检索结果-内蒙古大学图书馆

Exploring Context Alignment and Structure Perception for Building Change Detection

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Wang, Qi Zhang, Mingwei Ren, Jiawei Li, Qiang Northwestern Polytech Univ Sch Artificial Intelligence Opt & Elect iOPEN Xian 710072 Peoples R China Northwestern Polytech Univ Sch Comp Sci Xian 710072 Peoples R China

Automatically monitoring building changes can assist human experts in disaster rescue, urban planning, and resource protection. Consequently, much research focuses on building change detection. Recently, the methods based on deep learning have achieved impressive performance. However, most of them ignore the effect of bitemporal image misalignment, which is prone to lead to false detection. To this end, a building change detection model with context alignment and structure perception (CASP) is proposed. First, imitating the brain logic of humans to identify changes, a bitemporal interactive alignment module (BIAM) is designed, which suppresses the spatial dislocation noise via a bidirectional reference-guided feature aggregation strategy. Building on this, a difference-induced alignment module (DIAM) is introduced to mitigate the adverse impact of misalignment errors further and improve the accuracy of building change detection. Second, a structure-aware feature fusion module is developed and integrated into the feature encoder, to enhance the discrimination of building representations and highlight the specificity of the proposed method. Extensive experiments on three representative building change detection datasets are implemented to verify the superiority of the above improvements. The quantitative and qualitative results demonstrate that the proposed method achieves competitive performance. The code is available at https://***/ptdoge/CASP.

关键词： Feature extraction Buildings Image edge detection Accuracy Training Remote sensing Deep learning Context modeling computational modeling Biological system modeling Building change detection context alignment feature refinement structure perception

来源：评论

学校读者我要写书评

暂无评论

Beyond the Cloud: Edge Inference for Generative Large Language Models in Wireless Networks

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2025年第1期24卷 643-658页

作者： Zhang, Xinyuan Nie, Jiangtian Huang, Yudong Xie, Gaochang Xiong, Zehui Liu, Jiang Niyato, Dusit Shen, Xuemin BUPT State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Nanyang Technol Univ Sch Comp Sci & Engn Singapore 639798 Singapore Singapore Univ Technol & Design Informat Syst Technol & Design ISTD Pillar Singapore 487372 Singapore Purple Mt Labs Nanjing 211111 Peoples R China Nanyang Technol Univ Coll Comp & Data Sci Singapore 639798 Singapore Univ Waterloo Dept Elect & Comp Engn Waterloo ON N2L 3G1 Canada

Generative Artificial Intelligenge (GAI) is revolutionizing the world with its unprecedented content creation ability. Large Language Model (LLM) is one of its most embraced branches. However, due to LLM's substantial size and resource-intensive nature, it is cloud-hosted, raising concerns about privacy, usage limitations, and latency. In this paper, we propose to utilize ubiquitous distributed wireless edge computing resources for real-time LLM inference. Specifically, we introduce a novel LLM edge inference framework, incorporating batching and model quantization to ensure high throughput inference on resource-limited edge devices. Then, based on the architecture of transformer decoder-based LLMs, we formulate an edge inference optimization problem which is NP-hard, considering batch scheduling and joint allocation of communication and computation resources. The solution is the optimal throughput under edge resource constraints and heterogeneous user requirements on latency and accuracy. To solve this NP-hard problem, we develop an OT-GAH (Optimal Tree-search with Generalized Assignment Heuristics) algorithm with reasonable complexity and 1/2-approximation ratio. We first design the OT algorithm with online tree-pruning for single-edge-node multi-user case, which navigates the inference request selection within the tree structure to miximize throughput. We then consider the multi-edge-node case and propose the GAH algorithm, which recrusively invokes the OT in each node's inference scheduling iteration. Simulation results demonstrate the superiority of OT-GAH batching over other benchmarks, revealing an over 45% time complexity reduction compared to brute-force searching.

关键词： computational modeling Quantization (signal) Accuracy Inference algorithms Throughput Wireless networks Transformers Resource management Optimization Chatbots Generative AI edge inference wireless networks multiuser edge computing

来源：评论

学校读者我要写书评

暂无评论

Large-Language-Model-Enabled Health Management for Internet of Batteries in Electric Vehicles

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第6期12卷 6082-6094页

作者： Peng, Hui Liu, Chenyuan Li, Heng Cent South Univ Sch Elect Informat Changsha 410083 Peoples R China Univ Chinese Acad Sci Sch Optoelect Beijing 100049 Peoples R China

