Search Results (351)

Accurate crop mapping is essential for food security and water resource management in semi-arid North Africa. This study evaluated four machine learning algorithms for crop classification using Sentinel-2 NDVI time series in the Al Haouz region, Morocco with a time series of 12 dates (December 2023–May 2024) using 105,869 ground reference samples. Support Vector Machine (SVM) achieved the highest performance (macro F1-score = 0.80, Overall Accuracy = 81%), followed by XGBoost (0.79), Random Forest (0.79), and Decision Tree (0.71). Class-wise analysis revealed excellent discrimination for apricots (F1 = 0.99) due to distinctive spring phenology, while citrus showed the lowest accuracy (F1 = 0.61) due to confusion with olives. Dynamic Time Warping (DTW) analysis quantified phenological similarity between crops, revealing that classification confusion correlates with profile similarity. Temporal sensitivity analysis revealed that reducing acquisitions from 12 to 8 dates results in only 2.4% performance loss, offering significant operational advantages for resource-limited contexts. February–March acquisitions proved most discriminative, coinciding with peak vegetative differentiation. These findings provide practical recommendations for operational crop monitoring in semi-arid African regions facing water scarcity and food security challenges. Full article

Surface electromyography (sEMG), increasingly delivered through wireless wearable systems, is a key non-invasive tool for the objective monitoring of muscle activation during repetitive motor tasks. The clinical and longitudinal usefulness of wearable sEMG during rowing depends on the test–retest reliability of the parameters extracted from the signal during high-intensity, multi-muscle cyclic locomotor tasks. This study aimed to use advanced sEMG processing to quantify the between-session reliability of EMG-derived parameters (onset, offset, active duration, and peak position) across seven major muscles, to characterize the between-session similarity of ensemble-averaged activation waveforms, and to describe within-trial activation dynamics. Fifteen competitive rowers (10 males, five females; aged 14–22 years) performed two identical 2000 m all-out trials seven days apart, with sEMG recorded by a wireless wearable system. Reliability was assessed by ICC(A,1) with 95% CIs, SEM, MDC₉₅, CV%, and Bland–Altman analysis. The waveform similarity of the session ensemble cycles was quantified by Pearson correlation, cosine similarity, normalized cross-correlation maximum, and normalized dynamic time warping (DTW). Within-trial dynamics were assessed across ten consecutive stroke-count windows. Onset showed excellent reliability across all seven muscles (ICC = 0.943–0.995); offset, moderate-to-excellent (0.524–0.907); peak position, poor-to-excellent (0.114–0.948); active duration, poor-to-good (0.077–0.814). Ensemble-waveform similarity between sessions was high for each athlete across all muscles (Pearson r = 0.832–0.972; cosine similarity = 0.924–0.983), confirming that the individual activation fingerprint of the mean stroke cycle is stable over a 7-day interval. Both amplitude (FMPR) and active duration revealed a reproducible U-shaped within-trial pattern. These findings highlight the potential of wearable sEMG to provide reliable, personalized insights into rowing-specific muscle activation patterns, supporting more individualized monitoring and training optimization in rowers. Full article

AI-empowered smart sensor networks are driving Internet of Things (IoT) systems from passive data acquisition toward human-centric dynamic perception. In such scenarios, multimodal emotion recognition is expected to infer subtle affective states from heterogeneous audio, visual, and textual sensing streams. However, existing multimodal emotion recognition and emotion-oriented multimodal large-language-model (MLLM) methods still face several limitations for fine-grained emotion perception. Temporal asynchrony weakens cross-modal correspondence, redundant or heterogeneous features blur emotion-discriminative cues, unreliable sensing streams reduce robustness, and directly injecting all multimodal tokens into a large language model increases decoding redundancy. To address these issues, this paper proposes an Emotion-Enhanced Large Language Model (EELLM), a unified multimodal collaborative interaction framework for emotion perception in IoT-enabled smart sensor networks. Specifically, EELLM employs a dynamic time warping (DTW)-based Cross-Modal Alignment Module (DCAM) to mitigate temporal inconsistency, a Gaussian maximum mean discrepancy (MMD)-based Multimodal Feature Interaction Module (GMFIM) to disentangle shared and private representations and suppress fusion redundancy, a Modality Reliability-Aware Gating module (MRG) to adaptively weight heterogeneous modalities, and an Emotion-Salient Token Compression strategy (ESTC) to retain emotion-discriminative prefix tokens before instruction-guided LLaMA decoding. Extensive experiments on the trimodal MER2023 and MER2024 benchmarks and the visual-only DFEW benchmark demonstrate the effectiveness of EELLM. Under the adopted evaluation settings, EELLM achieves an F1 score of 0.9068 on MER2023, an average score of 67.10 on MER2024, and a UAR of 68.41 on DFEW, presenting competitive emotion perception performance across trimodal and visual-only benchmark settings. In addition, EELLM improves the recognition accuracy of the underrepresented disgust category on DFEW to 24.03%, showing better class-balanced emotion perception. These results indicate that EELLM provides an effective and efficient solution for fine-grained multimodal emotion perception in resource-sensitive intelligent sensing scenarios. Full article

