Search Results (1,360)

Bridge health monitoring and machine learning are increasingly intertwined for civil engineers and artificial intelligence experts. Bridges’ poor health can result in severe outcomes if not addressed in time. Therefore, continuous monitoring is required to detect any anomaly or damage. Sensors, such as accelerometers, inclinometers, thermistors, etc., can help actively monitor these bridges. The signals from these sensors help record physiological activities. Such activities are helpful for anomaly detection, damage localization, and bridge health predictions with the help of machine learning algorithms. The proposed method extracts features from the dynamic response of a bridge to ambient excitation. It focuses on processing the signal received from different accelerometers installed on a steel railway bridge to determine the location of the damage and the level of the damage predictions. Initially, features are extracted from time-series data; then, they are fed to a deep neural network after some pre-processing. Normal and augmented data are used with different parameter tuning for results. Original data is also subdivided, and the effect of data slicing on the predictions is investigated. The results show that one-fourth of the slicing of the original data gives the best results for training and testing accuracy with a deep neural network. The results show that the reduced matrix representation, particularly the 40 × 40 feature slicing, improved the classification performance for the predefined bridge scenario classes under the considered experimental settings. For bridge scenario classification, the best reported accuracy was 93.54%, while for damage intensity classification the best reported accuracy was 98.21%. In the DNN-based optimizer comparison, the Adam optimizer achieved higher and more stable performance than Stochastic Gradient Descent (SGD), with test accuracies of 92.3% and 93.7% compared with 75.2% and 86.4%, respectively. It is also observed that the Adam optimizer outperformed Stochastic Gradient Descent (SGD) in terms of both damage localization and damage intensity estimation. Full article

The rapid evolution of financial technology demands sophisticated artificial intelligence systems capable of handling diverse challenges across multiple domains simultaneously. This paper presents a unified framework that integrates Proximal Policy Optimization (PPO) for robo-advisory systems, multi-scale time-series prediction models for high-frequency trading, in-context learning mechanisms for dynamic investment advisory, game-theoretic reasoning for competitive banking scenarios, and unified embeddings for cross-modal financial sentiment analysis. Our comprehensive framework addresses the critical gap in the existing literature where these technologies have been developed in isolation, failing to leverage their synergistic potential. Through extensive experimentation across multiple financial datasets and real-world scenarios, we demonstrate that our integrated approach achieves superior performance compared to specialized single-domain systems. Specifically, our framework shows a 23.7% improvement in portfolio optimization metrics, reduces prediction error in high-frequency trading by 31.2%, enhances investment recommendation accuracy by 18.9%, optimizes competitive banking strategies with a 27.4% increase in Nash equilibrium convergence speed, and improves sentiment analysis accuracy by 15.6% through cross-modal fusion. The theoretical foundation of our work establishes convergence guarantees for the integrated optimization problem, while our empirical results validate the practical applicability across diverse financial institutions. This research not only advances the state-of-the-art in financial AI but also provides a blueprint for developing comprehensive intelligent systems that can adapt to the complex, interconnected nature of modern financial markets. Full article

Artificial intelligence (AI) and machine learning (ML) algorithms possess the capability to accelerate the design of novel materials; however, their advancement in materials science is severely hindered by a fundamental deficit of experimental data, commonly referred to as data starvation. Unlike solution-based chemistry, where high-throughput (HT) technologies are a well-established standard, the automated synthesis of solid materials—particularly polymers and multicomponent composites—poses an extreme engineering challenge. Furthermore, the traditional, manual research model is inherently flawed by human bias, notably the systematic non-publication of negative results, which deprives AI models of critical boundary information regarding the design space. This paper is the first in a three-part review series defining the architecture of a fully automated, unbiased “data factory” for closed-loop discovery. This section focuses on the physical foundations of the HT workflow: experimental planning, automated synthesis, and material management. Emphasis is placed on the paradigm shift from classical, discrete Design of Experiments (DoE) to the novel concept of Continuous Gradient DoE. It reviews how robotic platforms utilizing precise gravimetric and volumetric feeders, integrated with extruders and in-line capillary rheology, enable the seamless, high-throughput manufacturing of thermoplastics and composites. Moreover, an innovative approach to sample logistics is presented, redefining classical storage patterns through the implementation of Continuous Material Management. This encompasses direct physical tagging (e.g., inkjet marking on continuous filaments or films), spool-based transport systems, and precise, real-time metadata mapping. As demonstrated, the integration of these systems yields an order-of-magnitude increase in productivity (generating tens of thousands of novel material variants annually), a radical reduction in unit costs, and the production of terabytes of standardized, machine-readable data. Establishing this reliable hardware and analytical infrastructure represents the essential first step toward unlocking the full potential of artificial intelligence in advanced materials engineering. Full article

