Cross-domain Transfer Research Articles

An Improved Transfer Learning Method for Rotor Unbalance Position Identification from Simulated Data to Experimental Data

In the study of dynamic balancing for flexible rotors operating at high speeds, determining the unbalanced position of the rotor has consistently posed significant challenges. Accurate identification of the unbalanced position enables low-speed dynamic balancing to serve as a viable alternative to high-speed methods, ultimately reducing costs and enhancing operational efficiency. Although deep learning techniques utilizing limited labeled data have shown promising results in identifying unbalanced positions, the challenge of gathering a sufficient amount of labeled data for effectively training diagnostic models remains substantial. To address this issue, we propose a Pre-Adaptive Transfer Learning (PATL) approach that employs sample reconstruction through frequency domain correlation analysis. This technique facilitates cross-domain deep transfer recognition of rotor unbalanced positions by transferring insights from simulated dynamic model data to experimental datasets. Compared to existing methodologies, the proposed approach demonstrates significant improvements in both the accuracy and generalization of unbalanced position identification. The novelty of this research lies in the introduction of pre-adaptive transfer learning, which effectively minimizes the disparity between experimental and simulation data, thereby enhancing the model's recognition capabilities. Experimental results indicate that the proposed method achieves effective balancing outcomes across various operating conditions.

Speech Emotion Recognition Using Transfer Learning: Integration of Advanced Speaker Embeddings and Image Recognition Models

Automatic Speech Emotion Recognition (SER) plays a vital role in making human–computer interactions more natural and effective. A significant challenge in SER development is the limited availability of diverse emotional speech datasets, which hinders the application of advanced deep learning models. Transfer learning is a machine learning technique that helps address this issue by utilizing knowledge from pre-trained models to improve performance on a new task in a target domain, even with limited data. This study investigates the use of transfer learning from various pre-trained networks, including speaker embedding models such as d-vector, x-vector, and r-vector, and image classification models like AlexNet, GoogLeNet, SqueezeNet, ResNet-18, and ResNet-50. We also propose enhanced versions of the x-vector and r-vector models incorporating Multi-Head Attention Pooling and Angular Margin Softmax, alongside other architectural improvements. Additionally, reverberation from the Room Impulse Response datasets was added to the speech utterances to diversify and augment the available data. Notably, the enhanced r-vector model achieved classification accuracies of 74.05% Unweighted Accuracy (UA) and 73.68% Weighted Accuracy (WA) on the IEMOCAP dataset, and 80.25% UA and 79.81% WA on the CREMA-D dataset, outperforming the existing state-of-the-art methods. This study shows that using cross-domain transfer learning is beneficial for low-resource emotion recognition. The enhanced models developed in other domains (for non-emotional tasks) can further improve the accuracy of SER.

Cross-domain transfer fault diagnosis by class-imbalanced deep subdomain adaptive network

In variable working conditions and class imbalances, fault diagnosis in gearbox systems becomes difficult due to the difficulty in learning the classification boundaries of the minority class. Moreover, the diversity in fault mode distributions under various working conditions poses significant challenges for domain adaptation. To this end, this work proposed a Class-imbalanced Deep Subdomain Adaptive Network (CIDSAN) for complex cross-domain fault diagnosis scenarios involving feature and label shifts. We design a convolutional neural network embedded with SimAM (SimAM-CNN) to extract global feature information from time-domain vibration signals. Subsequently, a novel cost-sensitive classifier is presented for class re-weighting, along with a Joint Supervised Classifier that refines intra-class and inter-class distances by re-weighting class weights in the latent space using cost-sensitive classifiers while leveraging LDAM regularization to adjust classification boundaries. Diagnostic case studies on two datasets under various working conditions validate the effectiveness and superiority of the proposed approach. The code https://github.com/Zjy0121/CIDSAN.

