Search Results (1,655)

Short-term traffic forecasting is a critical component of intelligent transportation systems. While deep learning architectures for this task have proliferated rapidly, the sensor-level data characteristics—zero-value prevalence, distributional heterogeneity, and cross-sensor correlation structure—that drive architecture-specific failure modes remain insufficiently understood, and their implications for evidence-based model selection in real deployments have not been systematically addressed. This study addresses that question through a sensor-network diagnostic framework applied to the METR-LA dataset (Metropolitan Los Angeles; 207 inductive loop detectors, 5-min resolution). The framework integrates systematic characterization of sensor data properties, a controlled benchmark of four representative architectures—Transformer, Spatio-Temporal Graph Convolutional Network (STGCN), Diffusion Convolutional Recurrent Neural Network (DCRNN), and Gated Temporal Convolutional Network (Gated TCN)—under a unified 12→3 prediction setting, and a novel per-sensor regression analysis that quantitatively links zero-value ratios to model-specific prediction errors across all 207 sensors. Building on these findings, this study further proposes Graph-Enhanced Transformer (GETFormer), a lightweight hybrid architecture that augments the Transformer with a single-hop Graph Convolutional Network (GCN) layer and a gated residual fusion module. The diagnostic findings and condition-dependent model-selection guidelines provide an empirically grounded foundation for principled hybrid architecture development in urban traffic sensing. Full article

Industrial control systems (ICSs) are cyber–physical environments in which physical process data and network communication data are generated simultaneously. Existing studies have mainly focused on either sensor-based or network-based anomaly detection, making it difficult to capture diverse attack indicators and motivating the use of multimodal methods that can leverage complementary information from both modalities. In this paper, we propose an unsupervised multimodal anomaly detection framework for ICSs that jointly uses sensor and network modalities. For each modality, autoencoder-based single-modality models are trained in an unsupervised manner, and their anomaly scores and latent feature vectors are extracted. These outputs are temporally aligned to construct a time-aligned multimodal table, which is then used to implement and compare two fusion strategies: anomaly score fusion and latent feature fusion. In latent feature fusion, aligned modality-specific latent features are combined with canonical correlation analysis (CCA)-derived cross-modal correlation features. The experimental results showed that latent feature fusion achieved stable performance across multiple sensor–network encoder combinations. In particular, the gated recurrent unit–convolutional neural network (GRU–CNN) combination achieved the best F1-score of 0.9166 and ROC-AUC of 0.9795. In addition, the complementarity analysis showed that latent feature fusion recovered some missed detections by integrating complementary sensor and network evidence. These results demonstrate that latent feature fusion is an effective multimodal strategy for ICS anomaly detection. Full article

As tunnel engineering continues to advance toward deeper, longer, and more complex projects, the risks encountered during the construction phase have evolved into a combination of various disaster types and the accumulation of multiple contributing factors. Traditional empirical and semi-empirical risk management methods are increasingly revealing shortcomings in terms of timeliness, accuracy, and the ability to process multi-source data. In recent years, driven by advancements in computing power and sensor technology, artificial intelligence algorithms (AI algorithms) such as machine learning and deep learning have been rapidly adopted in tunnel construction risk management. This paper retrieved relevant literature from the Web of Science database covering the period from 2010 to 2025. After rigorous screening, 96 highly relevant papers were selected for bibliometric analysis. This paper systematically reviews research progress from two perspectives: algorithmic models and engineering applications. The review indicates that, in terms of algorithmic models, traditional machine learning, convolutional neural network, recurrent neural network, generative adversarial network, Transformer, and graph neural network constitute a multi-level technical framework encompassing feature representation, risk perception, and intelligent decision-making. In terms of applications, AI algorithms have been widely integrated into typical scenarios such as geological hazard identification and prediction, surrounding rock stability and deformation prediction, rock burst assessment and early warning, lining defect detection and structural safety assessment, construction-induced ground settlement prediction, and tunnel gas and fire hazard prediction, significantly enhancing risk identification and early warning capabilities. However, several challenges remain, including the scarcity of high-quality datasets, the prevalence of noisy, incomplete, and heterogeneous monitoring data, insufficient coupling between model interpretability and engineering mechanisms, limited cross-project transferability, and the lack of integrated management systems for multi-hazard lifecycle control. Based on this, this paper proposes future research directions in areas such as data infrastructure development, integration of mechanism constraints, and multi-hazard collaborative modeling, aiming to provide guidance for the further development of intelligent risk management in tunnel construction. Full article