Reservoir computing (RC) is a simple and highly efficient artificial neural network. For such a network, only the output connection weights need training, effectively reducing computational complexity. Optoelectronic time-delayed RC is typically based on an optoelectronic oscillator (OEO) with simultaneous broadband processing capabilities for both optical and electrical signals, while being readily implementable based on existing technologies. In this work, a new OEO-based RC (OEO-RC) using an electroabsorption modulated laser (EML) is designed, and the electroabsorption modulator (EAM) integrated in the EML serves as a nonlinear node. This scheme simplifies the architecture of an OEO-RC. And it is validated by using two typical tasks of the NARMA 10 time series prediction and the handwritten digit image recognition. Numerical results demonstrate that with optimized hyperparameters, this EML-based OEO-RC exhibits a comparable performance compared with some existing photonic time-delayed RCs. Full article

Modern artificial intelligence methods are increasingly used in power systems for renewable energy generation and electricity load forecasting. However, the limited interpretability of complex machine learning and deep learning models constrains their adoption in critical energy applications where transparency and trust are essential. Explainable Artificial Intelligence (XAI) provides tools for interpreting model behavior, yet its application to multivariate time series remains associated with significant methodological challenges. This paper presents a systematic review of XAI applications in solar power, wind power, and electricity load forecasting based on 154 peer-reviewed journal articles published between 2019 and 2026, identified through searches in Scopus, IEEE Xplore, ScienceDirect, and MDPI, following the PRISMA 2020 methodology. The review covers widely used forecasting architectures, including LSTMs, Transformers, and tree-based ensembles, as well as XAI methods. The analysis identifies a fundamental limitation of conventional XAI approaches for multivariate time series, referred to as the curse of dimensionality in XAI-based interpretation of time series, in which each time step is treated as an independent feature, resulting in explanations that are difficult to interpret in practice. To address this challenge, eight categories of XAI adaptations for time series forecasting are systematized. A classification of knowledge extraction mechanisms is proposed, including feature-level, temporal, regime-based, causal, diagnostic, model-level, and decision-support knowledge. The results demonstrate a gradual transition from explainability toward knowledge extraction, where XAI serves not only to explain individual forecasts but also to generate actionable knowledge about data, models, and energy processes. The review is limited to peer-reviewed English-language journal articles published between 2019 and 2026. The findings suggest that Knowledge Extraction represents a key mechanism for building trust in intelligent energy forecasting systems. Full article

Understanding vegetation sustainability is crucial for ensuring ecological security in dryland interior river systems. Focusing on the Manas River Basin in Xinjiang, our research extracted Landsat time-series data from 2000 to 2024 via Google Earth Engine, employing statistical approaches alongside Geodetector modeling to quantitatively evaluate the spatiotemporal dynamics of vegetation sustainability and its influencing factors. Our findings reveal that the basin’s Normalized Difference Vegetation Index (NDVI) displayed a significant upward trajectory (Sen’s slope = 0.010/yr, R² = 0.95, p < 0.01), with distinct temporal phases: the period 2000–2013 was characterized by rapid oasis expansion driven by cultivated land, while the period 2014–2024 was characterized by systematic vegetation improvement with a stabilizing land use pattern. Spatially, areas exhibiting extremely significant improvement accounted for 56.24% of the total basin area (concentrated mainly in artificial oases and the mid-mountain zone), and non-significant degradation accounted for only 1.89%. Land use type and soil texture were identified as the dominant spatial differentiation factors, followed by annual precipitation, with all pairwise factor interactions exhibiting enhancement effects. By identifying the optimal thresholds for vegetation growth (annual average temperature of 0.82–3.96 °C, elevation of 1826–2598 m, and loamy sand), this study defines the boundaries for sustainable vegetation development. These findings deliver a theoretical foundation for zonation management and habitat rehabilitation planning, supplying decision-making support for safeguarding regional ecological security and fostering sustainable development of oasis systems in arid Central Asia. Full article

