In the Internet of Medical Things (IoMT), cardiotocography (CTG) is the primary non-invasive tool for fetal assessment in late pregnancy, enabling continuous monitoring of fetal heart rate (FHR) and its relationship with uterine contractions. However, acquiring sufficient high-quality FHR signals remains challenging because of ethical constraints, privacy concerns, and substantial human and annotation costs, while the long-tail distribution of IoMT datasets further hinders the training of robust intelligent CTG diagnostic systems. To overcome these, this study proposes a deep generative framework for synthesizing realistic and diverse FHR signals. Specifically, we develop an Adaptive Masking-guided Conditional Diffusion model (AM-CDiff) for multi-scenario FHR generation. First, an adaptive masking mechanism is designed to randomly mask signal segments with varying positions and lengths, enabling the model to learn deeper physiological patterns and temporal dependencies. Next, an enhanced Transformer backbone with a dual-attention mechanism is introduced to effectively model the data distribution. Finally, a progressive constraint strategy guided by medical priors is devised to transform the unconstrained denoising process into a clinically guided generation of valid synthetic data. Extensive experiments on a publicly available CTG dataset demonstrate the effectiveness of the proposed approach, including ablation studies, multi-scenario generation, comparisons with state-of-the-art Data Augmentation (DA) methods, and downstream classification evaluation. The results show that the diffusion-based DA approach effectively mitigates the long-tail problem, and that AM-CDiff further improves downstream classification accuracy by approximately 3.7%.

Electrocardiogram (ECG) signal exhibits inherent uniqueness, making it a promising biometric modality for identity authentication. As a result, ECG authentication has gained increasing attention in recent years. However, most existing methods focus primarily on improving authentication accuracy within closed-set settings, with limited research addressing the challenges posed by open-set scenarios. In real-world applications, identity authentication systems often encounter a substantial amount of unseen data, leading to potential security vulnerabilities and performance degradation. To address this issue, we propose a robust ECG identity authentication system that maintains high performance even in open-set settings. To enhance the encoder’s sensitivity to region-specific ECG features, we propose a multimodal pretraining framework that aligns ECG signals with textual descriptions derived from fiducial features. During fine-tuning, we introduce Self-constraint Center Learning and Reciprocal Points Learning to constrain the feature distribution, ensuring that the encoded representations exhibit clear decision boundaries for classification. Our method achieves 99.83% authentication accuracy and maintains a False Accept Rate as low as 5.39% in the presence of open-set samples. Furthermore, across various open-set ratios, our method demonstrates exceptional stability, maintaining an Open-set Classification Rate above 95%.

With the continuous advancement of industrial automation, motors as essential driving components play a vital role in maintaining the stability and safety of the entire production system. To improve the accuracy and real-time performance of motor fault diagnosis, this paper proposes an intelligent multi-fault diagnosis method for motors based on deep learning and data fusion. Unlike existing approaches that typically rely on single-source signals or shallow feature representations, the proposed method introduces a unified framework that combines multisource data fusion with a wide-kernel CNN, residual learning, BiLSTM, and an adaptive attention mechanism to enhance spatiotemporal feature extraction. Focusing on bearing faults and inter-turn short circuit faults in stator windings, the method integrates current and vibration signals collected during motor operation. First, discrete wavelet transform is applied to denoise the raw signals and enhance their time-frequency features. Then, a wide kernel one-dimensional convolutional neural network (Wide Kernel 1D-CNN) is employed to extract spatial features, with residual connections introduced to mitigate gradient vanishing in deep networks. Subsequently, a bidirectional long short-term memory network (BiLSTM) models the temporal dynamics of the signals, and an adaptive attention mechanism is incorporated to enhance the focus on critical features. Finally, the trained model is deployed to edge computing devices and integrated with a cloud platform for remote monitoring and fault diagnosis. Experimental results show that the model achieves an accuracy of 98.16

