Search Results (12,680)

Quantum machine learning (QML) has emerged as a promising approach for enhancing image classification by exploiting quantum computational principles such as superposition and entanglement. However, practical applications on complex datasets like CIFAR-100 remain limited due to the low expressivity of shallow circuits and challenges in circuit optimization. In this study, we propose HQCNN–REGA—a novel hybrid quantum–classical convolutional neural network architecture that integrates data re-uploading and genetic algorithm optimization for improved performance. The data re-uploading mechanism allows classical inputs to be encoded multiple times into quantum states, enhancing the model’s capacity to learn complex visual features. In parallel, a genetic algorithm is employed to evolve the quantum circuit architecture by optimizing gate sequences, entanglement patterns, and layer configurations. This combination enables automatic discovery of efficient parameterized quantum circuits without manual tuning. Experiments on the MNIST and CIFAR-100 datasets demonstrate state-of-the-art performance for quantum models, with HQCNN–REGA outperforming existing quantum neural networks and approaching the accuracy of advanced classical architectures. In particular, we compare our model with classical convolutional baselines such as ResNet-18 to validate its effectiveness in real-world image classification tasks. Our results demonstrate the feasibility of scalable, high-performing quantum–classical systems and offer a viable path toward practical deployment of QML in computer vision applications, especially on noisy intermediate-scale quantum (NISQ) hardware. Full article

Skeletal muscle regeneration depends on muscle stem cells, which give rise to myoblasts that drive muscle growth, repair, and maintenance. In bats—the only mammals capable of powered flight—these processes must also sustain contractile performance under extreme mechanical and metabolic stress. However, the cellular and molecular mechanisms underlying bat muscle physiology remain largely unknown. To enable mechanistic investigation of these traits, we established the first myoblast cell lines from the pectoralis muscle of Pteronotus mesoamericanus, a highly maneuverable aerial insectivore. Using both spontaneous immortalization and exogenous hTERT/CDK4 gene overexpression, we generated two stable cell lines that retain proliferative capacity and differentiate into contractile myotubes. These cells exhibit frequent spontaneous contractions, suggesting robust functional integrity at the neuromuscular junction. In parallel, we performed transcriptomic and metabolic profiling of native pectoralis tissue in the closely related Pteronotus parnellii to define molecular programs supporting muscle specialization. Gene expression analyses revealed enriched pathways for muscle metabolism, development, and regeneration, highlighting supporting roles in tissue maintenance and repair. Consistent with this profile, the flight muscle is triglyceride-rich, which serves as an important fuel source for energetically demanding processes, including muscle contraction and cellular recovery. Integration of transcriptomic and metabolic data identified three key metabolic modules—glucose utilization, lipid handling, and nutrient signaling—that likely coordinate ATP production and support metabolic flexibility. Together, these complementary tools and datasets provide the first in vitro platform for investigating bat muscle research, enabling direct exploration of muscle regeneration, metabolic resilience, and evolutionary physiology. Full article

This paper explores the intervening role in SEP performance of corporate environmental, cultural, and ethnic activities (ECEAs) and diversity, equity, inclusion, and social initiatives (DEISIs) on blockchain adoption (BCA) strategy, particularly useful in the Western Balkans (WB), which demands transparency due to extended fraud and ethnic complexities. In this domain, a question has been raised: In BCA strategies, is there any correlation between SEP performance and ECEAs and DEISIs in a mediating role? A serial mediation model was tested on a dataset of 630 WB and EU companies, and the research conceptual model was validated by CFA (Confirmation Factor Analysis), and the SEM (Structural Equation Model) fit was assessed. We found a statistically sound (significant, positive) correlation between BCA and ESG success performance, especially in the innovation and integrity ESG performance success indicators, when DEISIs mediate. The findings confirmed the influence of technology, and environmental, cultural, ethnic, and social factors on BCA strategy. The findings revealed some important issues of BCA that are of worth to WB companies’ managers to address BCA for better performance. This study adds to the literature on corporate blockchain transformation, especially for organizations seeking investment opportunities in new international markets to diversify their assets and skill pool. Furthermore, it contributes to a deeper understanding of how DEI initiatives impact the correlation between business transformation and socioeconomic performance, which is referred to as the “social impact”. Full article

