Search Results (71)

The present investigation presents the field measurement and prediction of tunneling-induced surface ground settlement in Tianjin Metro Line 7, China. The cross-section of a metro tunnel exhibits circular symmetry, thereby making it suitable for tunneling with a circular shield machine. The ground surface may deform during the tunneling stage. In the early stage of tunneling, few measurement data can be collected. To obtain a better usable prediction model, two kinds of neural networks according to the model-agnostic meta-learning (MAML) scheme are presented. One kind of deep learning strategy is a combination of the Back-Propagation Neural Network (BPNN) and the MAML model, named MAML-BPNN. The other prediction model is a mixture of the MAML model and the Long Short-Term Memory (LSTM) model, named MAML-LSTM. Founded on several measurement datasets, the prediction models of the MAML-BPNN and MAML-LSTM are successfully trained. The results show the present models possess good prediction ability for tunneling-induced surface ground settlement. Based on the coefficient of determination, the prediction result using MAML-LSTM is superior to that of MAML-BPNN by 0.1. Full article

Leaf chlorophyll content (LCC), leaf area index (LAI), and above-ground biomass (AGB) are important growth parameters for characterizing potato growth and predicting yield. While deep learning has demonstrated remarkable advancements in estimating crop growth parameters, the limited availability of field data often compromises model accuracy and generalizability, impeding large-scale regional applications. This study proposes a novel deep learning model that integrates multi-task learning and few-shot learning to address the challenge of low data in growth parameter prediction. Two multi-task learning architectures, MTL-DCNN and MTL-MMOE, were designed based on deep convolutional neural networks (DCNNs) and multi-gate mixture-of-experts (MMOE) for the simultaneous estimation of LCC, LAI, and AGB from Sentinel-2 imagery. Building on this, a few-shot learning framework for growth prediction (FSLGP) was developed by integrating simulated spectral generation, model-agnostic meta-learning (MAML), and meta-transfer learning strategies, enabling accurate prediction of multiple growth parameters under limited data availability. The results demonstrated that the incorporation of calibrated simulated spectral data significantly improved the estimation accuracy of LCC, LAI, and AGB (R² = 0.62~0.73). Under scenarios with limited field measurement data, the multi-task deep learning model based on few-shot learning outperformed traditional mixed inversion methods in predicting potato growth parameters (R² = 0.69~0.73; rRMSE = 16.68%~28.13%). Among the two architectures, the MTL-MMOE model exhibited superior stability and robustness in multi-task learning. Independent spatiotemporal validation further confirmed the potential of MTL-MMOE in estimating LAI and AGB across different years and locations (R² = 0.37~0.52). These results collectively demonstrated that the proposed FSLGP framework could achieve reliable estimation of crop growth parameters using only a very limited number of in-field samples (approximately 80 samples). This study can provide a valuable technical reference for monitoring and predicting growth parameters in other crops. Full article

A fault diagnosis method based on meta-learning and an improved multi-channel convolutional neural network (MAML-MCCNN-ISENet) was proposed to solve the problems of insufficient feature extraction and low fault type identification accuracy of vibration signals at small sample sizes. The signal is first preprocessed using adaptive chirp mode decomposition (ACMD) methods. A multi-channel input structure is then employed to process the multidimensional signal information after preprocessing. The improved squeeze and excitation networks (ISENets) have been enhanced to concurrently enhance the network’s adaptive perception of the significance of each channel feature. On this basis, a meta-learning strategy is introduced, the learning process of model initialization parameters is improved, the network is optimized by a multi-task learning mechanism, and the initial parameters of the diagnosis model are adaptively adjusted, so that the model can quickly adapt to new fault diagnosis tasks on limited datasets. Then, the overfitting problem under small sample conditions is alleviated, and the accuracy and robustness of fault identification are improved. Finally, the performance of the model is verified on the experimental data of the fault diagnosis of the laboratory plunger pump and the vibration dataset of the centrifugal pump of the Saint Longoval Institute of Engineering and Technology. The results show that the diagnostic accuracy of the proposed method for various diagnostic tasks can reach more than 90% on small samples. Full article

