Search Results (1,448)

With the increasing frequency extreme weather events associated with climate change, real-time monitoring of rainfall intensity is critical for water resource management, disaster warning, and other applications. Traditional methods, such as ground-based rain gauges, radar, and satellites, face challenges like high costs, low resolution, and monitoring gaps. This study proposes a novel real-time rainfall intensity monitoring method based on deep learning and audio signal processing, using acoustic features from rainfall to predict intensity. Conducted in the semi-arid region of Northwest China, the study employed a custom-designed sound collection device to capture acoustic signals from raindrop-surface interactions. The method, combining multi-feature extraction and regression modeling, accurately predicted rainfall intensity. Experimental results revealed a strong linear relationship between sound pressure and rainfall intensity (r = 0.916, R² = 0.838), with clear nonlinear enhancement of acoustic energy during heavy rainfall. Compared to traditional methods like CML and radio link techniques, the acoustic approach offers advantages in cost, high-density deployment, and adaptability to complex terrain. Despite some limitations, including regional and seasonal biases, the study lays the foundation for future improvements, such as expanding sample coverage, optimizing sensor design, and incorporating multi-source data. This method holds significant potential for applications in urban drainage, agricultural irrigation, and disaster early warning. Full article

Accurate quantification of field-grown rice seedlings is essential for evaluating yield potential and guiding precision field management. Unmanned aerial vehicle (UAV)-based remote sensing, with its high spatial resolution and broad coverage, provides a robust basis for accurate seedling detection and population density estimation. However, in previous studies, UAVs were typically employed at relatively low altitudes, which provided high-resolution imagery and facilitated seedling recognition but limited efficiency. To enable large-area monitoring, higher flight altitudes are required, which reduces image resolution and adversely affects rice seedling recognition accuracy. In this study, UAVs were flown at a height of 30 m, and the resulting lower-resolution imagery, combined with the small size of seedlings, their dense spatial distribution, and the complex field background, necessitated algorithmic improvements for accurate detection. To address these challenges, we propose an enhanced You Only Look Once version 8 nano (YOLOv8n)-based detection model specifically designed to improve seedling recognition under high-altitude UAV imagery. The model incorporates an improved Bidirectional Feature Pyramid Network (BiFPN) for multi-scale feature fusion and small-object detection, a Global-to-Local Spatial Aggregation (GLSA) module for enriched spatial context modeling, and a Content-Guided Attention Fusion (CGAFusion) module to enhance discriminative feature learning. Experiments on high-altitude UAV imagery demonstrate that the proposed model achieves an mAP@0.5 of 94.7%, a precision of 91.0%, and a recall of 91.2%, representing a 2.3% improvement over the original YOLOv8n. These results highlight the model’s innovation in handling high-altitude UAV imagery for large-area rice seedling detection, demonstrating its effectiveness and practical potential under complex field conditions. Full article

Object detection systems deployed in industrial environments are often constrained by limited annotation budgets, severe class imbalance, and heterogeneous visual conditions. Active learning (AL) aims to reduce labeling costs by selecting informative samples; however, existing strategies struggle to simultaneously ensure robust performance, rare-class coverage, and stability under realistic industrial constraints. In this work, we propose a rarity-aware, stratified AL framework for industrial object detection that explicitly aligns sample selection with class imbalance and annotation efficiency. The method relies on a composite image-level score that jointly captures model uncertainty, informativeness, and complementary diversity cues, while adaptively emphasizing rare classes. Crucially, a stratified querying mechanism is introduced to explicitly regulate class-wise sample allocation during selection, playing a key role in improving performance stability and rare-class coverage under severe imbalance, without sacrificing global informativeness. The proposed approach operates purely at the data-selection level, making it detector-agnostic and directly applicable to modern object detection pipelines. Experiments conducted on two real-world industrial datasets involving lobster and snow crab parts, using YOLOv10 and YOLOv12, demonstrate improved training stability and annotation efficiency across balanced, imbalanced, and noisy settings over multiple active learning cycles up to 15% labeled data. Complementary comparisons with fully supervised training further show that using only 45–65% of the labeled data is sufficient to retain more than 97% of full-supervision mAP@50 and over 90% of mAP@50:95. Full article

