检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wei, Qiusen Huang, Guoheng Yuan, Xiaochen Chen, Xuhang Zhong, Guo Huang, Jianwen Huang, Jiajie School of Automation Guangdong University of Technology Guangzhou China School of Computer Science and Technology Guangdong University of Technology Guangzhou China Faculty of Applied Sciences Macao Polytechnic University China School of Computer Science and Engineering Huizhou University Huizhou China School of Information Science and Technology Guangdong University of Foreign Studies Guangzhou China

Medical landmark detection is crucial in various medical imaging modalities and procedures. Although deep learning-based methods have achieve promising performance, they are mostly designed for specific anatomical regions or tasks. In this work, we propose a universal model for multi-domain landmark detection by leveraging transformer architecture and developing a prompting component, named as Adaptive Query Prompting (AQP). Instead of embedding additional modules in the backbone network, we design a separate module to generate prompts that can be effectively extended to any other transformer network. In our proposed AQP, prompts are learnable parameters maintained in a memory space called prompt pool. The central idea is to keep the backbone frozen and then optimize prompts to instruct the model inference process. Furthermore, we employ a lightweight decoder to decode landmarks from the extracted features, namely Light-MLD. Thanks to the lightweight nature of the decoder and AQP, we can handle multiple datasets by sharing the backbone encoder and then only perform partial parameter tuning without incurring much additional cost. It has the potential to be extended to more landmark detection tasks. We conduct experiments on three widely used X-ray datasets for different medical landmark detection tasks. Our proposed Light-MLD coupled with AQP achieves SOTA performance on many metrics even without the use of elaborate structural designs or complex frameworks. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Robust Static Feature Extraction in Dynamic Scenes: An Advanced RGBD Visual SLAM Framework Leveraging YOLOv9

Robust Static Feature Extraction in Dynamic Scenes: An Advan...

引用

2025 2nd International Conference on Algorithms, Software engineering and Network Security (ASENS)

作者： Bo Wang Sen Zhang Qifeng Jiang Lu Lu Zongren Chen Computer Engineering Technical College (Artificial Intelligence College) Guangdong Polytechnic of Science and Technology Zhuhai China School of Automation Harbin University of Science and Technology Harbin China Faculty of Science and Technology Beijing Normal University Hong Kong Baptist University United International College Zhuhai China

ISBN: (数字)9798331520298

ISBN: (纸本)9798331520304

Dynamic elements in dynamic environment are important factors that affect the localization accuracy of visual Simultaneous Localization and Mapping (vSLAM), and may even lead to tracking failures. To address this issue, we propose an enhanced dense visual SLAM method specifically designed for dynamic environments. The whole framework of our approach is based on ORB-SLAM2, while integrating the YOLOv9 network to detect dynamic objects. By transmitting the detection results of YOLOv9 to the SLAM module, dynamic feature elements are then removed from the dense map construction thread. Finally, the dense map that only contains static information is created. The experimental results show that the filtering of dynamic objects not only can reduce the average root mean square error (RMSE), but also help and then improve the robustness of the SLAM system in dynamic environment.

关键词： Point cloud compression Visualization Simultaneous localization and mapping Accuracy Three-dimensional displays Target tracking Target recognition Heuristic algorithms Feature extraction Software engineering

来源：评论

学校读者我要写书评

暂无评论

Fusionngfpe: An Image Fusion Approach Driven by Non-Global Fuzzy Pre-Enhancement Framework

SSRN

引用

SSRN 2024年

作者： Zhang, Xiangbo Liu, Gang Li, Mingyi Ren, Qin Tang, Haojie Bavirisetti, Durga Prasad School of Automation Engineering Shanghai University of Electric Power Shanghai201306 China School of Environmental Science and Engineering Southwest Jiaotong University Chengdu610000 China School of Software and Microelectronics Peking University Beijing100000 China Department of Computer Science Faculty of Information Technology and Electrical Engineering Norwegian University of Science and Technology Trondheim7034 Norway

