Search Results (1,410)

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

This study proposes a deep learning-based framework for the automated classification of photovoltaic solar cells as defective or normal using electroluminescence (EL) imaging. A balanced dataset containing 20,400 EL images, comprising 10,200 defective and 10,200 normal solar cells, was used for model development and evaluation. To reflect practical inspection requirements, cracked and broken cells were combined into a single defective category, resulting in a binary classification task. The dataset includes both monocrystalline and polycrystalline solar cells, which were analyzed together within a unified classification framework to improve applicability to real-world photovoltaic systems. To ensure a fair and unbiased evaluation, dataset partitioning was performed prior to any preprocessing or augmentation operations, and each image was assigned exclusively to the training, validation, or test subset. Data augmentation was applied only to the training set, eliminating the possibility of data leakage. Four state-of-the-art deep learning architectures, EfficientNet-B2, ConvNeXt-Tiny, MaxViT-T, and ResNet-50, were trained and evaluated under identical experimental conditions using the same preprocessing pipeline, training strategy, and dataset split. Model performance was assessed using accuracy, precision, recall, F1-score, ROC-AUC, confusion matrices, and explainability-based activation and attention heat maps. All evaluated models achieved classification accuracies exceeding 98%, demonstrating strong capability for EL-based defect detection. EfficientNet-B2 achieved the highest numerical performance, reaching 99.31% accuracy, 0.9931 F1-score, and 0.9987 ROC-AUC. MaxViT-T exhibited similarly strong performance with rapid convergence and balanced class-wise metrics, while ConvNeXt-Tiny and ResNet-50 also produced highly reliable results. Heat map visualizations revealed that EfficientNet-B2 and MaxViT-T concentrated their attention more precisely on defect regions such as cracks and fractures, providing visual interpretability in addition to quantitative performance. The results demonstrate that modern deep learning architectures can accurately and reliably detect photovoltaic cell defects from EL images under a unified binary classification framework. Furthermore, explainability techniques enhance the transparency of model predictions, supporting the practical deployment of intelligent inspection systems for photovoltaic manufacturing and maintenance applications. Full article

Artificial intelligence (AI), particularly deep learning (DL), is revolutionizing optical metamaterial design by overcoming the fundamental challenges of multidimensional parameter spaces, nonlinear structure–property relationships, and the intrinsic non-uniqueness of inverse problems. By learning complex mappings between geometric structures and electromagnetic responses, DL enables rapid forward prediction and on-demand inverse design without computationally intensive full-wave simulations. This review provides a comprehensive survey of AI-driven design methodologies across four key metamaterial platforms: localized resonant nanostructures, metasurfaces, periodic and guided-wave photonic structures, and complex scattering systems. For each platform, we systematically examine the neural network architectures employed, the specific design challenges addressed, and the representative achievements attained. These data-driven approaches not only significantly accelerate the discovery of high-performance structures but also offer new opportunities for extracting physical insights into light–matter interactions. We assess the critical challenges of data efficiency, model interpretability, and experimental feasibility, and outline emerging research directions that may address these barriers. This review aims to provide both a comprehensive summary of the current state of the art and forward-looking perspectives for this rapidly evolving interdisciplinary field. Full article

Detecting unmanned aerial vehicles (UAVs) remains a difficult task, primarily due to their tiny size, rapid motion, and complex backgrounds. Fusing visible and infrared imagery offers complementary advantages for robust detection, yet existing methods rely on spatial feature aggregation that overlooks spectral disparities, coupling noise with textures. Moreover, the small scale and high dynamics of UAVs hinder standard convolution from decoupling target signals from background interference due to limited receptive fields. To solve these limitations, the Wavelet-guided Frequency–Spatial Decoupling Network (WFSD-Net) is designed for visible–infrared UAV detection. First, to tackle fusion noise, the Discrete Wavelet Band-Differentiated Fusion (DWBF) module is designed to explicitly decouple noise-dominant sub-bands from information-rich components by performing spectral decomposition. It aligns low-frequency distributions via adaptive spatial weighting and disentangles high-frequency details using physics-aware rules, achieving source-level noise suppression. Second, an Axial Strip Contextual Attention (ASCA) module is proposed. By utilizing anisotropic strip convolution via orthogonal decomposition, this module captures global contextual dependencies to effectively decouple weak target features from background clutter, enhancing the spatial position encoding capability for weak targets. Finally, the proposed WFSD-Net method is validated on Anti-UAV300 and Multi-Sensor and Multi-View Fixed-Wing UAV (MMFW-UAV) datasets, and experiments demonstrate that the proposed method is superior to existing state-of-the-art (SOTA) methods. Full article