Identifying inflow and infiltration (I/I) in urban sewer networks is challenging due to nonlinear hydraulic interactions and time-lag effects between river stages and pipeline water levels. This study proposes a multi-scale fusion correlation model integrating Dynamic Time Warping (DTW), Pearson correlation, and Spearman rank correlation coefficients. The framework evaluates water level sequences across temporal windows (2, 6, and 12 h) under flexible displacement constraints (1 and 2 h), utilizing a dynamic weight-allocation mechanism based on sequence volatility and data density. Leveraging a 12-month monitoring dataset from 513 sensing devices in Zhongshan City, China, the model was evaluated on 36 typical water-level sequences. It achieved a classification accuracy of 91.7% for low-correlation sequences and perfect accuracy (100%) for both medium- and high-correlation levels. Furthermore, practical deployment in the Shaxi–Qijiang Highway section and Yicheng Area successfully isolated multiple vulnerable pipe segments suffering from Baishiyong River (tidal) water intrusion, yielding an empirical field-verification hit rate of 83.3%. The results demonstrate that the proposed framework effectively overcomes temporal asynchrony and nonlinear hydraulic noise, providing a robust, data-driven diagnostic tool for urban drainage infrastructures. Full article

This paper presents an explainable defense framework against perception-layer and Man-in-the-Middle (MitM) attacks in Internet of Things (IoT)-based environmental hazard warning systems. These systems rely on heterogeneous sensors (gas, light, sound, temperature, and humidity) whose integrity is crucial for reliable environmental alerts. Perception-layer attacks such as spoofing, jamming, and data injection can compromise sensor readings, while MitM attacks threaten communication reliability. The proposed approach integrates incremental Dynamic Time Warping (DTW) for time-series anomaly detection with a tree- based ensemble classifier (XGBoost), in addition to Shapley Additive Explanations (SHAP) for interpretability. A comparative evaluation framework jointly considers detection performance and explanation quality through metrics including pre-registering a Casual Ground Truth based on network protocol localized Precision@ K feature overlap metrics (Q), instead of relying on subjective human-expert or global rank correlations to quantitively evaluate the explanation transparency. Experimental simulations using an authentic EdgeIIoT-2022 dataset under 3-fold forward–chaining cross-validation demonstrated high detection accuracy and moderated explainability scores. The results prove the framework’s ability to detect and explain adversarial behaviors in sensor networks, strengthening trust, transparency, and resilience in safety-critical IoT infrastructures. Full article

Crop monitoring is an important aspect of agricultural management, as it provides insights into cultivated area, crop health, growth patterns, and yields potential. Mapping cultivated areas and identifying crop types was historically conducted through field surveys and manual mapping, which are time-consuming and labor-intensive. Remote sensing classification has transformed large-scale land cover mapping, including crop identification. This work aims to: (1) compare the performance of Dynamic Time Warping (DTW) and two machine learning families (artificial neural networks and decision trees) for crop classification using Sentinel-2 data; (2) assess whether reflectance data, spectral indices, or both yield better classification results; and (3) evaluate the effect of hyperparameters on model performance. Among the DTW variants evaluated, dynamic time warping without a time constraint performed the best, with an overall accuracy of 0.921 using the combination of both reflectance and spectral indices. Most machine learning methods outperformed DTW. Although the convolutional neural network reached the highest single accuracy (0.948), the transformer was selected as the best model overall (accuracy of 0.944), as it combined a comparable accuracy with the lowest sensitivity to hyperparameter variations, making it a reliable option when testing machine learning architectures applied to crop mapping. This work also provides insights for model architecture development based on an exhaustive hyperparameter search for the machine learning models. Full article