The performance of visual SLAM in complex, real-world scenarios is often compromised by unreliable feature extraction and matching when using handcrafted features. Although deep learning-based local features excel at capturing high-level information and perform well on matching benchmarks, they struggle with generalization in continuous motion scenes, adversely affecting loop detection accuracy. Our system employs a Model-Agnostic Meta-Learning (MAML) strategy to optimize the training of keypoint extraction networks, enhancing their adaptability to diverse environments. Additionally, we introduce a coarse-to-fine feature tracking mechanism for learned keypoints. It begins with a direct method to approximate the relative pose between consecutive frames, followed by a feature matching method for refined pose estimation. To mitigate cumulative positioning errors, DK-SLAM incorporates a novel online learning module that utilizes binary features for loop closure detection. This module dynamically identifies loop nodes within a sequence, ensuring accurate and efficient localization. Experimental evaluations on publicly available datasets demonstrate that DK-SLAM outperforms leading traditional and learning-based SLAM systems, such as ORB-SLAM3 and LIFT-SLAM. DK-SLAM achieves 17.7% better translation accuracy and 24.2% better rotation accuracy than ORB-SLAM3 on KITTI and 34.2% better translation accuracy on EuRoC. These results underscore the efficacy and robustness of our DK-SLAM in varied and challenging real-world environments. Full article

Human activity recognition (HAR) using Wi-Fi-based sensing has emerged as a powerful, non-intrusive solution for monitoring human behavior in smart environments. Unlike wearable sensor systems that require user compliance, Wi-Fi channel state information (CSI) enables device-free recognition by capturing variations in signal propagation caused by human motion. This makes Wi-Fi sensing highly attractive for ambient healthcare, security, and elderly care applications. However, real-world deployment faces two major challenges: (1) significant cross-subject signal variability due to physical and behavioral differences among individuals, and (2) limited labeled data, which restricts model generalization. To address these sensor-related challenges, we propose TCN-MAML, a novel framework that integrates temporal convolutional networks (TCN) with model-agnostic meta-learning (MAML) for efficient cross-subject adaptation in data-scarce conditions. We evaluate our approach on a public Wi-Fi CSI dataset using a strict cross-subject protocol, where training and testing subjects do not overlap. The proposed TCN-MAML achieves 99.6% accuracy, demonstrating superior generalization and efficiency over baseline methods. Experimental results confirm the framework’s suitability for low-power, real-time HAR systems embedded in IoT sensor networks. Full article

In recent manufacturing environments, the use of digitally retrofitted equipment has grown substantially, yet this trend also amplifies the challenge of ensuring stable operation through effective anomaly detection. Retrofitted systems suffer from two critical obstacles: a severe scarcity of labeled data and substantial variability in operational patterns across machines and products. To overcome these issues, this study introduces a novel anomaly detection framework that integrates Model-Agnostic Meta-Learning (MAML) with a Long Short-Term Memory Autoencoder (LSTM-Autoencoder) under a multi-machine-based task formulation. By constructing meta-tasks from time-series datasets collected on multiple five-axis computer numerical control (CNC) machines, our method enables rapid adaptation to unseen machines and production scenarios with only a few training examples. The experimental results demonstrate that, even under data-scarce conditions, the proposed model achieves an accuracy of 98.02% and an F1-score of 94.74%, representing improvements of 4.2 percentage points in accuracy and 16.9 percentage points in F1-score over conventional transfer learning approaches. Furthermore, in cross-validation on entirely new machine data, our framework outperforms existing models by 18.1% in accuracy, evidencing superior generalization capability. These findings suggest that the proposed multi-machine-based Model-Agnostic Meta-Learning Long Short-Term Memory Autoencoder (MAML LSTM-Autoencoder) can significantly enhance operational efficiency and reduce maintenance costs in retrofitted manufacturing equipment, thereby improving overall productivity and paving the way for real-time industrial deployment. Full article