The co-circulation of respiratory viruses, including SARS-CoV-2, influenza A/B, and respiratory syncytial virus (RSV), represents a significant global health challenge that requires rapid, accurate, and differential diagnosis to support infection control and appropriate clinical decision-making. This narrative review summarizes emerging multimodal point-of-care testing (POCT) strategies for the detection and management of these respiratory viruses. Relevant studies were identified through literature searches of major scientific databases, including PubMed, Scopus, and Web of Science, focusing on recent advances in molecular diagnostics, biosensors, microfluidics, and digital health technologies. To improve clinical interpretation and comparative assessment, current POCT platforms were organized into four operational tiers based on infrastructure dependence, degree of portability, and level of decentralization of testing. Tier 1 (Professional Clinical Systems) includes fully integrated automated molecular diagnostic platforms designed for use in hospital and emergency care settings. Tier 2 (Field-Deployable Systems) comprises portable molecular and isothermal amplification technologies designed for use in decentralized or resource-limited environments. Tier 3 (Hardware-Lite Assays) includes simplified diagnostic approaches that minimize instrument requirements and are suitable for near-patient or low-infrastructure settings. Tier 4 (Consumer-Digital Diagnostics) encompasses emerging smartphone- and IoT-integrated diagnostic platforms that support user-driven testing and digital health connectivity. This tier-based framework reflects a proposed stratification of POCT technologies along a decentralization continuum and aims to facilitate comparison and selection of diagnostic strategies across diverse healthcare settings. Full article

Voice phishing, commonly known as vishing, has become one of the fastest-growing threats in social engineering. The rapid advancement and accessibility of AI voice cloning tools have enabled attackers to produce highly convincing synthetic speech at minimal cost, driving a sharp increase in impersonation fraud. Accordingly, automatic detection of synthetic voices could contribute, as one component of a broader defense, to mitigating vishing attacks. This paper studies the automatic detection of AI-generated speech, with a particular focus on how well such detectors generalize beyond their training data to modern, unseen synthesis methods. Two detection approaches are evaluated: a Residual CNN (convolutional neural network) trained as a binary classifier on three different time–frequency representations and a one-class learning strategy with a ResNet-18 backbone, yielding four models in total. Models were trained on the well-known ASVspoof 2019 Logical Access dataset and tested on its standard partitions. Then, models were tested on the SONAR benchmark, which gathers voices generated with state-of-the-art synthesis techniques unseen during training. Experimental results show that, on the modern systems gathered in SONAR, all four configurations fall close to chance. The LFCC one-class detector generalizes comparatively best, but the apparently higher accuracy of some models reflects a tendency to label most speech as spoofed. These findings indicate that the evaluated detectors can provide, at most, a partial security layer against vishing driven by current and emerging speech-synthesis technologies, although continuous model updates are recommended. Full article