The timely, efficient, and accurate diagnosis of Chronic Fetal Distress (CFD) in late pregnancy is of great significance in reducing neonatal morbidity and mortality and improving pregnancy outcomes. Cardiotocography (CTG) monitoring was introduced to detect fetus at risk of CFD by observing alterations in Fetal Heart Rate (FHR) patterns and their temporal correlation with uterine contractions. However, human factors and clinical risks can influence the interpretation of CTG recordings. Most existing intelligent CTG approaches focus solely on blackbox modeling of input-output relationships, neglecting the dynamic characteristics of time series, leading to calibration bias and underutilization of CTG data. This study addresses these issues by modeling dynamic graphstructured data and proposing a novel Expert Consensus-driven Spatial-Temporal graph neural Network (EcSTnet) approach for CFD auxiliary diagnosis. It is a contribution in artificial intelligence and is the application in biomedical engineering. First, a graph structure learning module is devised, concentrates on generating structured data from expert consensus static graphs and automatically learning the hidden spatial-temporal dependencies from the original FHR series. Next, we designed a dynamic graph mechanism to capture the random instability in dynamic time series from static graphs and construct optimal dynamic graphs. Finally, an enhanced spatial-temporal graph convolutional network model is constructed to simultaneously capture temporal and spatial dependencies, facilitating the transmission of pathological information. Extensive experiments, including parameter sensitivity analysis, ablation study, and classification performance evaluation, were conducted to comprehensively evaluate the proposed EcSTnet. In all cases, EcSTnet demonstrates superior performance in the ICTG task and achieves a high test accuracy of 95.33 %.

Fetal Heart Rate (FHR) signals are widely used in fetal monitoring and maternal-fetal health assessment. However, their acquisition is constrained by ethical limitations, motion artifacts, and signal loss, resulting in limited data availability for intelligent clinical analysis. To address these, this paper proposes a deep generative Data Augmentation (DA) framework for FHR synthesis. Specifically, we propose a Mask-Enhanced Diffusion Transformer model (MEDiT) to model various missing data scenarios and generate high-fidelity FHR signals in data-scarce clinical settings. First, a mask-enhanced reinforcement mechanism is designed to randomly mask signal segments at varying positions and lengths, forcing the model to reconstruct targeted regions from unmasked regions containing clinically critical information and thereby learn intrinsic physiological patterns under partial observability. Next, a Diffusion Transformer (DiT)-based generative architecture with a dual-branch learning strategy is developed to adaptively adjust the optimization objective under different masking ratios, improving both global temporal coherence and local waveform fidelity. Owing to self-attention-based global interaction and the threshold-guided branch design, MEDiT is able to capture long-range temporal dependencies while maintaining stable. Comprehensive experiments on a publicly available CTG dataset, including parameter sensitivity analysis, robustness evaluation, comparisons with state-of-the-art methods, downstream classification tasks, and clinician assessment, demonstrate the effectiveness of MEDiT. The results show that diffusion-based DA approaches perform better in both generation quality and training stability, and MEDiT further improves classification accuracy by 14.0% over the best baseline method (DDPM).

Recently, electrocardiogram (ECG) signals have garnered significant attention in the field of identity authentication due to its biological uniqueness. For identity authentication, the ECG signals that collected by wearing smart devices need to be determined whether the signal belongs to an enrolled one. Constrained by the computational efficiency of smart devices in practical scenarios, it is essential to reduce the complexity of the method to lower the computational load. To maintain the accuracy of identity authentication, most research efforts rely on both R-wave extraction and segmentation for subsequent authentication. Moreover, many methods constantly require the model to be retrained during the user enrollment stage, leading to performance degradation and waste of training resources. Hence, we propose a simple yet effective ECG identity authentication method that applies blind segmentation and is free from retraining, which greatly simplifies the authentication process. To mitigate the Equal Error Rate (EER) during the verification phase, a combination of AAM-softmax and triplet losses is employed, along with the incorporation of the hard negative mining within batch samples. Extensive experiments demonstrate that our method outperforms competitors by a large margin, e.g., achieving 0.40% EER on the large-scale Autonomic dataset.

