process, our approach uses CDMA metrics to compute a weights to each source instances based on their impact in reducing distribution differences between domains. Instances with a greater effect receive higher weights and vice versa. These weights are then used to distinguish and select source domain instances before incorporating them into weight KELM for proposing an adaptive classifier. Finally, we apply our approach to conduct classification experiments on publicly available domain adaptation datasets, and the results demonstrate its superiority over KELM and numerous other domain adaptation approaches.

Enhanced domain transfer deep fuzzy echo state network for rotating machinery fault diagnosis based on current signal

Although vibration-based fault diagnosis methods have achieved remarkable results in rotating machinery, they are still limited by various factors, such as environment noise and additional sensor installation. Meanwhile, due to inevitable distribution differences in practical engineering, deep transfer learning models are commonly used in fault diagnostic fields. Although deep architectures can extract representative domain-invariant features, they typically result in substantial computational burdens and training time. Therefore, to address the above problems, an enhanced domain transfer deep fuzzy echo state network (EDFESN) is proposed for rotating machinery fault diagnosis based on current signals. Firstly, current signals derived from the driving motor are directly collected without additional sensors. Secondly, an enhanced domain mapping method is raised to solve the problem of data distribution discrepancies between cross domain. Furthermore, a deep fuzzy echo state network (DFESN) integrated with fuzzy clustering is constructed, which utilizes layer-wise fuzzy-tuning learning paradigm instead of backpropagation step to reduce training time. Two datasets from gearbox and bearing both verify the effectiveness of the proposed method. Compared with other popular transfer methods, EDFESN not only achieves highest accuracy, but also has fastest training speed.

Heterogeneous cross domain coordinated control of ASV-AUV system for maritime search and rescue

This paper is concerned with a coordinated search and rescue problem of heterogeneous ocean vehicle cluster composed of autonomous surface vehicles (ASVs) and autonomous underwater vehicles (AUVs) subject to model uncertainties and ocean disturbances. Firstly, a three dimensions (3D) cross domain kinematic controller with auto-stop function at the rescue points is designed for the coordinated ASV-AUV system by using a line-of-sight guidance law. Secondly, an event-triggered based communication mechanism is constructed to ensure that the ASV-AUV system can broadcast information at its trigger moments except to the auto-stop points. Finally, an adaptive motion control law based on a low-frequency learning fuzzy predictor is designed, which is able to filter out the high-frequency components of uncertainties and disturbances. The stability of the closed-loop system is proven by employing input-to-state stability and cascade stability analysis. Simulation results and numerical analysis show the effectiveness of the proposed 3D heterogeneous cross domain coordinated path following controller with auto-stop function for marine search and rescue.

Prediction and practical application of bauxite mineralization in Wuzhengdao area, Guizhou, China.

Wu-Zheng-Dao District in China is the world's most famous mining areas. It hosts several world-class deposits, such as Xinming, Datang and Luolong bauxite deposits. Although this area still has significant potential for the discovery of new deposits, mineral prediction has become increasingly diffcult as the number of shallow deposits diminishes. Therefore, it is necessary to explore new and effective metallogenic prediction methods.Weights of evidence and machine-learning algorithms were used for mineral prospecting in this study. This study used a confusion matrix, receiver operating characteristic (ROC) curve,and prediction efficiency curve to evaluate the prediction results of each machine algorithm. The results showed that 95.9% of the deposits were located in high and distant scenic areas, accounting for 10% of the total area.The prospectivity map of the Wu-Zheng-Dao district shows that the high prospective areas are generally confined to the claystone and carbonatite rocks of the Eastern region, in particular, of the clay layers, and several areas of high prospectivity also occur in the Southern Cross Domain. According to the predicted results, after on-site exploration, design, and construction, Yanfengqian bauxite deposit was discovered, with an average thickness of 1.82 meters; The average content of Al2O3 is 61.24%; The resource amount is 28.9503 million tons.

