The purpose is to explore the feature recognition, diagnosis, and forecasting performances of Semi-Supervised Support Vector Machines (S3VMs) for brain image fusion Digital Twins (DTs). Both unlabeled labeled data are used regarding many in images, semi supervised support vector machine (SVM) proposed. Meantime, AlexNet model improved, images real space mapped virtual by using digital twins. Moreover, a diagnosis prediction twins based on SVM improved constructed. Magnetic Resonance Imaging...

Volatile organic compounds (VOCs) pose a significant threat to human health, and it is essential develop advanced VOC gas sensors by understanding the mechanisms. Metal oxide semiconductor have advantages of high sensitivity, high-temperature resistance, stability, safety. The rational design crystal facets doping components can improve sensing properties. However, time-consuming experimental optimization sensor has tremendously inhibited development new material. Nevertheless, density...

Abstract The ridge beast is a placed on the of roof ancient Chinese buildings, not only has decorative function, and strict hierarchical meaning, number form different levels buildings are strictly limited. detection technology parts important application value in fields fine 3D reconstruction historical dating cultural tourism services. Aiming at problem poor performance traditional algorithms due to high texture similarity discrimination beast, this paper proposed an improved YOLOv3 based...

Introduction Automatic modulation recognition (AMR) plays a crucial role in modern communication systems for efficient signal processing and monitoring. However, existing methods often lack comprehensive feature extraction suffer from inaccuracies. Methods To overcome these challenges, we present multi-task approach leveraging multimodal features. In this method, network is proposed to differentiate between multi-domain features temporal extraction. Simultaneously, capable of extracting at...

Icicle damage is common in tunnels cold regions, posing a major threat to the operational safety of railway trains. To address many drawbaks existing deicing methods, this paper proposes design tunnel vehicle with an icicle detection and positioning system. Firstly, structure designed for scenario which operates. Moreover, experiments are conducted based on You Only Look Once (YOLO) deep-learning method. In addition, ice carried out stereo vision, relative error within 2.2%, proving...

In recent years, the frequency and severity of large-scale forest fires have increased globally, threatening ecosystems, human lives, property while potentially triggering cascading ecological social crises. Despite significant advancements in remote sensing-based fire monitoring, early warning systems, risk zoning, post-fire thermal damage assessment remains insufficiently addressed. This study introduces an innovative approach combining multispectral imaging with a dual annealing...

Abstract Point cloud semantic segmentation is a key step in the scan-to-HBIM process. In order to reduce information process of DGCNN, this paper proposes Mix Pooling Dynamic Graph Convolutional Neural Network (MP-DGCNN) for ancient architecture point clouds. The proposed MP-DGCNN differs from DGCNN mainly two aspects: (1) more comprehensively characterize local topological structure points, edge features are redefined, and distance neighboring points added original features; (2) based on...

Abstract Environmental changes and human activities can cause serious degradation of murals, where sootiness is one the most common problems ancient Chinese indoor murals. In order to improve visual quality a restoration method proposed for murals based on dark channel prior Retinex by bilateral filter using hyperspectral imaging technology. First, radiometric correction denoising through band clipping minimum noise fraction rotation forward inverse transform were applied data mural produce...

The progressive TIN (triangular irregular network) densification (PTD) filter algorithm is widely used for filtering point clouds. In the PTD algorithm, iterative parameters become smaller over entire process of filtering. This leads to performance—especially type I errors algorithm—being poor clouds with high density and standard variance. Hence, an improved variance proposed in this paper. method divides into two stages. first stage, used, smaller. When points belonging higher than a...

Abstract This article presents the virtual restoration of Nine Eyes Watchtower, a significant cultural heritage site along Great Wall. By applying Seville Charter and digital technology, detailed workflow is developed. The methodology involves acquiring data from multiple sources, including physical evidence, historical data, comparative data. Advanced survey technologies, architectural knowledge, research, computer modelling techniques are integrated to accurately capture significance...

The Range–Doppler (R-D) model is extensively employed for the geometric processing of Synthetic Aperture Radar (SAR) images. Refining sensor motion state and imaging parameters most common method achieving high-precision using R-D model, comprising a process that involves numerous complex computations. In this study, we introduce novel approach to improve positioning accuracy implementing low-order polynomial compensate original errors without altering initial parameters. We also design...

