Search Results (55,082)

This work presents the development of a low-cost and high-performance multi-sensory gas detection instrument named the AIMNet Sensor, with the integration of a machine learning-based data processing method. The compact and low-power instrument (8.5 × 11.5 cm, 1.4 W) houses the core sensing hardware module, Senseair K96, that integrates both a non-dispersive infrared (NDIR)-based gas sensing unit and a BME280 environmental sensing unit. To address the outdoor operation challenges caused by environmental fluctuation due to the varying temperature, humidity, and pressure, from the software aspect, multiple machine learning-based regression models were trained in this work on 13,125 calibration data points collected under controlled laboratory conditions. Among ten tested algorithms, the Multilayer Perceptron (MLP) and Elastic Net models achieved the highest accuracy, with R-squared coefficient $R^2>0.8$ on both indoor and outdoor scenarios, and with inter-sensor root mean square error (RMSE) within 1.5 ppm across four identical instruments. Moreover, field mobile validation was performed near a wastewater management facility using this solution, confirming a strong correlation with LI-COR reference measurements and a reliable detection of CH${}_4$ leaks with concentrations up to 18 ppm at the test site. Overall, this machine learning-integrated NDIR sensing solution (i.e., AIMNet) offers a practical and scalable solution towards a more robust distributed CH${}_4$ monitoring network for real-world field-deployable applications. Full article

Lithium has emerged as a pivotal material for the global energy transition, yet its supply security is challenged by limited geographical availability and growing demand. These constraints highlight the need for analytical methods that are not only accurate but also sustainable and deployable across the entire lithium value chain. In this context, Laser-Induced Breakdown Spectroscopy (LIBS) offers distinctive advantages, including minimal sample preparation, real-time and in situ analysis and the potential for portable and automated implementation. Such features make LIBS a valuable tool for monitoring and optimizing lithium extraction, refining and recycling processes. This review critically examines the recent progress in the use of LIBS for lithium detection and quantification in geological, industrial, biological and extraterrestrial matrices. It also discusses emerging applications in closed-loop recycling and highlights future prospects related to the integration of LIBS with artificial intelligence and machine learning to enhance analytical accuracy and material classification. Full article

Direct Air Capture (DAC) technology plays a crucial role in reducing atmospheric CO₂, but large-scale deployment faces challenges such as high energy consumption, operational costs, and slow material development. This study provides a comprehensive review of DAC principles, including chemical and solid adsorption methods, with a focus on emerging technologies like Metal–Organic Frameworks (MOFs) and graphene aerogels. MOFs have achieved adsorption capacities up to 1.5 mmol/g, while modified graphene aerogels reach 1.3 mmol/g. Other advancing approaches include DAC with Methanation (DACM), variable-humidity adsorption, photo-induced swing adsorption, and biosorption. The study also examines global industrialization trends, noting a significant rise in DAC projects since 2020, particularly in the U.S., China, and Europe. The integration of DAC with renewable energy sources, such as photovoltaic/electrochemical regeneration, offers significant cost-reduction potential and can cut reliance on conventional heat by 30%. This study focuses on the integration of Artificial Intelligence (AI) for accelerating material design and system optimization. AI and Machine Learning (ML) are accelerating DAC R&D: high-throughput screening shortens material design cycles by 60%, while AI-driven control systems optimize temperature, humidity, and adsorption dynamics in real time, improving CO₂ capture efficiency by 15–20%. The study emphasizes DAC’s future role in achieving carbon neutrality through enhanced material efficiency, integration with renewable energy, and expanded CO₂ utilization pathways, providing a roadmap for scaling DAC technology in the coming years. Full article