Anti-forgetting source-free domain adaptation method for machine fault diagnosis

Unsupervised domain adaptation methods have made significant progress in the field of machine fault diagnosis. However, these methods generally assume the accessibility of source domain data during the cross-domain transfer phase. In practice, this assumption is often impractical due to data privacy requirements and the burden of data transmission and storage. Additionally, a key challenge lies in preventing the forgetting of source domain knowledge while performing cross-domain diagnosis in a source-free scenario. To address these issues, this paper proposes an anti-forgetting source-free domain adaptation method for machine fault diagnosis. Specifically, a prototype-based pseudo-label generation strategy, combined with a nearest-neighbor constraint, is employed to deeply explore diagnosis information in the unlabeled target domain data. Then, a fast nuclear-norm maximization constraint is introduced to reduce the density of target domain samples near the classification boundary, thereby decreasing the probability of misdiagnosis. Furthermore, a weighted Fisher regularization is designed to retain the diagnosis information of healthy states inherent in the source domain, thus mitigating information forgetting. Finally, comprehensive experiments are conducted to validate the superiority of our method in source-free cross-domain diagnosis from multiple perspectives, while also demonstrating its anti-forgetting properties.

Θ-Net: A Deep Neural Network Architecture for the Resolution Enhancement of Phase-Modulated Optical Micrographs In Silico.

Optical microscopy is widely regarded to be an indispensable tool in healthcare and manufacturing quality control processes, although its inability to resolve structures separated by a lateral distance under ~200 nm has culminated in the emergence of a new field named fluorescence nanoscopy, while this too is prone to several caveats (namely phototoxicity, interference caused by exogenous probes and cost). In this regard, we present a triplet string of concatenated O-Net ('bead') architectures (termed 'Θ-Net' in the present study) as a cost-efficient and non-invasive approach to enhancing the resolution of non-fluorescent phase-modulated optical microscopical images in silico. The quality of the afore-mentioned enhanced resolution (ER) images was compared with that obtained via other popular frameworks (such as ANNA-PALM, BSRGAN and 3D RCAN), with the Θ-Net-generated ER images depicting an increased level of detail (unlike previous DNNs). In addition, the use of cross-domain (transfer) learning to enhance the capabilities of models trained on differential interference contrast (DIC) datasets [where phasic variations are not as prominently manifested as amplitude/intensity differences in the individual pixels unlike phase-contrast microscopy (PCM)] has resulted in the Θ-Net-generated images closely approximating that of the expected (ground truth) images for both the DIC and PCM datasets. This thus demonstrates the viability of our current Θ-Net architecture in attaining highly resolved images under poor signal-to-noise ratios while eliminating the need for a priori PSF and OTF information, thereby potentially impacting several engineering fronts (particularly biomedical imaging and sensing, precision engineering and optical metrology).

SD-MDN-TM: A traceback and mitigation integrated mechanism against DDoS attacks with IP spoofing

Traceback has been very attractive against DDoS attacks with IP spoofing instead of traditional mitigation methods because attacks require removal near attackers, resulting in affecting legitimate traffic as little as possible. There have been some approaches dedicated to achieving effective traceback. However, existing approaches often modify protocols to apply to multi-domain scenarios, and the implemented mitigation usually lags behind traceback. Therefore, this paper proposes the Software-Defined Multi-Domain Network Tracer and Mitigator (SD-MDN-TM) to traceback and mitigate DDoS attacks with IP spoofing in multi-domain SDN scenarios. We apply systematic sampling and flow feature extraction based on the Count-Min Sketch data structure for the lightweight statistics collection of massive DDoS attack traffic. We also design the TracebackTree data structure to construct the traceback paths of attackers of distributed attack sources. The Border Switch Trigger Mechanism is proposed to overcome the drawbacks of the commonly-used packet marking in cross-domain traceback information transfer, achieving no modification of existing network protocols and independent traceback among multiple domains. Mitigation is integrated with traceback for faster removal of attacks from the network. The proposed scheme can traceback DDoS attack sources both inside and outside domains accurately and effectively by constructing traceback path. It can be implemented without modifying the existing protocols, therefore achieving direct application to the existing network architecture. Furthermore, the traceback of attack sources outside domains can maintain independence in multi-domain scenarios. Mitigation integrated with traceback can achieve less impact on legitimate traffic and faster removal of attacks from the network.

