检索结果-内蒙古大学图书馆

ExpertDRL: Request Dispatching and Instance Configuration for Serverless Edge Inference with Foundation Models

IEEE Transactions on Mobile Computing 2025年

作者： Zeng, Yue Zhou, Junlong Ye, Baoliu Qu, Zhihao Guo, Song Gong, Tianjian Li, Pan Nanjing University of Science and Technology Department of Computer Science and Engineering Jiangsu Nanjing210094 China Nanjing University State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing210023 China Hohai University Key Laboratory of Water Big Data Technology of Ministry of Water Resources Nanjing211100 China Hong Kong University of Science and Technology Hong Kong Southwest University College of Electronic and Information Engineering Chongqing400715 China

The prevalence of the pre-training & fine-tuning paradigm enables machine learning models to quickly adapt to various downstream tasks by fine-tuning pre-trained foundation models (FMs), greatly facilitating various IoT applications that rely on model inference in dynamic edge serverless environments. Efficiently dispatching inference requests and configuring instances to batch inference requests can significantly enhance resource efficiency. However, existing serverless inference solutions are tailored for traditional models, make coarse-grained request dispatching and instance configuration decisions, fail to exploit the shared model backbone characteristics of the FM and capture delayed rewards in dynamic environments, and ignore communication latency between edge sites, resulting in high costs and constraint violations. In this paper, we leverage our insight that fine-grained batch inference requests can effectively exploit the shared model backbone feature of FM to save monetary costs. We propose an algorithm that incorporates deep reinforcement learning (DRL) and expert intervention for fine-grained request dispatching and instance configuration, where the DRL component outputs fractional solutions as guidance, while the expert intervention module integrates our insights—batching reduces monetary costs at the expense of increased inference latency, whereas higher configurations shorten inference latency. This module rounds fractional solutions and adjusts instance configurations to search for optimal solutions while satisfying constraints, with theoretical guarantees rigorously proved. Finally, we conducted our experiments on an OpenFaas-based platform and simulator, and extensive trace-driven evaluation results show that ExpertDRL can save costs by up to 85.14% and improve request acceptance ratio by up to 26.93%, compared to the state-of-the-art solution. © 2002-2012 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Server Cooperative Video Caching Strategy Based on Deep Reinforcement Learning in Cloud-Edge Computing

Multi-Server Cooperative Video Caching Strategy Based on Dee...

引用

International Conference on Big data Computing and Communications (BIGCOM)

作者： Guanyu Li Yingchi Mao XinXin Peng Haotian Zheng Zibo Wang College of Computer Science and Software Engineering Hohai University Nanjing China Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China Huaneng Hydro Lancang Xiaowan Hydropower Plant Dali China

ISBN: (数字)9798331509538

ISBN: (纸本)9798331509545

The soaring number of mobile devices has led the innovation of the edge caching in edge computing, which relieves the heavy pressure of cloud computing. However, with the escalating popularity of short video services, the prevalence of video content in edge server caches has seen a marked increase. Previous work ignored the impact of edge server performance on video caching and failed to automatically adjust the optimal video bit rate in response to users' demand. To improve users' evaluation for watching videos on devices with different display sizes, we propose a novel edge caching strategy called Gate Self-attention Recurrent Network-Multi Agent Reinforcement Learning(GSRN-MARL). GSRN-MARL utilizes leverages Gate Recurrent Unit(GRU) and attention mechanisms to predict cache content based on user historical request information and device details, consequently improving edge server caching performance and users' evaluation of video. Experiment demonstrates that GSRN-MARL surpasses LRU, DRL, and MAAC across two critical metrics: video cache hit rate and users' QoE (Quality of Experience).