Rolling bearing fault diagnosis remains challenging due to environmental noise, insufficient information sharing between diagnosis and prediction tasks, and poor model generalization ability. To address these issues, this paper proposes a fault diagnosis and severity prediction method integrating probabilistic principal component analysis (PPCA) and empirical mode decomposition (EMD) with a one-dimensional convolutional neural network (1DCNN) and bidirectional gated recurrent unit (BiGRU). The proposed model consists of two parallel branches for fault diagnosis and fault severity prediction. A self-attention mechanism is integrated into both branches to enhance feature extraction via adaptive feature weighting. In addition, parameter sharing and weighted loss functions are adopted to improve the training efficiency and collaborative learning between the two tasks. PPCA and EMD are employed for signal denoising and reconstruction while preserving fault-related features. Experiments on public datasets and industrial production-line data show that the proposed method improves the fault classification accuracy from 92.43% to 99.71% under different load conditions, while achieving 98.99% accuracy in fault severity prediction. Noise interference tests further demonstrate the effectiveness of the model. A production-line case study further illustrates the feasibility of applying the proposed method to real monitoring signals. These results confirm the effectiveness and practical potential of the proposed method for rolling bearing fault diagnosis and health assessment. Full article

Early depression screening is important for timely intervention, and electroencephalography (EEG) offers an objective and potentially portable sensing modality for computer-aided assessment. However, recognition from fixed three-channel frontal EEG remains difficult because of limited spatial information and incomplete modeling of temporal–frequency characteristics and temporal dependencies. This study proposes DEP-TFDualNet for acquisition-constrained frontal resting-state EEG. The framework integrates multi-scale convolution, dual-domain channel attention, temporal modeling derived from the independent recurrent neural network (IndRNN) architecture, and decision-stage fusion of deep representations with low-order statistical descriptors through a Kolmogorov–Arnold Network (KAN)-based nonlinear projection layer. Experiments were conducted on the publicly available three-channel frontal EEG subset of the MODMA dataset. After additional quality control, 48 subjects were retained (22 patients with major depressive disorder, 26 healthy controls). Under subject-wise stratified five-fold cross-validation, DEP-TFDualNet achieved 85.42% accuracy, 85.26% macro-F1, 81.82% sensitivity, 88.46% specificity, an AUC of 0.82, and a Brier score of 0.121. It achieved the best threshold-based subject-level performance and the lowest Brier score among the evaluated models. These results provide preliminary evidence that simplified frontal EEG sensing may support depression recognition in acquisition-constrained settings, although larger and external validation is still required. Full article

Urban acoustic environments and performing-arts spaces strongly influence speech communication quality, acoustic comfort, and public wellbeing, particularly in noise-exposed shared environments such as transport hubs, campuses, healthcare spaces, public service facilities, music-education settings, and rehearsal or performance-related spaces. To address speech–noise separation in low signal-to-noise ratio and acoustically complex scenarios, this study proposes a lightweight two-stage deep learning framework termed LCGRU–Wave-SkipConvNet. In the preprocessing stage, a Lightweight Convolutional Gated Recurrent Unit (LCGRU) model is employed to achieve preliminary separation of target speech and background noise by capturing both spatial and temporal acoustic features. In the post-processing stage, a Wave-SkipConvNet model is introduced to further suppress residual noise and enhance speech quality. Experimental results demonstrate that the proposed framework achieves superior performance under different signal-to-noise ratios, sound-source angles, and target angle errors. For example, in the preprocessing stage, the LCGRU model achieved a perceptual evaluation of speech quality (PESQ) score of 2.64 at source angles between 0° and 30°, outperforming the convolutional neural network-long short-term memory (CNN-LSTM) model by 1.17. In the post-processing stage, the Wave-SkipConvNet model achieved higher short-time objective intelligibility (STOI) and segmental signal-to-noise ratio (segSNR) values than the comparison models under different SNR conditions. The proposed framework provides an effective and deployment-oriented AI solution for improving speech accessibility and acoustic comfort in urban acoustic environments and performing-arts spaces. Beyond speech enhancement, it offers practical potential for supporting healthier, more inclusive, and more equitable acoustic environments in noise-sensitive public and educational spaces. It should be noted that this study focuses on the objective acoustic environment and signal-level speech enhancement, rather than subjective soundscape perception, musical perception, or human perceptual evaluation. Full article

