检索结果-内蒙古大学图书馆

Energy-efficient computation offloading via deep reinforcement learning in mobility-aware multi-access edge computing systems with diverse users

引用

Expert systems with Applications 2025年 286卷

作者： Wu, Haixing Jin, Shunfu School of Information Science and Engineering Yanshan University Qinhuangdao066004 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University Qinhuangdao066004 China

Multi-access Edge Computing (MEC) has been a promising solution that enables Internet of Things (IoT) devices to support computation-intensive applications by offloading some tasks to the network edge. However, most existing offloading methods in MEC systems are based on the premise of scenarios with either single-type or stable users, which is not aligned with the practical situations of users’ diversity and mobility. In addition, these methods always ignore energy saving strategies in MEC systems, which inevitably degrades Utility Energy Efficiency (UEE). To tackle these issues, considering personalized requirements from diverse users and idle energy consumption in MEC servers, we propose a novel computation offloading architecture with adaptive sleeping mechanism and heterogeneous MEC servers. Based on the architecture, we investigate energy-efficient computation offloading in mobility-aware MEC systems with diverse users. Under the Deep Reinforcement Learning (DRL) framework, we propose a Twin Delayed Deep Deterministic Policy Gradient Algorithm with Bursty Traffic (TD3-BT), in which the inherent correlation of task arrivals is taken into account to capture the behavior of correlated traffic and provide rational metrics estimation within one time slot. A long-term system cost minimization problem is formulated to optimize computation offloading for the trade-off between system delay and UEE. Assisted by TD3-BT, the formulated problem is effectively solved and the decision making in each time slot is provided for diverse users. Experimental results demonstrate that our TD3-BT algorithm achieves superior performance under various offloading scenarios compared to some benchmarks. © 2025 Elsevier Ltd

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Refining Boundary Sample Space for Differentiable Rendering 16

Refining Boundary Sample Space for Differentiable Rendering

引用

2024 16th International Conference on Graphics and Image Processing, ICGIP 2024

作者： Gao, Ruicheng Qi, Yue State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China Jingdezhen Research Institute Beihang University Jingdezhen333000 China Qingdao Research Institute Beihang University Qingdao266104 China

ISBN: (数字)9781510688780

ISBN: (纸本)9781510688773

The objective of physics-based differentiable rendering (PBDR) is to propagate gradients between scene parameters and the intensities of image pixels in a manner that is physically correct. The gradients obtained can be applied in optimization algorithms for the reconstruction of 3D geometry or materials, or they can be further propagated into neural network to learn neural representations of the scene. However, applying automatic differentiation techniques directly to the primary rendering process will result in biased gradients, as the rendering integral contains moving high-dimensional discontinuities. Based on how these discontinuities are managed-either implicitly or explicitly-existing PBDR methods can be categorized into two groups: reparameterization methods and boundary sampling methods. Boundary sampling methods need to construct paths that have one segment tangent to the geometry being differentiated in order to estimate a boundary integral to address the discontinuities explicitly. Such paths are usually constructed by sampling the tangent segment first and then extending it to complete the paths for subsequent processing. Fortunately, the number of dimensions in the space composed of such tangent segments is only three. In scenes comprised solely of triangle meshes, the first dimension is used to parameterize all the edges on the mesh, which determines a point on the tangent segment. The remaining two dimensions are used to parameterize the direction of the tangent segment. However, state-of-the-art boundary sampling methods parameterize the first dimension uniformly, which is inefficient because only a small portion of the edges contributes to the boundary integral, resulting in wasted parameter space. In this paper, we parameterize the first dimension by considering both edge length and contributions, thereby allocating more parameter space to important edges. Experiments demonstrate that our methods achieve lower variance gradients in the forward dif

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Binary-Encoding-Based Quantized Kalman Filter: An Approximate MMSE Approach

引用

IEEE Transactions on Automatic Control 2025年第5期70卷 3181-3196页

作者： Liu, Qinyuan Nie, Yao Wang, Zidong Dong, Hongli Jiang, Changjun Tongji University School of Computer Science and Technology Shanghai201804 China Tongji University Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai201804 China Tongji University Shanghai Artificial Intelligence Laboratory Shanghai201804 China Brunel University London Department of Computer Science UxbridgeUB8 3PH United Kingdom Northeast Petroleum University Artificial Intelligence Energy Research Institute Daqing163318 China Northeast Petroleum University Heilongjiang Provincial Key Laboratory of Networking and Intelligent Control Daqing163318 China

