检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Mumuxin Cai Xupeng Wang Ferdous Sohel Hang Lei School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China School of Information Technology Murdoch University Murdoch Australia

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

The advancements in light detection and ranging (LiDAR) sensors and 3D object detection techniques have boosted their deployment in a wide range of applications, autonomous driving, in particular. However, it has been demonstrated that 3D object detection models based on deep neural networks exhibit vulnerabilities and tend to be susceptible to adversarial attacks. Nonetheless, there exists a scarcity of defensive strategies explicitly tailored for mitigating adversarial attacks on 3D object detection. In this paper, we introduce LiDAR-SPD, a novel approach to defend against adversarial attacks targeting LiDAR-based 3D object detectors. Specifically, a spherical purification unit is designed, which encompasses two pivotal processes: spherical projection and spherical diffusion. The former leverages a spatial projection strategy to eliminate adversarial point clouds inserted in occluded regions, while the latter employs a diffusion model to regenerate points, rendering it closer to a pristine LiDAR scene. Comprehensive experiments conducted on the KITTI dataset demonstrate that our proposed LiDAR-SPD method effectively thwarts various types of adversarial attacks, decreasing the attack success rates against 3D object detectors by 60%.

关键词： Solid modeling Three-dimensional displays Laser radar Purification Object detection Detectors Signal processing Diffusion models Robustness Speech processing

来源：评论

学校读者我要写书评

暂无评论

A multimodal data-driven framework and system for evaluating the ideological and political education of courses under the Chinese new engineering science 24

A multimodal data-driven framework and system for evaluating...

引用

Proceedings of the 2024 2nd International Conference on information Education and Artificial Intelligence

作者： Jun Zhang Shihan Zhang School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu Sichuan China

ISBN: (纸本)9798400711732

To address the existing challenges in the teaching ideological and political assessment system within Chinese universities, particularly in the context of New engineering disciplines, this study proposes a new six-dimensional teaching ideological and political evaluation framework. This framework is designed to provide a comprehensive, systematic, and scientifically grounded approach to evaluating the integration of ideological and political education into engineering curricula. By focusing on six key dimensions—socialist core values, Chinese excellent traditional culture, professional ethics and engineering ethics, craftsmanship and creative awareness, teamwork and communication skills, and social responsibility and patriotism—the framework ensures that ideological and political education is not only embedded in the curriculum but also effectively assessed and continuously improved. To operationalize this framework, a teaching ideological and political evaluation system was designed and implemented, leveraging multimodal data-driven algorithms. This system integrates diverse data types, such as text, images, audio, video, and behavioral data, to provide a holistic and objective assessment of teaching effectiveness. The use of advanced data mining and machine learning techniques enables the system to analyze complex datasets, extract meaningful insights, and generate actionable feedback for educators and administrators. The introduction of this pedagogical and political evaluation system provides a scientific and efficient evaluation system for educational administrators to assess potentially valuable ideological and political education in the teaching and learning process and apply it to the management of ideological and political work.

关键词： Curriculum Ideological and Political Education

来源：评论

学校读者我要写书评

暂无评论

RGB-Based Category-Level Object Pose Estimation via Depth Recovery and Adaptive Refinement

引用

IEEE Robotics and Automation Letters 2025年第6期10卷 5377-5384页

作者： Yang, Hui Sun, Wei Liu, Jian Zheng, Jin Zeng, Zhiwen Mian, Ajmal Hunan University National Engineering Research Center for Robot Visual Perception and Control Technology College of Electrical and Information Engineering Changsha410082 China Hunan University State Key Laboratory of Advanced Design and Manufacturing for Vehicle Body Changsha410082 China Central South University School of Architecture and Art Changsha410082 China University of Western Australia Department of Computer Science and Software Engineering CrawleyWA6009 Australia