Materials such as steel, concrete, and various alloys are used to build infrastructure and machinery across all industries. Due to their long service life, some of these materials will eventually develop surface damage (such as crazing, corrosion, and pitting) that will negatively affect both the structural integrity and the reliability of the machinery/infrastructure. Thus, the rapid and accurate classification of defects on material surfaces is crucial for ensuring high-quality materials and a continuous process without machinery breakdowns. In this work, we compare the effectiveness of two types of deep learning models (a VGG16 convolutional neural network with transfer learning and the state-of-the-art YOLOv8) for automatic defect classification on surfaces. The dataset used in our experiment included data from the Phase 5 Capstone Corrosion and the NEU Surface Defects Databases, resulting in eight distinct classes of surface defects. The effectiveness of both models was determined using stratified 10-fold cross-validation. The results of the experiment revealed that YOLOv8 achieved 98.5% accuracy, whereas VGG16 achieved only 92.5%. Moreover, YOLOv8 exhibited greater consistency under noise perturbations, demonstrating superior robustness compared with VGG16. Beyond model comparison, this study introduces a unified benchmark constructed from heterogeneous industrial defect datasets. It systematically evaluates classification performance, generalization capability, and robustness using stratified cross-validation and noise-based testing. The results indicate that YOLOv8 is a practical solution for automated industrial surface defect classification. Full article

This review systematically summarizes the inherent characteristics and application superiorities of various nanomaterials, including metallic nanomaterials, metal oxides, carbon-based materials, metal–organic frameworks (MOFs), and quantum dots (QDs). State-of-the-art research progress is elaborated on the applications of these nanomaterials in multiple analytical techniques, such as surface-enhanced Raman spectroscopy (SERS), fluorescence spectroscopy, infrared spectroscopy, ultraviolet-visible spectroscopy, and electrochemistry. Furthermore, their pivotal functions in signal amplification, specific molecular recognition, and rapid analyte enrichment are thoroughly discussed. Additionally, this paper analyzes the prevailing challenges, including material heterogeneity, potential biosafety risks, poor anti-interference capacity against complex matrices, and the absence of unified industrial standardization. Future development directions are also proposed, involving green synthesis strategies, precise functional modification, portable intelligent detection, and simultaneous multi-component detection. This work aims to provide a reliable reference for further fundamental research and industrial translation of nanomaterials in the rapid and high-precision detection of pesticide residues. Full article

With the rapid growth of Chinese social media data, many language-driven analytical tasks, such as sentiment analysis and malicious account detection, are increasingly formulated as computationally expensive optimization problems, particularly in the context of hyperparameter tuning for deep learning models. Due to the intrinsic characteristics of Chinese text, including implicit word boundaries, strong context dependency, and high linguistic variability, the resulting feature representations are often high-dimensional, sparse, and heterogeneously distributed. From an optimization perspective, these properties induce highly irregular, non-smooth, and multimodal objective landscapes, posing significant challenges to conventional surrogate-assisted data-driven evolutionary algorithms (DDEAs). To address this problem, this paper proposes a Normal Selection-based data-driven evolutionary algorithm (NSEA) for improving surrogate-assisted optimization under complex conditions. Specifically, a Normal distribution-based selection strategy (NSS) is developed to enable probabilistic selection of surrogate models, balancing exploitation of high-performing models and exploration of alternative candidates, thereby alleviating premature convergence in multimodal search spaces. In addition, an exponential weighting ensemble (EWE) method is introduced to aggregate surrogate models based on their relative ranking performance, which enhances the stability and generalization capability of fitness approximation across different regions of the search space. Extensive experiments on benchmark functions demonstrate that the proposed NSEA consistently outperforms several state-of-the-art DDEAs in terms of optimization accuracy and robustness. Furthermore, a real-world application of cheating official account (COA) detection on Chinese social media is conducted, in which the hyperparameter optimization of a heterogeneous graph transformer (HGT) model is formulated as an EOP. The results further prove the effectiveness and practical applicability of the NSEA in complex data-driven scenarios. Overall, this study provides an effective optimization framework for handling EOPs with complex and multimodal characteristics and offers a feasible computational approach for tasks associated with large-scale Chinese textual data. Full article