In this article, the Kalman filter design problem is investigated for linear discrete-time systems under binary encoding schemes. Under such a scheme, the local information is quantized into a bit string by the remote sensor based on a probabilistic quantizer, and then the bit string is transmitted via memoryless binary symmetric channels (BSCs). Due to the communication link noises, the bit flipping occurs in a random manner, and thus, the transmission of the bit string would suffer from specific bit-error rates. With the received bits, a recursive binary-encoding-based quantized Kalman filter is established in the approximate minimum mean-square error (MMSE) sense, which relies on the Gaussian approximation of the conditional probability density function at each iteration. Furthermore, the proposed estimator is shown to be of a Kalman-like type through performance analysis, which exhibits computational complexity comparable to the conventional Kalman filter. Subsequently, a posterior Cramér-Rao lower bound is derived for the proposed binary-encoding-based quantized Kalman filter. The effectiveness of the proposed estimator is demonstrated through numerical results. © 1963-2012 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Air traffic complexity assessment based on multi-scale spatio-temporal data 4

Air traffic complexity assessment based on multi-scale spati...

引用

2024 4th International Conference on Intelligent Traffic systems and Smart City, ITSSC 2024

作者： Zhou, Zhihui Chen, Haiyan Fu, Yirui Yuan, Ligang State Key Laboratory of Air Traffic Management System Nanjing China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China College of Civil Aviation Nanjing University of Aeronautics and Astronautics Nanjing China

ISBN: (纸本)9781510686304

Accurately assessing air traffic complexity is crucial for ensuring flight safety and efficiency. In this paper, we propose an air traffic complexity assessment method based on multi-scale spatio-temporal images. We first convert numerical air traffic data collected by surveillance radar into image data, and then interpolate the spatial and temporal scales of the images to generate multiple sets of images with different spatial and temporal scales. We found the best image set based on the Circle metric learning model by evaluating the performance of 20 image sets combined from different spatiotemporal scales. On this image set, we applied multiple deep metric learning methods to assess air traffic complexity. The results show that the new dataset performs better on several assessment metrics, confirming the validity of the approach to improve air traffic complexity assessment by adjusting the data scale. This demonstrates that the accuracy of air traffic complexity assessment can be effectively improved by adjusting the data scale. It also demonstrates the importance of choosing the right scale of dataset to improve the performance of machine learning algorithms. © 2025 SPIE.

关键词： Air transportation

来源：评论

学校读者我要写书评

暂无评论

A flight slots allocation method for single airport based on Q-Learning algorithm 4

A flight slots allocation method for single airport based on...

引用

2024 4th International Conference on Intelligent Traffic systems and Smart City, ITSSC 2024

作者： Fang, Xinyi Chen, Haiyan Qian, Yuhang Yang, Lei State Key Laboratory of Air Traffic Management System Nanjing China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China College of Civil Aviation Nanjing University of Aeronautics and Astronautics Nanjing China

ISBN: (纸本)9781510686304

The air traffic demand surpasses the capacity of most of the busiest airports worldwide. The mismatch between airport capacity and air traffic demand leads to serious congestion and delay problems. Since airport capacity is difficult to expand in a short time, in order to reduce flight delays, we need to adjust and optimize flight slots for flight applications, and allocate flight time resources scientifically and efficiently under the premise of meeting airspace resource constraints such as airport capacity. In this paper, we proposed an airport flight slots allocation method based on the Q-Learning algorithm in reinforcement learning. Firstly, we preprocess the original data set. Data cleaning processes data with missing attribute values and removes irrelevant attributes. Through data transformation, the data of string attribute is transformed into discrete numbers, and the time attribute is processed. After that, we construct a mathematical model of single-airport flight time allocation, which is a combinatorial optimization problem and determines the optimization objectives and constraints. Then we apply the reinforcement learning algorithm Q-Learning to solve this optimization problem, and the algorithm updates the strategy through interaction with the environment to get a better solution. Finally, we take Guangzhou Baiyun International Airport as a study case to train and verify the proposed single-airport flight time allocation model. The experimental results show that, the optimized flight slots satisfy the airport capacity constraints while minimizing the adjustment of flight schedules as much as possible, and adjust the flights at some times to alleviate the congestion. © 2025 SPIE ·

