检索结果-内蒙古大学图书馆

Distributed Collaborative inference System in Next-Generation Networks and Communication

IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING 2025年第2期11卷 923-932页

作者： Zhang, Chuan Zheng, Xixi Tao, Xiaolong Hu, Chenfei Zhang, Weiting Zhu, Liehuang Beijing Inst Technol Sch Cyberspace Sci & Technol Beijing 100081 Peoples R China Minist Educ China Key Lab Cyberspace Secur Zhengzhou 450001 Peoples R China Beijing Jiaotong Univ Sch Elect & Informat Engn Beijing 100044 Peoples R China

With the rapid advancement of artificial intelligence, generative artificial intelligence (GAI) has taken a leading role in transforming data processing methods. However, the high computational demands of GAI present challenges for devices with limited resources. As we move towards the sixth generation of mobile networks (6G), the higher data rates of 6G create a need for more efficient data processing in GAI. Traditional GAI, however, shows its limitations in meeting these demands. To address these challenges, we introduce a multi-level collaborative inference system designed for next-generation networks and communication. Our proposed system features a deployment strategy that assigns models of varying sizes to devices at different network layers. Then, we design a task offloading strategy to optimise both efficiency and latency. Furthermore, a modified early exit mechanism is implemented to enhance the inference process for single models. Experimental results demonstrate that our system effectively reduces inference latency while maintaining high-quality output. Specifically, compared to existing work, our system can reduce inference time by up to 17% without sacrificing the inference accuracy.

关键词： Computational modeling Accuracy Transformers inference algorithms Collaboration Next generation networking Adaptation models 6G mobile communication Servers Probabilistic logic Generative artificial intelligence early exit collaborative inference next-generation networks and communication

来源：评论

学校读者我要写书评

暂无评论

A 4.69-TOPS/W Training, 2.34-μJ/Image inference On-Chip Training Accelerator With inference-Compatible Backpropagation and Design Space Exploration in 28-nm CMOS

引用

IEEE JOURNAL OF SOLID-STATE CIRCUITS 2025年第1期60卷 298-307页

作者： Qian, Junyi Ge, Haitao Lu, Yicheng Shan, Weiwei Southeast Univ Sch Integrated Circuits Nanjing 210096 Peoples R China

On-chip training (OCT) accelerators improve personalized recognition accuracy while ensuring user privacy. However, previous OCT accelerators often required significant additional hardware costs to support retraining, even though inference is the primary use case. We propose an inference-pattern-compatible backpropagation (BP) circuit, which enables the training process to reuse inference hardware. To achieve high energy efficiency, we utilize three hardware-friendly optimization methods that significantly reduce redundant computation and external memory access (EMA). Additionally, we propose a design space exploration (DSE) to search for the optimal hardware configurations, which improves system performance while reducing the design time cost. Fabricated in a 28-nm CMOS process, this single-core OCT chip is able to train all the layers of a neural network (NN), achieving a peak training efficiency of 4.69 Tera operations per second per watt (TOPS/W). It also achieves the lowest inference energy of 2.34 mu J/inf/image under a core voltage of 0.48 V and 40 MHz.

关键词： Convolution Training Kernel Hardware inference algorithms System-on-chip Energy efficiency Backpropagation (BP) circuit design space exploration (DSE) energy efficiency neural network (NN) on-chip training (OCT) transfer learning

来源：评论

学校读者我要写书评

暂无评论

On-Orbit DNN Distributed inference for Remote Sensing Images in Satellite Internet of Things

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第5期12卷 5687-5703页

作者： Qiao, Ying Teng, Shuyang Luo, Juan Sun, Peng Li, Fan Tang, Fengxiao Hunan Univ Coll Informat Sci & Engn Changsha 410082 Peoples R China Cent South Univ Coll Comp Sci & Engn Changsha 410017 Peoples R China

In satellite Internet of Things (IoT), the remote sensing satellites capture images and then transmit them to a ground station through low Earth orbit (LEO) communication satellites for model inference. However, this process results in significant transmission latency and communication overhead. In response, researchers have proposed various satellite on-orbit model inference methods. Nonetheless, the limited computation capacity and memory space of a single remote sensing satellite impose processing delays when dealing with large quantities of high-resolution images, thereby making it difficult to ensure real-time service. To tackle this issue, we propose an on-orbit deep neural network (DNN) distributed inference framework for remote sensing images in satellite IoT, leveraging the availability of numerous LEO computing satellites. Designing such a framework involves two crucial questions: first, determining which LEO satellites should participate in distributed DNN inference, and second, how to partition the images among the selected LEO satellites. To address these questions, we formulate the distributed inference process as a mixed integer nonlinear optimization problem, which is known to be NP-hard. The objective is to minimize overall energy consumption while ensuring that the distributed inference is accomplished when the satellite dynamic network remains unchanged. We initially propose a dynamic optimization algorithm that derives the optimal solution with rigorous theoretical guarantees. Subsequently, to reduce computational complexity, we introduce an approximate solution based on an improved simulated annealing algorithm. We demonstrate that the approximate algorithm performs within a limited range of the optimal algorithm. Finally, we build a heterogeneous testbed based on Kubernetes and conduct extensive experiments to validate that our proposed algorithms reduce energy consumption by an average of 24.63% and 25.98% on the Faster-RCNN inference model, 4