In recent years, large-scale linear infrastructure developments have been developed across hundreds of kilometers of permafrost regions on the Qinghai–Tibet Plateau. The implementation of major engineering projects, including the Qinghai–Tibet Highway, oil pipelines, communication cables, and the Qinghai–Tibet Railway, has spurred intensified research into permafrost dynamics. Climate warming has accelerated permafrost degradation, leading to a range of geological hazards, most notably widespread thermokarst landslides. This study investigates the spatiotemporal distribution patterns and influencing factors of thermokarst landslides in Qinghai Province through an integrated approach combining field surveys, remote sensing interpretation, and statistical analysis. The study utilized multi-source datasets, including Landsat-8 imagery, Google Earth, GF-1, and ZY-3 satellite data, supplemented by meteorological records and geospatial information. The remote sensing interpretation identified 1208 cryogenic hazards in Qinghai’s permafrost regions, comprising 273 coarse-grained soil landslides, 346 fine-grained soil landslides, 146 thermokarst slope failures, 440 gelifluction flows, and 3 frost mounds. Spatial analysis revealed clusters of hazards in Zhiduo, Qilian, and Qumalai counties, with the Yangtze River Basin and Qilian Mountains showing the highest hazard density. Most hazards occur in seasonally frozen ground areas (3500–3900 m and 4300–4900 m elevation ranges), predominantly on north and northwest-facing slopes with gradients of 10–20°. Notably, hazard frequency decreases with increasing permafrost stability. These findings provide critical insights for the sustainable development of cold-region infrastructure, environmental protection, and hazard mitigation strategies in alpine engineering projects. Full article

The demand for high data rates and large system capacity has posed significant challenges for medium access control (MAC) methods. Successive interference cancellation (SIC) is a classical multi-user detection (MUD) method; however, it suffers from an error propagation problem. To address this deficiency, we propose a method called Virtual Signal Processing-Based Integrated Multi-User Detection (VSP-IMUD). In VSP-IMUD, the received mixed multi-user signals are treated as an equivalent signal. The channel ambiguity corresponding to each user’s signal is then examined. For channels with non-zero ambiguity values, the signal components are detected using zero-forcing (ZF) reception. Next, the detected ambiguous signal components are reconstructed and subtracted from the received mixed signal using SIC. Once all the ambiguous signals are detected, the remaining signal components with zero ambiguity values are equated to a virtual integrated signal, to which a matched filter (MF) is applied. Finally, by selecting the signal with the highest channel gain and adopting its data as the reference symbol, the remaining signals’ dataset can be determined. Our theoretical analysis and simulation results demonstrate that VSP-IMUD effectively reduces the frequency of SIC applications and mitigates its error propagation effects, thereby improving the system’s bit-error rate (BER) performance. Full article

Timely and accurate identification of surface damage in hydraulic structures is essential for maintaining structural integrity and ensuring operational safety. Traditional manual inspections are time-consuming, labor-intensive, and prone to subjectivity, especially for large-scale or inaccessible infrastructure. Leveraging advancements in aerial imaging, unmanned aerial vehicles (UAVs) enable efficient acquisition of high-resolution visual data across expansive hydraulic environments. However, existing deep learning (DL) models often lack architectural adaptations for the visual complexities of UAV imagery, including low-texture contrast, noise interference, and irregular crack patterns. To address these challenges, this study proposes a lightweight, robust, and high-precision segmentation framework, called LFPA-EAM-Fast-SCNN, specifically designed for pixel-level damage detection in UAV-captured images of hydraulic concrete surfaces. The developed DL-based model integrates an enhanced Fast-SCNN backbone for efficient feature extraction, a Lightweight Feature Pyramid Attention (LFPA) module for multi-scale context enhancement, and an Edge Attention Module (EAM) for refined boundary localization. The experimental results on a custom UAV-based dataset show that the proposed damage detection method achieves superior performance, with a precision of 0.949, a recall of 0.892, an F1 score of 0.906, and an IoU of 87.92%, outperforming U-Net, Attention U-Net, SegNet, DeepLab v3+, I-ST-UNet, and SegFormer. Additionally, it reaches a real-time inference speed of 56.31 FPS, significantly surpassing other models. The experimental results demonstrate the proposed framework’s strong generalization capability and robustness under varying noise levels and damage scenarios, underscoring its suitability for scalable, automated surface damage assessment in UAV-based remote sensing of civil infrastructure. Full article