Gait symmetry analysis has emerged as an important tool in rehabilitation engineering and neurological disorder assessment, as it provides clinically relevant indicators of mobility impairment and gait abnormalities. The proposed framework integrates gait symmetry variability, statistical gait features and Dynamic Time Warping (DTW)-based temporal alignment to enhance robustness against gait variations and irregular walking patterns. A hybrid feature vector comprising DTW similarity scores, the hybrid gait symmetry index (GSI), and statistical gait descriptors was employed to classify gait patterns into five categories: normal, slow, medium, fast, and abnormal. The system was implemented as a wearable edge-computing platform using an NI myRIO device equipped with a tri-axial Inertial Measurement Unit (IMU) mounted on the subject’s body. The onboard FPGA performs real-time signal preprocessing, GSI computation, feature extraction, constrained DTW matching, and gait classification using fixed-point streaming architectures and BRAM-based buffering. Meanwhile, the embedded ARM processor manages TCP/IP communication and transmits real-time gait information to a remote monitoring workstation via a WiFi interface for visualization and analysis. Operating at a clock frequency of 100 MHz, the complete architecture achieves an end-to-end processing latency of approximately 4 ms. The proposed FPGA-based implementation provides low-latency, energy-efficient, and real-time gait analysis, making it well suited for wearable rehabilitation systems, assistive healthcare devices, and continuous mobility monitoring applications. Full article

Wind power forecasting plays a crucial role in power dispatch and safety management of wind farms. However, the insufficient integration of multimodal heterogeneous data and the limitations of conventional graph construction strategies significantly restrict forecasting performance. Existing approaches either rely on simple feature aggregation, which cannot fully capture cross-modal dependencies, or adopt predefined or single-criterion graph construction methods that fail to characterize complex turbine relationships involving spatial, temporal, and nonlinear correlations. To address these challenges, this paper proposes a Multimodal Adaptive Fusion Graph Neural Network (MAF-GNN) for short-term wind power forecasting. First, a Modality-Aware Representation Learning (MARL) module is developed to extract informative multimodal representations by modeling modality-specific characteristics and cross-modal dependencies through attention-based fusion. Second, an Adaptive Graph Learning with Multi-Similarity (AGL-MS) module is introduced to parametrically integrate four complementary similarity priors—geographic distance, Dynamic Time Warping (DTW), Maximal Information Coefficient (MIC), and cosine similarity—for adaptive turbine correlation graph construction. Furthermore, a Credibility-Modulated Graph Convolutional Network (CM-GCN) is developed to reduce the influence of unreliable node information during message propagation. Extensive experiments conducted on the SDWPF dataset demonstrate that MAF-GNN reduces MAE by 14.0–21.3% compared with sequential baselines and achieves 5.3–10.2% improvement over spatiotemporal graph-based models. Ablation studies further verify the complementary effectiveness of each proposed module in improving forecasting performance. Full article

This study proposes a multiscale prediction method that couples the DTW-CEMHYD3D hydration kinetics model with Mori–Tanaka homogenization theory to establish a quantitative relationship between hydration microstructure evolution and macroscopic heat and mass transport properties of cement-based materials. First, dynamic time warping (DTW) is introduced to correct the mapping relationship between the hydration cycle number in CEMHYD3D and the real hydration time. Then, cement-based materials are regarded as multiphase composites, and a unified calculation method for the effective diffusion coefficient and thermal conductivity is established. The results show that the DTW-CEMHYD3D model can markedly improve the prediction accuracy of early-age hydration heat. The average relative error between the predicted effective diffusion coefficient and the N-phase sphere model is 0.67%, while the coefficients of determination for thermal conductivity prediction and relative diffusion coefficient prediction during hydration reach 0.9812 and 0.987, respectively. Parametric analysis indicates that a higher water-to-binder ratio significantly increases the relative diffusion coefficient, and this effect exhibits nonlinear enhancement with hydration age. The influence of fly ash content is age-dependent. An increase in the degree of saturation reduces the chloride diffusion coefficient but only slightly increases the thermal conductivity. The proposed method provides a reference for durability analysis and parameter determination in multiphysics coupling models of cement-based materials. Full article