Biometrics is one of the most prominent sources of knowledge for human identification in the rapidly advancing field of cybersecurity. Among various types of biometric information, electrocardiogram (ECG) and photoplethysmography (PPG) signals gained considerable attention due to its inherent resistance to spoofing. However, existing researches are predominantly conducted in controlled environments, where ECG or PPG signals are susceptible to interference from motion and noise in real-world scenarios, resulting in suboptimal model robustness. Additionally, the few multimodal ECG identification studies mainly based on different conversion methods of ECG signal, resulting in information redundancy between modalities. To address these, we propose a lightweight identity recognition model based on cross-domain multimodal feature fusion of ECG and PPG signals. It incorporates an enhanced MultiRes block that forwards upsampled data for multi-resolution analysis of signal features, and employs spatial pyramid pooling for multi-scale feature extraction. Using this network structure, we separately extract and fuse features from ECG and PPG signals, then perform identity recognition based on the fused features. Extensive experiments were conducted to evaluate the proposed algorithm. The proposed fusion model reaches a high accuracy of 97.26%, improving by 17.06% and 40.48% compared to single-modal ECG and PPG identification models, respectively. By visualizing the fused features alongside single-modal ECG and PPG features, we intuitively explain the effectiveness of multimodal feature fusion for feature extraction, offering a new approach for multimodal biometric recognition.

Fetal heart rate (FHR) signals are widely used for fetal health assessment in clinical settings, making them popular in artificial intelligence-based algorithms for fetal health diagnosis. However, a major challenge for such algorithms is the need for a large amount of labeled and category-balanced clinical data to train the models. Like other medical data, FHR faces severe class imbalance in pathological data. Therefore, this paper proposes a minority sample generation method to generate high-quality pathological FHR signals to improve downstream classification task performance. We propose a long time series progressive growing generative adversarial network, TSP-GAN, which dynamically increases the network during training to achieve a transition from coarse-grained to fine-grained time features, thus generating long-time series with rich detailed information. The loss function of this network introduces L2 regularization on the basis of Wasserstein distance and gradient penalty terms to generate high-fidelity signals while avoiding mode collapse. On the one hand, visual and quantitative comparison experiments are designed and the results show that signals of different lengths generated by our network all obtained superior performance. On the other hand, downstream classification tasks are designed and the results indicate that the augmented category-balanced dataset improved by 10

In the face of the mounting challenges posed by cybersecurity threats, there is an imperative for the development of robust identity authentication systems to safeguard sensitive user data. Conventional biometric authentication methods, such as fingerprinting and facial recognition, are vulnerable to spoofing attacks. In contrast, electrocardiogram (ECG) signals offer distinct advantages as dynamic, “liveness”-assured biomarkers, exhibiting individual specificity. This study proposes a novel fusion network model, the convolutional neural network (CNN)-transformer fusion network (CTFN), to achieve high-precision ECG-based identity authentication by synergizing local feature extraction and global signal correlation analysis. The proposed framework integrates a multistage enhanced CNN to capture fine-grained local patterns in ECG morphology and a transformer encoder to model long-range dependencies in heartbeat sequences. An adaptive weighting mechanism dynamically optimizes the contributions of both modules during feature fusion. The efficacy of CTFN was evaluated in three critical real-world scenarios: single/multi-heartbeat authentication, cross-temporal consistency, and emotional variability resistance. The evaluation was conducted on 283 subjects from four public ECG databases: CYBHi, PTB, ECG-ID, and MIT-BIH. The CYBHi dataset revealed that CTFN exhibited a state-of-the-art recognition accuracy of 98.46%, 80.95%, and 90.76%, respectively, signifying its remarkable performance. Notably, the model attained a 100% authentication accuracy rate using only six heartbeats. This represents a 25% decrease in input requirements when compared to prior works, while concurrently maintaining its robust performance against physiological variations induced by emotional states or temporal gaps. These results demonstrate that CTFN significantly advances the practicality of ECG biometrics by balancing high accuracy with minimal data acquisition demands, offering a scalable and spoof-resistant solution for secure authentication systems.