关键词： Performance evaluation Training Cloud computing Technological innovation Bit rate Logic gates Mobile handsets Servers Quality of experience Edge computing

来源：评论

学校读者我要写书评

暂无评论

Research Progress on Optimization-Based Disassembly Sequence Planning

引用

Computer engineering and Applications 2025年第11期61卷 51-66页

作者： Guo, Hongfei Fu, Wenjie Li, Leixiao Lin, Hao College of Data Science and Application Inner Mongolia University of Technology Hohhot010080 China Inner Mongolia Autonomous Region Software Service Engineering Technology Research Center Based on Big Data Hohhot010080 China College of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China

Disassembly sequence planning, as the first step to achieve product recycling, plays a decisive role in the quality and efficiency of recycling waste products. This paper addresses the three core issues of modelling methods, solution algorithms and uncertainty handling methods in demolition sequence planning. Firstly, the current mainstream modelling approaches for disassembly sequences and the disassembly scenarios tackled by various modelling approaches are collated and analyzed. Secondly, from the perspective of decision solving, the characteristics of three different solving methods, namely mathematical planning methods, intelligent optimization algorithms and reinforcement learning algorithms, as well as the challenges faced when making optimal decisions, are discussed. And the solving methods of single-objective optimization problems and multi-objective optimization problems in the field of disassembly are systematically analyzed. Thirdly, the strategies for dealing with uncertain disassembly problems in the disassembly process are summarized. The advantages and disadvantages of the different strategies are analyzed. Finally, the current state of research on disassembly sequence planning is summarized, and future research directions are discussed. © 2025 Journal of Computer engineering and Applications Beijing Co., Ltd.;science Press. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Enabled Healthcare Balancing Patient Privacy and data Utility

Machine Learning Enabled Healthcare Balancing Patient Privac...

引用

International Conference on science Technology engineering and Management (ICONSTEM)

作者： Manoj Ram Tammina Bhargavi Posinasetty Prabha Shreeraj Nair Santosh Kumar Pavithra G Harpreet Kaur Sr Software Developer Innovation Bread Financial Columbus Ohio Clinical Data Management Sr. Clinical Data Manager PROMETRIKA LLC Department of IT Noida Institute of Engineering and Technology Greater Noida Computer Science ERA University Lucknow Uttar Pradesh Electronics & Communication Engineering Dayananda Sagar College of Engineering Bangalore Karnataka Lovely Professional University Punjab Phagwara

ISBN: (数字)9798350365092

ISBN: (纸本)9798350365108

When applied to healthcare, machine learning ushers in a new age of data-driven medical practice that holds great promise for better patient outcomes and individualized treatment. However, this evolution isn't without significant difficulties, such as the difficulty of striking a balance between patient confidentiality and data use. In this study, we use -Differential Privacy as a privacy-protecting technique and a number of machine learning models to quantify the value of the data collected. Our research demonstrates a subtle trade-off, where more stringent privacy safeguards often result in less useful data, and vice versa. We stress the need for ethical frameworks, patient permission, and flexible privacy restrictions as means of negotiating this space. Achieving responsible and successful machine learning-enabled healthcare calls for a number of future steps, including optimization of privacy settings, adoption of federated learning, data ownership through blockchain, validations in the actual world, and extensive ethical advice.

关键词： data privacy Ethics Privacy Federated learning Medical services data models Blockchains

来源：评论

学校读者我要写书评

暂无评论

A Lightweight and Robust Access Control Protocol for IoT-based e-Healthcare Network

引用

IEEE Transactions on Mobile Computing 2025年

作者： Ghaffar, Zahid Kuo, Wen-Chung Mahmood, Khalid Tariq, Tayyaba Shamshad, Salman Das, Ashok Kumar Alenazi, Mohammed J.F. National Yunlin University of Science and Technology Graduate School of Engineering Science and Technology Douliu64002 Taiwan National Yunlin University of Science and Technology Department of Computer Science and Information Engineering Douliu64002 Taiwan National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Douliu64002 Taiwan The University of Lahore Department of Software Engineering Lahore54590 Pakistan International Institute of Information Technology Center for Security Theory and Algorithmic Research Hyderabad500 032 India Korea University Department of Computer Science and Engineering College of Informatics 145 Anam-ro Seongbuk-gu Seoul02841 Korea Republic of King Saud University College of Computer and Information Sciences Department of Computer Engineering Riyadh Saudi Arabia

