检索结果-内蒙古大学图书馆

MCDS: An Effective Multi-UAV Collaborative Decision-Making System in Mobile Edge Computing Networks

IEEE Internet of Things Journal 2025年

作者： Xiong, Naixue Zhong, Weiyu Chen, Yuxiang He, Dacheng Li, Yuhui Chen, Linshu Liang, Wei Sanya Research Institute of Hunan University of Science and Technology School of Computer Science and Engineering Hunan University of Science and Technology Hunan Key Laboratory for Service Computing and Novel Software Technology China Sanya Research Institute of Hunan University of Science and Technology Hunan University School of Computer Science and Engineering Hunan University of Science and Technology Hunan Key Laboratory for Service Computing and Novel Software Technology School of Information Science and Engineering China The Hong Kong Polytechnic University Department of Computing Hong Kong

Mobile Edge Computing (MEC) pushes computing resources from the network center to the network edge to provide efficient and reliable computing services. However, due to the mobility and diversity of mobile users (MUs), edge servers (ESs) are likely to be overloaded, which leads to a rapid decline in the quality of service provided by the MEC system. This paper introduces unmanned aerial vehicles (UAVs) to solve the problem of ES overload. This paper presents an effective Multi-UAV Collaborative Decision-Making System (MCDS) tailored to optimize task offloading and resource allocation in MEC networks. The proposed system seeks to reduce task computing delays and energy consumption while guaranteeing timely task completion and compliance with resource constraints. We design a distributed two-stage optimization algorithm to jointly optimize the task offloading decision and resource allocation of the collaborative computing system (UAVs, ESs, and MUs). To address the flight cooperation problem of multi-UAVs, we also proposed a task-aware scheduling algorithm for multi-UAVs. In addition, we conducted a large number of simulation experiments. Experimental results show that our two-stage optimization scheme is lower than other benchmark algorithms in terms of task completion delay, energy consumption and total cost of objective function. Specifically, compared with seven baseline algorithms under three different system setting scenarios, our algorithm reduces the total cost by an average of 38.79%, the energy consumption by an average of 40.70%, and the delay by an average of 15.67%. © 2014 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

PoolKANNeXt: A new pooling-based Kolmogorov Arnold convolutional neural network

引用

Alexandria engineering Journal 2025年 128卷 144-152页

作者： Fangxing Lv Qing Wei Yuwen Huang Turker Tuncer Sengul Dogan Fatih Özyurt School of Computer Heze University Heze 274015 China Department of Digital Forensics Engineering Technology Faculty Firat University Elazig Turkey Department of Software Engineering Engineering Faculty Firat University Elazig Turkey

The Kolmogorov–Arnold Network (KAN) is a new-generation neural network. It provides an alternative to multilayer perceptrons (MLPs). PoolFormer showed that pooling alone can mix features efficiently. We propose PoolKANNeXt, a CNN that merges the KAN structure with pooling-based feature mixing. This design targets high accuracy with a low number of the learnable parameters. We evaluated PoolKANNeXt on six image datasets, five biomedical and one general (CIFAR-10). The model comprises four stages. In the stem stage, a ConvNeXt-style patchify block converts each 224 × 224 × 3 image into a 56 × 56 × 96 tensor. In the main stage, average pooling first mixes local features; then two parallel 3 × 3 convolutions—one followed by GELU and the other by Swish—extract complementary representations, and a 1 × 1 convolution scales the combined output and adds it back to the input via a residual connection. In the downsampling stage, strided 3 × 3 convolutions halve spatial dimensions and double the channel count. In the output stage, global average pooling produces a feature vector that feeds into a softmax classifier. PoolKANNeXt achieved over 90 % accuracy on all datasets and reached 99.43 % on CIFAR-10, ranking among the top five models on that benchmark. PoolKANNeXt offers a lightweight yet powerful architecture. Its innovative combination of pooling and dual-activation KAN blocks yields strong performance across diverse tasks. The design is scalable and adaptable to larger or more complex datasets.