Multiscale Conditional Adversarial Networks based domain-adaptive method for rotating machinery fault diagnosis under variable working conditions

Deep learning has been increasingly used in health management and maintenance decision-making for rotating machinery. However, some challenges must be addressed to make this technology more effective. For example, the collected data is assumed to follow the same feature distribution, and sufficient labeled training data are available. Unfortunately, domain shifts occur inevitably in real-world scenarios due to different working conditions, and acquiring sufficient labeled samples is time-consuming and expensive in complex environments. This study proposes a novel domain adaptive framework called deep Multiscale Conditional Adversarial Networks (MCAN) for machinery fault diagnosis to address these shortcomings. The MCAN model comprises two key components. Constructed by a novel multiscale module with an attention mechanism, the first component is a shared feature generator that captures rich features at different internal perceptual scales, and the attention mechanism determines the weights assigned to each scale, enhancing the model’s dynamic adjustment and self-adaptation capabilities. The second component consists of two domain classifiers based on Bidirectional Long Short-Term Memory (BiLSTM) leveraging spatiotemporal features at various levels to achieve domain adaptation in the output space. The deep domain classifier also captures the cross-covariance dependencies between feature representations and classifier predictions, thereby improving the predictions’ discriminability. The proposed method has been evaluated using two publicly available fault diagnosis datasets and one condition monitoring experiment. The results of cross-domain transfer tasks demonstrated that the proposed method outperformed several state-of-the-art methods in terms of transferability and stability. This result is a significant step forward in deep learning for health management and maintenance decision-making for rotating machinery, and it has the potential to revolutionize its future application.

In-domain versus out-of-domain transfer learning for document layout analysis

AbstractData availability is a big concern in the field of document analysis, especially when working on tasks that require a high degree of precision when it comes to the definition of the ground truths on which to train deep learning models. A notable example is represented by the task of document layout analysis in handwritten documents, which requires pixel-precise segmentation maps to highlight the different layout components of each document page. These segmentation maps are typically very time-consuming and require a high degree of domain knowledge to be defined, as they are intrinsically characterized by the content of the text. For this reason in the present work, we explore the effects of different initialization strategies for deep learning models employed for this type of task by relying on both in-domain and cross-domain datasets for their pre-training. To test the employed models we use two publicly available datasets with heterogeneous characteristics both regarding their structure as well as the languages of the contained documents. We show how a combination of cross-domain and in-domain transfer learning approaches leads to the best overall performance of the models, as well as speeding up their convergence process.

Domain-Adaptive Framework for ACL Injury Diagnosis Utilizing Contrastive Learning Techniques

In sports medicine, anterior cruciate ligament (ACL) injuries are common and have a major effect on knee joint stability. For the sake of prognosis evaluation and treatment planning, an accurate clinical auxiliary diagnosis of ACL injuries is essential. Although existing deep learning techniques for ACL diagnosis work well on single datasets, research on cross-domain data transfer is still lacking. Building strong domain-adaptive diagnostic models requires addressing domain disparities in ACL magnetic resonance imaging (MRI) from different hospitals and making efficient use of multiple ACL datasets. This work uses the publicly available KneeMRI dataset from Croatian hospitals coupled with the publicly available MRnet dataset from Stanford University to investigate domain adaptation and transfer learning models. First, an optimized model efficiently screens training data in the source domain to find unusually misclassified occurrences. Subsequently, before being integrated into the contrastive learning module, a target domain feature extraction module processes features of target domain samples to improve extraction efficiency. By using contrastive learning between positive and negative sample pairs from source and target domains, this method makes domain adaptation easier and improves the efficacy of ACL auxiliary diagnostic models. Utilizing a spatially augmented ResNet-18 backbone network, the suggested approach produces notable enhancements in experimentation. To be more precise, the AUC for transfer learning improved by 3.5% from MRnet to KneeMRI and by 2.5% from KneeMRI to MRnet (from 0.845 to 0.870). This method shows how domain transfer can be used to improve diagnostic accuracy on a variety of datasets and effectively progresses the training of a strong ACL auxiliary diagnostic model.