Electrocardiogram (ECG) signal exhibits inherent uniqueness, making it a promising biometric modality for identity authentication. As a result, ECG authentication has gained increasing attention in recent years. However, most existing methods focus primarily on improving authentication accuracy within closed-set settings, with limited research addressing the challenges posed by open-set scenarios. In real-world applications, identity authentication systems often encounter a substantial amount of unseen data, leading to potential security vulnerabilities and performance degradation. To address this issue, we propose a robust ECG identity authentication system that maintains high performance even in open-set settings. Firstly, we employ a multi-modal pretraining framework, where ECG signals are paired with textual reports derived from their corresponding fiducial features to enhance the representational capacity of the signal encoder. During fine-tuning, we introduce Self-constraint Center Learning and Irrelevant Sample Repulsion Learning to constrain the feature distribution, ensuring that the encoded representations exhibit clear decision boundaries for classification. Our method achieves 99.83 Rate as low as 5.39 various open-set ratios, our method demonstrates exceptional stability, maintaining an Open-set Classification Rate above 95

Training-free deepfake image detection aims to discern whether inputs are authentic or synthetic by directly conduct evaluation on testing samples. Prior approaches predominantly measure the similarity between original images and perturbation-generated versions. Leveraging pre-trained foundation models like DINOv2, these methods typically deliver remarkable detection performance on natural images. However, their effectiveness diminishes significantly when applied to deepfake face detection, particularly for faces of varying resolutions. Additionally, the computational demands are high due to the complexity of these foundational models, hindering the application in real-world scenarios. To overcome these challenges, we elaborate a simple yet effective Upsampling-Perturbation-Downsampling method for training-free deepfake face detection. This approach enhances both the robustness against diverse input resolutions and the efficiency of detection process. Extensive experiments on our augmented DeepFakeFaceForensics dataset demonstrate that our approach significantly outperforms state-of-the-art methods.

Fetal Heart Rate (FHR) signal is widely used in doppler fetal heart monitors. However, incomplete FHR signals reduce the effectiveness of fetal heart rate monitoring. Filling missing data is a key technique to improve FHR quality, but existing filling algorithms lack consideration the correlation of FHR signals. Therefore, we focus on two correlations related to FHR, and propose a filling algorithm called Diffusion model for Missing Data Imputation in FHR (DMDI-FHR). Firstly, we construct the Dual-dimensional Sample Construction (DDSC) method that finds two FHR signals with maximizing the difference to form correlations between them. Secondly, the Multi-period Decomposition (MPD) method is introduced to obtain the internal correlation of FHR signal. Finally, DMDI-FHR algorithm controls the filling process based on the diffusion model. Experimental results demonstrate the performance of DMDI-FHR algorithm, which provides an effective way to improve the quality of FHR signal.

Cardiotocography (CTG) is an important medical diagnostic tool when it comes to monitoring fetal wellbeing. It records Fetal Heart Rate (FHR) and uterine contraction activity, and can be used to detect whether the fetus is receiving oxygen adequately or in distress. Unfortunately, the interpretation of CTG recordings is highly subjective which can lead to unnecessary medical intervention that represents a risk for both the mother and the fetus. In this regard, intelligent CTG (ICTG) classification is a challenging research that can assist obstetricians in making clinical decisions, thereby improving the efficiency and accuracy of pregnancy management. But, many of these models focus on one specific modality that lack generalization to unseen or test data samples. In this study, a multi-modal fusion learning approach is proposed for pathological diagnosis of fetal distress. It combines signal and image modalities for multi-modal inputs and develops a Multi-modal Encoder Network (MENet) model based on DNN for capturing the underlying distribution of multi-modal data samples. Experimental results demonstrate that under the constraints of same classifier structure, MENet performs well in terms of classification accuracy and stability, far superior to several existing ICTG algorithms.