A multi-domain adversarial transfer network for cross domain fault diagnosis under imbalanced data

In the intelligent fault diagnosis of rolling bearings, transfer learning methods extend the applicability of models to diverse working scenarios. However, real-world scenarios often suffer from data imbalance, which reduces diagnostic accuracy. To address this issue, this paper proposes a multi-domain adversarial transfer (MDAT) framework to enhance cross-domain fault diagnosis accuracy for rolling bearings under imbalanced data conditions. First, an enhanced information generation method is introduced to produce realistic and useable synthetic data to mitigate data imbalance. Subsequently, an adversarial multi-domain adaptation module is designed to learn invariant features across multiple domains. Finally, a domain reweighting method is proposed to improve domain alignment and enhance domain confusion. The effectiveness of the proposed method was validated through two case studies on rolling bearing fault diagnosis. The results demonstrated that MDAT achieved cross-domain diagnosis accuracies of 89.2% and 99.0% under imbalanced data conditions, confirming the effectiveness and superiority of the MDAT framework.

Aligning the domains in cross domain model inversion attack

Model Inversion Attack reconstructs confidential training dataset from a target deep learning model. Most of the existing methods assume the adversary has an auxiliary dataset that has similar distribution with the private dataset. However, this assumption does not always hold in real-world scenarios. Since the private dataset is unknown, the domain divergence between the auxiliary dataset and the private dataset is inevitable. In this paper, we use Cross Domain Model Inversion Attack to represent the distribution divergence scenario in MIA. With the distribution divergence between the private images and auxiliary images, the distribution between the feature vectors of the private images and those of the auxiliary images is also different. Moreover, the outputted prediction vectors of the auxiliary images are also misclassified. The inversion attack is thus hard to be performed. We perform both the feature vector inversion task and prediction vector inversion task in this cross domain setting. For feature vector inversion, Domain Alignment MIA (DA-MIA) is proposed. While performing the reconstruction task, DA-MIA aligns the feature vectors of auxiliary images with the feature vectors of private images in an adversarial manner to mitigate the domain divergence between them. Thus, semantically meaningful images can be reconstructed. For prediction vector inversion, we further introduce an auxiliary classifier and propose Domain Alignment MIA with Auxiliary Classifier (DA-MIA-AC). The auxiliary classifier is pretrained by the auxiliary dataset and fine-tuned during the adversarial training stage. Thus, the misclassification problem caused by domain divergence can be solved, and the images can be reconstructed correctly. Various experiments are performed to show the advancement of our methods, the results show that DA-MIA can improve the SSIM score of the reconstructed images for up to 191%, DA-MIA-AC can increase the classification accuracy score of the reconstructed images from 9.18% to 81.32% in Cross Domain Model Inversion Attack.

AdaTreeFormer: Few shot domain adaptation for tree counting from a single high-resolution image

The process of estimating and counting tree density using only a single aerial or satellite image is a difficult task in the fields of photogrammetry and remote sensing. However, it plays a crucial role in the management of forests. The huge variety of trees in varied topography severely hinders tree counting models to perform well. The purpose of this paper is to propose a framework that is learnt from the source domain with sufficient labeled trees and is adapted to the target domain with only a limited number of labeled trees. Our method, termed as AdaTreeFormer, contains one shared encoder with a hierarchical feature extraction scheme to extract robust features from the source and target domains. It also consists of three subnets: two for extracting self-domain attention maps from source and target domains respectively and one for extracting cross-domain attention maps. For the latter, an attention-to-adapt mechanism is introduced to distill relevant information from different domains while generating tree density maps; a hierarchical cross-domain feature alignment scheme is proposed that progressively aligns the features from the source and target domains. We also adopt adversarial learning into the framework to further reduce the gap between source and target domains. Our AdaTreeFormer is evaluated on six designed domain adaptation tasks using three tree counting datasets, i.e. Jiangsu, Yosemite, and London. Experimental results show that AdaTreeFormer significantly surpasses the state of the art, e.g. in the cross domain from the Yosemite to Jiangsu dataset, it achieves a reduction of 15.9 points in terms of the absolute counting errors and an increase of 10.8% in the accuracy of the detected trees’ locations. The codes and datasets are available at https://github.com/HAAClassic/AdaTreeFormer.

