检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Cheng, Yuqi Cao, Yunkang Xie, Guoyang Lu, Zhichao Shen, Weiming The State Key Laboratory of Intelligent Manufacturing Equipment and Technology Huazhong University of Science and Technology Wuhan430074 China The Department of Intelligent Manufacturing Contemporary Amperex Technology Limited Ningde352000 China The Department of Computer Science City University of Hong Kong Hong Kong

Detecting anomalies within point clouds is crucial for various industrial applications, but traditional unsupervised methods face challenges due to data acquisition costs, early-stage production constraints, and limited generalization across product categories. To overcome these challenges, we introduce the Multi-View Projection (MVP) framework, leveraging pre-trained Vision-Language Models (VLMs) to detect anomalies. Specifically, MVP projects point cloud data into multi-view depth images, thereby translating point cloud anomaly detection into image anomaly detection. Following zero-shot image anomaly detection methods, pre-trained VLMs are utilized to detect anomalies on these depth images. Given that pre-trained VLMs are not inherently tailored for zero-shot point cloud anomaly detection and may lack specificity, we propose the integration of learnable visual and adaptive text prompting techniques to fine-tune these VLMs, thereby enhancing their detection performance. Extensive experiments on the MVTec 3D-AD and Real3D-AD demonstrate our proposed MVP framework’s superior zero-shot anomaly detection performance and the prompting techniques’ effectiveness. Real-world evaluations on automotive plastic part inspection further showcase that the proposed method can also be generalized to practical unseen scenarios. The code is available at https://***/hustCYQ/MVP-PCLIP. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Differentially Private K-Means Publishing with Distributed Dimensions

Differentially Private K-Means Publishing with Distributed D...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Boyu Zhu Yuan Zhang Tingting Chen Sheng Zhong Computer Science and Technology Department State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Computer Science Department College of Science California State Polytechnic University Pomona USA

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

In this paper, we address the critical concerns related to dataset privacy in the context of k-means clustering publishing within a distributed dimension setting. By leveraging differential privacy mechanisms, we propose a novel framework that integrates a differentially private classifier, constructed through voting based on raw clustering results, and an enhanced generative adversarial network (GAN) simulating the classifier’s behavior in inferring class labels for a public dataset. Our approach generates synthetic clustering results that mimic real outcomes in classification tasks, ensuring differential privacy and minimizing noise. Our contributions include a comprehensive exploration of privacy issues, the introduction of a novel privacy-preserving k-means clustering framework, and theoretical analyses demonstrating sensitivity and differential privacy guarantees. Evaluation on the MNIST dataset demonstrates the effectiveness of the framework, achieving 82.22% accuracy with a (10.48, 10 −9 )-differential-privacy guarantee, compared to 83.45% accuracy without privacy-preserving.

关键词： Differential privacy Privacy Accuracy Sensitivity Publishing Federated learning Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Resilient Time-Varying Formation-Tracking of Multi-UAV systems Against Composite Attacks: A Two-Layered Framework

引用

IEEE/CAA Journal of Automatica Sinica 2023年第4期10卷 969-984页

作者： Xin Gong Michael V.Basin Zhiguang Feng Tingwen Huang Yukang Cui School of Cyber Science and Engineering Southeast UniversityNanjing 210096the School of AstronauticsNorthwestern Polytechnical UniversityXi’an 710072 Department of Mechanical Engineering The University of Hong KongHong Kong 999077China School of Physical and Mathematical Sciences the Autonomous University of Nuevo LeonNaevo Leon 66455Mexico Ningbo Institute of Intelligent Equipment Technology Ningbo 315299China College of Intelligent Systems Science and Engineering Harbin Engineering UniversityHarbin 150001China Texas A&M University at Qatar Doha 23874Qatar Guangdong Key Laboratory of Electromagnetic Control and Intelligent Robots the College of Mechatronics and Control EngineeringShenzhen UniversityShenzhen 518060 Peng Cheng Laboratory Shenzhen 518000China