Background/Objectives: Artificial intelligence (AI) has rapidly evolved from experimental algorithms to transformative tools in clinical dentistry. Between 2020 and 2025, advances in machine learning (ML) and deep learning (DL) have reshaped diagnostic imaging, caries detection, prosthodontic design, and teledentistry, while raising new ethical and regulatory challenges. This study aimed to provide a comprehensive bibliometric and conceptual review of AI applications in dental care, highlighting research trends, thematic clusters, and future directions for equitable and responsible integration of AI technologies. In addition, the review further considers the implications of AI adoption for patient-centered care, including its potential role in supporting shared decision-making processes in oral healthcare. Methods: A comprehensive search was conducted in PubMed, Scopus and Embase for articles published between January 2020 and October 2025 using AI-related keywords in dentistry. Eligible records were analyzed using VOSviewer (v.1.6.20) to map co-occurrence networks of keywords, authors, and citations. A narrative synthesis complemented the bibliometric mapping, emphasizing conceptual and ethical dimensions of AI adoption in oral health care. Results: A total of 50 documents met the inclusion criteria. Bibliometric network visualization identified that the largest and most interconnected clusters were centered around the keywords “artificial intelligence,” “machine learning,” and “deep learning,” reflecting the technological backbone of AI-based applications in dentistry. Thematic evolution analysis indicated increasing interest in generative and multimodal AI models, explainability, and fairness in clinical deployment. Conclusions: AI has become a core driver of innovation in dentistry, enabling precision diagnostics and personalized care. However, responsible translation requires robust validation, transparency, and ethical oversight. Future research should integrate interdisciplinary approaches linking AI performance, patient outcomes, and equity in oral health. Full article

End-of-life wind turbine blade accumulation is a growing global materials management problem and current industrial recycling routes for glass fiber-reinforced polymer composites remain limited in material recovery value. There is limited understanding on how to recover clean glass fibers while keeping thermal exposure and energy input low, and existing studies have not quantified whether very short isothermal thermal residence can still result in complete matrix removal. The hypothesis of this study is that a mild two-step thermochemical sequence can recover clean glass fibers at lower temperature and near zero isothermal dwell if pyrolysis and oxidation are separated. We used wind-blade epoxy-based GFRP in a step-batch reactor and combined TGA-based thermodynamic mapping, short pyrolysis at 425 °C, and mild oxidation at 475 °C with controlled dwell from zero to thirty minutes. We applied model-free kinetics and machine learning methods to quantify activation energy trends as a function of conversion. The thermal treatment of 425 °C for zero minutes in nitrogen, followed by 475 °C for fifteen minutes in air, resulted in mechanically sound, visually clean white fibers. These fibers retained 76% of the original tensile strength and 88% of the Young’s modulus, which indicates the potential for energy-efficient GFRP recycling. The activation energy was found to be approximately 120 to 180 kJ mol⁻¹. These findings demonstrate energy lean recycling potential for GFRP and can inform future industrial scale thermochemical designs. Full article

Epilepsy is a prevalent neurological disorder where reliable seizure tracking is essential for patient care. Existing documentation often relies on self-reports, which are unreliable, creating a need for objective, wearable-based solutions. Prior work has shown that Electrocardiography (ECG)-based seizure detection is feasible but limited by small datasets. This study addresses this issue by evaluating Matrix Profile, MADRID, and TimeVQVAE-AD on SeizeIT2, the largest open wearable-ECG dataset with 11,640 recording hours and 886 annotated seizures. Using standardized preprocessing and clinically motivated windows, we benchmarked sensitivity, false-alarm rate (FAR), and a Harmonic Mean Score integrating both metrics. Across methods, TimeVQVAE-AD achieved the highest sensitivity, while MADRID produced the lowest FAR, illustrating the trade-off between detecting seizures and minimizing spurious alerts. Our findings show ECG anomaly detection on SeizeIT2 can reach clinically meaningful sensitivity while highlighting the sensitivity–false alarm trade-off. By releasing reproducible benchmarks and code, this work establishes the first open baseline and enables future research on personalization and clinical applicability. Full article

This study investigates the key factors that influence marriage decision among Chinese youth using machine learning techniques. Using data from the China Family Panel Studies (2018–2020), we extracted 1700 samples and filtered 26 significant variables. Seven machine learning algorithms were evaluated, with CatBoost emerging as the most effective. SHAP (SHapley Additive exPlanations) analysis revealed that work-related variables were the most strongly associated with predictions, accounting for 30% of the predictive power, followed by other factors such as demographic and education. Notably, we found that commute time and working hours exceeding 50 min/hours were negatively associated with marriage likelihood, while job satisfactions showed a non-linear relationship with marriage decision. The findings highlight the determinant of work–life balance in marriage decision and the complexity and nonlinear relationship in social decision-making. The objective of this study is to provide scientific data support for policy makers in an era of declining marriage rates in China. This study not only reveals the key factors affecting marriage decision but also provides critical evidence-based support for policymakers to prioritize resource allocation and formulate targeted policies amid declining marriage rates in China. Full article