Exposure to Particulate Matter (PM) is linked to respiratory and cardiovascular diseases, certain types of cancer, and accounts for approximately seven million premature deaths globally. While governments and organizations have implemented various strategies for Air Quality (AQ) such as the deployment of Air Quality Monitoring Networks (AQMN), these networks often suffer from limited spatial coverage and involve high installation and maintenance costs. Consequently, the implementation of networks based on Low-Cost Sensors (LCS) has emerged as a viable alternative. Nevertheless, LCS systems have certain drawbacks, such as lower reading precision, which can be mitigated through specific calibration models and methods. This paper presents the results and conclusions derived from simultaneous PM₁₀ and PM_2.5 monitoring comparisons between LCS nodes and a T640X reference sensor. Additionally, Relative Humidity (RH), temperature, and absorption flow measurements were collected via an Automet meteorological station. The monitoring equipment was installed at the Faculty of Environment of the Universidad Distrital in Bogotá. The LCS calibration process began with data preprocessing, which involved filtering, segmentation, and the application of FastDTW. Subsequently, calibration was performed using a variety of models, including two statistical approaches, three Machine Learning algorithms, and one Deep Learning model. The findings highlight the critical importance of applying FastDTW during preprocessing and the necessity of incorporating RH, temperature, and absorption flow factors to enhance accuracy. Furthermore, the study concludes that Random Forest and XGBoost offered the highest performance among the methods evaluated. While satellites map city-wide patterns and MAX-DOAS enables hourly source attribution, our calibrated LCS network supplies continuous, street-scale data at low CAPEX/OPEX—forming a practical backbone for sustained micro-scale monitoring in Bogotá. Full article

The Philippines experiences intense rainfall but has limited ground-based monitoring infrastructure for flood prediction. Satellite rainfall products provide broad coverage but contain systematic biases that reduce operational usefulness. This study evaluated whether three correction methods—Quantile Mapping (QM), Random Forest (RF), and Hybrid Ensemble—maintain accuracy when applied to future periods with substantially different rainfall characteristics. Using the Cagayan de Oro River Basin in Northern Mindanao as a case study, models were trained on 2019–2020 data and tested on an independent 2021 period exhibiting 120% higher mean rainfall and 33% increased rainy-day frequency. During training, Random Forest and Hybrid Ensemble substantially outperformed Quantile Mapping (R² = 0.71 and 0.76 versus R² = 0.25 for QM). However, when tested under realistic operational constraints using seasonally incomplete calibration data (January–April only), performance rankings reversed completely. Quantile Mapping maintained operational reliability (R² = 0.53, RMSE = 5.23 mm), while Random Forest and Hybrid Ensemble failed dramatically (R² dropping to 0.46 and 0.41, respectively). This demonstrates that training accuracy poorly predicts operational reliability under changing rainfall regimes. Quantile Mapping’s percentile-based correction naturally adapts when rainfall patterns shift without requiring recalibration, while machine learning methods learned magnitude-specific patterns that failed when conditions changed. For flood early warning in data-limited basins with equipment failures and variable rainfall, only Quantile Mapping proved operationally reliable. This has practical implications for disaster risk reduction across the Philippines and similar tropical regions where standard validation approaches may systematically mislead model selection by measuring calibration performance rather than operational transferability. Full article

The adoption of novel technologies such as Unmanned Aerial Vehicles (UAVs) in Search and Rescue (SAR) operations remains limited. As a result, their full potential is not yet realized. Although UAVs have been deployed on an ad hoc basis, typically under manual control by dedicated operators, assisted and fully autonomous configurations remain largely unexplored. In this study, three SAR frameworks are systematically evaluated within a unified benchmarking framework: conventional ground missions, UAV-assisted missions, and fully autonomous UAV operations. As the key performance indicator, the target localization time was quantified and used as the means of comparison amongst frameworks. The conventional and assisted frameworks were experimentally tested through physical hardware in a controlled outdoor setting, wherein simulated callouts occurred via rescue teams. The autonomous swarm framework was simulated in the form of a multi-agent Reinforcement Learning (RL) method via the use of the Proximal Policy Optimization (PPO) algorithm. This enabled the optimization of the decentralized cooperative actions that could occur for efficient exploration of a partially observed three-dimensional environment. Our results demonstrated that the autonomous swarm significantly outperformed the conventional and assisted approaches in terms of speed and coverage. Finally, a detailed depiction of the framework’s integration into an operational system is provided. Full article