Category-level pose estimation methods have received widespread attention as they can be generalized to intra-class unseen objects. Although RGB-D-based category-level methods have made significant progress, reliance on depth image limits practical application. RGB-based methods offer a more practical and cost-effective solution. However, current RGB-based methods struggle with object geometry perception, leading to inaccurate pose estimation. We propose depth recovery and adaptive refinement for category-level object pose estimation from a single RGB image. We leverage DINOv2 to reconstruct the coarse scene-level depth from the input RGB image and propose an adaptive refinement network based on an encoder-decoder architecture to dynamically improve the predicted coarse depth and reduce its gap from the ground truth. We introduce a 2D–3D consistency loss to ensure correspondence between the point cloud obtained from depth projection and the objects in the 2D image. This consistency supervision enables the model to maintain alignment between the depth image and the point cloud. Finally, we extract features from the refined point cloud and feed them into two confidence-aware rotation regression branches and a translation and size prediction residual branch for end-to-end training. Decoupling the rotation matrix provides a more direct representation, which facilitates parameter optimization and gradient propagation. Extensive experiments on the REAL275 and CAMERA25 datasets demonstrate the superior performance of our method. Real-world estimation and robotic grasping experiments demonstrate our model robustness to occlusion, clutter environments, and low-textured objects. Our code and robotic grasping video are available at DA-Pose. © 2016 IEEE.

关键词： Depth perception

来源：评论

学校读者我要写书评

暂无评论

GL-CrackNet: A Lightweight Network for Crack Segmentation in Vehicular Systems 18th

GL-CrackNet: A Lightweight Network for Crack Segmentation i...

引用

18th China Conference on Wireless Sensor Networks, CWSN 2024

作者： Zhang, Jing Jiang, Nan Li, Ziyi Zou, Zefeng Yu, Zesheng Zhang, Yuejing School of Information and Software Engineering East China University of Technology Jiangxi Nanchang330013 China

ISBN: (纸本)9789819621859

Deep neural networks in IoV must meet stringent requirements for real-time performance, low latency, lightweight design, and low power consumption. However, most existing deep neural networks are challenged by their complex structures, which demand significant time and computational resources for feature extraction. This limitation hinders their application on portable devices, particularly in the context of in-vehicle image and video processing. To address this, we introduce GL-CrackNet, a lightweight deep neural network tailored for crack detection on portable devices. GL-CrackNet is based on DeepLabv3+ and includes an encoder and decoder. The encoder integrates the GhostNet embedded network and two CCAM modules to capture a comprehensive representation of features. The decoder employs RFB and Dense Aggregation modules for focused feature processing and fusion. On a custom dataset, GL-CrackNet achieves a mIoU of 80.93%, surpassing the baseline by 0.9%–1.5%. This demonstrates a significant improvement in crack detection efficiency while maintaining low storage and power consumption. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Toward Understanding Federated Learning over Unreliable Networks

IEEE Transactions on Machine Learning in Communications and ...

引用

IEEE Transactions on Machine Learning in Communications and Networking 2025年 3卷 80-97页

作者： Feng, Chenyuan Arafa, Ahmed Chen, Zihan Zhao, Mingxiong Quek, Tony Q. S. Yang, Howard H. EURECOM Department of Communication Biot06410 France University of North Carolina at Charlotte Department of Electrical and Computer Engineering CharlotteNC28223 United States Singapore University of Technology and Design Information Systems Technology and Design Pillar Tampines487372 Singapore Yunnan University Engineering Research Center of Cyberspace National Pilot School of Software Kunming650106 China Zhejiang University ZJU-UIUC Institute Haining314400 China Zhejiang University College of Information Science and Electronic Engineering Hangzhou310007 China University of Illinois at Urbana-Champaign Department of Electrical and Computer Engineering ChampaignIL61820 United States

This paper studies the efficiency of training a statistical model among an edge server and multiple clients via Federated Learning (FL) - a machine learning method that preserves data privacy in the training process - over wireless networks. Due to unreliable wireless channels and constrained communication resources, the server can only choose a handful of clients for parameter updates during each communication round. To address this issue, analytical expressions are derived to characterize the FL convergence rate, accounting for key features from both communication and algorithmic aspects, including transmission reliability, scheduling policies, and momentum method. First, the analysis reveals that either delicately designed user scheduling policies or expanding higher bandwidth to accommodate more clients in each communication round can expedite model training in networks with reliable connections. However, these methods become ineffective when the connection is erratic. Second, it has been verified that incorporating the momentum method into the model training algorithm accelerates the rate of convergence and provides greater resilience against transmission failures. Last, extensive empirical simulations are provided to verify these theoretical discoveries and enhancements in performance. © 2023 CCBY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