Fetal distress is a symptom of fetal intrauterine hypoxia, which is seriously harmful to both the fetus and the pregnant woman. The current primary clinical tool for the assessment of fetal distress is Cardiotocography (CTG). Due to subjective variability, physicians often interpret CTG results inconsistently, hence the need to develop an auxiliary diagnostic system for fetal distress. Although the deep learning-based fetal distress-assisted diagnosis model has a high classification accuracy, the model not only has a large number of parameters but also requires a large number of computational resources, which is difficult to deploy to practical end-use scenarios. Therefore, this paper proposes a lightweight fetal distress-assisted diagnosis network, LW-FHRNet, based on a cross-channel interactive attention mechanism. The wavelet packet decomposition technique is used to convert the one-dimensional fetal heart rate (FHR) signal into a two-dimensional wavelet packet coefficient matrix map as the network input layer to fully obtain the feature information of the FHR signal. With ShuffleNet-v2 as the core, a local cross-channel interactive attention mechanism is introduced to enhance the model’s ability to extract features and achieve effective fusion of multichannel features without dimensionality reduction. In this paper, the publicly available database CTU-UHB is used for the network performance evaluation. LW-FHRNet achieves 95.24% accuracy, which meets or exceeds the classification results of deep learning-based models. Additionally, the number of model parameters is reduced many times compared with the deep learning model, and the size of the model parameters is only 0.33 M. The results show that the lightweight model proposed in this paper can effectively aid in fetal distress diagnosis.

Clinically, Fetal Heart Rate (FHR)-based intelligent cardiotocography classification to diagnose fetal well-being is of utmost importance for obstetricians and gynecologists. However, the current Fetal Distress Diagnosis (FDD) algorithms based on Artificial Intelligence (AI) methods are designed as black box models that usually result in poor performance on clinical interpretation and lack explicit diagnostic evidence. This paper focuses on two aspects: enhancing the accuracy of FD and providing explanations for the model's decisions. Specifically, we propose a novel clinically interpretable dual-stream AI architecture for FDD. The two streams embed multi-feature category representations and the original FHR into the Digital Twin model (DT) and the deep convolutional neural Networks-based Case Tracking model (CTNet), respectively, thus marking as DT-CTNet. And the former makes the input-outcome dependency transparent, while the latter provides the samples that are the most similar to the object being diagnosed. By this design, not only is high-precision FDD achievable, but a transparent explanation with global, local and instantiation interpretation can be obtained. To the best of our knowledge, this work is the first to provide an interpretable diagnosis of fetal distress. The proposed method is comprehensively evaluated from five aspects: classification model accuracy, explanation of the classification model decision, consistency of the evidence explanation, pathological difference in visual analysis, and a comparison with state-of-the-art methods. Experimental results, which are performed on a challenging dataset, show that the proposed fetal distress diagnosis method outperforms the state-of-the-art methods and has a high accuracy (0.963).

A channel rendezvous is a significant aspect of communication. In this context, blind rendezvous is the process of selecting a common available channel and establishing a communication link for wireless devices in a wireless sensor network. The rendezvous of asymmetric and heterogeneous wireless devices is a challenge. Thus, to improve speeds and stability of rendezvous, we analyze time slot overlap and channel determinism in the rendezvous algorithm and propose a rendezvous algorithm named Multiple Prime Expansion (MPE). In a final simulation study, we compare the performance of the MPE with other existing algorithms in an asymmetric and heterogeneous scenario. Results show that MPE has excellent performance for the ATTR and MTTR.