关键词： Satellites Low earth orbit satellites Remote sensing Heuristic algorithms Computational modeling Collaboration inference algorithms Delays Data models Energy consumption Deep neural network (DNN) inference dynamic programming Kubernetes low Earth orbit (LEO) satellites satellite Internet of Things (IoT) simulated annealing algorithm

来源：评论

学校读者我要写书评

暂无评论

Causal inference-Based Large-Scale Multiobjective Optimization

引用

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION 2025年第2期29卷 444-458页

作者： Li, Bingdong Yang, Yanting Yang, Peng Li, Guiying Tang, Ke Zhou, Aimin East China Normal Univ Shanghai Frontiers Sci Ctr Mol Intelligent Synth Sch Comp Sci & Technol Shanghai Inst AI Educ Shanghai 200062 Peoples R China East China Normal Univ Key Lab Adv Theory & Applicat Stat & Data Sci Minist Educ Shanghai 200062 Peoples R China East China Normal Univ Shanghai Inst AI Educ Shanghai Frontiers Sci Ctr Mol Intelligent Synth Shanghai 200062 Peoples R China East China Normal Univ Sch Comp Sci & Technol Shanghai 200062 Peoples R China Southern Univ Sci & Technol Dept Comp Sci & Engn Guangdong Prov Key Lab Brain Inspired Intelligent Shenzhen 518055 Peoples R China Southern Univ Sci & Technol Dept Stat & Data Sci Shenzhen 518055 Peoples R China Peng Cheng Lab Dept Networked Intelligence Shenzhen 518000 Peoples R China

Large-scale multiobjective optimization problems (LSMOPs), characterized by a substantial number of decision variables, pose significant challenges for many existing evolutionary algorithms. However, the search efficiency of these algorithms is not yet satisfactory. This is mainly because that the search efficiency of these algorithms may deteriorate dramatically since the search space increases exponentially with the number of decision variables. Having this in mind, we proposed a large-Scale multiobjective optimization framework named causal inference-based competitive swarm optimizer (CI-CSO). Specifically, a causal-information-(CI)-based operator is designed for competitive swarm optimizers. First, a causal inference technique named information geometric causal inference (IGCI) is introduced to adequately explore the CI between decision variables and fitness values. To further distinguish the positive or negative impacts of these critical variables on solution quality, a CI processing module is designed, facilitating targeted optimization. To enhance search efficiency, CI-based offspring generator are employed, leveraging the variance of causal effects to dynamically adjust the search step size and sampling range. To evaluate its performance, the proposed CI-based operator is embedded into two multiobjective evolutionary algorithms (MOEAs) (LSTPA and LMOCSO). To demonstrate the effectiveness of the proposed framework, experimental results are presented using the LSMOP test suite and five real-world problems, each involving up to 10 000 decision variables. In addition, six classic algorithms are included for comparison.

关键词： Optimization Convergence inference algorithms Evolutionary computation Robustness Data models Vectors Transfer functions Space exploration Search problems Causal inference competitive swarm optimizer large-scale optimization multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

A Spatial Model and Multiobjective Fuzzy inference-Based Clustering Routing Algorithm for Bridge Monitoring

引用

IEEE SENSORS JOURNAL 2025年第1期25卷 1669-1681页

作者： Yang, Jiguang Huo, Jiuyuan Mu, Cong Lanzhou Jiaotong Univ Sch Elect & Informat Engn Lanzhou 730070 Peoples R China Lanzhou Jiaotong Univ Sch Elect & Informat Engn Lanzhou 730070 Peoples R China Natl Cryosphere Desert Data Ctr NCDC Lanzhou 730000 Peoples R China