Accurate prediction of individual treatment effects in survival analysis is often complicated by the presence of competing risks and the inherent unobservability of counterfactual outcomes. While machine learning models offer improved discriminative power, they typically lack rigorous guarantees for uncertainty quantification, which are essential for safety-critical clinical decision-making. In this paper, we introduce CONFIDE (CONFormal Inference for Distribution-free Estimation), a novel framework that bridges causal inference and conformal prediction to construct valid prediction sets for cause-specific cumulative incidence functions. Unlike traditional confidence intervals for population-level parameters, CONFIDE provides individual-level prediction sets for time-to-event outcomes, which are more clinically actionable for personalized treatment decisions by directly quantifying uncertainty in future patient outcomes rather than uncertainty in population averages. By integrating semi-parametric hazard estimation with targeted bias correction strategies, CONFIDE generates calibrated prediction sets that cover the true potential outcome with a user-specified probability, irrespective of the underlying data distribution. We empirically validate our approach on four diverse medical datasets, demonstrating that CONFIDE achieves competitive discrimination (C-index up to 0.83) while providing robust finite-sample marginal coverage guarantees (e.g., 85.7% coverage on the Bone Marrow Transplant dataset). We note two key limitations: (1) coverage may degrade under heavy censoring (>40%) unless inverse probability of censoring weighted (IPCW) conformal quantiles are used, as demonstrated in our sensitivity analysis; (2) while the method guarantees marginal coverage averaged over the covariate distribution, conditional coverage for specific covariate values is theoretically impossible without structural assumptions, though practical approximations via locally-adaptive calibration can improve conditional performance. Our framework effectively enables trustworthy personalized risk assessment in complex survival settings. Full article

(1) Background: The convergence of Big Data and the Internet of Things (IoT) is transforming digital accounting from retrospective documentation into real-time operational intelligence. This systematic review examines how Industry 4.0 technologies—artificial intelligence (AI), blockchain, edge computing, and digital twins—transform accounting practices through intelligent automation, continuous compliance, and predictive decision support. (2) Methods: The study synthesizes 176 peer-reviewed sources (2015–2025) selected using explicit inclusion criteria emphasizing empirical evidence. Thematic analysis across seven domains—conceptual foundations, system evolution, financial reporting, fraud detection, audit transformation, implementation challenges, and emerging technologies—employs systematic bias-reduction mechanisms to develop evidence-based theoretical propositions. (3) Results: Key findings document fraud detection accuracy improvements from 65–75% (rule-based) to 85–92% (machine learning), audit cycle reductions of 40–60% with coverage expansion from 5–10% sampling to 100% population analysis, and reconciliation effort decreases of 70–80% through triple-entry blockchain systems. Edge computing reduces processing latency by 40–75%, enabling compliance response within hours versus 24–72 h. Four propositions are established with empirical support: IoT-enabled reporting superiority (15–25% error reduction), AI-blockchain fraud detection advantage (60–70% loss reduction), edge computing compliance responsiveness (55–75% improvement), and GDPR-blockchain adoption barriers (67% of European institutions affected). Persistent challenges include cybersecurity threats (300% incident increase, $5.9 million average breach cost), workforce deficits (70–80% insufficient training), and implementation costs ($100,000–$1,000,000). (4) Conclusions: The research contributes a four-layer technology architecture and challenge-mitigation framework bridging technical capabilities with regulatory requirements. Future research must address quantum computing applications (5–10 years), decentralized finance accounting standards (2–5 years), digital twins with 30–40% forecast improvement potential (3–7 years), and ESG analytics frameworks (1–3 years). The findings demonstrate accounting’s fundamental transformation from historical record-keeping to predictive decision support. Full article