MP-NER: Morpho-Phonological Integration Embedding for Chinese Named Entity Recognition

引用

IEEE Access 2025年 13卷 78427-78440页

作者： Li, Pu Cheng, Guopeng Deng, Guojun Qu, Shuanghong Huang, Min Li, Guoxiang Zhengzhou University of Light Industry College of Software Engineering Zhengzhou450002 China Henan Zhongcheng Information Technology Company Ltd. Zhengzhou450000 China Zhengzhou University of Light Industry College of Mathematics and Information Science Zhengzhou450001 China Guangxi University of Finance and Economics Department of Academic Affairs Nanning530031 China

Named Entity Recognition (NER) aims to automatically extract specific entities from unstructured text. Compared with English NER, Chinese NER faces challenges due to heterophony, where the same Chinese character may have different pronunciations and meanings. Additionally, the lack of clear separators between Chinese characters exacerbates these challenges, leading to difficulties in boundary detection and entity category determination. Inspired by the hieroglyphic and phonetic features of Chinese characters, this study proposes a multi-feature fusion embedding model (MP-NER). The model employs CNN for extracting radicals and phonetic features of Chinese characters, combines the encoded information from these features with pre-trained word vectors to generate fusion embedding vectors, and uses a fully-connected layer for feature transformation. Experiments were conducted on the Chinese benchmark datasets Resume, Weibo and MSRA. Compared to current mainstream models, the proposed model demonstrates superior performance in terms of F1 score, F1 score stability, and individual entity recognition accuracy. Ablation experiments further validate the effectiveness of the introduced radicals and phonetic features. The experimental results demonstrate that this model effectively captures the semantic information of Chinese characters, addresses the problem of Chinese character heterophony, and improves entity recognition performance. © 2013 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Anything-DT Modeling: A New Framework for Digital Twin Modeling of Wild Objects from a Single RGB Image

Anything-DT Modeling: A New Framework for Digital Twin Model...

引用

Electrical Automation and Artificial Intelligence (ICEAAI), International Conference on

作者： Jun Geng Siqi Wang Xiaoyun Yi Wanqing Xiong Hongchao Yin Xiaoyu Li The School of Software Xinjiang University Urumqi China The School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798331506797

ISBN: (纸本)9798331506803

Given the significant limitations of current digital twin modeling methods in practical applications, their lack of sufficient generalizability, and the inherent diversity and complexity of real-world objects and environments, digital twin modeling from a single RGB image in unconstrained scenarios faces several maj or challenges. In this paper, we first improve the Segment Anything Model (SAM) and propose the CSAM model, which enables more accurate segmentation of any object. Next, we introduce the Anything-DT Modeling framework, which cleverly integrates the CSAM object segmentation model with a vision-language model to accomplish digital twin modeling tasks using only a single image. The CSAM model can maintain high accuracy and efficiency in complex scenarios, providing high-quality input data for subsequent digital twin modeling. The framework fully utilizes the latest advances in computer vision and natural language processing, providing strong technical support for digital twin modeling, thereby ensuring the feasibility of digital twin modeling from a single RGB image. Compared with existing state-of-the-art methods, the Anything-DT Modeling framework demonstrates its ability to produce detailed and accurate digital twin models for a wide range of objects, showcasing promising potential in overcoming the limitations of current approaches.

关键词： Image segmentation Visualization Solid modeling Accuracy Three-dimensional displays Computational modeling Text to image Data models Digital twins Faces

来源：评论

学校读者我要写书评

暂无评论

Automatic Adjustment of HPA Parameters and Attack Prevention in Kubernetes Using Random Forests 24

Automatic Adjustment of HPA Parameters and Attack Prevention...