The strategic allocation of advertising billboards has become a critical aspect of urban planning and resource management. While previous studies have explored site selection based on road network and population data, they have often overlooked the diminishing marginal returns of overlapping coverage and neglected to efficiently process large-scale urban datasets. To address these challenges, this study proposes two complementary optimization methods: an enhanced greedy algorithm based on geometric modeling and spatial acceleration techniques, and a reinforcement learning approach using Proximal Policy Optimization (PPO). The enhanced greedy algorithm incorporates population-weighted road coverage modeling, employs a geometric series to capture diminishing returns from overlapping coverage, and integrates spatial indexing and parallel computing to significantly improve scalability and solution quality in large urban networks. Meanwhile, the PPO-based method models billboard site selection as a sequential decision-making process in a dynamic environment, where agents adaptively learn optimal deployment strategies through reward signals, balancing coverage gains and redundancy penalties and effectively handling complex multi-step optimization tasks. Experiments conducted on Wuhan’s road network demonstrate that both methods effectively optimize population-weighted billboard coverage under budget constraints while enhancing spatial distribution balance. Quantitatively, the enhanced greedy algorithm improves coverage effectiveness by 18.6% compared to the baseline, while the PPO-based method further improves it by 4.3% with enhanced spatial equity. The proposed framework provides a robust and scalable decision-support tool for urban advertising infrastructure planning and resource allocation. Full article

Multimodal review helpfulness prediction (MRHP) aims to identify the most helpful reviews by leveraging both textual and visual information. However, prior studies have primarily focused on modeling interactions between these modalities, often overlooking the consistency between review content and ratings, which is a key indicator of review credibility. To address this limitation, we propose CRCNet (Content–Rating Consistency Network), a novel MRHP model that jointly captures the semantic consistency between review content and ratings while modeling the complementary characteristics of text and image modalities. CRCNet employs RoBERTa and VGG-16 to extract semantic and visual features, respectively. A co-attention mechanism is applied to capture the consistency between content and rating, and a Gated Multimodal Unit (GMU) is adopted to integrate consistency-aware representations. Experimental results on two large-scale Amazon review datasets demonstrate that CRCNet outperforms both unimodal and multimodal baselines in terms of MAE, MSE, RMSE, and MAPE. Further analysis confirms the effectiveness of content–rating consistency modeling and the superiority of the proposed fusion strategy. These findings suggest that incorporating semantic consistency into multimodal architectures can substantially improve the accuracy and trustworthiness of review helpfulness prediction. Full article

Multimodal sentiment analysis (MSA) faces key challenges such as incomplete modality inputs, long-range temporal dependencies, and suboptimal fusion strategies. To address these, we propose MGMR-Net, a Mamba-guided multimodal reconstruction and fusion network that integrates modality-aware reconstruction with text-centric fusion within an efficient state-space modeling framework. MGMR-Net consists of two core components: the Mamba-collaborative fusion module, which utilizes a two-stage selective state-space mechanism for fine-grained cross-modal alignment and hierarchical temporal integration, and the Mamba-enhanced reconstruction module, which employs continuous-time recurrence and dynamic gating to accurately recover corrupted or missing modality features. The entire network is jointly optimized via a unified multi-task loss, enabling simultaneous learning of discriminative features for sentiment prediction and reconstructive features for modality recovery. Extensive experiments on CMU-MOSI, CMU-MOSEI, and CH-SIMS datasets demonstrate that MGMR-Net consistently outperforms several baseline methods under both complete and missing modality settings, achieving superior accuracy, robustness, and generalization. Full article