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

DD-Net: Dynamic Network Architecture for Optimized Curve Segmentation and Reduce Computational Redundancy 27th

DD-Net: Dynamic Network Architecture for Optimized Curve Seg...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Cao, Yunxiang Chen, Li Wang, Yubo Feng, Zhida Tian, Jing School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan China Institute of Systems Science National University of Singapore Singapore Singapore

ISBN: (纸本)9783031783821

Curvilinear Structure segmentation has numerous applications in various fields, including providing a better understanding of defects such as cracks on roads or walls, thereby assessing the structural safety of buildings. Numerous curve segmentation methods based on Convolutional Neural Networks(CNN) have been developed in recent years. However, preserving feature integrity remains a challenge. To address this issue, this paper introduces a double dynamic network, called DD-Net, which consists of a dynamic structure for training and dynamic masking for inference. Firstly, to enhance the nonlinearity of the model, a paradigm to auto-adjust the CNN structure via a trainable module is formed for better fine-grained feature extraction. This dynamic structure (DS) paradigm enables a trade-off to extract or discard the feature data in the model training. Due to the data heterogeneity between the training and inference data, models may contain some useless nodes that are less effective during inference. The dynamic masking (DM) is proposed to omit the useless nodes based on the score difference between the train and inference feature statistics, thereby reducing redundant computations. To further improve the model’s performance on thin-curve segmentation and to preserve feature integrity, we introduce a non-curve suppression (NCS) module. This module focuses on background information while considering foreground prediction to address noisy conditions. The experimental results show that our DD-Net achieves promising results on three benchmark datasets and outperforms state-of-the-art curve segmentation models. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Small Signal Stability-Guaranteed Moving Target Defense Against Load Redistribution Attack On IoT-based Smart Grid

引用

IEEE Internet of Things Journal 2025年第11期12卷 17413-17429页

作者： Wang, Bingdong Zhang, Zhenyong Wang, Mufeng Liu, Mengxiang Ye, Rui Deng, Ruilong Zhang, Xin Guizhou University State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang550025 China China Industrial Control Systems Cyber Emergency Response Team Beijing100040 China University of Sheffield Department of Automatic Control and System Engineering Sheffield United Kingdom Guizhou Power Grid Co. Ltd. Intelligent Operation Center China Zhejiang University State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Hangzhou310027 China Huzhou Institute of Industrial Control Technology Huzhou313000 China

Moving target defense (MTD) is a promising approach to defend against load redistribution attacks on the internet-of-things (IoT)-based smart grid networks by probing the distorted state estimates with the distributed flexible AC transmission system. However, existing studies mainly focus on optimizing the performance of MTD and ignore the safety effect of it on the system’s operation. In this paper, we fill this gap by deeply analyzing the effect of MTD on the small signal stability and aim to alleviate the negative impact and guarantee its defending performance simultaneously. Firstly, the stability is formally described using the eigenvalue sensitivity. The relationship between the MTD-induced perturbation (MTDper) and the stability criteria is derived. Secondly, a new indicator is proposed to measure the effectiveness of MTDper. Thirdly, a constrained optimization problem is formulated to compute the bound of MTDper for guaranteeing the small signal stability. In addition, a surprising finding is that the stability margin can be improved and enhanced by optimizing the value of MTDper without losing the MTD’s effectiveness. Finally, we evaluate the performance of MTDper and its impact on the small signal stability with extensive simulations on the IEEE 30-bus, 39-bus, and 68-bus test power systems. © 2014 IEEE.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

SSCCPC-Net: Simultaneously Learning 2D and 3D Features with CLIP for Semantic Scene Completion on Point Cloud 41st

SSCCPC-Net: Simultaneously Learning 2D and 3D Features with...