This study investigates the optimal sizing of a grid-connected hybrid renewable energy microgrid. The optimization, employing a multi-objective artificial hummingbird algorithm (MOAHA) combined with fuzzy decision-making (FDM), aims to minimize the cost of energy while maximizing renewable energy utilization. MOAHA is used to generate a well-distributed Pareto front, while FDM identifies the preferred configuration under the specified decision preference. However, the preferred solution obtained is a static configuration. Most existing studies focus on such static planning, with limited attention to dynamic mapping and validation of the optimized configuration. To bridge this gap, a digital twin architecture is further proposed for hybrid renewable energy microgrids, and a corresponding digital twin system is also developed to achieve virtual representation, dynamic state mapping, operational visualization, and configuration validation. An industrial park microgrid in Urumqi is selected as the case study. The results indicate that the preferred configuration achieves a cost of energy of 0.065 $/kWh and a renewable energy utilization of 0.675. Comparative results demonstrate that the proposed framework outperforms benchmark methods in terms of convergence, solution diversity, and computational efficiency. Meanwhile, the developed digital twin system effectively supports time-series state visualization and feasibility checking of the optimized configuration. Full article

The forecasting of road surface conditions is a pivotal component for intelligent transportation systems, in terms of supporting maintenance planning, safety and mobility management. The increasing availability of large-scale monitoring data, collected from passenger vehicle fleets, enables the development of data-driven forecasting approaches. However, systematic comparisons between classical time-series models and machine-learning methods in this context remain limited. The proposed benchmarking framework evaluates direct road surface roughness forecasts at 1-, 7-, 14-, 30-, and 90-day horizons using multi-year vehicle-derived data collected across heterogeneous road segments. Daily roughness indicators are derived from raw measurements and modeled following a consistent, segment-wise experimental protocol. The proposed analysis involves the evaluation of multiple machine-learning regressors including Ridge, Random Forest and Gradient Boosting which are trained on lagged observations and rolling statistics. Performance of the models is assessed using two error metrics: unweighted and uncertainty-aware weighted. Findings indicate significant variations in predictive accuracy and robustness across models and segments, emphasizing the influence of feature-based learning strategies and data-quality weighting. The research provides a scalable and transparent methodology for evaluating forecasting models on vehicle-based road monitoring data, contributing practical guidance for the deployment of artificial intelligence in Intelligent Transport Systems (ITSs). Full article

Non-invasive methods used for PH detection in clinical practice have several limitations. The combination of high spatiotemporal sensitivity magnetocardiography (MCG) and artificial intelligence algorithms may offer an accurate approach for PH detection. In this study, we develop a convolutional neural network (CNN) model based on the 64-channel MCG time-series data. This exploratory study enrolled patients undergoing 64-channel MCG, including right-heart-catheterization confirmed PH patients and symptomatic controls with low echocardiographic probability of PH. After data preprocessing, a temporal CNN integrating MCG signals with age, sex, and body mass index was developed and compared with conventional machine learning models. The CNN model achieved strong discrimination, with area under the curve (AUC) values of 0.939 (95% confidence interval [CI]: 0.913–0.961) in the development out-of-fold evaluation and 0.974 (95% CI: 0.944–0.994) in the hold-out test set, outperforming conventional machine learning models. Decision curve analysis showed the greatest net benefit at clinically relevant thresholds. Attribution analysis indicated that spatial QRS morphology redistribution contributed substantially to PH classification. The temporal CNN model based on raw 64-channel MCG signals showed promising performance for non-invasive PH detection and outperformed conventional machine learning approaches in this exploratory single-center cohort enriched for PAH and CTEPH. Full article