The Global Navigation Satellite System-Scattering (GNSS-S) radar has a wide coverage and strong concealment, enabling large-scale and long-term monitoring of sea surface targets. However, its signal power is extremely low and susceptible to sea clutter interference. To address the challenge of detecting and tracking moving targets in complex maritime environments using low-resolution radar, this paper proposes a method for extracting moving target trajectories from GNSS-S radar under low signal-to-noise ratio (SNR) conditions. The method constructs a feature plane consisting of statistical and polarization characteristics, based on the unique distribution of different motion targets in this plane, the distinction between sea clutter and multi-motion targets is carried out using machine learning algorithms, and finally the trajectory association of the targets is achieved by the Kalman filter, and the tracking correctness can reach more than 93.89%. Compared with the tracking method based on high-resolution imaging targets, this technique does not require complex imaging operations, and only requires certain processing on the radar echo, which has the advantages of easy operation and high reliability. Full article

With the growing global popularity of Android apps, ensuring their quality and reliability has become increasingly important, as low-quality apps can lead to poor user experiences and potential business losses. A common approach to testing Android apps involves automatically generating event sequences that interact with the app’s graphical user interface (GUI) to detect crashes. To support this, we developed ACE (Android Crawler), a tool that systematically generates events to test Android apps by automatically exploring their GUIs. However, ACE’s original heuristic-driven exploration can be inefficient in complex application states. To address this, we extend ACE with a deep reinforcement learning-based crawling strategy, called Reinforcement Learning Strategy (RLS), which tightly integrates with ACE’s GUI exploration process by learning to intelligently select GUI components and interaction actions. RLS leverages the Proximal Policy Optimization (PPO) algorithm for stable and efficient learning and incorporates an action mask to filter invalid actions, thereby reducing training time. We evaluate RLS on 15 real-world Android apps and compare its performance against the original ACE and three state-of-the-art Android testing tools. Results show that RLS improves code coverage by an average of 2.1% over ACE’s Nearest unvisited event First Search (NFS) strategy and outperforms all three baseline tools in terms of code coverage. Paired t-test analyses further confirm that these improvements are statistically significant, demonstrating its effectiveness in enhancing automated Android GUI testing. Full article

Water quality monitoring is essential for assessing a freshwater ecosystem’s status. This knowledge is indispensable for selecting restoration measures to ensure the provision of ecosystem services and sustainable growth of human communities. Remote sensing (RS) has proven to be effective for this purpose, offering broad coverage and high temporal and spatial resolution, which is particularly important for small water bodies. In this study, UAV-based multispectral imagery is employed to estimate key water quality parameters, namely, Chlorophyll-a (Chl-a) and turbidity, which are relevant to global and national legislation and policies. Machine learning models were developed using the support vector regression (SVR) algorithm. The Chl-a model resulted in an R² value of 0.49 and an RMSE of 0.24 μg/L, while the turbidity model resulted in an R² value of 0.70 and an RMSE of 0.38 Formazin Nephelometric Unit (FNU). These models enabled the generation of detailed spatial distribution maps of water quality indicators for the studied river. The proposed approach provides valuable information that supports monitoring for both pressure and restoration impacts, promoting the sustainability of freshwater ecosystems. Full article

The survival and growth of mangroves along coastal China is threatened by invasive smooth cordgrass (Spartina alterniflora). Due to the high mortality and frequent replanting of mangrove trees and the impacts of invasive smooth cordgrass, the exact mangrove forest area in Zhejiang Province, China, is still unclear. Based on provincial-scale fine-resolution Unmanned Aerial Vehicle (UAV) imagery and a large number of field survey plots, this study mapped the distribution of mangroves and smooth cordgrass in 2023 using three machine learning classifiers, including Classification and Regression Tree (CART), Convolutional Neural Networks (CNNs), and Support Vector Machine (SVM). The accuracy assessment indicated that the CNN algorithm was superior to the other two algorithms and yielded an overall accuracy and Kappa coefficient of 97% and 0.96, respectively. The total areas of mangrove forest and smooth cordgrass were 140.83 ha and 52.95 ha, respectively, in 2023 in Zhejiang Province. The mangrove forest area was mostly concentrated in Yuhuan, Dongtou, Yueqing, and Longgang districts. The mean canopy coverage of mangrove trees was only 36.41%, with lower than 20% coverage in all northern and some central districts. At the spatial scale, the mangrove trees showed a scattered distribution pattern, and over 70.04% of the planting area had canopy coverage lower than 20%. Smooth cordgrass has widely invaded all 11 districts, accounting for about 13.7% of the total planting area of mangrove trees. Over 67.3% and 85.4% of the planting areas have been occupied by smooth cordgrass in Wenling and Jiaoxiang districts, respectively, which necessitates an intensive anthropogenic intervention to control its spread in these districts. Our study provides more accurate monitoring of the mangrove and smooth cordgrass distribution areas at a provincial scale. The findings will help guide the replanting and management activities of mangrove trees, control planning for smooth cordgrass, and provide a data basis for the accurate estimation of carbon stock for mangrove forests in Zhejiang Province. Full article