Wireless sensors have the advantages of distributed and flexible deployment, real-time monitoring, multisensor collaboration, self-organization, and self-adaptation. They can be widely used in bridge structural health monitoring systems (BHMSs). At the same time, wireless sensors are still limited by battery life and communication distance;extending the life cycle of wireless sensor networks (WSNs) employing optimal deployment and effective improvement of routing algorithms is a research hotspot for domestic and foreign engineering and academic circles. In this article, a WSN clustering routing algorithm based on bridge spatial model and multiobjective fuzzy inference (BSMOFC) is proposed to solve the problem that the existing research has not considered the spatial characteristics of bridges and the reasonable choice of cluster head (CH) in the clustering routing algorithm. First, a bridge space model is designed to simulate the 3-D deployment of WSN nodes;second, the CH selection process of the WSN clustering routing algorithm is defined as a multiobjective optimization problem, and the multiobjective non-dominated sorted whale optimization algorithm (NSWOA) is used to solve the set of Pareto solutions. All the solutions are defined as the candidate CHs (C-CHs), and then a fuzzy inference system is used to choose the final CHs (F-CHs). Finally, the simulation platform MATLAB completes the performance verification of the BSMOFC algorithm. The simulation results show that the BSMOFC algorithm can effectively extend the WSN lifetime and provide a new practical method for selecting a Pareto optimal solution.

关键词： Wireless sensor networks Clustering algorithms Bridges Routing Optimization Monitoring inference algorithms Wireless communication Fuzzy logic Sensor phenomena and characterization Bridge space model bridge structural health monitoring system (BHMS) fuzzy inference system multiobjective optimization wireless sensor network (WSN)

来源：评论

学校读者我要写书评

暂无评论

An Efficient and Zero-Knowledge Classical Machine Learning inference Pipeline

引用

IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING 2025年第2期22卷 1347-1364页

作者： Wang, Haodi Bie, Rongfang Hoang, Thang Beijing Normal Univ Sch Artificial Intelligence Beijing 100875 Peoples R China Virginia Tech Blacksburg VA 24061 USA

Machine Learning as a Service (MLaaS) offers powerful data analytics services to clients with limited resources. However, it still raises concerns about the integrity of delegated computation and the privacy of the server's model parameters. To address these issues, zero-knowledge Machine Learning (zkML) has been suggested for computation verifiability with privacy guarantee for ML models. Nevertheless, the existing zkML schemes focus on only one classical ML classification algorithm or deep neural networks, which may not achieve satisfactory accuracy or require large-scale training data and model parameters, thus limiting their usefulness in certain applications. In this article, we propose ezDPS, an efficient and zero-knowledge scheme for classical ML inference that processes data in multiple stages for improved accuracy. Unlike prior works, each stage of the ezDPS pipeline is based on a well-established classical ML algorithm, including Discrete Wavelet Transformation, Zero-Score Normalization, Principal Components Analysis, and Support Vector Machine. We design new gadgets to prove various ML operations effectively. Our implementation of ezDPS has been fully tested on real datasets, and experimental results show that it is up to three orders of magnitude more efficient than generic circuit-based approaches, while also maintaining greater accuracy than single ML classification approaches.

关键词： Pipelines Computational modeling Servers Accuracy Privacy inference algorithms Feature extraction Classical machine learning zero knowledge proofs inference pipeline

来源：评论

学校读者我要写书评

暂无评论

Input-to-state stable predictive control based on continuous projected kinky inference

引用

INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL 2025年第7期35卷 2521-2536页

作者： Manzano, Jose Maria Munoz de la Pena, David Limon, Daniel Univ Loyola Andalucia Engn Dept Dos Hermanas Sevilla Spain Univ Seville Dept Syst Engn & Automat Seville Spain Univ Loyola Andalucia Engn Dept Avda La Univ S-N Dos Hermanas 41704 Sevilla Spain

In this article, the authors propose a novel continuous projected kinky inference algorithm, which inherits the good properties of projected kinky inference in terms of prediction error bound and computational time while ensuring Lipschitz continuity. Based on this, a learning based MPC is presented which is demonstrated to be input-to-state stable by design. Illustrative examples are shown in a learning-based MPC framework.

关键词： inference algorithms machine learning predictive control input-to-state stability system identification

来源：评论

学校读者我要写书评

暂无评论

Mobility and Cost Aware inference Accelerating Algorithm for Edge Intelligence

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2025年第3期24卷 1530-1549页

作者： Yuan, Xin Li, Ning Wei, Kang Xu, Wenchao Chen, Quan Chen, Hao Guo, Song Harbin Inst Technol Sch Ocean Engn Harbin 150001 Peoples R China Harbin Inst Technol Sch Comp Sci & Technol Harbin 150001 Peoples R China TheHong Kong Polytech Univ Dept Comp Hong Kong 999077 Peoples R China Guangdong Univ Technol Sch Comp Sci & Technol Guangzhou 510006 Peoples R China Hong Kong Univ Sci & Technol Dept Comp Sci & Engn Hong Kong Peoples R China