Optical remote sensing images are of considerable significance in a plethora applications, including feature recognition and scene semantic segmentation. However, the quality is compromised by influence various types noise, which has detrimental impact on their practical applications aforementioned fields. Furthermore, intricate texture characteristics inherent to present significant hurdle removal noise restoration image details. In order address these challenges, we propose interaction...

Aerial images are widely used for building detection. However, the performance of detection methods based on aerial alone is typically poorer than that using both LiDAR and image data. To overcome these limitations, we present a framework detecting regularizing boundary individual buildings feature-level-fusion strategy features from dense matching (DIM) point clouds, orthophoto original images. The proposed divided into three stages. In first stage, DIM points fused to detect obtain...

The Ming and Qing Dynasty type of official-style architecture roof can provide plenty prior knowledge relating to the structure size these works architecture, plays an important role in fields 3D modeling, semantic recognition culture inheriting. In this paper, we take point cloud as data source, automatic classification method for based on hierarchical network is illustrated. To classify roofs into correct categories, characteristics different types are analyzed features including SoRs,...

The ancient roof decorative components of the official-style architectures from Ming and Qing dynasties in China hold both physical symbolic significance. These structures are essential objects three-dimensional (3D) modeling for traditional Chinese cultural preservation. Although can be surveyed by a 3D laser scanner, complex geometry diverse pattern their make point cloud reconstruction challenging, or at some points, nearly impossible fully automated manner. In this paper, we propose...

Abstract Dougong, a distinctive component of ancient wooden architecture, holds significant importance for the preservation and restoration such structures. In realm cultural heritage preservation, application deep learning has gradually expanded, demonstrating remarkable effectiveness. Point cloud serving as crucial source encapsulates various information, enabling support tasks like Dougong point classification completion. The quality datasets directly impacts outcomes learning, they serve...

Abstract Dougong, a distinctive component of ancient Chinese wooden architecture, holds significant importance for the preservation and restoration such structures. In particular, northern official-style buildings represent pinnacle construction techniques. realm cultural heritage preservation, application deep learning has gradually expanded, demonstrating remarkable effectiveness. Point cloud serving as crucial source encapsulates various information, enabling support tasks like Dougong...

Communication interference identification is critical in electronic countermeasures. However, existed methods based on deep learning, such as convolutional neural networks (CNNs) and transformer, seldom take both local characteristics global feature information of the signal into account. Motivated by convolution property CNNs attention mechanism we designed a novel network that combines architectures, which make better use signals. Additionally, recognizing challenge distinguishing...

Point cloud semantic segmentation has played an important role in the scan-to-BIM process of Ming and Qing Dynasties’ official-style architecture roof. To overcome complexity roof components’ shape scale differences between different component types, a point method for MQDOAs considering construction regulations is proposed this paper. This composed two stages. In first stage, features from rules MQDOAs, including normalized symmetrical distance (NSD), relative height (RH) local difference...

A waterlogging assessment framework based on the stormwater management model (SWMM), considering microtopography, is proposed (taking into account complexity of underlying surface, which contains various micro-surface features within Chinese ancient city site). We used site PuZhou as study case and detailed in this paper. First, land cover was classified by combining analysis UAVs field surveys; subsequently, a revised sub-catchment division method to obtain more accurate reliable...

Abstract. Chinese ancient architecture is a valuable heritage wealth, especially for roof that reflects the construction age, structural features and cultural connotation. Point cloud data, as flexible representation with characteristics of fast, precise, non-contact, plays crucial role in variety applications architectural heritage, such 3D fine reconstruction, HBIM, disaster monitoring etc. However, there are still many limitations data editing tasks need to be worked out manually, which...

Abstract Environmental changes and human activities can cause serious degradation of murals, where sootiness is one the most common problems ancient Chinese indoor murals. In order to improve visual quality a restoration method proposed for murals based on dark channel prior Retinex by bilateral filter using hyperspectral imaging technology. First, radiometric correction denoising through band clipping minimum noise fraction rotation forward inverse transform were applied data mural produce...