This paper studies the countermeasure design problems of distributed resilient time-varying formation-tracking control for multi-UAV systems with single-way communications against composite attacks,including denial-of-services(DoS)attacks,false-data injection attacks,camouflage attacks,and actuation attacks(AAs).Inspired by the concept of digital twin,a new two-layered protocol equipped with a safe and private twin layer(TL)is proposed,which decouples the above problems into the defense scheme against DoS attacks on the TL and the defense scheme against AAs on the cyber-physical ***,a topologyrepairing strategy against frequency-constrained DoS attacks is implemented via a Zeno-free event-triggered estimation scheme,which saves communication resources *** upper bound of the reaction time needed to launch the repaired topology after the occurrence of DoS attacks is ***,a decentralized adaptive and chattering-relief controller against potentially unbounded AAs is ***,this novel adaptive controller can achieve uniformly ultimately bounded convergence,whose error bound can be given *** practicability and validity of this new two-layered protocol are shown via a simulation example and a UAV swarm experiment equipped with both Ultra-WideBand and WiFi communication channels.

关键词： Composite attacks multi-UAV systems resilient control time-varying formation-tracking

来源：评论

学校读者我要写书评

暂无评论

Forget less,count better:a domain-incremental self-distillation learning benchmark for lifelong crowd counting

引用

Frontiers of Information technology & Electronic Engineering 2023年第2期24卷 187-202页

作者： Jiaqi GAO Jingqi LI Hongming SHAN Yanyun QU James ZWANG Fei-Yue WANG Junping ZHANG Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200433China Institute of Science and Technology for Brain-inspired Intelligence Fudan UniversityShanghai 200433China Shanghai Center for Brain Science and Brain-inspired Technology Shanghai 201210China School of Information Science and Technology Xiamen UniversityXiamen 361005China College of Information Sciences and Technology the Pennsylvania State UniversityUniversity ParkPA 16802USA State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China

Crowd counting has important applications in public safety and pandemic control.A robust and practical crowd counting system has to be capable of continuously learning with the newly incoming domain data in real-world scenarios instead of fitting one domain ***-the-shelf methods have some drawbacks when handling multiple domains:(1)the models will achieve limited performance(even drop dramatically)among old domains after training images from new domains due to the discrepancies in intrinsic data distributions from various domains,which is called catastrophic forgetting;(2)the well-trained model in a specific domain achieves imperfect performance among other unseen domains because of domain shift;(3)it leads to linearly increasing storage overhead,either mixing all the data for training or simply training dozens of separate models for different domains when new ones are *** overcome these issues,we investigate a new crowd counting task in incremental domain training setting called lifelong crowd *** goal is to alleviate catastrophic forgetting and improve the generalization ability using a single model updated by the incremental ***,we propose a self-distillation learning framework as a benchmark(forget less,count better,or FLCB)for lifelong crowd counting,which helps the model leverage previous meaningful knowledge in a sustainable manner for better crowd counting to mitigate the forgetting when new data arrive.A new quantitative metric,normalized Backward Transfer(nBwT),is developed to evaluate the forgetting degree of the model in the lifelong learning *** experimental results demonstrate the superiority of our proposed benchmark in achieving a low catastrophic forgetting degree and strong generalization ability.

关键词： Crowd counting Knowledge distillation Lifelong learning

来源：评论

学校读者我要写书评

暂无评论

Meta Computing-Driven Optimization of AoI in Industrial IoT: A Hybrid Scheme with Self-Organizing Maps and Reinforcement Learning

引用

IEEE Internet of Things Journal 2025年

作者： Wang, Min Wang, Yike Wang, Nuanlai Pang, Shanchen Sun, Xiaobing Li, Ming Yangzhou University School of Information Engineering Yangzhou225127 China College of Computer Science and Technology Qingdao China College of Computer Science and Technology China State Key Laboratory of Chemical Safety Shandong Key Laboratory of Intelligent Oil and Gas Industrial Software China Shandong Inspur Database Technology Co. Ltd Jinan250101 China

In the domain of Industrial Internet of Things (IIoT) applications, methodologies such as meta computing are essential for ensuring timely and efficient data acquisition within intricate environments characterized by multiple edge devices and isolated sensor networks. The Age of Information (AoI), a key metric for evaluating data timeliness and relevance, has emerged as a focal point for improving decision-making and system responsiveness. However, managing these systems in resourcelimited edge environments is challenging, as traditional methods struggle to link sink node selection with data collection path planning, leading to inefficiency and poor AoI performance. This paper develops a collaborative optimization framework based on meta computing, which dynamically coordinates distributed computational resources as a unified virtual system. It combines self-organizing mapping (SOM) with reinforcement learning (RL) to optimize sink node selection and data collection paths using AoI metrics. Experimental results show the method significantly reduces AoI, improves data freshness, and optimizes energy use, highlighting meta computing's potential for scalable, efficient IIoT solutions. © 2014 IEEE.

