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

Privacy-Preserving Machine Learning (PPML) inference for Clinically Actionable Models

引用

IEEE ACCESS 2025年 13卷 37431-37456页

作者： Balaban, Baris Magara, Seyma Selcan Yilgor, Caglar Yucekul, Altug Obeid, Ibrahim Pizones, Javier Kleinstueck, Frank Perez-Grueso, Francisco Javier Sanchez Pellise, Ferran Alanay, Ahmet Savas, Erkay Bagci, Cetin Sezerman, Osman Ugur European Spine Study Group, European Spine Study Acibadem Mehmet Ali Aydinlar Univ Inst Hlth Sci Dept Biostat & Bioinformat TR-34638 Istanbul Turkiye Sabanci Univ Dept Comp Sci & Engn TR-34956 Istanbul Turkiye Univ Tubingen Dept Comp Sci D-72074 Tubingen Germany Acibadem Univ Dept Orthoped & Traumatol Sch Med TR-34750 Istanbul Turkiye Elsan Jean Villar Private Hosp Clin Dos F-33520 Bordeaux France Hosp Univ La Paz Spine Surg Unit Madrid 28046 Spain Schulthess Klin Spine Ctr Div Dept Orthoped & Neurosurg CH-8008 Zurich Switzerland Hosp Univ Vall Hebron Spine Surg Unit Barcelona 08035 Spain Bilmed Comp & Software Co TR-34742 Istanbul Turkiye

Machine learning (ML) refers to algorithms (often models) that are learned directly from data, germane to past experience. As algorithms have constantly been evolving with the exponential increase of computing power and vastly generated data, privacy of algorithms as well as of data becomes extremely important due to regulations and IP rights. Therefore, it is vital to address privacy and security concerns of both data and model together with other performance metrics when commercializing machine learning models. Our aim is to show that privacy-preserving machine learning inference methods can safeguard the intellectual property of models and prevent plaintext models from disclosing information about the sensitive data employed in training these ML models. Additionally, these methods protect the confidentiality of model users' sensitive patient data. We accomplish this by performing a security analysis to determine an appropriate query limit for each user, using the European Spine Study Group's (ESSG) adult spinal deformity dataset. We implement a privacy-preserving tree-based machine learning inference and run two security scenarios (scenario A and scenario B) containing four parts with progressively increasing the number of synthetic data points, which are used to enhance the accuracy of the attacker's substitute model. A target model is generated with particular operation site(s) in each scenario, and substitute models are built with nine-time threefold cross-validation using the XGBoost algorithm with the remaining sites' data to assess the security of the target model. First, we create box plots of the test sets' accuracy, sensitivity, precision, and F-score metrics to compare the substitute models' performance with the target model. Second, we compare the gain values of the target and substitute models' features. Third, we provide an in-depth analysis to check the inclusion of target model split points in substitute models with a heatmap. Finally, we compare t

关键词： Data models Computational modeling Machine learning Machine learning algorithms Cryptography Accuracy Analytical models inference algorithms Homomorphic encryption Data privacy Homomorphic Encryption Privacy-Preserving Machine Learning XGBoost

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 Online Algorithm for inference Service Scheduling Using Combinations of Server-Based and Serverless Instances in Cloud Environments

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第8期12卷 11153-11165页

作者： Liu, Siyuan Pan, Li Liu, Shijun Qi, Kaiyuan Shandong Univ Sch Software Jinan 250101 Peoples R China Jinan Inspur Data Technol Co Ltd Jinan 250101 Peoples R China

With the continuous development in the field of machine learning, there is an increasing demand for the cloud-based machine learning inference services, which are latency-sensitive tasks, such as the service requests from the Internet of Things (IoT) devices. These inference services are generally accompanied by fluctuations and uncertainties, so they often require vastly varied numbers of servers at different time spots. As a result, how to dynamically and rationally schedule cloud servers for inference services has become an important issue. Alibaba Cloud currently provides its serverless instances called elastic container instance (ECI), and due to the advantages of pay-as-you-go billing and second-level elasticity, they are well-suited for handling bursty or fluctuating workloads. At the same time, Alibaba Cloud's subscription-based elastic compute service (ECS) instances can be used for steady-state workloads. Our objective is to dynamically combine these two types of instances to deal with inference service requests. In this article, we propose a deterministic online algorithm that can rationally schedule these two types of instances to optimize costs without requiring knowledge of future workloads. We prove that the proposed online algorithm achieves a competitive ratio of no more than 2 compared to the optimal offline algorithm. Through simulation experiments, we demonstrate that our algorithm outperforms three benchmarks, which are all-reserved algorithm, all-on-demand algorithm, and traditional online algorithms that only use ECS instances. Our algorithm exhibits superiority across various workloads and can significantly reduces costs in most cases.

关键词： Cloud computing Costs Pricing inference algorithms Servers Optimization Machine learning Internet of Things Scheduling Prediction algorithms competitive analysis cost management inference service online algorithm

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

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：