Advances in deep learning are impressive in various fields and have achieved performance beyond human capabilities in tasks such as image classification, as demonstrated in competitions such as the ImageNet Large Scale Visual Recognition Challenge. Nonetheless, complex applications like medical imaging continue to present significant challenges; a prime example is the Human Protein Atlas (HPA) dataset, which is computationally challenging and complex due to the high-class imbalance with the presence of rare patterns and the need for multi-label classification. It includes 28 distinct patterns and more than 500 unique label combinations, with protein localization that can appear in different cellular regions such as the nucleus, the cytoplasm, and the nuclear membrane. Moreover, the dataset provides four distinct channels for each sample, adding to its complexity, with green representing the target protein, red indicating microtubules, blue showing the nucleus, and yellow depicting the endoplasmic reticulum. We propose a two-phase transfer learning approach based on feature-block extraction from twelve ImageNet-pretrained CNNs. In the first phase, we address single-label multiclass classification using CNNs as feature extractors combined with SVM classifiers on a subset of the HPA dataset. We demonstrate that the simple concatenation of feature blocks extracted from different CNNs improves performance. Furthermore, we apply a genetic algorithm to select the sub-optimal combination of feature blocks. In the second phase, based on the results of the previous stage, we apply two simple multi-label classification strategies and compare their performance with four classifiers. Our method integrates image-level and cell-level analysis. At the image level, we assess the discriminative contribution of individual and combined channels, showing that the green channel is the strongest individually but benefits from combinations with red and yellow. At the cellular level, we extract features from the nucleus and nuclear-membrane ring, an analysis not previously explored in the HPA literature, which proves effective for recognizing rare patterns. Combining these perspectives enhances the detection of rare classes, achieving an F1 score of 0.8 for “Rods & Rings”, outperforming existing approaches. Accurate identification of rare patterns is essential for biological and clinical applications, underscoring the significance of our contribution. Full article

The mechanical and durability performance of cementitious materials is fundamentally governed by the symmetry, anisotropy, and hierarchical organization of their microstructures. Conventional experimental characterization—based on imaging, spectroscopy, and physical testing—often struggles to capture these multiscale spatial patterns and their nonlinear correlations with macroscopic performance. Recent advances in machine learning (ML) provide unprecedented opportunities to interpret structural symmetry and anisotropy through data-driven analytics, computer vision, and physics-informed models. Furthermore, we summarize cases where symmetry-informed descriptors improve performance prediction accuracy in fiber- and nano-modified composites, demonstrating that ML-based symmetry analysis can substantially complement the limitations of conventional experimental-based characterization. We confirm that image-based models such as CNN and U-Net quantify the directionality and connectivity of pores and cracks, and that physically informative neural networks (PINNs) and heterogeneous data-based models enhance physical consistency and computational efficiency compared to conventional FEM and CFD. Finally, we present the conceptual and methodological foundation for developing AI-based microstructural symmetry analysis, aiming to go beyond simple prediction and establish a conceptual foundation for AI-driven cement design based on microstructure–performance causality. Full article

The rapid development of the Internet of Things (IoT), a network of interconnected devices and sensors, has improved operational efficiency, comfort, and sustainability in smart buildings. However, relying on interconnected systems also introduces cybersecurity vulnerabilities. For instance, attackers can exploit zero-day vulnerabilities (previously unknown security flaws), launch Distributed Denial of Service (DDoS) attacks (overwhelming network resources with traffic), or access sensitive Building Management Systems (BMS, centralized platforms for controlling building operations). By targeting critical assets such as Heating, Ventilation, and Air Conditioning (HVAC) systems, security cameras, and access control networks, they may compromise the safety and functionality of the entire building. To address these threats, this paper presents a cybersecure intelligent sensor framework to protect smart buildings from various IoT-related cyberattacks. The main component is an automated Intrusion Detection System (IDS, software that monitors network activity for suspicious actions), which uses machine learning algorithms to rapidly identify, classify, and respond to potential threats. Furthermore, the framework integrates intelligent sensor networks with AI-based analytics, enabling continuous monitoring of environmental and system data for behaviors that might indicate security breaches. By using predictive modeling (forecasting attacks based on prior data) and automated responses, the proposed system enhances resilience against attacks such as denial of service, unauthorized access, and data manipulation. Simulation and testing results show high detection rates, low false alarm frequencies, and fast response times, thereby supporting the cybersecurity of smart building infrastructures and minimizing downtime. Overall, the findings suggest that AI-enhanced cybersecurity systems offer promise for IoT-based smart building security. Full article