关键词： Self organizing maps

来源：评论

学校读者我要写书评

暂无评论

Small Scale Data-Free Knowledge Distillation

Small Scale Data-Free Knowledge Distillation

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： He Liu Yikai Wang Huaping Liu Fuchun Sun Anbang Yao China Telecom Cloud Technology Co. Ltd. Department of Computer Science and Technology BNRist Center State Key Lab on Intelligent Technology and Systems Tsinghua University Intel Labs China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Data-free knowledge distillation is able to utilize the knowledge learned by a large teacher network to augment the training of a smaller student network without accessing the original training data, avoiding privacy, security, and proprietary risks in real applications. In this line of research, existing methods typically follow an inversion-and-distillation paradigm in which a generative adversarial network on-the-fly trained with the guidance of the pre-trained teacher network is used to synthesize a large-scale sample set for knowledge distillation. In this paper, we reexam-ine this common data-free knowledge distillation paradigm, showing that there is considerable room to improve the overall training efficiency through a lens of “small-scale inverted data for knowledge distillation”. In light of three empirical observations indicating the importance of how to balance class distributions in terms of synthetic sample di-versity and difficulty during both data inversion and distillation processes, we propose Small Scale Data-free Knowledge Distillation (SSD-KD). Informulation, SSD-KD introduces a modulating function to balance synthetic samples and a priority sampling function to select proper samples, facilitated by a dynamic replay buffer and a reinforcement learning strategy. As a result, SSD-KD can perform dis-tillation training conditioned on an extremely small scale of synthetic samples (e.g., 10x less than the original training data scale), making the overall training efficiency one or two orders of magnitude faster than many mainstream methods while retaining superior or competitive model performance, as demonstrated on popular image classification and semantic segmentation benchmarks. The code is available at https://***/OSVAI/SSD-KD.

关键词： Training Knowledge engineering Semantic segmentation Training data Reinforcement learning Benchmark testing Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A genetic programming approach with adaptive region detection to skin cancer image classification

引用

Journal of Automation and Intelligence 2024年第4期3卷 240-249页

作者： Kunjie Yu Jintao Lian Ying Bi Jing Liang Bing Xue Mengjie Zhang School of Electrical and Information Engineering Zhengzhou UniversityZhengzhou450001China State Key Laboratory of Intelligent Agricultural Power Equipment Luoyang471000China Longmen Laboratory Luoyang471000China School of Electrical Engineering and Automation Henan Institute of TechnologyXinxiang453000China School of Engineering and Computer Science&Centre for Data Science and Artificial Intelligence Victoria University of WellingtonWellington6201New Zealand

Dermatologists typically require extensive experience to accurately classify skin *** recent years,the development of computer vision and machine learning has provided new methods for assisted *** skin cancer image classification methods have certain limitations,such as poor interpretability,the requirement of domain knowledge for feature extraction,and the neglect of lesion area information in skin *** paper proposes a new genetic programming(GP)approach to automatically learn global and/or local features from skin images for *** achieve this,a new function set and a new terminal set have been *** proposed GP method can automatically and flexibly extract effective local/global features from different types of input images,thus providing a comprehensive description of skin images.A new region detection function has been developed to select the lesion areas from skin images for feature *** performance of this approach is evaluated on three skin cancer image classification tasks,and compared with three GP methods and six non-GP *** experimental results show that the new approach achieves significantly better or similar performance in most *** analysis validates the effectiveness of our parameter settings,visualizes the multiple region detection functions used in the individual evolved by the proposed approach,and demonstrates its good convergence ability.