Video surveillance is widely used in different areas like roads, malls, education, industries, retail, parks, bus stands, and restaurants, each presenting distinct anomaly patterns that demand specialized detection strategies. Adapting anomaly detection models to new camera viewpoints or environmental variations within the same scenario remains a significant challenge. Extending these models to entirely different surveillance environments or scenarios often requires extensive retraining, which can be both resource-intensive and time-consuming. To overcome these limitations, model frameworks, i.e., the video anomaly detector model, have been proposed, leveraging the meta-learning framework for faster adaptation using swin transformer for feature extraction to new concepts. In response, the dataset named MSAD (multi-scenario anomaly detection) having 14 different scenarios from multiple camera views, is the high resolution anomaly detection dataset that includes diverse motion patterns and challenging variations such as varying lighting and weather conditions, offering a robust foundation for training advanced anomaly detection models. Experiments validate the effectiveness of the proposed framework, which integrates model-agnostic meta-learning (MAML) with a ten-shot, one-query adaptation strategy. Leveraging the swin transformer as a spatial feature extractor, the model captures rich hierarchical representations from surveillance videos. This combination enables rapid generalization to novel viewpoints within the same scenario and maintains competitive performance when deployed in entirely new environments. These results highlight the strength of MAML in few-shot learning settings and demonstrate its potential for scalable anomaly detection across diverse surveillance scenarios. Full article

To thoroughly investigate the distribution of heavy rain disaster risks in the Beijing–Tianjin–Hebei region, this paper analyzes the spatiotemporal evolution characteristics of heavy rain disaster-inducing factors. Based on disaster system theory, we constructed a heavy rain disaster risk assessment framework from four dimensions. We improved the application of model-agnostic meta-learning (MAML) in hyperparameter optimization for the random forest (RF) algorithm, thereby developing the MAML-RF heavy rain disaster risk assessment model. This model was compared with the SCV-RF model, which is based on random search and cross-validation (SCV), to determine which model had higher accuracy. Then we introduced the SHAP (Shapley additive explanations) interpretability algorithm to quantify the impact of each risk factor. The results indicate that (1) the annual characteristics of heavy rain days and rainfall amounts show a significant upward trend over the past 17 years; (2) the MAML-RF model improved the accuracy and precision of heavy rain disaster risk simulation by 4.44% and 3.71%, respectively, and reduced training time by 27.95% compared to the SCV-RF model; and (3) the SHAP interpretability algorithm results show that the top five influential factors are the number of heavy rain days, rainfall amount, slope, drainage pipe density, and impervious surface ratio. Full article

The construction industry frequently encounters safety hazards, with falls related to undetected openings being a major cause of fatalities. Identifying unstructured openings using computer vision is challenging due to their unpredictable nature and the difficulty of acquiring large labeled datasets in dynamic construction environments. Conventional deep learning methods require substantial data, limiting their applicability. Few-shot learning (FSL) offers a promising alternative by enabling models to learn from limited examples. This study investigates the effectiveness of an FSL approach, specifically model-agnostic meta-learning (MAML), enhanced with domain-specific attributes, for identifying unstructured openings with minimal labeled data. We developed and evaluated an attribute-enhanced MAML framework under various few-shot conditions (k-way, n-shot) and compared its performance against conventional supervised fi-ne-tuning. The results demonstrate that the proposed FSL model achieved high classification accuracy (over 90.5%) and recall (over 85.5%) using only five support shots per class. Notably, the FSL approach significantly outperformed supervised fine-tuning methods under the same limited data conditions, exhibiting substantially higher recall crucial for safety monitoring. These findings validate that FSL, augmented with relevant attributes, provides a data-efficient and effective solution for monitoring unpredictable hazards like unstructured openings, reducing the reliance on extensive data annotation. This research contributes valuable insights for developing adaptive and robust AI-powered safety monitoring systems in the construction domain. Full article