WiFi channel state information (CSI) has become a compelling sensing modality for contactless human activity recognition. However, differences in datasets, preprocessing protocols and model configurations make consistent comparison and reproducibility challenging. This study presents a unified baseline evaluation of four widely adopted deep learning architectures: multilayer perceptron (MLP), convolutional neural network (CNN), gated recurrent unit (GRU) and a hybrid CNN–GRU model across multiple publicly available CSI datasets encompassing a range of sensing tasks. We harmonize the datasets, implement a standardized preprocessing and training pipeline to reduce experimental inconsistencies and support controlled within-dataset comparisons of model behavior. Evaluations include single-person activity recognition, fall-risk estimation, multiperson occupancy classification and localization-aware activity recognition, representing progressively higher temporal and spatial complexity. Our results show dataset-dependent trends: CNNs provide an efficient accuracy–complexity trade-off in several structured activity scenarios, whereas GRUs are advantageous when temporal dynamics are more prominent, although with greater training and inference costs. In contrast, MLPs generally underperform due to limited capacity to capture spatial and temporal dependencies. Confusion matrix analysis reveals that dynamic behaviors and low-motion states remain challenging to distinguish, underscoring the importance of temporal modeling. By releasing the complete experimental pipeline and benchmarking results, this work establishes a reproducible reference framework for the research community and highlights directions for future investigation, including cross-dataset generalization, hybrid model design and lightweight deployment strategies. Full article

Recursive Plots (RPs) can fully utilize the information of signals on a time scale, but their application involves the issue of manual threshold selection, and different thresholds have a significant impact on the analysis results of recursive plots, which in turn affects the accuracy of subsequent fault diagnosis models. Some scholars have proposed the no-threshold recursive plot method to address the above issues, but this method is not comprehensive enough and has limitations. On the basis of RPs, this article proposes a Threshold-Free Recurrence Distance (TFRD), which is combined with a Convolutional Neural Network (CNN) to form a TFRD-CNN rotating machinery fault diagnosis model. The accuracy of the method is tested using bearing vibration data from Western Reserve University, and the effectiveness of the model is verified using a planetary gearbox gear fault dataset. At the same time, the TFRD-CNN method is compared with a Markov Transition Field (MTF), Gramian Angular Fields (GAF), and RP and URP combined with CNN methods. The results show that the TFRD-CNN method has significant advantages. Full article

Acoustic gait recognition is an emerging passive biometric modality that identifies individuals by unique walking sound patterns. This work presents a reproducible benchmarking framework for convolutional neural network (CNN)-based acoustic gait recognition, providing a systematic evaluation methodology across varying identity pool sizes. Raw footstep recordings from the AFPILD dataset were converted into 128-bin mel-spectrograms and used to train a compact CNN across identity pool sizes from 10 to 40 subjects. To ensure statistical reliability, a three-times-repeated five-fold stratified cross-validation protocol was implemented. Experimental results demonstrate strong discriminative capability, with validation accuracy reaching 94.92% and Equal Error Rate (EER) of 1.31% for the 40-subject configuration. A multi-seed subset validation experiment across five independent random subject draws per pool size confirmed that the observed scaling trend is consistent across subset compositions rather than an artifact of a single subject selection. Additional analysis confirmed the framework’s resilience to moderate environmental noise and its superiority over classical Mel-Frequency Cepstral Coefficients paired with a Support Vector Machine (MFCC-SVM) and Convolutional Recurrent Neural Network (CRNN) baselines, supporting the feasibility of acoustic gait recognition as a passive biometric modality. Full article

Soluble solids content (SSC) is one of the most important indicators of sweetness, ripeness, and market quality in sweet cherries. However, conventional SSC determination is destructive, labor-intensive, and unsuitable for rapid or large-scale quality assessment. Therefore, there is a need for fast, non-destructive, and data-driven sensing approaches that can estimate internal fruit quality without damaging the sample. This study aimed to develop a non-destructive approach for SSC prediction in sweet cherries by combining open-ended coaxial probe dielectric spectroscopy with deep learning models. An open-ended coaxial probe measurement system was designed and developed to determine the dielectric properties of sweet cherries and was coupled with an Agilent E4991A impedance analyzer operating over a frequency range of 5–3005 MHz. A total of 10,080 dielectric measurements and 2100 reference SSC measurements were collected over 26 experimental days. The dielectric constant (ε′), loss factor (ε″), and loss tangent (tan δ) were extracted and used to construct separate ε′, ε″, tan δ, and integrated combined datasets. Six deep learning architectures, namely convolutional neural network (CNN), long short-term memory (LSTM), bidirectional long short-term memory (BiLSTM), gated recurrent unit (GRU), CNN-LSTM, and convolutional long short-term memory (ConvLSTM), were trained and optimized using Bayesian optimization and early stopping. CNN achieved the best performance on the tan δ dataset (test R² = 0.9099, RMSE = 0.8354 °Brix, MAE = 0.6599 °Brix), whereas GRU yielded the highest accuracy on the integrated combined dataset (test R² = 0.8622, RMSE = 1.0331 °Brix, MAE = 0.7958 °Brix). ConvLSTM provided the most consistent performance across all four datasets (test R² = 0.8081–0.8651), demonstrating strong predictive capability and practical computational efficiency. These findings confirm the potential of reduced-range dielectric spectroscopy combined with deep learning for rapid, non-destructive SSC assessment in sweet cherries. Full article