A Survey of Trustworthy Representation Learning Across Domains

As AI systems have obtained significant performance to be deployed widely in our daily lives and human society, people both enjoy the benefits brought by these technologies and suffer many social issues induced by these systems. To make AI systems good enough and trustworthy, plenty of researches have been done to build guidelines for trustworthy AI systems. Machine learning is one of the most important parts of AI systems, and representation learning is the fundamental technology in machine learning. How to make representation learning trustworthy in real-world application, e.g., cross domain scenarios, is very valuable and necessary for both machine learning and AI system fields. Inspired by the concepts in trustworthy AI, we proposed the first trustworthy representation learning across domains framework, which includes four concepts, i.e., robustness, privacy, fairness, and explainability, to give a comprehensive literature review on this research direction. Specifically, we first introduce the details of the proposed trustworthy framework for representation learning across domains. Second, we provide basic notions and comprehensively summarize existing methods for the trustworthy framework from four concepts. Finally, we conclude this survey with insights and discussions on future research directions.

Nxopaxopo wa swivuriso swa Xitsonga swo vulavula hi swiharhi swa le nhoveni

The aim of the study reported in this paper is to examine Xitsonga proverbs, which are coined from wild animals, to demonstrate how they depict different lessons of life, behaviour and philosophy of life in aspects such as working together, promoting good behaviour, reprimanding bad behaviour and adjudication of cases. This study employed the qualitative approach, focusing on people’s perceptions and insights. This method displays how people think and view things and how they are depicted from animal proverbs. The selected proverbs were critically analysed using the Conceptual Theory of Metaphor, in which it is argued that the generalisations governing poetic, metaphorical expressions are not in language but in thoughts. The theory used cross-domain mapping, with the central issues being the source and target domain. According to this theory, one mental domain is conceptualised in terms of the other. That is, the target domain can be understood better in terms of the source domain. Animal proverbs are included in both primary and secondary school curricula, which is why proverbs are treated as useful and linked to different aspects of life and behaviour of certain cultures. In conclusion and findings of this study it has been found that the proverbs coined from animals, their meanings are related even though proverbs are not exactly the same, even though they do not fall into one theme like working together, lessons of life, even the way they depict the philosophy of life they are closely related. The analysed proverbs in this study are selected with the view and motive of teaching learners, educators, and everyone in the Vatsonga culture. Under the selected working together theme, it has been found that proverbs greatly influence learners and educators to work together in schools, even when they are home with everyone around them. NKOMISO Xikongomelonkulu xa dyondzo leyi i ku xopaxopa swivuriso swa Xitsonga lewi tshuriweke kusuka eka swiharhi swa le nhoveni ku kombisa hilaha swi paluxaka tidyondzo, mahanyelo ni mavonelo ya vutomi eka swiyenge swa: Ntirhisano, ku hlohlotela mahanyelo lamanene, ku tshinya mahanyelo lamobiha ni milandzu ni maahlulele ya yona. Ndzavisiso lowu wu tirhisile maendlelo ma nkoka, maendlelo ma muxaka lowu ma kongomisa eka mavonelo ya munhu xikan’we ni nsusumeto lowu endleke leswaku a vona swilo hi ndlela leyi a swi vonaka hayona. Maendlelo lama ma andlala mavonelo na mianakanyo ya vanhu hilaha swi paluxiwaka hakona hi swivuriso swa swiharhi. Swivuriso leswi swi xopaxopiwa hi tihlo ra vuxoperi hi ku tirhisa maendlelo ya thiyori ya mianakanyo ya vugego (Conceptual Metaphor Theory). Eka thiyori leyi ku vuriwa leswaku mhakankulu leyi lawulaka matirhelo ya swivulwana swa vugegovutlhokovetseri a hi ririmi, kambe i mianakanyo. Thiyori leyi yi tirhisa mpananiso (cross domain mappings), laha mhaka ya nkoka ku nga xitikoxihlovo (source domain) na xitikoxikongomisiwa (target domain). Hi ku ya hi thiyori leyi, nchumu wo karhi wu twisiseka kahle hi ku wu pimanisa na wun’wana. Hileswaku, xitikoxikongomisiwa xi twisiseka ku antswa hi ku xiya xitikoxihlovo. Swivuriso swa swiharhi swi katsiwile eka kharikhulamu ya dyondzo ya le purayimari na le sekondari. Leswi hi swona swi endlaka leswaku swivuriso swi va swi tirhisiwa leswi khomeke swinene tidyondzo ta vutomi hambi ku ri mahanyelo ya rixaka ro karhi. Eka nkatsakanyo na mikumisiso ku kumekile leswaku swivuriso leswi tshuriweke ku suka eka swiharhi, tinhlamuselo ta swivuriso swo hlaya, hambiloko ti nga fani, swi tlhela swi nga weli ehansi ka mikongomelo yo fana mitirho, tidyondzo na mikucetelo ya swona swa yelana swi tlhela swi va na vuxaka swinene. Swivuriso leswi hlawuriweke swi dyondzisa vadyondzi ni vadyondzisi mahanyelo na mavonelo ya vutomi eswikolweni na le makaya, swi tlhela swi dyondzisa mani na mani exikarhi ka rixaka ra Vatsonga. Xikombiso: Ehansi ka nkongomelo wa ntirhisano ku kumekile leswaku swivuriso swi kucetela vadyondzi ni vadyondzisi eswikolweni na le makaya ku tirhisana leswaku va ta humelela.