Fault diagnosis in large-scale systems presents significant challenges due to the complexity and high dimensionality of data, as well as the scarcity of labeled fault data, which are hard to obtain during the practical operation process. This paper proposes a novel approach, called Multi-Variable Meta-Transformer (MVMT), to tackle these challenges. In order to deal with the multi-variable time series data, we modify the Transformer model, which is the currently most popular model on feature extraction of time series. To enable the Transformer model to simultaneously receive continuous and state inputs, we introduced feature layers before the encoder to better integrate the characteristics of both continuous and state variables. Then, we adopt the modified model as the base model for meta-learning—more specifically, the Model-Agnostic Meta-Learning (MAML) strategy. The proposed method leverages the power of Transformers for handling multi-variable time series data and employs meta-learning to enable few-shot learning capabilities. The case studies conducted on the Tennessee Eastman Process database and a Power-Supply System database demonstrate the exceptional performance of fault diagnosis in few-shot scenarios, whether based on continuous-only data or a combination of continuous and state variables. Full article

In underwater signal processing, accurate time delay estimation (TDE) is of crucial importance for ensuring the reliability of data transmission. However, the complex propagation of sound waves and strong noise interference in the underwater environment make this task extremely challenging. Especially under the condition of low signal-to-noise ratio (SNR), the existing methods based on cross-correlation and deep learning struggle to meet requirements. Aiming at this core issue, this paper proposed an innovative solution. Firstly, a multi-sub-window reconstruction is performed on the frequency-sliding generalized colorboxpinkcross-correlation (FS-GCC) matrix between signals to capture the time delay characteristics from different frequency bands and conduct the enhancement and extraction of features. Then, the grayscale image corresponding to the generated FS-GCC matrix is used, and the multi-level noise features are extracted by the multi-layer convolution of denoising convolutional neural network (DnCNN), effectively suppressing the noise and improving the estimation accuracy. Finally, the model-agnostic meta-learning (MAML) framework is introduced. Through training tasks under various SNR conditions, the model is enabled to possess the ability to quickly adapt to new environments, and it can achieve the desired estimation accuracy even when the number of underwater training samples is limited. Simulation validation was conducted under the NOF and NCS underwater acoustic channels, and results demonstrate that our proposed approach exhibits lower estimation errors and greater stability compared with existing methods under the same conditions. This method enhances the practicality and robustness of the model in complex underwater environments, providing strong support for the efficient and stable operation of underwater sensor networks. Full article

With the rapid emergence of the Internet of Things (IoT) devices, there were new vectors for attacking cyber, so there was a need for approachable intrusion detection systems (IDSs) with more innovative custom tactics. The traditional IDS models tend to find difficulties in generalization in the continuously changing and heterogeneous IoT environments. This paper contributes to an adaptive intrusion detection framework using Model-Agnostic Meta-Learning (MAML) and few-shot learning paradigms to quickly adapt to new tasks with little data. The goal of this research is to improve the security of IoT by developing a strong IDS that will perform well across assorted datasets and attack environments. Finally, we apply our proposed framework to two benchmark datasets, UNSW-NB15 and NSL-KDD99, which provide different attack scenarios and network behaviors. The methodology trains a base model with MAML to allow fast adaptation on specific tasks during fine-tuning. Our approach leads to experimental results with 99.98% accuracy, 99.5% precision, 99.0% recall, and 99.4% F1 score on the UNSW-NB15 dataset. The model achieved 99.1% accuracy, 97.3% precision, 98.2% recall, and 98.5% F1 score on the NSL-KDD99 dataset. That shows that MAML can detect many cyber threats in IoT environments. Based on this study, it is concluded that meta-learning-based intrusion detection could help build resilient IoT systems. Future works will move educated meta-learning to a federated setting and deploy it in real time in response to changing threats. Full article

Nonlinear noise power (NLNP) estimation, optical signal-to-noise ratio (OSNR) monitoring, and modulation format identification (MFI) are crucial for optical performance monitoring (OPM) in future dynamic WDM optical networks. This paper proposes an OPM scheme to simultaneously implement these three tasks in both single-channel and WDM systems by combining amplitude-differential phase histograms (ADPH) with the MAML-CNN-ATT algorithm that integrates model-agnostic meta-learning (MAML), the convolutional neural network (CNN), and the attention mechanism (ATT). The meta-learning algorithms can learn optimal initial model parameters across multiple related tasks, enabling them to quickly adapt to new tasks through fine-tuning with a small amount of data. This results in superior self-adaptability and generalizability, making them more suitable for WDM scenarios than the transfer learning (TL) algorithms. The CNN-ATT algorithm can effectively extract comprehensive features, capturing both local and global dependencies, thus improving the quality of the feature representation. The ADPH sequence data combine the amplitude information and the differential phase information that indicate the signal’s overall characteristics. The results demonstrate that the MAML-CNN-ATT algorithm achieves errors of less than 1 dB in both NLNP estimation and OSNR monitoring tasks while achieving 100% accuracy in the MFI task. It exhibits excellent OPM performance not only in the single channel but also in the WDM transmission, with only a few steps of fine-tuning. The MAML-CNN-ATT algorithm provides a solution with high performance and rapid self-adaptation for the multi-task OPM in dynamic optical networks. Full article