Machine learning models have become a prominent technique for predicting battery state in electric vehicles (EVs). However, due to the significant variability in the operating environments and conditions of different EVs, traditional machine learning models often exhibit limited generalization capabilities. Additionally, the computational limitations of on-board chips in conventional battery management systems (BMSs) can lead to considerable computational overhead. Furthermore, acquiring large-scale battery data for model training can be economically prohibitive. To address these challenges, this article proposes an Internet of Batteries (IoB) approach for battery health management, leveraging large language model (LLM) to monitor battery health. First, this article introduces the concept of IoB in EVs. Subsequently, an experimental IoB system is established. Through comparisons with other machine learning methods, the study demonstrates that LLM exhibit strong generalization capabilities for predicting the battery data of EVs, even with small-scale data fine-tuning. The experimental results suggest that the combination of LLM and IoB may represent a promising advancement over traditional machine learning approaches.

关键词： Batteries Internet of Things Cloud computing computational modeling Battery management systems Monitoring Machine learning Computer architecture Wireless communication Real-time systems Electric vehicles (EVs) Internet of Batteries (IoB) large language model (LLM)

来源：评论

学校读者我要写书评

暂无评论

A Pre-Trained Collaborative Network Leveraging Multi-Scale Depth Information for Image Deraining and Defogging Enhancement

引用

IEEE ACCESS 2025年 13卷 45089-45099页

作者： Mu, Dingdiao Liu, Changjiang Sichuan Univ Sci & Engn Sch Math & Stat Zigong 643000 Peoples R China

Rain and fog are prevalent weather conditions that negatively impact advanced computer vision tasks such as object detection and recognition. The recently proposed NeRD-Rain model attains state of the art performance in rain removal. However, it fails to comprehensively address the veiling effect in complex rainy environments. To enhance the NeRD-Rain model, we integrate a pre-trained depth prediction model, grounded in the atmospheric scattering model, into its architecture. This integration is implemented across multiple scales. Experimental evaluations on the RainCityScapes dataset, where rain and fog co-occur, demonstrate that our proposed network substantially improves the dehazing performance of NeRD-Rain under foggy conditions. Quantitative assessments reveal a 1.5% increase in the Structural Similarity Index Measure (SSIM), a 0.01 reduction in Laplacian variance, and a 1.41 decrease in the Frechet Inception Distance (FID).

关键词： Rain Atmospheric modeling Transformers computational modeling Mathematical models Image restoration Computer vision Feature extraction Data models Adaptation models Information-guided pre-trained model multi-scale depth information NeRD-rain

来源：评论

学校读者我要写书评

暂无评论

MonoDFM: Density Field modeling-Based End-to-End Monocular 3D Object Detection

引用

IEEE ACCESS 2025年 13卷 74015-74031页

作者： Liu, Gang Huang, Xinrui Xie, Xiaoxiao Hubei Univ Technol Sch Comp Sci Wuhan 430068 Peoples R China

Monocular 3D object detection aims to infer the 3D properties of objects from a single RGB image. Existing methods primarily rely on planar features to estimate 3D information directly. However, the limited 3D information available in 2D images often results in suboptimal detection accuracy. To address this challenge, we propose MonoDFM, an end-to-end monocular 3D object detection method based on density field modeling. By modeling the density field from the features of a single image, MonoDFM enables a more accurate transition from 2D to 3D representations, improving 3D attribute prediction accuracy. Unlike traditional depth map methods, which are limited to visible regions, MonoDFM infers geometric information from occluded regions by predicting the scene's density field. Moreover, compared with more complex approaches like Neural Radiance Fields (NeRF), MonoDFM provides a streamlined and efficient prediction process. Experiments conducted on the KITTI dataset show that MonoDFM achieves AP3D of (25.13, 16.61, 13.82) and APBEV of (32.61, 22.14, 18.71) on the KITTI benchmark for the Car category under three difficulty settings (easy, moderate, and hard), achieving competitive performance. Ablation studies further validate the effectiveness of each component. As a result, MonoDFM offers an effective approach to monocular 3D object detection, demonstrating strong performance.