This work aims to determine whether pre-seismic ground dislocations extracted from interferometric satellite synthetic aperture radar (InSAR) imagery contain predictive information for distinguishing between two magnitude classes of an upcoming earthquake, assuming that an earthquake’s occurrence is already imminent. For this reason, twenty-three earthquakes of various magnitudes that occurred in Greece during the year 2020 were analyzed using SAR data to construct a time-series of five six-day InSAR images for each earthquake, spanning a total 24-day period before the earthquake. For each earthquake, four ground dislocation images covering the area around each earthquake were derived from the interferograms, each showing the dislocation during a six-day time interval. Images showing the total ground dislocation during the entire 24-day period before the earthquake were also produced by fusing the four images. Three machine learning classifiers were used to relate the earthquake magnitude class to pre-seismic ground dislocations. High accuracies were obtained with both support vector machine (SVM) and random forest (RF), yet they were highly dependent on the type of images used. In a subsequent analysis, five regression models were applied to estimate the earthquakes’ epicenters from dislocation images. The results reveal that the proposed approach is able to achieve well-localized epicentral area prediction, indicating the potential predictive value of this tool for seismic hazard assessment and emergency planning. Full article

Wildfires are a major ecological disturbance in Mediterranean ecosystems, affecting vegetation dynamics and landscape resilience. However, the relative importance of environmental factors controlling post-fire vegetation recovery remains insufficiently quantified at regional scales. This study investigates the drivers of vegetation regeneration following 45 large wildfires (>1000 ha) that occurred across Greece between 2017 and 2023. Vegetation recovery was assessed using Moderate Resolution Imaging Spectroradiometer (MODIS) Normalized Difference Vegetation Index (NDVI) time series, while environmental predictors included burn severity metrics, soil moisture at four depth layers derived from the European Centre for Medium-Range Weather Forecasts Reanalysis 5-Land (ERA5-Land) climate reanalysis dataset, terrain characteristics (slope and aspect), land cover, and time since fire. All variables were harmonized at the fire-perimeter scale and analyzed using two complementary modeling approaches: multiple linear regression and artificial neural network (ANN) modeling. The linear regression model explained approximately 38% of the variability in vegetation recovery (R² = 0.38), while the ANN showed improved predictive performance, indicating the presence of complex relationships among predictors. Across the applied modeling approaches, burn severity, topographic conditions, and soil moisture emerged as important drivers of post-fire vegetation recovery. In particular, Soil Moisture Layer 1 (SM₁) showed the strongest positive association with NDVI recovery, followed by Soil Moisture Layer 4 (SM₄), highlighting the importance of water availability for vegetation regeneration under post-fire conditions. Overall, the results confirm that vegetation recovery is strongly controlled by environmental conditions rather than time alone. The findings contribute to a better understanding of post-fire ecosystem dynamics in Mediterranean landscapes and provide a useful framework for supporting wildfire management and restoration planning. Full article

The growing complexity of software-defined automotive systems generates massive heterogeneous sensor and ECU data during real and virtual validation, and conventional rule-based analysis of such multivariate time series struggles under dynamic operating conditions, noise, and diverse fault scenarios. Deep learning-based anomaly detection has shown promising performance, yet existing approaches remain limited by static thresholds, insufficient robustness, and reduced interpretability. This study proposes an adaptive framework for intelligent fault detection in test recordings of automotive software systems (ASSs), integrating deep denoising autoencoders (DAEs), adaptive Gaussian thresholding, and explainable artificial intelligence (XAI) techniques. Four DAE architectures (ANN-, RNN-, GRU-, and LSTM-DAE) are systematically evaluated under different noise levels, system versions, and fault conditions, with detection thresholds that adapt dynamically to the statistical behavior of the reconstructed signals, thereby reducing false alarms under varying operating conditions. The framework was evaluated using real-world test recordings from IAV and Hardware-in-the-Loop (HIL)-based digital test drives, where ANN-DAE achieved the most robust detection performance, with F1-scores of 93.91% and 96.39% on the real and virtual test-drive data, respectively. Furthermore, the integration of XAI improved the transparency of anomaly interpretation at the signal level. Overall, the proposed framework shows strong potential for intelligent anomaly detection and quality assurance in safety-critical automotive systems. Full article