关键词： PoolKANNeXt Kolmogorov Arnold Network CNN computer Vision Image classification

来源：评论

学校读者我要写书评

暂无评论

Runtime Enforcement of CPS against Signal Temporal Logic

arXiv

引用

arXiv 2025年

作者： Su, Han Shankar, Saumya Pinisetty, Srinivas Roop, Partha S. Zhan, Naijun Institute of Software CAS & University of CAS Beijing China Department of Electrical Computer and Software Engineering The University of Auckland Auckland New Zealand Indian Institute of Technology School of Electrical Sciences Bhubaneswar India The University of Auckland Department of Electrical Computer and Software Engineering Auckland New Zealand Peking University School of Computer Science Institute of Software CAS Beijing China

Cyber-Physical Systems (CPSs), especially those involving autonomy, need guarantees of their safety. Runtime Enforcement (RE) is a lightweight method to formally ensure that some specified properties are satisfied over the executions of the system. Hence, there is recent interest in the RE of CPS. However, existing methods are not designed to tackle specifications suitable for the hybrid dynamics of CPS. With this in mind, we develop runtime enforcement of CPS using properties defined in Signal Temporal Logic (STL). In this work, we aim to construct a runtime enforcer for a given STL formula to minimally modify a signal to satisfy the formula. To achieve this, the STL formula to be enforced is first translated into a timed transducer, while the signal to be corrected is encoded as timed words. We provide timed transducers for the temporal operators until and release noting that other temporal operators can be expressed using these two. Our approach enables effective enforcement of STL properties for CPS. A case study is provided to illustrate the approach and generate empirical evidence of its suitability for CPS. © 2025, CC BY-NC-ND.

关键词： Transducers

来源：评论

学校读者我要写书评

暂无评论

EU-Nets: Enhanced, Explainable and Parsimonious U-Nets

arXiv

引用

arXiv 2025年

作者： Sun, Bohang Liò, Pietro School of Information and Software Engineering University of Electronic Science and Technology of China China Department of Computer Science and Technology University of Cambridge United Kingdom

In this study, we propose MHEX+, a framework adaptable to any U-Net architecture. Built upon MHEX+, we introduce novel U-Net variants, EU-Nets, which enhance explainability and uncertainty estimation, addressing the limitations of traditional U-Net models while improving performance and stability. A key innovation is the Equivalent Convolutional Kernel, which unifies consecutive convolutional layers, boosting interpretability. For uncertainty estimation, we propose the collaboration gradient approach, measuring gradient consistency across decoder layers. Notably, EU-Nets achieve an average accuracy improvement of 1.389% and a variance reduction of 0.83% across all networks and datasets in our experiments, requiring fewer than 0.1M parameters. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine Learning in Higher Education using RF and SVM for Pedagogical Enhancement 3

Machine Learning in Higher Education using RF and SVM for Pe...

引用

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Kunwar, Fateh Bahadur Srivastava, Satyajee Dhivya, R. Gulati, Monika Anand, Taruna Raj, D. Antony Arul Geetanjali Institute of Technical Studies Department of Computer Science and Engineering Udaipur India School of Engineering and Technology Manav Rachna International Institute of Research and Studies Department of Computer Science and Engineering Faridabad India M.Kumarasamy College of Engineering Department of Information Technology Karur India Ambala India University Department of Humanities and Social Sciences Dehradun India Psg College of Arts & Science Department of Software Systems Coimbatore India

ISBN: (纸本)9798331508456

AI's revolutionary potential in higher education is examined in this proposal, including how it could revolutionize teaching, learning, administration, and research. Adaptive learning platforms, intelligent tutoring systems, and virtual learning assistants may change how students learn by improving engagement, providing quick feedback, and enabling tailored learning. The suggested process includes preprocessing, feature extraction, and model training. Preprocessing involves de-anonymizing, tokenizing, and removing punctuation, spaces, and numbers before analysis. The linear transformation method PCA extracts features. Training the systems uses the RF -SVM approach, which combines the advantages of RF and SVM. The suggested RF -SVM model beats two RF and SVM models with an average accuracy of 90.39 *** improves resource use, strategic decision-making, and research capacity in university management. The RF-SVM model's success in academia highlights the practicality of AI-driven solutions. © 2025 IEEE.