With the rapid development in generative artificial intelligence (GenAI) technologies, their application in STEAM education offers new possibilities for promoting interdisciplinary integration of technology and the arts. This study employs a systematic literature review method. Six databases—Google Scholar, Web of Science, PubMed, Taylor & Francis, Springer Link, and Scopus—were searched for publications from January 2021 to January 2026. After independent screening and review by two reviewers, 21 empirical studies out of 424 initial records were included. A comprehensive analysis was conducted using a combination of open and axial coding. The findings indicate that GenAI’s support for artistic creativity in STEAM education is primarily manifested in four dimensions: lowering the threshold for creation to enhance the accessibility of artistic creativity, stimulating interdisciplinary associations to strengthen subject integration, supporting critical artistic recreation to deepen cultural engagement, and building a human–GenAI collaborative creation ecosystem to foster reflexivity. Based on this, the study constructs a GCD (Guiding questioning–Co-refining–Deepening reflection) cyclic instructional framework, providing teachers with an actionable pedagogical pathway for using GenAI to cultivate students’ interdisciplinary artistic creativity across different educational stages. Furthermore, the study systematically analyzes ethical challenges such as technological dependency, cultural homogenization, educational equity, and originality, and proposes corresponding pedagogical strategies to address them. It should be noted that the current body of relevant empirical research is limited in quantity and exhibits substantial heterogeneity, and the GCD framework still requires further classroom-based practical validation. Future research could strengthen empirical longitudinal tracking of longterm effects, deepen the construction of support systems for teachers’ digital literacy, and continue to advance the exploration of ethical, equity, and cultural diversity issues in GenAI-based artistic creativity education. Full article

The rapid expansion of online real estate (RE) platforms has intensified information overload, making property search and decision-making increasingly complex. Real estate recommendation systems (RERSs) have emerged as essential decision-support tools; however, their development has not kept pace with advances in explainable artificial intelligence (XAI), transfer learning (TL), and fairness-aware machine learning. This PRISMA-compliant systematic review synthesizes 59 peer-reviewed studies published between 2005 and 2025 to critically examine algorithmic approaches, data modalities, evaluation practices, and ethical considerations in RERS research. Our analysis reveals a substantial lag in the adoption of state-of-the-art AI techniques: While deep learning is employed in 15% of studies, no reviewed work implements state-of-the-art post hoc XAI or TL frameworks, despite their relevance for addressing interpretability and data scarcity challenges. Furthermore, we identify systemic research biases, including reliance on proprietary datasets (80%), geographic concentration in Asia (56%), the dominance of residential property studies (91%), and limited fairness auditing despite documented discrimination risks in housing markets. To address these gaps, we propose a trust-based evaluation (T-EVAL) framework that integrates predictive accuracy, user trust, fairness, and market efficiency, and introduces a comprehensive nine-layer conceptual architecture for transparent, ethical, and data-efficient next-generation RERS. This review establishes an empirical benchmark for technology adoption gaps and outlines a research agenda for advancing responsible AI in RE decision-support systems. Full article

Advances in electric flight technologies have enabled distributed electric propulsion, opening a large design space for electric vertical take-off and landing (eVTOL) aircraft with diverse configurations and mission profiles. To support rapid exploration of these trade-offs, a computationally efficient sizing and performance evaluation tool has been developed. This study focuses on the verification of the key methods within the framework. The propeller sizing and performance model is verified against conventional helicopter rotors and representative eVTOL designs, while the battery discharge model is assessed using experimental data. In addition, the overall aircraft sizing is evaluated for two configurations of NASA’s Urban Air Mobility reference vehicles and compared with results obtained using NASA’s state-of-the-art rotorcraft design tool NDARC. The results show good agreement across all levels of verification. Average deviations are within 8% for propeller performance, below 5% for battery discharge, and within 4% for maximum take-off and empty mass. Mission performance and energy consumption are predicted within approximately 10%, demonstrating the suitability of the methodology for early-stage eVTOL design. Full article