Remote sensing images are often degraded by atmospheric haze, which not only reduces image quality but also complicates information extraction, particularly in high-level visual analysis tasks such as object detection and scene classification. State-space models (SSMs) have recently emerged as a powerful paradigm for vision tasks, showing great promise due to their computational efficiency and robust capacity to model global dependencies. However, most existing learning-based dehazing methods lack physical interpretability, leading to weak generalization. Furthermore, they typically rely on spatial features while neglecting crucial frequency domain information, resulting in incomplete feature representation. To address these challenges, we propose ScaleViM-PDD, a novel network that enhances an SSM backbone with two key innovations: a Multi-scale EfficientViM with Physical Decoupling (ScaleViM-P) module and a Dual-Domain Fusion (DD Fusion) module. The ScaleViM-P module synergistically integrates a Physical Decoupling block within a Multi-scale EfficientViM architecture. This design enables the network to mitigate haze interference in a physically grounded manner at each representational scale while simultaneously capturing global contextual information to adaptively handle complex haze distributions. To further address detail loss, the DD Fusion module replaces conventional skip connections by incorporating a novel Frequency Domain Module (FDM) alongside channel and position attention. This allows for a more effective fusion of spatial and frequency features, significantly improving the recovery of fine-grained details, including color and texture information. Extensive experiments on nine publicly available remote sensing datasets demonstrate that ScaleViM-PDD consistently surpasses state-of-the-art baselines in both qualitative and quantitative evaluations, highlighting its strong generalization ability. Full article

Compared to traditional real-valued neural networks, which process only amplitude information, complex-valued neural networks handle both amplitude and phase information, leading to superior performance in polarimetric synthetic aperture radar (PolSAR) image classification tasks. This paper proposes a multi-scale feature extraction (MSFE) method based on a 3D complex-valued network to improve classification accuracy by fully leveraging multi-scale features, including phase information. We first designed a complex-valued three-dimensional network framework combining complex-valued 3D convolution (CV-3DConv) with complex-valued squeeze-and-excitation (CV-SE) modules. This framework is capable of simultaneously capturing spatial and polarimetric features, including both amplitude and phase information, from PolSAR images. Furthermore, to address robustness degradation from limited labeled samples, we introduced a multi-scale learning strategy that jointly models global and local features. Specifically, global features extract overall semantic information, while local features help the network capture region-specific semantics. This strategy enhances information utilization by integrating multi-scale receptive fields, complementing feature advantages. Extensive experiments on four benchmark datasets demonstrated that the proposed method outperforms various comparison methods, maintaining high classification accuracy across different sampling rates, thus validating its effectiveness and robustness. Full article

Digital image quality is crucial for reliable analysis in applications such as medical imaging, satellite remote sensing, and video surveillance. However, traditional denoising methods struggle to balance noise removal with detail preservation and lack adaptability to various types of noise. We propose a novel three-module architecture for image denoising, comprising a generator, a dual-path-UNet-based denoiser, and a discriminator. The generator creates synthetic noise patterns to augment training data, while the dual-path-UNet denoiser uses multiple receptive field modules to preserve fine details and dense feature fusion to maintain global structural integrity. The discriminator provides adversarial feedback to enhance denoising performance. This dual-path adversarial training mechanism addresses the limitations of traditional methods by simultaneously capturing both local details and global structures. Experiments on the SIDD, DND, and PolyU datasets demonstrate superior performance. We compare our architecture with the latest state-of-the-art GAN variants through comprehensive qualitative and quantitative evaluations. These results confirm the effectiveness of noise removal with minimal loss of critical image details. The proposed architecture enhances image denoising capabilities in complex noise scenarios, providing a robust solution for applications that require high image fidelity. By enhancing adaptability to various types of noise while maintaining structural integrity, this method provides a versatile tool for image processing tasks that require preserving detail. Full article