关键词： Genetic programming Skin cancer image classification Region detection Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Method for Image-Based Preliminary Assessment of Car Park for the Disabled and the Elderly Using Convolutional Neural Networks and Transfer Learning 1

引用

15th Multi-disciplinary International Conference on Artificial Intelligence, MIWAI 2022

作者： Hanpinitsak, Panawit Posawang, Pitiphum Phankaweerat, Sumate Pattara-atikom, Wasan Department of Computer Engineering Khon Kaen University Khon Kaen40002 Thailand Intelligent Transportation Systems Laboratory National Electronics and Computer Technology National Science and Technology Development Agency Pathumthani12120 Thailand Department of Computer Science Vongchavalitkul University Nakhon Ratchasima30000 Thailand

ISBN: (数字)9783031209925

ISBN: (纸本)9783031209918

It is critical to assess the standards of disabled facilities in order to ensure the comfort and safety of disabled individuals who use them. In this study, deep convolutional neural networks (CNNs) with multi-label classification capability are employed for a preliminary evaluation of the car park for the disabled and the elderly in accordance with ministerial regulations, reducing the burden of on-site inspection by specialists. Using a transfer learning technique, the weights of an Inception-V3, Xception, and EfficientNet-B2 architectures previously trained on the ImageNet dataset were updated with the disabled car park image dataset. We used 4,812 training images and 355 test images to train, evaluate, and compare the model. The results revealed that the EfficientNet-B2 model yielded the best performance for 5 out of 6 classes, with the F1-score between 79.8% and 95.6%. In contrast, the remaining one class was best predicted by the Xception model, where the F1-score was 83.33%. This implies that it is possible to apply CNNs to aid in the evaluation of handicap facilities. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Boosting Meaningful Dependency Mining with Clustering and Covariance Analysis

Boosting Meaningful Dependency Mining with Clustering and Co...

引用

International Conference on Data Engineering

作者： Xi Wang Ruochun Jin Wanrong Huang Yuhua Tang Institute for Quantum Information & State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha China Department of Intelligent Data Science College of Computer Science and Technology National University of Defense Technology Changsha China

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Functional dependencies (FDs) form a valuable ingredient for various data management tasks. However, existing methods can hardly discover practical and interpretable FDs, especially in large noisy real-life datasets. This paper studies the problem of discovering meaningful functional dependencies (FDms) that utilize support and error parameters to capture interesting dependencies in such datasets and proposes an efficient discovery algorithm called FDMε. In order to scale with large datasets, FDM ε employs an efficient sampling method with accuracy guarantees to capture the differences between tuple pairs and to quantify the connection between support/error of dependencies on samples and those on the entire dataset. Moreover, it adopts a clustering-based correlated attributes extraction to divide the exponentially large search space into multiple small sub-spaces and proposes an easy-first traversal strategy with covariance-based guidance that quickly detects candidate dependencies and validates them. Additionally, we prove a covariance lower bound as an additional pruning criterion to reduce the search space. Extensive experiments on real-life and synthetic datasets demonstrate that FDM ε is 14 times faster than existing discovery algorithms on average, up to 31 times, and scales to larger datasets with the least memory cost.

关键词： Accuracy Costs Clustering algorithms Search problems Data engineering Noise measurement Frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Energy Efficiency Prediction Model of Suction Hopper Dredger Based on Correlation Analysis and Convolutional Neural Network 20

Energy Efficiency Prediction Model of Suction Hopper Dredger...

引用

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Zhang, Jinyue Chen, Liheng Qin, Daqing Harbin Engineering University College of Intelligent Systems Science and Engineering Harbin150001 China University of Macau Faculty of Science and Technology Department of Electromechanical Engineering Macau China State Key Laboratory of Hydro-power Equipment Harbin150040 China Harbin Electric Machinery Company Limited Harbin150040 China

ISBN: (纸本)9798350320831

Suction hopper dredgers are the main type of ship used in dredging projects. Due to the complex dynamic characteristics of the dredging process and the fact that the power consumption characteristics of dredgers are affected by many factors such as soil, meteorological environment, and hydrology, it is difficult to obtain accurate prediction results using traditional methods. This paper proposes a data extraction method based on correlation analysis to filter out the most critical influencing features from a large amount of data that affects the working efficiency of dredgers. An energy efficiency prediction model is established using convolutional neural network method to estimate the actual production efficiency of bucket-wheel dredgers and applied to actual production cases. The results show that the energy efficiency prediction model established using this method can effectively predict the power consumption of suction hopper dredgers. © 2023 IEEE.

关键词： Energy efficiency

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：