关键词： Teaching

来源：评论

学校读者我要写书评

暂无评论

Polynomial Projection and Information Exchange Architecture for Long-Term Time Series Forecasting

引用

computer engineering and Applications 2025年第10期61卷 120-132页

作者： Liu, Jianxin Ma, Tinghuai Su, Yuming Rong, Huan School of Software Nanjing University of Information Science and Technology Nanjing 210044 China School of Computer Engineering Jiangsu Ocean University Jiangsu Lianyungang 222000 China School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing 210044 China

Long-term time series forecasting utilizes historical data to predict the trends of future sequences over extended periods, providing support for long-term warning, planning, and decision-making. Existing methods commonly encounter issues of distribution shifts and long-term dependencies that are difficult to capture when conducting long-term forecasting. This paper proposes a Legendre polynomial projection and information exchange architecture (LPPIEA) tailored for long-term time series forecasting. Reversible instance data normalization is introduced to reduce the influence of distribution shifts in long-term time series on predictions. Legendre polynomial projection is employed to handle complex temporal patterns, acquiring high-dimensional feature representations of the data to enhance the model inference capability for long-term time series. To effectively capture long-term temporal dependencies, a lightweight information exchange architecture is constructed to efficiently capture such dependencies, thus achieving accurate and efficient long-term time series forecasting. Experimental results on four commonly used public datasets demonstrate that the LPPIEA model reduces prediction errors by an average of 11.4% compared to baseline methods, while exhibiting higher computational efficiency. © 2025 Journal of computer engineering and Applications Beijing Co., Ltd.;Science Press. All rights reserved.

关键词： deep learning information exchange architecture long-term temporal dependencies polynomial projection time series forecasting

来源：评论

学校读者我要写书评

暂无评论

Neural network-driven parallel accelerated selective image encryption with semantic understanding

引用

The European Physical Journal Special Topics 2025年 1-16页

作者： Song, Wei Fu, Chong Zheng, Yu Chen, Junxin Zhang, Yanfeng School of Computer Science and Engineering Northeastern University Shenyang China Engineering Research Center of Security Technology of Complex Network System Ministry of Education Shenyang China University of California Irvine Irvine USA School of Software Dalian University of Technology Dalian China

Existing batch image encryption schemes often directly encrypt images without considering their source. However, in real-life scenarios, these images are typically part of a larger collection stored in a directory on a computer or in the cloud. To efficiently protect those sensitive images distributed within the collection, we rethink selective image encryption (SIE) from the perspective of batch image encryption and proposes a novel SIE scheme using deep neural networks (DNN) and parallel computing. First, a DNN method is employed to identify sensitive images by analyzing their semantics. Next, a parallel cross-bitplane permutation algorithm is introduced to shuffle the retrieved images in bit-level. Then, a bi-directional diffusion strategy is employed to spread the encryption influence of a pixel to all images. Experimental results demonstrate the proposed scheme effectively understands the semantic of images, identifies sensitive images, and encrypts them with high permutation and diffusion efficiency. Further security analyses show that the proposed algorithm successfully resists various attacks with desired performance, including achieving high information entropy and low correlation coefficients in statistical analysis, and ideal values of the number of pixels changing rate (NPCR) and the unified averaged changing intensity (UACI) to resist differential attack, as well as high key sensitivity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Low-shot Video Object Segmentation

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 PP页

作者： Yan, Kun Wei, Fangyun Dai, Shuyu Wu, Minghui Wang, Ping Xu, Chang Peking University School of Computer Science Beijing100871 China University of Sydney School of Computer Science DarlingtonNSW2008 Australia Peking University School of Software and Microelectronics Beijing100871 China Shanghai Artificial Intelligence Laboratory and Mininglamp Technology China Peking University National Engineering Research Center for Software Engineering Beijing100871 China Peking University School of Software and Microelectronics China China

Prior research in video object segmentation (VOS) predominantly relies on videos with dense annotations. However, obtaining pixel-level annotations is both costly and time-intensive. In this work, we highlight the potential of effectively training a VOS model using remarkably sparse video annotations - specifically, as few as one or two labeled frames per training video, yet maintaining near equivalent performance levels. We introduce this innovative training methodology as low-shot video object segmentation, abbreviated as low-shot VOS. Central to this method is the generation of reliable pseudo labels for unlabeled frames during the training phase, which are then used in tandem with labeled frames to optimize the model. Notably, our strategy is extremely simple and can be incorporated into the vast majority of current VOS models. For the first time, we propose a universal method for training VOS models on one-shot and two-shot VOS datasets. In the two-shot configuration, utilizing just 7.3% and 2.9% of labeled data from the YouTube-VOS and DAVIS benchmarks respectively, our model delivers results on par with those trained on completely labeled datasets. It is also worth noting that in the one-shot setting, a minor performance decrement is observed in comparison to models trained on fully annotated datasets. Code and models are available at https://***/yk-pku/Low-shot-VOS. © 1979-2012 IEEE.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