Landslide displacement prediction is crucial for disaster mitigation, yet traditional methods often fail to capture the complex, non-stationary spatiotemporal dynamics of slope evolution. This study introduces an enhanced prediction framework that integrates multi-scale signal processing with dynamic, geology-aware graph modeling. The proposed methodology first employs the Maximum Overlap Discrete Wavelet Transform (MODWT) to denoise raw Global Navigation Satellite System (GNSS)-monitored displacement time series data, enhancing the underlying deformation features. Subsequently, a geology-aware graph is constructed, using the temporal correlation of displacement series as a practical proxy for physical relatedness between monitoring nodes. The framework’s core innovation lies in a dynamic graph optimization model with low-rank constraints, which adaptively refines the graph topology to reflect time-varying inter-sensor dependencies driven by factors like mining activities. Experiments conducted on a real-world dataset from an active open-pit mine demonstrate the framework’s superior performance. The DCRNN-proposed model achieved the highest accuracy among eight competing models, recording a Root Mean Square Error (RMSE) of 2.773 mm in the Vertical direction, a 39.1% reduction compared to its baseline. This study validates that the proposed dynamic graph optimization approach provides a robust and significantly more accurate solution for landslide prediction in complex, real-world engineering environments. Full article

Unmanned platforms such as unmanned aerial vehicles, unmanned ground vehicles, and autonomous underwater vehicles often face challenges of data, device, and model heterogeneity when performing collaborative data processing tasks. Existing research does not simultaneously address issues from these three aspects. To address this issue, this study designs an unmanned platform cluster architecture inspired by the cloud-edge-end model. This architecture integrates federated learning for privacy protection, leverages the advantages of distributed model training, and utilizes edge computing’s near-source data processing capabilities. Additionally, this paper proposes a federated edge intelligence method (DSIA-FEI), which comprises two key components. Based on traditional federated learning, a data sharing mechanism is introduced, in which data is extracted from edge-side platforms and placed into a data sharing platform to form a public dataset. At the beginning of model training, random sampling is conducted from the public dataset and distributed to each unmanned platform, so as to mitigate the impact of data distribution heterogeneity and class imbalance during collaborative data processing in unmanned platforms. Moreover, an intelligent model aggregation strategy based on similarity measurement and loss gradient is developed. This strategy maps heterogeneous model parameters to a unified space via hierarchical parameter alignment, and evaluates the similarity between local and global models of edge devices in real-time, along with the loss gradient, to select the optimal model for global aggregation, reducing the influence of device and model heterogeneity on cooperative learning of unmanned platform swarms. This study carried out extensive validation on multiple datasets, and the experimental results showed that the accuracy of the DSIA-FEI proposed in this paper reaches 0.91, 0.91, 0.88, and 0.87 on the FEMNIST, FEAIR, EuroSAT, and RSSCN7 datasets, respectively, which is more than 10% higher than the baseline method. In addition, the number of communication rounds is reduced by more than 40%, which is better than the existing mainstream methods, and the effectiveness of the proposed method is verified. Full article

Synthetic aperture radar (SAR), as an active microwave imaging system, has the capability of all-weather and all-time observation. In response to the challenges of aircraft detection in SAR images due to the complex background interference caused by the continuous scattering of airport buildings and the demand for real-time processing, this paper proposes a YOLOv7-MTI recognition model that combines the attention mechanism and involution. By integrating the MTCN module and involution, performance is enhanced. The Multi-TASP-Conv network (MTCN) module aims to effectively extract low-level semantic and spatial information using a shared lightweight attention gate structure to achieve cross-dimensional interaction between “channels and space” with very few parameters, capturing the dependencies among multiple dimensions and improving feature representation ability. Involution helps the model adaptively adjust the weights of spatial positions through dynamic parameterized convolution kernels, strengthening the discrete strong scattering points specific to aircraft and suppressing the continuous scattering of the background, thereby alleviating the interference of complex backgrounds. Experiments on the SAR-AIRcraft-1.0 dataset, which includes seven categories such as A220, A320/321, A330, ARJ21, Boeing737, Boeing787, and others, show that the mAP and mRecall of YOLOv7-MTI reach 93.51% and 96.45%, respectively, outperforming Faster R-CNN, SSD, YOLOv5, YOLOv7, and YOLOv8. Compared with the basic YOLOv7, mAP is improved by 1.47%, mRecall by 1.64%, and FPS by 8.27%, achieving an effective balance between accuracy and speed, providing research ideas for SAR aircraft recognition. Full article