A Review of Deep Learning Based Video Action Recognition Techniques

Video action recognition is an important research direction in the field of computer vision and pattern recognition, with extensive applications in intelligent video surveillance, human-computer interaction, and sports analysis. The development of data storage and computing hardware over the past decade has driven a shift from traditional feature extraction and machine learning algorithms to deep learning-based approaches. This paper reviews the current state of development, problems, and future research directions of video action recognition techniques. Traditional methods are gradually being replaced by deep learning methods such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long-short-term memory networks (LSTMs). These methods automatically extract features and handle time-dependency, significantly improving the accuracy and robustness of action recognition. In particular, models based on the attention mechanism further enhance action recognition performance by dynamically adjusting the focus of attention, a current hot spot in research. Despite many advances, video action recognition still faces several challenges, including high computational resource requirements, complex model training, dataset bias issues, and variations in real-world application scenarios such as viewpoint changes, lighting changes, and occlusion. Future research can explore multi-modal fusion, lightweight models, self-supervised learning, and cross-domain transfer learning to improve the accuracy, robustness, and generalization of action recognition. The review provided aims to offer researchers a comprehensive perspective on the current state of development and future research directions of video action recognition technology.

UDANet: An unsupervised domain adaptive vehicle density estimation network based on joint adversarial learning

Unsupervised domain adaptive vehicle density estimation aims to transfer the knowledge learned from the labeled source domain to the unlabeled target domain, which has received extensive attention due to its practicality and effectiveness. However, the existing methods often rely on a large amount of expensive labeled data, and ignore the large differences between different data domains, making the network trained in one scene difficult to apply to the target scene. To solve these problems, this paper proposes an unsupervised domain adaptive vehicle density estimation network based on joint adversarial learning (UDANet), which effectively extends the model to unlabeled target domain data by adding two domain adaptive components to the pre-trained backbone. Specifically, a multi-level feature discriminator is designed to align vehicle features from the image level and refine features from the pixel level by joint adversarial learning, thus achieving cross-domain transfer of features from the source domain to the target domain. In addition, to address the shared convolutional structure that incorrectly highlights irrelevant information, a feature correction module is designed to improve the adaptability of the network to target domain data by re-modeling the source and target data according to channel independence. Several well-known backbones are used to prove the superiority of the backbone and the mobility of the two domain adaptive components. The domain adaptation experimental results on four vehicle datasets show that UDANet achieves high estimation accuracy compared to current state-of-the-art unsupervised methods, and is suitable for the task of vehicle density estimation in complex scenes.

Fault Diagnosis Method of Special Vehicle Bearing Based on Multi-Scale Feature Fusion and Transfer Adversarial Learning.