LV-Mamba: Integrating Denoising Mechanism with Mamba for Improved Segmentation of the Pediatric Echocardiographic Left Ventricle 5th

LV-Mamba: Integrating Denoising Mechanism with Mamba for Imp...

引用

5th International Conference on Medical Imaging and computer Aided Diagnosis, MICAD 2024

作者： Chen, Tianxiang Chang, Zeyu Wang, Fangyijie Wang, Ziyang Ye, Zi University of Science and Technology of China Hefei China School of Biomedical Engineering and Imaging Sciences King’s College London London United Kingdom School of Medicine University College Dublin Dublin Ireland Department of Computer Science University of Oxford Oxford United Kingdom Institute of Intelligent Software Guangzhou China

ISBN: (纸本)9789819638628

In pediatric cardiology, the accurate and immediate assessment of cardiac function through echocardiography is crucial since it can determine whether urgent intervention is required in many emergencies. However, echocardiography is characterized by ambiguity and heavy background noise interference, causing more difficulty in accurate segmentation. Present methods lack efficiency and are prone to mistakenly segmenting some background noise areas, such as the left ventricular area, due to noise disturbance. We introduce LV-Mamba for efficient pediatric echocardiographic left ventricular segmentation to relieve the two issues. Specifically, we turn to the recently proposed vision mamba layers in our vision mamba encoder branch to improve our model’s computing and memory efficiency while modeling global dependencies. In the other DWT-based PMD encoder branch, we devise DWT-based Perona-Malik Diffusion (PMD) Blocks that utilize PMD for noise suppression while preserving the left ventricle’s local shape cues. Leveraging the strengths of both encoder branches, LV-Mamba achieves superior accuracy and efficiency to established models, such as vision transformers with quadratic and linear computational complexity. This innovative approach promises significant advancements in pediatric cardiac imaging and beyond. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Pediatrics

来源：评论

学校读者我要写书评

暂无评论

HybridFL: Hybrid Approach Toward Privacy-Preserving Federated Learning 6th

HybridFL: Hybrid Approach Toward Privacy-Preserving Federate...

引用

6th International Conference on Security and Privacy in New Computing Environments, SPNCE 2023

作者： Ali, Sheraz Mamoon, Saqib Usman, Areeba Abidin, Zain ul Zhao, Chuan School of Information Science and Engineering University of Jinan Jinan250022 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China University of Sargodha Sargodha Pakistan Shandong Provincial Key Laboratory of Network-Based Intelligent Computing University of Jinan Jinan250022 China Shandong Provincial Key Laboratory of Software Engineering University of Jinan Jinan250022 China

ISBN: (纸本)9783031736988

In this study, we introduce a novel Hybrid Federated Learning (HybridFL) approach aimed at enhancing privacy and accuracy in collaborative machine learning scenarios. Our methodology integrates Differential Privacy (DP) and secret sharing techniques to address inference risks during training and protect against information leakage in the output model. Drawing inspiration from recent advances, we present a HybridFL framework that combines the strengths of Homomorphic Encryption (HE) and Multi-Party Computation (MPC) to achieve secure computation without the computational overhead of pure HE methods. Our contributions include a privacy-preserving design for Federated Learning (FL) that ensures local data privacy through secret sharing while leveraging DP mechanisms for noise addition. The system offers resilience against unreliable participants and is evaluated using various machine learning models, including Convolutional Neural Networks (CNN), Multi-Layer Perceptrons (MLP), and linear regression. Furthermore, we address potential external threats by deploying predictive model outputs as robust services against inference attacks. Experimental results demonstrate improved accuracy and convergence speed, establishing the viability of HybridFL as an effective solution for collaborative machine learning with enhanced privacy guarantees. © ICST Institute for computer Sciences, Social Informatics and Telecommunications engineering 2025.

关键词： Federated learning

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：