According to recent global public health studies, chronic kidney disease (CKD) is becoming more and more recognized as a serious health risk as many people are suffering from this disease. Machine learning techniques have demonstrated high efficiency in identifying CKD, but their opaque decision-making processes limit their adoption in clinical settings. To address this, this study employs a generative adversarial network (GAN) to handle missing values in CKD datasets and utilizes few-shot learning techniques, such as prototypical networks and model-agnostic meta-learning (MAML), combined with explainable machine learning to predict CKD. Additionally, traditional machine learning models, including support vector machines (SVM), logistic regression (LR), decision trees (DT), random forests (RF), and voting ensemble learning (VEL), are applied for comparison. To unravel the “black box” nature of machine learning predictions, various techniques of explainable AI, such as SHapley Additive exPlanations (SHAP) and local interpretable model-agnostic explanations (LIME), are applied to understand the predictions made by the model, thereby contributing to the decision-making process and identifying significant parameters in the diagnosis of CKD. Model performance is evaluated using predefined metrics, and the results indicate that few-shot learning models integrated with GANs significantly outperform traditional machine learning techniques. Prototypical networks with GANs achieve the highest accuracy of 99.99%, while MAML reaches 99.92%. Furthermore, prototypical networks attain F1-score, recall, precision, and Matthews correlation coefficient (MCC) values of 99.89%, 99.9%, 99.9%, and 100%, respectively, on the raw dataset. As a result, the experimental results clearly demonstrate the effectiveness of the suggested method, offering a reliable and trustworthy model to classify CKD. This framework supports the objectives of the Medical Internet of Things (MIoT) by enhancing smart medical applications and services, enabling accurate prediction and detection of CKD, and facilitating optimal medical decision making. Full article

Recently, remote sensing image scene classification (RSISC) has gained considerable interest from the research community. Numerous approaches have been developed to tackling this issue, with deep learning techniques standing out due to their great performance in RSISC. Nevertheless, there is a general consensus that deep learning techniques usually need a lot of labeled data to work best. Collecting sufficient labeled data usually necessitates substantial human labor and resource allocation. Hence, the significance of few-shot learning to RSISC has greatly increased. Thankfully, the recently proposed discriminative enhanced attention-based deep nearest neighbor neural network (DEADN4) method has introduced episodic training- and attention-based strategies to reduce the effect of background noise on the classification accuracy. Furthermore, DEADN4 uses deep global–local descriptors that extract both the overall features and detailed features, adjusts the loss function to distinguish between different classes better, and adds a term to make features within the same class closer together. This helps solve the problem of features within the same class being spread out and features between classes being too similar in remote sensing images. However, the DEADN4 method does not address the impact of large-scale variations in objects on RSISC. Therefore, we propose a two-stream deep nearest neighbor neural network (TSDN4) to resolve the aforementioned problem. Our framework consists of two streams: a global stream that assesses the likelihood of the whole image being associated with a particular class and a local stream that evaluates the probability of the most significant area corresponding to a particular class. The ultimate classification outcome is determined by putting together the results from both streams. Our method was evaluated across three distinct remote sensing image datasets to assess its effectiveness. To assess its performance, we compare our method with a range of advanced techniques, such as MatchingNet, RelationNet, MAML, Meta-SGD, DLA-MatchNet, DN4, DN4AM, and DEADN4, showcasing its encouraging results in addressing the challenges of few-shot RSISC. Full article