Learning to generalize with latent embedding optimization for few- and zero-shot cross domain fault diagnosis

Ensuring the safety and reliability of rotating machinery in modern industrial production and intelligent manufacturing is of paramount importance. While deep learning-based fault diagnosis methods offer promise, the scarcity of fault samples and the variations in distributions between training and test data due to variable working conditions make it difficult for these methods to be applied in industrial scenarios. To surmount these obstacles, we present a novel solution: learning to generalize with latent embedding optimization. Our proposed method, tailored for few-shot and zero-shot cross domain fault diagnosis, shows promise in addressing the industrial fault diagnosis problems under small samples and various working condition. The proposed method builds upon the latent embedding optimization algorithm which capitalizes on the essence of meta-learning, effectively addressing few-shot challenges. Additionally, we harness an efficient pretraining model, enhancing feature extraction and domain adaptation, effectively handling the scarcity of fault data. In tackling the cross domain issue, we introduce an innovative meta-task organization and amplify the episode training strategy within meta-learning. These enhancements empower the model to develop the ability to generalize effectively. The proposed approach is substantiated through comprehensive case studies in bearing and gearbox fault diagnosis. The results demonstrate its exceptional efficacy in both few-shot and zero-shot cross domain fault diagnosis scenarios.

Cross Domain Early Crop Mapping with Label Spaces Discrepancies using MultiCropGAN

Abstract. Mapping target crops before the harvest season for regions lacking crop-specific ground truth is critical for global food security. Utilizing multispectral remote sensing and domain adaptation methods, prior studies strive to produce precise crop maps in these regions (target domain) with the help of the crop-specific labelled remote sensing data from the source regions (source domain). However, existing approaches assume identical label spaces across those domains, a challenge often unmet in reality, necessitating a more adaptable solution. This paper introduces the Multiple Crop Mapping Generative Adversarial Neural Network (MultiCropGAN) model, comprising a generator, discriminator, and classifier. The generator transforms target domain data into the source domain, employing identity losses to retain the characteristics of the target data. The discriminator aims to distinguish them and shares the structure and weights with the classifier, which locates crops in the target domain using the generator’s output. This model’s novel capability lies in locating target crops within the target domain, overcoming differences in crop type label spaces between the target and source domains. In experiments, MultiCropGAN is benchmarked against various baseline methods. Notably, when facing differing label spaces, MultiCropGAN significantly outperforms other baseline methods. The Overall Accuracy is improved by about 10%.

A meta transfer learning method for gearbox fault diagnosis with limited data

Intelligent diagnosis of mechanical faults is an important means to guarantee the safe maintenance of equipment. Cross domain diagnosis may lack sufficient measurement data as support, and this bottleneck is particularly prominent in high-end manufacturing. This paper presents a few-shot fault diagnosis methodology based on meta transfer learning for gearbox. To be specific, firstly, the subtasks for transfer diagnosis are constructed, and then joint distribution adaptation is conducted to align the two domain distributions; secondly, through adaptive manifold regularization, the data of target working condition is further utilized to explore the potential geometric structure of the data distribution. Meta stochastic gradient descent is explored to dynamically adjust the model’s parameter based on the obtained task information to obtain better generalization performance, ultimately to achieve transfer diagnosis of gearbox faults with few samples. The effectiveness of the approach is supported by the experimental datasets of the gearbox.