Fetal heart rate (FHR) monitoring is an important medical-assisted diagnostic technique widely used by clinicians to assess fetal well-being. However, one challenge is that the capabilities of such diagnostic algorithms often rely on an enormous quantity of labeled clinical data to train a model, which do not preserve patient privacy. The high performance of such diagnostic algorithms is further hindered by category imbalance problems. Therefore, the general objective of this study is to develop a small-sample generation method that generates FHR signals of different physiological/pathological categories and arbitrary lengths. This study focuses on two significant impediments to the existing generation methods: the instability of generative adversarial networks (GAN) during model training, the mode collapse problem and the subsequent training of different specific models for different data categories, which contributes to high model training costs. To address these problems, we propose a novel generative adversarial architecture, referred to as CCWGAN-GP, based on a deep neural network optimized by the Wasserstein distance with gradient penalty, and incorporate an auxiliary classifier as a category constraint to enrich the diversity of generated data. The proposed method is comprehensively evaluated using 200 real FHR recordings from four aspects: training performance, the fidelity and diversity of generated data, and the potential improvement in the classification model. Compared with training on small-sample datasets and category-imbalanced datasets, training on augmented datasets improves the accuracy by approximately 12% and 8%, respectively. The developed architecture provides a reference value for a practical solution to the FHR data imbalance and insufficient sample problems.

胎心率(Fetal Heart Rate,FHR)是胎心宫缩监护(Cardiotocography,CTG)的重要生理参数.临床监测中,往往出现FHR信号丢失的现象.文章提出一种基于集成学习的胎心率缺失值填补算法,先采用线性插值法进行预处理,再采用集成学习方法填补缺失值,获取稳定且完整的FHR信号.从捷克技术大学布尔诺大学(Czech Technical University-University Hospital in Brno,CTU-UHB)采集的CTG数据库中随机选取100例FHR信号,模拟单段和多段缺失的FHR信号,进行缺失值填补,获得较好的填补效果,得到最佳的均方根误差、平均绝对误差、欧氏距离分别为0.004,1.7×10-4,0.192.

Premature delivery is one of the direct factors that affect the early development and safety of infants. Its direct clinical manifestation is the change of uterine contraction intensity and frequency. Uterine Electrohysterography(EHG) signal collected from the abdomen of pregnant women can accurately and effectively reflect the uterine contraction, which has higher clinical application value than invasive monitoring technology such as intrauterine pressure catheter. Therefore, the research of fetal preterm birth recognition algorithm based on EHG is particularly important for perinatal fetal monitoring. We proposed a convolution neural network(CNN) based on EHG fetal preterm birth recognition algorithm, and a deep CNN model was constructed by combining the Gramian angular difference field(GADF) with the transfer learning technology. The structure of the model was optimized using the clinical measured term-preterm EHG database. The classification accuracy of 94.38% and F1 value of 97.11% were achieved. The experimental results showed that the model constructed in this paper has a certain auxiliary diagnostic value for clinical prediction of premature delivery.

Cardiotocography (CTG) monitoring is an important medical diagnostic tool for fetal well-being evaluation in late pregnancy. In this regard, intelligent CTG classification based on Fetal Heart Rate (FHR) signals is a challenging research area that can assist obstetricians in making clinical decisions, thereby improving the efficiency and accuracy of pregnancy management. Most existing methods focus on one specific modality, that is, they only detect one type of modality and inevitably have limitations such as incomplete or redundant source domain feature extraction, and poor repeatability. This study focuses on modeling multimodal learning for Fetal Distress Diagnosis (FDD); however, exists three major challenges: unaligned multimodalities; failure to learn and fuse the causality and inclusion between multimodal biomedical data; modality sensitivity, that is, difficulty in implementing a task in the absence of modalities. To address these three issues, we propose a Multimodal Medical Information Fusion framework named MMIF, where the Category Constrained-Parallel ViT model (CCPViT) was first proposed to explore multimodal learning tasks and address the misalignment between multimodalities. Based on CCPViT, a cross-attention-based image-text joint component is introduced to establish a Multimodal Representation Alignment Network model (MRAN), explore the deep-level interactive representation between cross-modal data, and assist multimodal learning. Furthermore, we designed a simple-structured FDD test model based on the highly modal alignment MMIF, realizing task delegation from multimodal model training (image and text) to unimodal pathological diagnosis (image). Extensive experiments, including model parameter sensitivity analysis, cross-modal alignment assessment, and pathological diagnostic accuracy evaluation, were conducted to show our models' superior performance and effectiveness.