To address the issues of inadequate feature extraction for rolling bearings, inaccurate fault diagnosis, and overfitting in complex operating conditions, this paper proposes a rolling bearing diagnosis method based on multi-scale feature fusion and transfer adversarial learning. Firstly, a multi-scale convolutional fusion layer is designed to effectively extract fault features from the original vibration signals at multiple time scales. Through a feature encoding fusion module based on the multi-head attention mechanism, feature fusion extraction is performed, which can model long-distance contextual information and significantly improve diagnostic accuracy and anti-noise capability. Secondly, based on the domain adaptation (DA) cross-domain feature adversarial learning strategy of transfer learning methods, the extraction of optimal domain-invariant features is achieved by reducing the gap in data distribution between the target domain and the source domain, addressing the call for research on fault diagnosis across operating conditions, equipment, and virtual-real migrations. Finally, experiments were conducted to verify and optimize the effectiveness of the feature extraction and fusion network. A public bearing dataset was used as the source domain data, and special vehicle bearing data were selected as the target domain data for comparative experiments on the effect of network transfer learning. The experimental results demonstrate that the proposed method exhibits an exceptional performance in cross-domain and variable load environments. In multiple bearing cross-domain transfer learning tasks, the method achieves an average migration fault diagnosis accuracy rate of up to 98.65%. When compared with existing methods, the proposed method significantly enhances the ability of data feature extraction, thereby achieving a more robust diagnostic performance.

Embracing Large Natural Data: Enhancing Medical Image Analysis via Cross-Domain Fine-Tuning.

With the rapid advancements of Big Data and computer vision, many large-scale natural visual datasets are proposed, such as ImageNet-21K, LAION-400M, and LAION-2B. These large-scale datasets significantly improve the robustness and accuracy of models in the natural vision domain. However, the field of medical images continues to face limitations due to relatively small-scale datasets. In this article, we propose a novel method to enhance medical image analysis across domains by leveraging pre-trained models on large natural datasets. Specifically, a Cross-Domain Transfer Module (CDTM) is proposed to transfer natural vision domain features to the medical image domain, facilitating efficient fine-tuning of models pre-trained on large datasets. In addition, we design a Staged Fine-Tuning (SFT) strategy in conjunction with CDTM to further improve the model performance. Experimental results demonstrate that our method achieves state-of-the-art performance on multiple medical image datasets through efficient fine-tuning of models pre-trained on large natural datasets.

A Comment Aspect-Level User Preference Transfer Model for Cross-Domain Recommendations

Traditional cross-domain recommendation models make it difficult to deeply mine users' aspect-level preferences from comment information due to existing problems such as polysemy of comment text, sparse comment data, and user cold start. A Cross-Domain Recommender (CDR) model that integrates comment knowledge enhancement and aspect-level user preference transfer (C-KE-AUT) was proposed to address the above issues. Firstly, an aspect-level user preference extraction model was constructed by combining the RoBERTa word embedding model, high-level feature representation based on Transformer, and aspect-level attention-learning methods. Then, a user aspect-level preference cross-domain transfer model was constructed based on a two-stage generative adversarial network that can transfer the aspect-level interest preferences of users in the source domain to the target domain with sparse data. The experimental results on the Amazon 2018 comment dataset indicated that the recommendation performance of the proposed C-KE-AUT model was significantly superior to other advanced comparative models.

An information fusion-based meta transfer learning method for few-shot fault diagnosis under varying operating conditions

In recent years, meta-learning has gained increasing attention in the field of fault diagnosis due to its advantages of handling small samples and exhibiting fast adaptation across different diagnostic tasks. However, the scenario of sharply varying operating conditions and the heavy computation burden still limit the effective application of meta-learning in the field of transfer fault diagnosis. To address the above challenges, a few-shot meta transfer diagnosis method is proposed based on information fusion-based model agnostic meta-learning (IFMAML). Firstly, the information enhancement method based on sparse principal component analysis is introduced to enhance the domain invariant features and reduce data redundancy. Subsequently, the information fusion strategy of multiple sensor data is proposed to form the red, green, and blue (RGB) channel information of images, which can enrich the diversity of domain invariant features and mine the spatial information of multiple sensors. Then, the IFMAML, with its enhanced potential for diagnostic performance and computational efficiency, is developed to address the challenging few-shot cross-domain transfer diagnosis under varying operating conditions. Finally, two case studies for gearbox fault diagnostics considering sharply varying speed conditions and unknown health conditions have been conducted to demonstrate the effectiveness and superiority of the proposed method. Experimental results have indicated that the proposed IFMAML method can achieve superior diagnostic accuracy and can be quickly adapted to new transfer diagnosis scenarios under varying operating conditions, when compared with several mainstream meta-learning methods.