AIS, the global ship identification standard, is vulnerable to outages, coverage gaps, and deliberate deactivation, highlighting the need for independent ship identification methods. Optical imaging satellites offer a global, non-compliance-dependent solution. Paired with deep neural networks trained on satellite imagery of ships, it has become possible to determine the identity of specific vessels, based on their unique visual signatures. This enables re-identification, even when cooperative signals like AIS are unavailable or unreliable. Our paper builds on previous work with neural networks for ship identification, and presents an approach based on contrastive self-supervised learning. Self-supervised learning allows for existing, unlabeled, and freely available satellite imagery datasets with ships, to be leveraged for model training. Using these self-supervised models to initialize ship identification training results in almost 32% higher accuracy compared to baseline models. In one case equivalent to doubling the labeled training data. This lowers the threshold for optical ship identification from space by reducing dependence on large labeled datasets. This scalability is crucial for making space-based ship identification viable for global maritime situational awareness. Full article

This paper proposes a large-scale, self-healing multipoint fiber Bragg grating (FBG) sensor network that employs reinforcement learning (RL) techniques to enhance the resilience and efficiency of optical wireless communication networks. The system features a mesh-structured, self-healing ring-mesh architecture employing 2 × 2 optical switches, enabling robust multipoint sensing and fault tolerance in the event of one or more link failures. To further extend network coverage and support distributed deployment scenarios, free-space optical (FSO) links are integrated as wireless optical backhaul between central offices and remote monitoring sites, including structural health, renewable energy, and transportation systems. These FSO links offer high-speed, line-of-sight connections that complement physical fiber infrastructure, particularly in locations where cable deployment is impractical. Additionally, RL-based artificial intelligence (AI) techniques are employed to enable intelligent path selection, optimize routing, and enhance network reliability. Experimental results confirm that the RL-based approach effectively identifies optimal sensing paths among multiple routing options, both wired and wireless, resulting in reduced energy consumption, extended sensor network lifespan, and improved transmission delay. The proposed hybrid FSO–fiber self-healing sensor system demonstrates high survivability, scalability, and low routing path loss, making it a strong candidate for future services and mission-critical applications. Full article

As an essential blue carbon ecosystem, mangroves play a vital role in coastal protection, biodiversity conservation, and climate regulation. However, their complex and variable growth environments pose challenges for precise monitoring. Hainan Island represents a region within China where mangrove forests are the most concentrated and diverse in type. In recent years, ecological restoration efforts have led to the recovery of their coverage areas. This study analyzed the spatial distribution, canopy height, and aboveground carbon storage variations in Hainan mangrove forests. Deep-learning and multiple machine-learning algorithms were used to integrate multitemporal Sentinel-2 remote sensing imagery from 2019 to 2023 with unmanned aerial vehicle observations and field survey data. Multi-rule image fusion and deep-learning techniques effectively enhanced mangrove identification accuracy. The mangrove classification achieved an overall accuracy exceeding 90%. The mangrove area in Hainan increased from 3948.83 ha in 2019 to 4304.29 ha in 2023. Gradient-boosted decision tree (GBDT) models estimated average canopy height with a high coefficient of determination (R² = 0.89), and Random Forest (RF) models yielded the best estimations of total above-ground carbon stock with strong agreement to field observations. Integrating multisource remote sensing data with artificial intelligence algorithms enabled high-precision dynamic monitoring of mangrove distribution, structure, and carbon storage to provide scientific support for the assessment, management, and carbon sink accounting of Hainan mangrove ecosystems. Full article