Rapid and reliable flood segmentation utilizing optical remote-sensing imagery is critical for effective flood disaster response and risk assessment. Nevertheless, current models frequently struggle with imprecise boundary delineation and fragmented predictions in complex environments, especially where floodwater displays high spectral variability and closely resembles shadows, dark pavements, or wet soil. To overcome these challenges, we introduce FloodSeg, an innovative Mamba-CNN encoder–decoder network incorporating two lightweight yet highly effective components: a Shift module and a sequence-shuffle module. The spatial Shift module leverages spatially shifted feature aggregation to fortify boundary-aware representations, thereby ensuring the continuity of inundation contours even under varying illumination and cluttered backgrounds. Meanwhile, the sequence-shuffle module reorganizes multi-scale features via sequence-wise mixing and cross-regional interaction, significantly enhancing long-range dependency modeling. This facilitates the generation of globally consistent flood masks while mitigating local overfitting to dataset-specific textures. Evaluated on the Kaggle and FloodNet benchmark datasets, FloodSeg achieves outstanding mIoU scores of 81.85% and 91.21%, respectively. By outperforming various state-of-the-art CNN-, Transformer-, and Mamba-based baselines, our model demonstrates a superior accuracy-efficiency trade-off. These results substantiate that FloodSeg significantly advances boundary recognition and overall segmentation completeness, establishing it as a robust and practical solution for real-world remote-sensing flood mapping applications. Full article

Ceramics, as a handicraft, is the crystallization of art and science. In order to study the firing process of ceramics, improve their density, mechanical properties, viscosity, and surface tension, and enhance the surface quality of the shaft, this article uses first-principles methods to study the electronic properties of ceramic colorants Al₂O₃, Fe₂O₃, TiO₂, CaO, MgO, Na₂O, KO₂, and ceramic body SiO₂. Research has shown that these seven color-developing agents exhibit anisotropy and have stable crystal structures. The bandgap values of Al₂O₃, CaO, Fe₂O₃, KO₂, MgO, Na₂O, TiO₂, and ceramic SiO₂ are 6.325 eV, 3.654 eV, 0 eV, 0 eV, 4.731 eV, 1.972 eV, 2.18 eV and 6.002 eV, respectively. In Al₂O₃/SiO₂, Fe₂O₃/SiO₂, TiO₂/SiO₂, CaO/SiO₂, MgO/SiO₂, Na₂O/SiO₂, and KO₂/SiO₂ systems, due to the influence of the potential field in the SiO₂ system, the charge characteristics exhibit obvious interfacial and non-periodic characteristics. The research results revealed the charge transfer and distribution patterns at the interface between ceramic colorants and ceramic ligands, elucidating the influence mechanism of different colorants/embryo components on firing temperature, shrinkage rate, and finished product defects. This mechanism can be used to predict the advantages and disadvantages of alkali metals, iron, titanium, and aluminum components in raw materials, optimize low-temperature rapid firing formulas, suppress firing deformation, control pore defects, and improve the mechanical properties of finished products. It provides micro theoretical support for the industrialization, stabilization, and high-quality production of local ceramics in southwestern China. Full article

The rapid proliferation of image editing tools poses unprecedented challenges to information sustainability and social trust, as malicious digital forgeries can easily contaminate public discourse, news reporting, and legal forensics. Advanced image editing techniques make image tampering increasingly difficult for the naked eye to recognize, which requires highly accurate methods for detecting and localizing image tampering. In this paper, an end-to-end network model named AEM-Net is proposed. AEM-Net combines RGB and SRM features to enhance the model’s sensitivity to image details and potentially tampered regions through multi-scale feature extraction and fusion. AEM-Net consists of the HRNet-based Multiscale Feature Extraction Module and the Context-Aggregated Pyramid Localization Module (CAPLM). The multi-scale feature extraction module utilizes the Attentional Perceptual Feature Fusion Module to adaptively focus on the anomalous regions. In contrast, the CAPLM utilizes the Expanded Convolutional Feedback Enhancement Module to effectively exploit contextual feature information for achieving pixel-level localization of tampered regions. Experimental results on public benchmark datasets demonstrate that AEM-Net achieves superior performance compared with existing state-of-the-art methods. In particular, AEM-Net achieves an AUC/F1 score of 95.36%/67.19% on CasiaV1, 93.25%/79.75% on Coverage, and 87.36%/66.24% on NIST16, while requiring only 0.09 s to process a single image, demonstrating both high localization accuracy and computational efficiency. Full article