关键词： Three-dimensional displays Solid modeling Object detection computational modeling Neural radiance field Accuracy Feature extraction Depth measurement Point cloud compression Real-time systems 3D reconstruction density field modeling end-to-end detection monocular 3D object detection occlusion handling

来源：评论

学校读者我要写书评

暂无评论

Spatial-Temporal-Geometric Graph Convolutional Network for 3-D Human Pose Estimation From Multiview Video

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Dong, Kaiwen Zhou, Yu Riou, Kevin Yun, Xiao Sun, Yanjing Subrin, Kevin Le Callet, Patrick China Univ Min & Technol IOT Percept Mine Res Ctr Xuzhou 221008 Peoples R China China Univ Min & Technol Sch Informat & Control Engn Xuzhou 221116 Peoples R China Nantes Univ Ecole Cent Nantes CNRS UMR 6004LS2N F-44306 Nantes France Inst Univ France IUF F-75005 Paris France

The multiview 3-D human pose estimation (HPE) effectively addresses challenges, such as depth ambiguity and occlusion faced by monocular methods through the complementing of geometric information from multiple views. However, existing multiview methods often necessitate well-calibrated camera parameters or rely on complex parametric models. These requirements can result in inaccuracies when camera placement is perturbed and can negatively impact the deployability. This article proposes a lightweight approach that synergistically models geometric information with spatial-temporal information without relying on camera parameters, named spatial-temporal-geometric graph convolutional network (STG-GCN). We leverage the inherent connections in multiview sequences of 2-D poses, representing them as a spatial-temporal-geometric graph (STG-Graph), which allows for the simultaneous encoding of spatial-temporal-geometric relations across various joints, consecutive frames, and multiple views. Using a unified graph to model all features, this approach reduces the parameter explosion in existing methods, caused by separate modules extracting spatial, temporal, and view axis features. Building upon the STG-Graph, an adaptive confidence-aware graph convolution (ACA-GraphConv) is proposed to mitigate the impact of unreliable 2-D poses predicted by 2-D pose estimators. This is achieved by leveraging corresponding confidence scores to adjust the graph convolution accordingly. Experimental results on two public datasets demonstrate that our STG-GCN achieves performance comparable to state-of-the-art approaches while significantly reducing parameter volume. Ablation studies also illustrate the effectiveness of our ACA-GraphConv in both monocular and multiview scenarios.

关键词： Three-dimensional displays Cameras Pose estimation Convolution computational complexity Graph convolutional networks computational modeling Training Sun Solid modeling 3-D pose estimation confidence-aware attention (CAA) graph convolutional network (GCN) multiview

来源：评论

学校读者我要写书评

暂无评论

Puzzle-Level Generation With Simple-Tiled and Graph-Based Wave Function Collapse Algorithms

引用

IEEE TRANSACTIONS ON GAMES 2025年第1期17卷 52-61页

作者： Kim, Hwanhee Seo, Beomjoo Kang, Shinjin Hongik Univ Sch Games Jochiwon 30036 Sejong South Korea

This article presents case studies using two wave function collapse (WFC) methods, graph-based WFC and simple tiled WFC, to create playable levels for two logic puzzle games: Strimko (Latin Squares) and Flow (connecting dots with pipes). We then evaluate the quality of the generated levels through extensive experiments. Our results indicate that WFC-generated levels are high quality, follow the graph structures' constraints, and are generated faster than levels generated by depth-first search and genetic algorithms. WFC methods can also adapt to new system specifications, common in puzzle games, by changing only the data instead of the code. This increases the stability of content production based on procedural content generation since it relies on data rather than procedures. Furthermore, WFC methods increase the efficiency of the manual process of creating in-game puzzle levels, allowing game designers to complete more tasks in the same amount of time and create a wider variety of assets.

关键词： Games Data models computational modeling Genetic algorithms Wave functions Three-dimensional displays Machine learning algorithms Procedural content generation (PCG) puzzle game design wave function collapse (WFC) algorithm

来源：评论

学校读者我要写书评

暂无评论

Fusion of Image Filtering and Knowledge-Distilled YOLO Models for Root Canal Failure Diagnosis

引用

IEEE ACCESS 2025年 13卷 66557-66573页

作者： Apurba, Afifa Zain Titu, Md Fahim Shahoriar Pavel, Mahir Afser Naheen, Intisar Tahmid Khan, Riasat North South Univ Dept Elect & Comp Engn Dhaka 1229 Bangladesh