引用

9th International Conference on Cloud Computing and Internet of Things, CCIOT 2024

作者： Chan, Huah Yong Zhou, Hanlin Ni, Jingfei Wu, Mengchun Deng, Qing School of Computer Sciences Universiti Sains Malaysia Pulau Pinang Malaysia Xiamen Institute of Software Technology Xiamen China Department of Manzhouli Customs Manzhouli China College of Information Science and Engineering Jimei University Xiamen China

ISBN: (纸本)9798400717161

In this paper, HTTP status codes are used as custom metrics within the HPA as the experimental scenario. By integrating the Random Forest classification algorithm from machine learning, attacks are assessed and predicted, dynamically adjusting the maximum pod parameter in the HPA to manage attack traffic. This approach enables the adjustment of HPA parameters using machine learning scripts in targeted attack scenarios while effectively managing attack traffic. All access from attacking IPs is redirected to honeypot pods, achieving a lower incidence of 5XX status codes through HPA pod adjustments under high load conditions. This method also ensures effective isolation of attack traffic, preventing excessive HPA expansion due to attacks. Additionally, experiments conducted under various conditions demonstrate the importance of setting appropriate thresholds for HPA adjustments. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Incremental Wavelet-capsules: A Cross-Environment Solution for WiFi Identification

引用

IEEE Transactions on Mobile Computing 2025年

作者： Zhou, Zhiyi Lu, Xinxin Wang, Lei Tian, Yu Chen, Yunbo Lu, Bingxian Dalian University of Technology DUT School of Software Technology DUT-RU International School of Information Science and Engineering China Key Laboratory for Ubiquitous Network Service Software of Liaoning Province Dalian China

WiFi-based identity recognition differs from traditional identification technologies as it is not limited by lighting conditions and does not require dense, specialized sensors or wearable devices. This makes it valuable in modern human-machine interactions. However, the diversity of real-world environmental conditions substantially limits the application of existing WiFi-based identity recognition algorithms, particularly when applied across different environments. As a solution, we introduce the incremental wavelet capsule (IWC) model, which combines a newly designed wavelet convolution layer with a capsule network to accelerate precise feature extraction. We adopt a hybrid incremental learning strategy, solving the catastrophic forgetting problem in cross-environment tasks and enabling the model to adapt to new environments in the data stream without forgetting the original environment. Furthermore, we developed a customized data augmentation method for WiFi signals, enhancing the model's adaptability and stability across various environments. Experimental results show that the IWC model achieves an average recognition accuracy of 97.36% across five different environments and maintains an accuracy of 91.5% even when only 5% of the training data from a new environment is used. These findings demonstrate the model's robust performance and practicality in cross-environment scenarios. © 2025 IEEE.

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

Wireless Charging for Uncertain Location Nodes

引用

IEEE Transactions on Mobile Computing 2025年

作者： Lin, Chi Wang, Qiwei Li, Hengyi Hao, Shibo Wang, Yi Wang, Lei Fan, Xin Wu, Guowei Dalian University of Technology DUT School of Software Technology & DUT-RU International School of Information Science and Engineering China Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province Dalian China

Benefiting from Wireless Power Transfer (WPT) technology, Wireless Rechargeable Sensor Networks (WRSNs) effectively address the lifetime bottleneck of sensor nodes, enabling them to work perpetually. Most state-of-the-art studies assume that all WRSNs' information is known or precise in advance. However, sensor nodes may be deployed randomly in a large-scale area, and some critical information (such as node location) may be unavailable or difficult to obtain precisely. In this work, we eliminate the effect of uncertain or imprecise node location and formalize the Maximizing Charging Energy utility for uncertain location nodes problem (i.e., MCE problem). With magnetic resonance coupling and beamforming technologies, we propose a novel node localization method to determine precise node location information. In addition, we present a reinforcement learning framework and a charging path scheduling method to maximize charging energy. To validate the effectiveness of our proposed scheme in real-world scenarios, we conduct test-bed experiments. The results demonstrate that our approach significantly improves charging efficiency by an average of 20.9% in a large-scale network, even when the locations of sensors are entirely unknown. © 2002-2012 IEEE.

关键词： Inductive power transmission

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：