The edge intelligence (EI) has been widely applied recently. Splitting the model between device, edge server, and cloud can significantly improve the performance of EI. The model segmentation without user mobility has been investigated in detail in previous studies. However, in most EI use cases, the end devices are mobile. Few studies have been conducted on this topic. These works still have many issues, such as ignoring the energy consumption of mobile device, inappropriate network assumption, and low effectiveness on adapting user mobility, etc. Therefore, to address the disadvantages of model segmentation and resource allocation in previous studies, we propose mobility and cost aware model segmentation and resource allocation algorithm for accelerating the inference at edge (MCSA). Specifically, in the scenario without user mobility, the loop iteration gradient descent (Li-GD) algorithm is provided. When the mobile user has a large model inference task that needs to be calculated, it will take the energy consumption of mobile user, the communication and computing resource renting cost, and the inference delay into account to find the optimal model segmentation and resource allocation strategy. In the scenario with user mobility, the mobility aware Li-GD (MLi-GD) algorithm is proposed to calculate the optimal strategy. Then, the properties of the proposed algorithms are investigated, including convergence, complexity, and approximation ratio. The experimental results demonstrate the effectiveness of the proposed algorithms.

关键词： Servers Computational modeling inference algorithms Resource management Delays Costs Energy consumption Complexity theory Partitioning algorithms Mobile handsets Edge intelligence model segmentation inference accelerating mobility

来源：评论

学校读者我要写书评

暂无评论

Scene inference Using Saliency Graphs With Trust-Theoretic Semantic Information Encoding

引用

IEEE SIGNAL PROCESSING LETTERS 2025年 32卷 256-260页

作者： Meena, Preeti Kumar, Himanshu Yadav, Sandeep Indian Inst Technol Jodhpur Discipline Elect Engn Jodhpur 342030 India

Scene inference refers to the identification of the scene from a given set of scene representations such as images. A saliency graph of a scene contains scene-defining objects along with semantic information between them in the graph representation. Existing methods consider the entire scene with uniform weighting to all semantic information for scene inference, resulting in a suboptimal performance. This letter presents an optimal edge weight estimation using the trust theoretic framework to encode semantic information effectively in saliency graphs. We have utilized the notion of converged global absolute trust in saliency scores of salient objects to compute the weighting of semantic information. Experimental results highlight the efficacy of the proposed method.

关键词： Peer-to-peer computing Semantics Estimation Symmetric matrices Image edge detection Signal processing algorithms inference algorithms Eigenvalues and eigenfunctions Visualization Accuracy Scene inference saliency graph semantic information trust graph P2P

来源：评论

学校读者我要写书评

暂无评论

Beyond the Cloud: Edge inference for Generative Large Language Models in Wireless Networks

引用

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS 2025年第1期24卷 643-658页

作者： Zhang, Xinyuan Nie, Jiangtian Huang, Yudong Xie, Gaochang Xiong, Zehui Liu, Jiang Niyato, Dusit Shen, Xuemin BUPT State Key Lab Networking & Switching Technol Beijing 100876 Peoples R China Nanyang Technol Univ Sch Comp Sci & Engn Singapore 639798 Singapore Singapore Univ Technol & Design Informat Syst Technol & Design ISTD Pillar Singapore 487372 Singapore Purple Mt Labs Nanjing 211111 Peoples R China Nanyang Technol Univ Coll Comp & Data Sci Singapore 639798 Singapore Univ Waterloo Dept Elect & Comp Engn Waterloo ON N2L 3G1 Canada

Generative Artificial Intelligenge (GAI) is revolutionizing the world with its unprecedented content creation ability. Large Language Model (LLM) is one of its most embraced branches. However, due to LLM's substantial size and resource-intensive nature, it is cloud-hosted, raising concerns about privacy, usage limitations, and latency. In this paper, we propose to utilize ubiquitous distributed wireless edge computing resources for real-time LLM inference. Specifically, we introduce a novel LLM edge inference framework, incorporating batching and model quantization to ensure high throughput inference on resource-limited edge devices. Then, based on the architecture of transformer decoder-based LLMs, we formulate an edge inference optimization problem which is NP-hard, considering batch scheduling and joint allocation of communication and computation resources. The solution is the optimal throughput under edge resource constraints and heterogeneous user requirements on latency and accuracy. To solve this NP-hard problem, we develop an OT-GAH (Optimal Tree-search with Generalized Assignment Heuristics) algorithm with reasonable complexity and 1/2-approximation ratio. We first design the OT algorithm with online tree-pruning for single-edge-node multi-user case, which navigates the inference request selection within the tree structure to miximize throughput. We then consider the multi-edge-node case and propose the GAH algorithm, which recrusively invokes the OT in each node's inference scheduling iteration. Simulation results demonstrate the superiority of OT-GAH batching over other benchmarks, revealing an over 45% time complexity reduction compared to brute-force searching.

关键词： Computational modeling Quantization (signal) Accuracy inference algorithms Throughput Wireless networks Transformers Resource management Optimization Chatbots Generative AI edge inference wireless networks multiuser edge computing

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：