SoilMERGE (SMERGE) is a 0.125-degree root zone soil moisture (RZSM) product (0 to 40 cm depth) covering the contiguous United States. The study area included most of Oklahoma and Kansas, a region where SMERGE exhibited superior performance. The time frame examined was the warm season from 2008 to 2019. In this study, evaluation of a prototype downscaled (500 m) version of SMERGE was made using (1) Ranked correlation (R²) benchmarking against Normalized Difference Vegetation Index (NDVI) datasets and (2) Ranked correlation (R²) analysis of antecedent RZSM with storm-event streamflow across a range of precipitation intensities (5 to >35 mm/day) at a watershed scale. In the NDVI benchmarking, all three downscaled products outperformed (0.52 to 0.59) default SMERGE (0.44). EXtreme Gradient Boosting (XGB) and Gradient Boost recorded a higher ranked correlation (0.59) than Random Forest (0.52). Within the study area, ranked correlation analysis of antecedent RZSM with storm-event United States Geological Survey streamflow was examined in five watersheds. For the most intense storm events (>35 mm), antecedent XGB downscaled SMERGE (0.64) outperformed antecedent streamflow (0.43) and all other versions of SMERGE (0.52 to 0.56) as a predictor of storm event response. The results of this study demonstrated broad-scale benefits of Machine Learning-assisted downscaling, providing proof of concept for the development of state-based SMERGE products across the US Great Plains. Full article

Background: HER2-positive breast cancer patients receiving chemotherapy and targeted therapy (including anthracyclines and trastuzumab) face an elevated risk of cardiotoxicity, which can lead to long-term cardiovascular complications. Identifying predictive biomarkers is essential for early intervention. Circulating microRNAs (miRNAs), known regulators of gene expression and cardiovascular function, have emerged as potential indicators of cardiotoxicity. This study aims to evaluate the differential expression of circulating miRNAs in HER2-positive breast cancer patients undergoing chemotherapy and to assess their prognostic ability for therapy-induced cardiotoxicity using machine learning models. Methods: Forty-seven patients were assessed for cardiac toxicity at baseline and every 3 months, up to 15 months. Blood samples were collected at baseline. MiRNA expression profiling for 84 microRNAs was performed using the miRCURY LNA miRNA PCR Panel. Differential expression was calculated via the 2−∆∆Ct method. The five most upregulated and five most downregulated miRNAs were further assessed using univariate logistic regression and receiver operating characteristic (ROC) analysis. Five machine learning models (Decision Tree, Random Forest (RF), Support Vector Machine (SVM), Gradient Boosting Machine (GBM), k-Nearest Neighbors (KNN)) were developed to classify cardiotoxicity based on miRNA expression. Results: Forty-five miRNAs showed significant differential expression between cardiac toxic and non-toxic groups. ROC analysis identified hsa-miR-155-5p (AUC 0.76, p = 0.006) and hsa-miR-124-3p (AUC 0.75, p = 0.007) as the strongest predictors. kNN, SVM, and RF models demonstrated high prognostic accuracy. The decision tree model identified hsa-miR-17-5p and hsa-miR-185-5p as key classifiers. SVM and RF highlighted additional miRNAs associated with cardiotoxicity (SVM: hsa-miR-143-3p, hsa-miR-133b, hsa-miR-145-5p, hsa-miR-185-5p, hsa-miR-199a-5p, RF: hsa-miR-185-5p, hsa-miR-145-5p, hsa-miR-17-5p, hsa-miR-144-3p, and hsa-miR-133a-3p). Performance metrics revealed that SVM, kNN, and RF models outperformed the decision tree in overall prognostic accuracy. Pathway enrichment analysis of top-ranked miRNAs demonstrated significant involvement in apoptosis, p53, MAPK, and focal adhesion pathways, all known to be implicated in chemotherapy-induced cardiac stress and remodeling. Conclusions: Circulating miRNAs show promise as biomarkers for predicting cardiotoxicity in breast cancer patients. Machine learning approaches may enhance miRNA-based risk stratification, enabling personalized monitoring and early cardioprotective interventions. Full article