Land subsidence is one of the most critical geological hazards in Hainan Province, primarily driven by groundwater overexploitation. This study integrates regional-scale SBAS-InSAR deformation results with groundwater observations from nine representative monitoring wells to investigate the spatiotemporal evolution of land subsidence and its groundwater-related response mechanisms in Hainan Province. Sentinel-1A imagery from 2019 to 2023 was used to derive LOS deformation time series, which were converted into vertical land subsidence using local incidence-angle correction under the assumption of negligible horizontal displacement. Seasonal and Trend decomposition using Loess (STL), Pearson correlation analysis, dynamic time warping (DTW), and lag correlation analysis were applied to separate multiscale signals and examine groundwater–subsidence responses in representative hydrogeological settings. The results indicate that (1) land subsidence in Hainan Province is mainly concentrated in coastal plains, with Haikou, Wenchang, and Danzhou identified as the main subsidence centers, where local annual subsidence rates exceed −50 mm/yr; (2) representative well-based analysis shows that groundwater-level decline is closely synchronized with cumulative subsidence in major subsidence-sensitive areas, with DTW distances consistently below 10, indicating high temporal consistency; long-term groundwater depletion is an important driver of cumulative subsidence in these representative areas; (3) lag correlation analysis reveals spatially heterogeneous lag responses of 1–6 months between groundwater-level fluctuations and land subsidence, with lag time and phase relationship closely related to aquifer structure, low-permeability layer distribution, and groundwater extraction intensity. This study provides a scientific basis for land subsidence mitigation and sustainable groundwater management in tropical island regions. Full article

The rapid development of new energy has caused a sharp increase in the stochasticity on the source side of the new power system (NPS), and extreme weather along with climate variability have also led to increased stochasticity in power demand on the load side; thus, how to achieve source-load matching and enable the load to track the source under the new situation is the key to the efficient operation of the power system. Aiming at the problem that existing load regulation potential evaluation mainly focuses on physical capacity, making it difficult to reflect users’ subjective willingness to participate as well as the dynamic changes in regulation capability under different operating scenarios, this paper proposes a two-stage dynamic profiling classification method for multi-type power user loads considering regulation willingness. First, an evaluation index system is constructed from three dimensions, physical reliability, execution reliability, and behavioral willingness, to achieve the unified characterization of the regulation capabilities of heterogeneous resources such as industrial loads and electric vehicle (EV) aggregators. Second, the DBSCAN algorithm is adopted to identify typical annual operating scenarios. Finally, the Dynamic Time Warping (DTW) distance is introduced to improve the K-Means++ algorithm, achieving the profiling classification of user regulation potential. This paper takes a certain NPS demonstration park as an example for verification, and the results show that the annual operating scenarios can be divided into 4 types of typical days; the proposed DTW-K-Means++ method has better classification performance compared with traditional Euclidean distance clustering, can effectively identify the differences and dynamic migration characteristics of user regulation potential under different operating scenarios, and stably classifies users into three types of profiles: deep regulation type, agile response type, and rigid constraint type. The research results aim to provide reliable data support for the refined dispatch of the power grid by effectively quantifying the dynamic migration patterns of heterogeneous resources under variable scenarios. Full article

Background/Objectives: The accuracy and reliability of automated clinical analyzers are fundamental to patient safety and effective medical decision-making. Traditional quality control (QC) methods, which rely on periodic manual calibration and reactive maintenance, are inherently limited by high latency and labor costs; furthermore, they fail to provide continuous, real-time monitoring. This paper introduces a novel hybrid ensemble learning framework for the automated quality inspection of medical devices through the analysis of time-series reaction curves. Methods: Our system integrates three heterogeneous anomaly detection paradigms: an Enhanced Dynamic Time Warping (DTW) detector for robust non-linear pattern matching, a Shape Template Matching (STM) detector that mimics expert clinical logic by analyzing morphological features in a normalized shape space, and a specialized Time-series Variational Autoencoder (TimeVAE) for deep representation learning. The outputs of these detectors are fused using a weighted ensemble strategy, which is specifically designed to prioritize the minimization of false negatives—a critical requirement in medical diagnostics. Results: We evaluate our framework on a comprehensive, multi-center real-world dataset comprising seven distinct biochemical assays. Experimental results demonstrate that our proposed method achieves superior performance, attaining a $0\%$ false negative rate on CRE and DBIL assays and outperforming all baseline methods on the other five datasets. An ablation study confirms the model’s robustness even with limited training data, and a comparative analysis against eight state-of-the-art baseline methods further validates the effectiveness of our domain-optimized ensemble approach. Conclusions: The system provides a robust, interpretable, and highly automated solution for transitioning from reactive maintenance to proactive, real-time quality assurance in clinical laboratories. Full article