Zero-shot knowledge transfer for seismic damage diagnosis through multi-channel 1D CNN integrated with autoencoder-based domain adaptation

Accurate and timely structural damage diagnosis is crucial to efficient disaster response and city renovation in post-earthquake events. The scarcity of labeled data hinders the powerful deep learning techniques from in-domain damage detection on target structures. Cross-domain transfer learning has emerged as a captivating strategy through digging knowledge from the abundant source domain to detect the damage in the target domain. However, the heterogeneity among multi-domain structures poses the challenge in seismic damage diagnosis. This study proposes a novel zero-shot knowledge transfer approach for seismic damage diagnosis through multi-channel one-dimensional convolutional neural networks (1D CNN) integrated with deep autoencoder (DAE)-based domain adaptation (DA). The framework consists of three modules, namely, data preprocessor adaptive to seismic vibration signals, DAE-based DA module, and damage diagnosis via multi-channel 1D CNN. The DA module is customized to seamlessly translate the unseen target-domain data to mimic latent representation via a DAE pretrained on the source data, thus realizing rigorous zero-shot learning. Imbalanced data distribution is also considered during the network training and testing. Two representative phases of knowledge transfer are performed to substantiate the knowledge transferability of the proposed method. The first phase involves multi-class damage quantification on two ASCE benchmark models from the simplified model to the refined one, and the second phase conducts binary damage detection on a three-story reinforced frame structure from the finite element numerical model to the laboratory-tested physical model. Both examples show that the proposed method exhibits high prediction accuracy and a lower false negative rate in achieving zero-shot knowledge transfer for cross-domain structural damage diagnosis. With a delicate network design for diverse data, the proposed knowledge transfer framework can be further extended from the present zero-shot approach to the few-shot learning paradigm, thus suggesting a feasible algorithm adaptability and promising engineering applicability.

BarlowTwins-CXR: enhancing chest X-ray abnormality localization in heterogeneous data with cross-domain self-supervised learning.

Chest X-ray imaging based abnormality localization, essential in diagnosing various diseases, faces significant clinical challenges due to complex interpretations and the growing workload of radiologists. While recent advances in deep learning offer promising solutions, there is still a critical issue of domain inconsistency in cross-domain transfer learning, which hampers the efficiency and accuracy of diagnostic processes. This study aims to address the domain inconsistency problem and improve autonomic abnormality localization performance of heterogeneous chest X-ray image analysis, particularly in detecting abnormalities, by developing a self-supervised learning strategy called "BarlwoTwins-CXR". We utilized two publicly available datasets: the NIH Chest X-ray Dataset and the VinDr-CXR. The BarlowTwins-CXR approach was conducted in a two-stage training process. Initially, self-supervised pre-training was performed using an adjusted Barlow Twins algorithm on the NIH dataset with a Resnet50 backbone pre-trained on ImageNet. This was followed by supervised fine-tuning on the VinDr-CXR dataset using Faster R-CNN with Feature Pyramid Network (FPN). The study employed mean Average Precision (mAP) at an Intersection over Union (IoU) of 50% and Area Under the Curve (AUC) for performance evaluation. Our experiments showed a significant improvement in model performance with BarlowTwins-CXR. The approach achieved a 3% increase in mAP50 accuracy compared to traditional ImageNet pre-trained models. In addition, the Ablation CAM method revealed enhanced precision in localizing chest abnormalities. The study involved 112,120 images from the NIH dataset and 18,000 images from the VinDr-CXR dataset, indicating robust training and testing samples. BarlowTwins-CXR significantly enhances the efficiency and accuracy of chest X-ray image-based abnormality localization, outperforming traditional transfer learning methods and effectively overcoming domain inconsistency in cross-domain scenarios. Our experiment results demonstrate the potential of using self-supervised learning to improve the generalizability of models in medical settings with limited amounts of heterogeneous data. This approach can be instrumental in aiding radiologists, particularly in high-workload environments, offering a promising direction for future AI-driven healthcare solutions.