Network Music Performance (NMP) refers to remote musical collaboration over a network in applications such as music education, music production, and live performance. In NMP, synchronisation is a critical factor in musicians’ Quality of Experience (QoE). This interpersonal coordination of musical actions is highly sensitive to variable network conditions, particularly to end-to-end delay and signal degradation. Existing evaluations rely mainly on subjective questionnaires or isolated objective descriptors, creating a gap for a unified metric that quantifies synchrony directly from performance signals. To address this gap, we propose the Objective Synchrony Index (OSI), an AI-driven metric that quantifies ensemble synchrony from paired NMP recordings. We computed OSI using a two-tower multi-task convolutional recurrent neural network (CRNN) that estimates synchrony-relevant descriptors from paired Musician A and Musician B audio streams. We introduce two OSI variants: timing-OSI, which captures temporal coordination through offsets, onsets, beats, and tempo coherence; and ensemble-OSI, which extends this formulation by integrating chord agreement and signal fidelity to reflect structural and perceptual aspects of ensemble interaction. We evaluated OSI using recordings from two NMP studies in which eleven pairs of musicians performed under systematically varied delay and sampling-rate conditions. After each performance, musicians completed QoE questionnaires, allowing us to relate OSI and its components to subjective ratings using repeated-measures correlation. Results showed that, under delay, timing-OSI decreases as latency increases and demonstrates construct validity against subjective QoE measures. Higher synchrony-OSI was associated with greater perceived synchronisation and satisfaction, and with lower perceived delay, irritation, and effort to follow a partner. These relationships were most consistent for offset synchrony and most selective for onset synchrony, while beat and tempo remained relatively stable. Under audio-quality degradation, ensemble-OSI remained relatively stable across sampling rates and did not significantly track subjective QoE as a single predictor. Instead, modest component-level associations suggested that satisfaction was higher when temporal stability and fidelity were preserved, whereas irritation was more closely related to reduced chord agreement. Together, these findings support timing-OSI as a promising objective synchrony metric for delay-impaired NMP, while showing that the extended ensemble-OSI requires further perceptual calibration for audio-quality degradations. Full article

Longitudinal data, characterized by repeated measurements on the same subjects over time, are ubiquitous in biomedical sciences, economics, social sciences, and engineering. Analyzing such data presents unique statistical and computational challenges, including within-subject correlation, time-varying covariates, irregular observation times, informative dropout, and high dimensionality. While traditional statistical methods, such as linear mixed-effects models and generalized estimating equations, remain foundational, they often struggle with complex nonlinear dynamics, ultra-high-dimensional feature spaces, and very large sample sizes. Over the past two decades, machine learning (ML) and artificial intelligence (AI) methods have emerged as powerful complementary approaches to address these limitations. This review provides a comprehensive survey of mathematical and computational methods for longitudinal data analysis. We cover classical statistical models, penalized regression techniques, tree-based ensemble methods, kernel machines, Bayesian hierarchical models, and modern deep learning architectures, including recurrent neural networks, temporal convolutional networks, attention-based Transformers, neural ordinary differential equations, and generative models. We propose a unified taxonomy that organizes existing methods along two primary axes: the underlying mathematical framework and the analytical objective. For each category, we present detailed mathematical formulations, discuss key theoretical properties, examine computational considerations, and summarize representative reported applications drawn from the published literature. To increase the practical value of this review, we provide a cross-cutting comparison of method families against five key challenges (within-subject correlation, irregular sampling, missing data, high dimensionality, and scalability) and offer concrete guidance on method selection according to sample size, dimensionality, and analytical objective. Finally, we critically evaluate the strengths and limitations of these approaches, with particular emphasis on interpretability, scalability, handling of missing data, robustness to covariance misspecification, and uncertainty quantification. Full article