Root canal treatment involves the removal of inflamed pulp from infected teeth and sealing them to prevent re-entry of bacteria and infection. Early and accurate identification of root canal issues is crucial for improving treatment outcomes and minimizing complications. This study proposes a novel method for efficiently detecting failures in root canal treatments by incorporating image filtering techniques into deep learning models. A custom dataset has been collected from Square Hospital Ltd of Dhaka, Bangladesh, comprising 1,600 annotated, filtered radiographs. These images are processed using denoising algorithms (mean, median, Gaussian, contourlet transform, or Bayesian wavelet), non-local means, and BM3D. The YOLO models used for detection included YOLOv5, YOLOv7, and YOLOv8, with YOLOv5 achieving the highest accuracy of 90.6% on the filtered datasets. This work integrates an autodistillation technique with Grounded SAM as the base model for bounding box generation, YOLOv8 as an intermediate model to bridge architectural differences, and YOLOv5 as the target model due to its lightweight design, fewer parameters, and superior performance on the filtered dataset. Knowledge distillation was employed to optimize performance on lightweight models, resulting in precision and recall values of 99.16% and 97.29%, respectively, for YOLOv5. The filtered datasets outperformed raw images, with the Bayesian wavelet and contourlet transform yielding the best results on YOLOv5. This pipeline demonstrates the potential to develop one of the most accurate and clinically applicable diagnostic tools for root canal failure detection by combining deep learning and knowledge distillation techniques with image filtering. This study demonstrates how combining deep learning with advanced image enhancement techniques can provide a highly accurate, clinically relevant tool for the early detection of root canal treatment failures, potentially aiding dentists in making faster and more cons

关键词： Deep learning Teeth Irrigation Dentistry YOLO computational modeling Accuracy Diagnostic radiography Image filtering X-ray imaging Root canal failure detection filtered radiographs YOLO models knowledge distillation image filtering techniques deep learning in dentistry

来源：评论

学校读者我要写书评

暂无评论

CSI Compression for Massive MIMO: Model-Based or Data-Driven?

引用

IEEE WIRELESS COMMUNICATIONS 2025年第1期32卷 22-27页

作者： Chen, Jie Hillery, William J. Mestav, Kursat Rasim Nuzman, Carl Saniee, Iraj Xing, Yunchou Nokia Stand Coppell TX USA Nokia Bell Labs New Providence NJ 07974 USA

With increasing numbers of transmit antennas and the use of wider spectra, channel state information (CSI) feedback for massive MIMO systems can incur a large overhead in uplink capacity. For a 32-antenna system operating on 13 frequency sub-bands, uncompressed channel state feedback would consume about two Mb/s of uplink capacity for each receive antenna, and so compression of the feed-back is essential in practice. Communication theory provides foundational models for the compression of large arrays of numbers and it has been applied to reduce this overhead significantly. However, simplifying assumptions typically used to make these models tractable leave significant room for improvement. With the maturity of machine learning, alternative data-driven approaches have received much attention over the past few years. These approaches have a higher complexity and computational footprint, but demonstrate improved accuracy compared to legacy models and promise more robust customization and interoperability. In this article, we give an overview of both the legacy model-driven and the emerging data-driven approaches for CSI compression, provide macroscopic comparisons of the performance of the two approaches based on both efficiency and flexibility, and discuss the maturity of this technology for large-scale deployment in future 5G-Advanced and 6G systems.

关键词： State feedback computational modeling Transmitting antennas Receiving antennas Massive MIMO Machine learning Complexity theory Uplink Interoperability Channel state information

来源：评论

学校读者我要写书评

暂无评论

Multitenancy in Single Instance of Data Persistence Service for Supporting Low-Code Platforms

引用

IEEE ACCESS 2025年 13卷 13427-13439页

作者： Costa, Julio Gustavo Goncalves, Luiz Marcos Garcia Xavier-de-Souza, Samuel Univ Fed Rio Grande do Norte Programa Posgrad Engn Elect & Comp BR-59078970 Natal RN Brazil Univ Fed Rio Grande do Norte Dept Engn Comp & Automacao BR-59078970 Natal RN Brazil

Corporate digitalization, especially among Small and Medium Enterprises, has led to a significant increase in the demand for scarce professionals with expertise in the IT area, especially in Web Information Systems area. On the other hand, concerns about high levels of resource idleness in the cloud are constant. In this scenario, Low-Code Platforms have gained traction in the software industry, whose most commonly found service is the automation of code generation to perform data persistence tasks driven by data models. This approach, however, implies a mode of operation that is not the most mature among cloud computing providers, implying for each model a service instance running on the provider side. Here, we propose a data persistence service for these platforms that avoids code generation, since it interprets data models at runtime and operates in multi-tenant mode with a single service instance. This approach improves resource sharing, mitigating resource idleness within the platform. In addition, we present experiments to support the technical feasibility of the proposed approach. The proposed solution offers an alternative to code generation methods, with the potential to optimize resource utilization while preserving the flexibility to adapt to changes in data models as business needs evolve.

关键词： Data models Unified modeling language Load modeling Databases Business Software systems Runtime computational modeling Codes Transformers Model driven engineering low code development model interpretation multi-tenancy single instance separation of concerns

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：