Cross-Domain NER under a Divide-and-Transfer Paradigm

Cross-domain Named Entity Recognition (NER) transfers knowledge learned from a rich-resource source domain to improve the learning in a low-resource target domain. Most existing works are designed based on the sequence labeling framework, defining entity detection and type prediction as a monolithic process. However, they typically ignore the discrepant transferability of these two sub-tasks: the former locating spans corresponding to entities is largely domain-robust, whereas the latter owns distinct entity types across domains. Combining them into an entangled learning problem may contribute to the complexity of domain transfer. In this work, we propose the novel divide-and-transfer paradigm in which different sub-tasks are learned using separate functional modules for respective cross-domain transfer. To demonstrate the effectiveness of divide-and-transfer, we concretely implement two NER frameworks by applying this paradigm with different cross-domain transfer strategies. Experimental results on 10 different domain pairs show the notable superiority of our proposed frameworks. Experimental analyses indicate that significant advantages of the divide-and-transfer paradigm over prior monolithic ones originate from its better performance on low-resource data and a much greater transferability. It gives us a new insight into cross-domain NER. Our code is available on GitHub. 1

Leakage diagnosis of natural gas pipeline based on multi-source heterogeneous information fusion

Due to long-term service, natural gas pipelines are prone to corrosion, resulting in pipeline leakage failure and environmental pollution. However, it is challenging to provide an accurate leakage diagnosis for existing single-sensor detection techniques. In this paper, we propose a multi-source heterogeneous information fusion method for the complementary fusion of laser optical sensing and weak magnetic technologies. Firstly, the laser and weak magnetic signals are converted into two-dimensional images using continuous wavelet transform (CWT) and then fused in data-level. Secondly, deep reinforcement learning (DRL) combines the perception ability of deep learning and the decision-making ability of reinforcement learning. Consequently, the deep Q-network (DQN) method is proposed as a novel method for leakage diagnosis of natural gas pipelines. Then, an improved capsule network based on dense block is designed for feature enhancement. Finally, experimental results verify the effectiveness of the proposed method in recognizing the formed leakage and potential leakage. Moreover, the results demonstrate that the proposed method outperforms single-sensor-based and state-of-the-art methods in terms of diagnostic accuracy and cross-domain transfer tasks. This will provide a theoretical basis for pipeline leakage failure prevention and maintenance decision-making.

Multi-task self-supervised time-series representation learning

Time-series representation learning is crucial for extracting meaningful representations from time-series data with temporal dynamics and sparse labels. Contrastive learning, a powerful technique for exploiting the inherent data patterns, has been applied to explore the diverse consistencies in time-series data, achieved through careful selection of contrastive pairs and design of appropriate loss. Encouraging such consistency is essential for acquiring comprehensive representations of time-series data. In this paper, we propose a new framework for time-series representation learning that combines the advantages of contextual, temporal, and transformation consistencies. This framework enables the network to learn general representations suitable for different tasks and domains. First, positive and negative pairs are generated to establish a multi-task learning setup. Then, contrastive losses are formulated to explore contextual, temporal, and transformation consistencies, which are jointly optimized to learn general time-series representations. In addition, we investigate an uncertainty weighting approach to enhance the effectiveness of multi-task learning. To evaluate the performance of our framework, we conduct experiments on three downstream tasks: time-series classification, forecasting, and anomaly detection. The experimental results demonstrate the superior performance of our framework compared to benchmark models across different tasks. Furthermore, our framework shows efficiency in cross-domain transfer learning scenarios.