引用

41st computer Graphics International Conference, CGI 2024

作者： Duan, Wantong Bao, Yongtang Qi, Yue State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing100191 China Shandong University of Science and Technology Qingdao266590 China Jingdezhen Research Institute of Beihang University Jingdezhen333000 China Qingdao Research Institute of Beihang University Qingdao266000 China

ISBN: (纸本)9783031820236

Compare to traditional Scene Completion (SC), Semantic Scene Completion (SSC) is a challenging task that aims to generate complete and semantically consistent 3D scene from partial and sparse input data, which is fundamental to fully understanding the scene and being able to interact with it. Consequently, the SSC task has received much attention in recent years. Most of the methods are voxel-based approaches, but they have high computational and memory requirements. A few works based on point cloud do not sufficiently exploit the correlation between semantic segmentation and geometric completion subtasks, while focusing too much on point cloud shape features and ignoring the rich texture information that RGB images can provide. In this paper, we present SSCCPC-Net (Semantic Scene Completion with CLIP on Point Cloud-Net), a novel network architecture for point cloud semantic scene completion using a combination of 2D and 3D features. Inspired by recent works of large pretrained vision-language models in semantic segmentation, we explore to accomplish SSC task with the help of Contrastive Language-Image Pre-Training (CLIP) model. Specifically, we use the CLIP features for guidance to fuse the 2D features extracted from the RGB image and the 3D features extracted from the point cloud. The fused features are then fed into our designed Semantic-Completion Decoder for per-point semantic prediction and semantic labeling-assisted point cloud completion. Finally, we obtain the complete semantically point cloud. Numerous experiments have demonstrated that our method has higher effectiveness and generalizability compared to state-of-the-art methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Brillouin Frequency Shift Extraction for BOTDA Based on Gramian Angular Fields 4

Brillouin Frequency Shift Extraction for BOTDA Based on Gram...

引用

4th International Computational Imaging Conference, CITA 2024

作者： Zhu, Borong Zhang, Zhihao Qian, Yuhao Ma, Xiaole Wang, Liang Yu, Kuanglu Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China Institute of Information Science School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China National Engineering Laboratory for Next Generation Internet Access System School of Optics and Electronic Information Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781510688834

To accurately extract Brillouin frequency shift of BOTDA with large sweeping step sizes, a novel structure of GAFCNN is proposed, combining time series coding with convolutional neural networks. The experimental data validation results demonstrate that the GAFCNN is capable of obtaining more accurate results under large sweep steps and low signal-to-noise ratios (SNRs) than other current methods. © 2025 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimized Breast Lesion Segmentation in Ultrasound Videos Across Varied Resource-Scant Environments 17th

Optimized Breast Lesion Segmentation in Ultrasound Videos A...

引用

17th Asian Conference on computer Vision, ACCV 2024

作者： Li, Yunhao Chen, Zibin Yan, Junming Ding, Ziyu Li, Jie Huang, Teng Pei, Xiaoqing Zhang, Zheng Wang, Qiong Pang, Yan Institute of Artificial Intelligence Guangzhou University Guangzhou China Cancer Center Sun Yat-sen University Guangzhou China Moxibustion and Rehabilitation Guangzhou University of Chinese Medicine Guangzhou China Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9789819609659

Medical video segmentation plays a crucial role in clinical diagnosis and therapeutic procedures by enabling dynamic tracking of breast lesions across frames in ultrasound videos, thereby improving segmentation accuracy. However, the existing methods struggle to strike a balance between segmentation accuracy and inference speed, which impedes their real-time deployment in resource-limited medical environments. To overcome these challenges, we introduce a rapid breast lesion segmentation framework named RbS. RbS employs the Stem module and RbSBlock to enhance representations through intra-frame analysis of ultrasound videos. Moreover, we have developed two versions of RbS: RbS-S boasts enhanced segmentation accuracy, while RbS-L ensures faster inference speeds. Experimental evidence indicates that RbS surpasses current leading models in both segmentation efficiency and prediction accuracy, particularly on resource-limited devices. Our contribution significantly propels the progress of developing efficient medical video segmentation frameworks suitable for various medical platforms. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Image segmentation

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：