Background: Dental caries is a prevalent global oral health issue. The early detection of enamel caries, the initial stage of decay, is critical to preventive dentistry but is often limited by the subjectivity and variability of conventional diagnostic methods. Objective: This study aims to develop and evaluate two explainable deep learning models for the automated classification of enamel caries from intraoral images. Dataset and Methodology: A publicly available dataset of 2000 intraoral images showing early-stage enamel caries, advanced enamel caries, no-caries was used. The dataset was split into training, validation, and test sets in a 70:15:15 ratio, and data preprocessing and augmentation were applied to the training set to balance the dataset and prevent model overfitting. Two models were developed, ExplainableDentalNet, a custom lightweight CNN, and Interpretable ResNet50-SE, a fine-tuned ResNet50 model with Squeeze-and-Excitation blocks, and both were integrated with Gradient-Weighted Class Activation Mapping (Grad-CAM) for visual interpretability. Results: As evaluated on the test set, ExplainableDentalNet achieved an overall accuracy of 96.66% and a Matthews Correlation Coefficient [MCC] = 0.95, while Interpretable ResNet50-SE achieved 98.30% accuracy (MCC = 0.975). McNemar’s test indicated no significant prediction bias, with p > 0.05, and internal bootstrap and cross-validation analyses indicated stable performance. Conclusions: The proposed explainable models demonstrated high diagnostic accuracy in enamel caries classification on the studied dataset. While the present findings are promising, future clinical applications will require external validation on multi-center datasets. Full article

In the context of accelerating global urbanization and sustainable development challenges, impervious surfaces, as a key component of urban land cover, are significantly associated with regional economic development. This study takes Harbin, a typical cold region city, as a research object and constructs a three-level analytical framework of “land surface classification-economic simulation-mechanism analysis.” By innovatively integrating multi-source remote sensing, demographic, and economic data, the research addresses gaps in understanding urban sustainability in cold environments. An enhanced XGBoost algorithm was employed to achieve high-precision classification of ten land surface materials, resulting in a high overall accuracy. Furthermore, a gridded GDP spatialization model developed using high-resolution population data demonstrated superior performance compared to traditional methods. Machine learning-assisted analysis revealed that asphalt and metal surfaces are the most significant impervious materials driving economic output, reflecting the respective influences of transportation infrastructure and industrial agglomeration. Spatial pattern analysis indicates that Harbin’s impervious surfaces exhibit a lower fractal dimension and a distinct grid-like morphology compared to the typical subtropical city of Guangzhou, underscoring urban form adaptations to cold climatic constraints. The strong spatial coupling between gradients of GDP intensity and the attenuation of impervious surface density is quantitatively confirmed. This study provides a quantitative basis and a transferable technical framework for optimizing land use intensity and infrastructure planning in cold cities, thereby offering a scientific foundation for sustainable, intensive land utilization in climate-vulnerable urban systems. Full article

Brain–computer interfaces using motor imagery (MI-BCIs) offer a promising noninvasive communication pathway between humans and engineered equipment such as robots. However, for MI-BCIs based on electroencephalography (EEG), the reliability of the interface across recording sessions is limited by temporal non-stationary effects. Overcoming this barrier is critical to translating MI-BCIs from controlled laboratory environments to practical uses. In this paper, we present a comprehensive dual-validation framework to rigorously evaluate the temporal robustness of EEG signals of an MI-BCI. We collected data from six participants performing four motor imagery tasks (left/right hand and foot). Features were extracted using Common Spatial Patterns, and ten machine learning classifiers were assessed within a unified pipeline. Our method integrates within-session evaluation (stratified K-fold cross-validation) with cross-session testing (bidirectional train/test), complemented by stability metrics and performance heterogeneity assessment. Findings reveal minimal performance loss between conditions, with an average accuracy drop of just 2.5%. The AdaBoost classifier achieved the highest within-session performance (84.0% system accuracy, F1-score: 83.8%/80.9% for hand/foot), while the K-nearest neighbors (KNN) classifier demonstrated the best cross-session robustness (81.2% system accuracy, F1-score: 80.5%/80.2% for hand/foot, 0.663 robustness score). This study shows that robust performance across sessions is attainable for MI-BCI evaluation, supporting the pathway toward reliable, real-world clinical deployment. Full article