The majority of prevailing image fusion methods employ a global strategy, often resulting in a reduction of contrast. In this study, we propose an image fusion approach (FusionNGFPE), specifically tailored to the structural characteristics of infrared (IR) imagery. We introduce a contrast equalization algorithm based on the Fourth-order Partial Differential Equation (FPDE) to effectively enhance background regions. Recognizing the inherent disparities between IR and visible (VIS) images, we devise a hybrid fusion strategy leveraging the Expectation Maximization algorithm (EM) and Principal Component Analysis algorithm (PCA). Comparative analysis against state-of-the-art fusion methods demonstrates the superior performance of our proposed algorithm in both qualitative and quantitative assessments. Additionally, to assess the practical applicability of FusionNGFPE, we integrate the fusion framework into the RGBT target tracking task utilizing the VOT-RGBT and OTCBVS datasets. Through comprehensive comparative experiments, we ascertain that the FusionNGFPE framework seamlessly integrates with the tracking task, significantly enhancing tracking accuracy across diverse scenarios. © 2024, The Authors. All rights reserved.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Improved mayfly optimization algorithm by adaptive random opposition-based learning 6

Improved mayfly optimization algorithm by adaptive random op...

引用

6th International Conference on Mechatronics and Intelligent Robotics, ICMIR 2022

作者： Zhang, Hengqi Lin, Yong Qian, Qian Pan, Jiawen Feng, Yong Fu, Yunfa Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming Yunnan650500 China Yunnan Key Laboratory of Computer Technology Applications Kunming University of Science and Technology Kunming Yunnan650500 China Library and Archives Yunnan Communications Vocational and Technical College Kunming Yunnan650500 China

ISBN: (纸本)9781510656635

An adaptive random reverse learning mayfly algorithm is proposed to overcome the shortcomings of mayfly optimization. Specifically, hyperbolic tangent function is used as adaptive curve to flexibly optimize the personal experience and social experience coefficients of the algorithm, so that the algorithm can better balance the global and local search capabilities through the evolutionary iterations. In addition, on the basis of elite mayfly in each generation, random reverse learning mechanism is used to expand population diversity and speed up algorithm convergency. The calculation results of several test functions show that the algorithm presented has good convergence accuracy and improved algorithm performance. © 2022 SPIE.

关键词： Hyperbolic functions

来源：评论

学校读者我要写书评

暂无评论

Data-Filtered Prediction with Decomposition and Amplitude-Aware Permutation Entropy for Workload and Resource Utilization in Cloud Data Centers

引用

IEEE Internet of Things Journal 2025年

作者： Yuan, Haitao Hu, Qinglong Wang, Meijia Wang, Shen Bi, Jing Buyya, Rajkumar Shi, Shuyuan Yang, Jinhong Zhang, Jia Zhou, MengChu Beihang University School of Automation Science and Electrical Engineering Beijing100191 China City University of Hong Kong Department of Computer Science Hong Kong999077 Hong Kong Beijing University of Technology School of Software Engineering The Faculty of Information Technology Beijing100124 China Lab School of Computing and Information Systems MelbourneVIC3010 Australia Beihang University School of Integrated Circuit Science and Engineering Beijing China CSSC Systems Engineering Research Institute Beijing China Southern Methodist University Department of Computer Science The Lyle School of Engineering DallasTX75205 United States New Jersey Institute of Technology Department of Electrical and Computer Engineering NewarkNJ07102 United States

In recent years, cloud computing has witnessed widespread applications across numerous organizations. Predicting workload and computing resource data can facilitate proactive service operation management, leading to substantial improvements in quality of service and cost efficiency. However, these data often exhibit non-linearity, high volatility, and interdependencies across different categories, presenting challenges for accurate forecasting. Consequently, there is a critical need to develop a method that thoroughly and comprehensively analyzes all available data to forecast future trends effectively. This work proposes a novel integrated data-enhanced prediction model named SVAPI for achieving high-accuracy workload prediction in cloud computing systems. SVAPI employs the Savitzky-Golay filter, Variational mode decomposition, and the mode selection based on Amplitude-aware Permutation entropy for feature processing, whose features are subsequently utilized by Informer for multivariate joint analysis of the enhanced data, achieving high-precision prediction. Ablation and comparative experiments with advanced prediction models are conducted on the Google cluster trace and other typical datasets. Realistic data-driven results indicate that SVAPI improves the prediction accuracy by 37.7% compared to the original Informer, with each module contributing to the performance enhancement. Furthermore, compared with Autoformer, SVAPI enhances the prediction accuracy of workload, CPU, and memory by 65.6%, 66.9%, and 70.8%, respectively, demonstrating that SVAPI owns strong abilities in noise filtering, feature processing, and multivariate joint analysis for achieving higher prediction accuracy. © 2014 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Tackling Noisy Labels with Network Parameter Additive Decomposition