IoT devices operate as integrated systems spanning hardware, firmware/software layers, and communication layers. In operational settings, many faults and performance degradations are emergent: they arise from cross-layer interactions, workload changes, and telemetry artifacts, rather than a single physics-of-failure mechanism. These realities make traditional supervised fault classification difficult because labeled fault data are rarely available during deployment, and the fault surface is unknown and a priori. This paper presents a practitioner-oriented, label-free fault detection and diagnosis (FDD) pattern based on Dynamic Time Warping (DTW) for rapid implementation in production IoT telemetry. The method represents a device as a sequence of overlapping episodes and organizes telemetry into interpretable layers (hardware sensors, communication health proxies, and software/firmware-derived KPIs). A reference library of regular episodes is built from an assumed-healthy training window; new episodes are scored using constrained DTW distances against this library, while retaining per-layer and per-channel contributions for attribution. We show that production performance depends strongly on operational parameterization, including episode length, DTW constraints, robust threshold learning, and temporal validation. Within a verified-healthy evaluation window, the tuned configuration achieves an AUROC of 0.97 for the temporally structured faults DTW is suited to (bias, drift, and interaction faults, with spikes detected at an AUROC of 0.93), detecting 100% of injected faults, with a mean delay under 25 min. We further show that constant-value (stuck-at) and missing-data (dropout) faults fall outside DTW’s shape-matching scope (AUROC about 0.66) and are better served by complementary variance- and missingness-based detectors, a consequence of DTW’s shape-matching scope rather than a parameter choice. This work contributes a system-level methodological framework for deploying DTW as an IoT fault-detection-and-diagnosis capability: an episode-and-layer architecture aligned with hardware, communication, and software/firmware ownership; a label-free reference library requiring only assumed-healthy data; per-layer and per-channel attribution for cross-domain triage; and a reproducible operational tuning procedure. Together, these deliver a fast-to-deploy, scalable, and accurate first-line detector for label-scarce IoT systems. Full article

Epileptic seizure prediction using an Electroencephalogram (EEG) can improve patient safety by enabling early intervention, yet most existing approaches focus on short prediction horizons with limited personalization or computational efficiency. This study presents a unified deep learning framework evaluated across ten pre-ictal prediction windows up to 300 min before seizure onset, using recordings from 161 patients and 1023 seizure events. At the 5 min horizon, the generalized model achieved 96.30% accuracy and 91.62% sensitivity. Two complementary personalization strategies are introduced: incremental transfer learning, which progressively fine-tunes the generalized model using patient-specific data, and Dynamic Time Warping (DTW)-based similarity personalization, which constructs a morphology-aware training cohort from a single reference seizure. Personalized models consistently outperform generalized baselines, particularly at longer horizons, with the DTW-based approach achieving 89.68% accuracy using only 70 similar patients. Reliable prediction is demonstrated up to 60 min prior to onset, while model optimization reduces computational complexity with minimal performance loss, supporting deployment in resource-constrained clinical environments. Full article

Microsatellites operate in highly dynamic thermal environments due to severe physical constraints, making temperature telemetry a critical onboard health indicator. Conventional threshold-based monitoring fails to distinguish normal operational mode transitions from genuine faults, causing excessive false alarms. To address this, we propose a two-stage framework integrating unsupervised thermal mode discovery with mode-specific deep learning prediction. Raw temperature telemetry is downsampled and segmented into orbital cycles. Unsupervised clustering identifies two nominal thermal regimes and four canonical fault-type libraries (step, spike, drift, and noise), each corresponding to distinct in-orbit failure mechanisms. For each nominal mode, a Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) is trained on 7-day historical windows to forecast 3-day temperature evolution. Post-downlink, incoming cycle mode is inferred via nearest-neighbor DTW classification; anomalies are flagged when prediction residuals exceed mode-adaptive thresholds. Validation on Macau Science Satellite-1B (MSS-1B, COSPAR 2023-069-B, NORAD 56732) in-orbit telemetry from a 41° inclination low-Earth orbit—where solar illumination dominates external thermal loading and internal heat from the data-communication module and scientific payload constitutes the primary internal thermal source—shows the method reduces anomaly flags by 96.6% and improves prediction mean absolute error by 51.3% compared to a non-classified global baseline under nominal operating conditions, correctly detecting a known operational transient while suppressing spurious alarms. A synthetic fault injection experiment with four anomaly types and five baseline methods further confirms the framework’s detection capability, achieving an overall F1 score of 0.725 vs. 0.258 for the global baseline—a 2.8× improvement driven primarily by a 4× precision gain. Sensitivity analysis reveals that the two-stage advantage is most pronounced for low-magnitude and short-duration faults, where mode-specific context is essential. This work advances microsatellite autonomous health management by providing reliable anomaly detection with quantified fault detection performance. Full article