Topological data analysis (TDA) has evolved into a flexible and robust paradigm for obtaining qualitative, geometry-inspired insights from high-dimensional, noisy, and complex data. Grounded in algebraic topology, geometry, statistics, and machine learning (ML), TDA provides multiscale descriptions through persistent homology, Mapper (a graph-based method that summarizes the shape of high-dimensional data), and related topological signatures that are often inaccessible to standard linear and metric methods. In recent years, and especially during 2024–2025, TDA has expanded rapidly across science, engineering, biomedical research, and socio-economic studies, while also being integrated with modern learning paradigms such as deep learning (DL) and graph learning. This survey summarizes recent developments in TDA using a carefully selected set of articles, with emphasis on 2024–2025. We first present the mathematical and computational foundations of TDA, covering simplicial complexes, filtrations, persistent homology, the Mapper algorithm, and computational advances such as data simplification, stability, and efficiency. We then review applications in time series and dynamical systems, biomedical imaging and precision medicine, engineering and physical sciences, finance and risk analysis, DL and interpretability, and security and critical infrastructure systems. Throughout, we highlight how TDA can extract informative features, function as a model component, and provide a conceptual lens for studying complex systems. However, the survey also emphasizes recurrent failure patterns: TDA performance is highly sensitive to filtration, embedding, and vectorization choices; aggressive simplification can dilute or remove informative topological signals; and integration into standard ML workflows still lacks uniform validation and reporting protocols. We conclude by outlining key challenges—including scalability, statistical foundations, interpretability, and compatibility with rapidly evolving artificial intelligence (AI) paradigms—and by identifying directions for future research. The survey also provides a unifying design perspective for TDA systems, highlighting methodological trade-offs and emerging research directions for integrating topology with modern ML. Full article

Accelerometer sensors and artificial intelligence (AI) are reshaping automated behavior monitoring in precision livestock management, yet their joint deployment on extensive rangelands is constrained by energy and bandwidth budgets. Low-Power Long-Range Wide-Area Network (LoRaWAN) collars address these constraints by compressing the raw tri-axial signal on the device into a single scalar per reporting interval, the Motion Index (MI). This onboard compression preserves enough signal to separate active behaviors but discards the per-axis and frequency content that fine-grained classification typically relies on. On a dataset of 9222 labeled observations from 24 cows across four breeds, MI distinguishes walking from grazing reliably but fails to separate ruminating from resting; both correspond to a stationary animal and yield near-zero, statistically indistinguishable distributions. Earlier MI-only models reached only about 65% four-class accuracy, and ruminating was commonly merged into resting. We show that much of this loss can be recovered by treating the MI stream as a time series. Session-aware lag features, rolling statistics, and an autoregressive previous-behavior feature lift four-class macro-F1 from 0.647 to 0.94, with per-class F1 of 0.95 for ruminating and 0.92 for resting (and at least 0.92 for every behavior). In autonomous deployment the previous behavior must be predicted rather than observed; for this setting we add a Viterbi sequence-decoding step that combines the classifier’s per-step outputs with a learned behavior-transition model, recovering a substantial part of the ruminating signal from the activity stream alone while keeping walking and grazing reliable. The gain is consistent across seven classifiers and four genetically distinct breeds, indicating that it is driven by the features rather than by a specific model. Full article

This study investigated the optoelectronic synaptic properties of amorphous gallium oxide (GaO_x) thin films for low-power physical reservoir computing (PRC) applications. The fabricated devices were irradiated with time series UV-C light to characterize the paired pulse facilitation (PPF) index, a fundamental synaptic property governed by transient photocurrent dynamics. Furthermore, the short-term memory (STM) capacity and parity check (PC) nonlinearity were quantitatively evaluated as essential PRC performance metrics, alongside a practical demonstration using a handwritten digit recognition task. The experimental results revealed a high PPF index when the width and interval of the input light pulses were comparable to or shorter than the inherent photocurrent time constants of the device. Although the evaluated nonlinearity was lower than that of conventional optoelectronic artificial synapses based on other semiconductor materials, the GaO_x device exhibited a comparable short-term memory capacity. Consequently, the reservoir layer achieved a high classification accuracy of approximately 90% in the handwritten digit recognition task. As these performance metrics were higher than those of the annealed sample, the device without annealing proved to be more suitable for PRC applications. These findings indicate that the amorphous GaO_x thin film device holds significant potential to serve as a robust, UV-C-responsive edge artificial intelligence (AI) sensor in harsh environments, such as outer space. Full article