arXiv

引用

arXiv 2024年

作者： Wang, Jingyi Xia, Xiaobo Lan, Long Wu, Xinghao Yu, Jun Yang, Wenjing Han, Bo Liu, Tongliang The Department of Intelligent Data Science College of Computer Science and Technology National University of Defense Technology Changsha410073 China The Trustworthy Machine Learning Lab School of Computer Science Faculty of Engineering University of Sydney DarlingtonNSW2008 Australia The State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China The Department of Automation University of Science and Technology of China Hefei230026 China The Department of Computer Science Hong Kong Baptist University Hong Kong

Given data with noisy labels, over-parameterized deep networks suffer overfitting mislabeled data, resulting in poor generalization. The memorization effect of deep networks shows that although the networks have the ability to memorize all noisy data, they would first memorize clean training data, and then gradually memorize mislabeled training data. A simple and effective method that exploits the memorization effect to combat noisy labels is early stopping. However, early stopping cannot distinguish the memorization of clean data and mislabeled data, resulting in the network still inevitably overfitting mislabeled data in the early training stage. In this paper, to decouple the memorization of clean data and mislabeled data, and further reduce the side effect of mislabeled data, we perform additive decomposition on network parameters. Namely, all parameters are additively decomposed into two groups, i.e. , parameters w are decomposed as w = σ + γ. Afterward, the parameters σ are considered to memorize clean data, while the parameters γ are considered to memorize mislabeled data. Benefiting from the memorization effect, the updates of the parameters σ are encouraged to fully memorize clean data in early training, and then discouraged with the increase of training epochs to reduce interference of mislabeled data. The updates of the parameters γ are the opposite. In testing, only the parameters σ are employed to enhance generalization. Extensive experiments on both simulated and real-world benchmarks confirm the superior performance of our method. The implementation is available at: https://***/wangjingyi9924/TNLPAD. Copyright © 2024, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Practical engineering Education: Use of collaborative robots in the context of Industry 5.0

Practical Engineering Education: Use of collaborative robots...

引用

World engineering Education Forum - Global engineering Deans Council (WEEF-GEDC)

作者： Christian Vogel Fabian Lindner Alexander Kratzsch Faculty of Electrical Engineering and Computer Science Zittau/Görlitz University of Applied Science Zittau Germany Faculty of Business Administration and Engineering Zittau/Görlitz University of Applied Science Zittau Germany Institute of Process Technology Process Automation and Measuring Technology Zittau/Görlitz University of Applied Science Zittau Germany

This scientific paper examines the use of collaborative robots in the context of Industry 5.0 and its impact on practical engineering education. The aim of this paper is to highlight the importance as well as the challenges of using robots in Industry 5.0 and to analyze how this can be integrated into engineering education. The paper discusses various aspects such as the technological advances, the need for interaction between humans and robots, and the competencies that engineers need in an increasingly digitalized working world. Furthermore, practical methods and approaches in engineering education at the Zittau/Görlitz University of Applied sciences are presented to prepare students for the requirements of Industry 5.0. Additionally, a draft of a future interdisciplinary learning factory 5.0 will be presented, in which networked technologies with the focus on robotics run through various scenarios in the context of Industry 5.0 at different locations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Network Anomaly Detection with Stacked Sparse Shrink Autoencoders and Improved XGBoost