Hyperspectral images (HSIs) and Light Detection and Ranging (LiDAR) data offer complementary spectral and spatial information and are extensively applied to land cover classification. Nevertheless, current fusion–classification approaches frequently suffer from cross-modal feature entanglement and insufficient exploitation of LiDAR physical priors, particularly the Digital Surface Model (DSM), which limits the interpretability of learned features and restricts classification accuracy. To address these issues, this study presents a Physics-Guided Adaptive Decoupling and Collaborative Enhancement Network (ADCE-Net) that embeds explicit geometric guidance into multimodal feature learning. In ADCE-Net, the DSM serves as an explicit geometric conditioning signal to guide feature decoupling, decomposing input representations into modality-shared semantic features (SSF) and modality-specific discriminative features (MSF), thereby mitigating cross-modal interference at an early stage. Based on this decomposition, an adaptive collaborative enhancement mechanism is designed using bidirectional cross-attention and dynamic gating to achieve context-aware mutual refinement between SSF and MSF, facilitating more effective utilization of cross-modal complementary information. Furthermore, a multi-level collaborative classification architecture is constructed to integrate multi-scale contextual representations, enhancing spatial consistency and boundary delineation. Extensive experiments on three benchmark datasets—Trento, Houston 2013, and Muufl Gulfport—demonstrate that ADCE-Net achieves overall accuracies of 99.69%, 97.37%, and 94.90%, respectively, surpassing multiple representative methods including support vector machines, 3D convolutional neural networks, transformer-based models, and recurrent neural networks. Noticeable improvements are also achieved for minority classes and classes with highly similar spectral signatures. The DSM-driven physics guidance boosts both classification performance and feature interpretability, providing a reliable and explainable paradigm for multimodal remote sensing classification. Full article

Rolling bearing vibration signals often exhibit strong nonstationarity and are susceptible to noise interference, which makes fault feature extraction and accurate diagnosis challenging under complex operating conditions. To address these issues, this paper proposes a fault diagnosis pipeline that sequentially combines an improved snow ablation optimizer (ISAO), variational generalized nonlinear mode decomposition (VGNMD), and a bidirectional temporal sequence fusion network (BiTSF-Net). Firstly, ISAO is used to optimize the key parameters of VGNMD, including the bandwidth penalty parameter and smoothing constraint parameter, with minimum envelope entropy as the fitness function. Secondly, the optimized VGNMD decomposes raw vibration signals into modal components, and the modal component with the minimum envelope entropy is selected to highlight fault-related impulsive characteristics. Thirdly, 11-dimensional time-domain statistical features are extracted from the selected optimal modal component to characterize bearing health states. Finally, these extracted features are used as the input to BiTSF-Net, which combines bidirectional temporal convolutional networks and bidirectional long short-term memory networks in a parallel structure to learn local transient features and temporal dependencies for fault classification. Experimental validation is conducted on the Case Western Reserve University dataset. Comparative results with convolutional neural networks, gated recurrent units, and long short-term memory networks demonstrate that the proposed pipeline achieves superior diagnostic performance, with an average accuracy of 99.63% and a maximum accuracy of 100%. These results confirm the effectiveness and robustness of the proposed ISAO-VGNMD feature extraction and BiTSF-Net classification pipeline for bearing fault diagnosis under complex nonstationary conditions. Full article

Sepsis is life-threatening organ dysfunction caused by a dysregulated host response to infection, making early detection critical for improving outcomes in intensive care units (ICUs). This study presents a retrospective comparative evaluation of deep learning architectures for predicting sepsis up to 6 h before the PhysioNet/Computing in Cardiology 2019 Challenge onset label using hourly structured electronic health record (EHR) variables, including vital signs, laboratory measurements, and demographics. Evaluated architectures include Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Bidirectional Long Short-Term Memory (Bi-LSTM), Temporal Convolutional Network (TCN), Transformer, and hybrid Convolutional Neural Network–Vision Transformer (CNN-ViT) models. Median imputation and class-weighted loss were applied to address missing values and severe class imbalance, while Shapley Additive Explanations (SHAP) and attention analyses were used as complementary interpretability approaches. Among the evaluated models, CNN-ViT achieved the strongest overall minority-class performance, with 88.25% accuracy, 0.7480 recall, a 0.454 F1-score, and a 0.48 area under the precision–recall curve (AUPRC), although the numerical gains over other advanced temporal and hybrid architectures were modest. Leave-one-unit-out evaluation further demonstrated relatively stable performance under internal distribution shifts. The results suggest that combining local feature extraction with temporal and attention-based modeling can improve early sepsis prediction from structured ICU data. However, the study represents a retrospective computational benchmark using a public dataset and does not constitute prospective clinical validation or real-world deployment assessment. Full article