Network Anomaly Detection with Stacked Sparse Shrink Autoenc...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Jing Bi Ziyue Guan Haitao Yuan Jia Zhang Faculty of Information Technology Beijing University of Technology Beijing China School of Automation Science and Electrical Engineering Beihang University Beijing China Dept. of Computer Science in Lyle School of Engineering Southern Methodist University Dallas TX USA

Efficient and accurate identification of network anomalies is of great significance to the construction of network security systems in the information age. It is highly challenging to accurately detect abnormal behaviors in the increasing network data. Currently, classification methods based on feature extraction of autoencoders have been proven to be suitable for network anomaly detection. However, traditional detection models with autoencoders have poor detection accuracy in the face of massive network features. In addition, the hyperparameter optimization of their models cannot be effectively solved. For network anomaly detection, this work proposes a new network anomaly detection method named SAXP, which integrates Stacked sparse shrink Autoencoders and a XGBoost model based on genetic simulated annealing Particle swarm optimization (GSPSO). Specifically, features extracted by stacked sparse shrink autoencoders are introduced into the XG Boost model for classification, and GSPSO is used to optimize the hyperparameters of XGBoost. Experimental results based on two real-life data sets demonstrate that the proposed SAXP achieves higher recognition accuracy than several state-of-the-art algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Latency-Minimized Computation Offloading in Vehicle Fog Computing with Improved Whale Optimization Algorithm

Latency-Minimized Computation Offloading in Vehicle Fog Comp...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Jing Bi Xiangdong Xue Haitao Yuan Jia Zhang Faculty of Information Technology Beijing University of Technology Beijing China School of Automation Science and Electrical Engineering Beihang University Beijing China Dept. of Computer Science in Lyle School of Engineering Southern Methodist University Dallas TX USA

Fog computing provides lower latency and higher bandwidth compared to cloud computing and is widely used in Internet of Vehicles (IoV). Vehicles cannot compute all tasks locally due to their limited computing power and battery capacity. Thus, it is a useful way to offload some tasks of vehicles to other resource-rich servers. However, due to the high mobility of vehicles, there may be a failure of returning computing results. Thus, it is a challenge to minimize the latency of tasks while meeting the constraint of energy consumption. This work proposes a vehicle-fog offloading system that offloads tasks to fog servers or idle vehicles which is a probabilistic offloading problem. So this work proposes an improved optimization algorithm called an adaptive Lévy flight-based Whale optimization algorithm with Hierarchical learning (LWH) to solve this problem. Simulation experiments show that LWH has strong global search capability and outperforms its five typical and widely used algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modelling and automation of a process for obtaining coagulum in treatment of industrial 15

Modelling and automation of a process for obtaining coagulum...

引用

15th Global Congress on Manufacturing and Management, GCMM 2021

作者： Safonyk, A. Tarhonii, I. Burduk, A. Batako, A. National University of Water and Environmental Engineering Department of the Automation Electrotechnical and Computer-Integrated Technologies Soborna str. Rivne33028 Ukraine Wroclaw University of Science and Technology Faculty of Mechanical Engineering Wybrzeze Wyspianskiego 27 Wroclaw50-370 Poland Faculty of Engineering and Technology Liverpool John Moores University Byrom Street LiverpoolL3 3AF United Kingdom

This paper present the development a model for obtaining a coagulant for the process of cleaning and discoloration of industrial waste water and the development of a PID automated system for wastewater treatment. The description of the processes taking place in an electro-coagulator is given along with the solution obtained by model. The influence of current on the concentration of divalent iron water temperature is investigated. The algorithm of two-circuit regulation of concentration of pollution in sewage with the feedback current between the coagulator plates and the concentration pollutants in the water entering the automated purification system is developed. The automated control system for wastewater treatment process with the implementation of the coagulant forecasting algorithm in relation to the input pollution concentration is developed. The control of current magnitude in the electro-coagulator with minimal electricity consumption was realized. It is planned to manage the system with the ability to change the performance of the entire installation in real time using the SCADA - system. © Published under licence by IOP Publishing Ltd.

关键词： SCADA systems

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：