Internet of Things (IoT) devices are crucial components in e-healthcare networks. It enables remote patient health monitoring and facilitates seamless communication among medical sensors, wearable devices, and healthcare providers through public communication channels. Despite these advantages, the use of public communication among medical sensors in e-healthcare networks introduces critical challenges, such as vulnerability to impersonation, physical capture, and ephemeral secret leakage, particularly in resource-constrained environments. In recent years, various access control protocols have been developed to mitigate these risks. However, these protocols often fail to ensure robust security while incurring significant communication and computation overhead. To overcome these limitations, we propose a lightweight and robust access control protocol for IoT-based e-healthcare networks using chaotic maps. We propose a novel protocol that integrates a PUF-based mechanism to mitigate the challenges of physical tampering and cloning attacks in e-healthcare networks. It leverages the inherent uniqueness of PUF and enhances security through the high-entropy properties of chaotic maps. We analyze the proposed protocol informally, which confirms that it significantly bolsters efficiency and security. We also validate the security using the Random or Real (RoR) model. Moreover, we verify the security of the proposed protocol using Scyther. These analyses highlight that the proposed protocol offers robust resistance to numerous attacks, such as impersonation, physical capture, and ephemeral secret leakage. Moreover, we also compare it with existing and relevant protocols. The comparative analysis showcases its superior performance. Notably, the proposed authentication protocol significantly reduces 46.84% computational overhead and decreases 31.30% communication overhead, underscoring its enhanced performance and resource efficiency. © 2002-2012 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Crowdsourcing for data Labeling with Heterogeneous Crowd

Hierarchical Crowdsourcing for Data Labeling with Heterogene...

引用

International Conference on data engineering

作者： Haodi Zhang Wenxi Huang Zhenhan Su Junyang Chen Di Jiang Lixin Fan Chen Zhang Defu Lian Kaishun Wu College of Computer Science and Software Engineering Shenzhen University Department of Computing Hong Kong Polytechnic University WeBank Institute of Financial Technology Shenzhen University Webank Co. Ltd. School of Data Science University of Science and Technology of China

With the rapid and continuous development of data-driven technologies such as supervised learning, high-quality labeled data sets are commonly required by many applications. Due to the easiness of crowdsourcing small tasks with low cost, a straightforward solution for label quality improvement is to collect multiple labels from a crowd, and then aggregate the answers. The aggregation strategies include majority voting and its many variants, EM-based approaches, Graph Neural Nets and so on. However, due to the uncertainty information loss and commonly existing task correlations, the aggregated labels usually contain errors and may damnify the downstream model *** address the above problem, we propose a hierarchical crowdsourcing framework 1 for data labeling with noisy answers about correlated data. We make use of the heterogeneity of the labeling crowd and form an initialization-checking-update loop to improve the quality of labeled data. We formalize and successfully solve the core optimization problem, namely, selecting a proper set of checking tasks for each round. We prove that maximizing the expected quality improvement is equivalent to minimizing the conditional entropy of the observations given the crowdsourced answer families for the selected task set, which is NP-hard to solve. Therefore, we design an efficient approximation algorithm and conduct a series of experiments on real data. The experimental results show that the proposed method effectively improves the quality of the labeled data sets as well as the SOTA performance, yet without extra human labor costs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning

arXiv

引用

arXiv 2024年

作者： Xia, Tianle Ding, Liang Wan, Guojia Zhan, Yibing Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China The University of Sydney Australia JD Explore Academy China College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore

Answering complex queries over incomplete knowledge graphs (KGs) is a challenging task. Most previous works have focused on learning entity/relation embeddings and simulating first-order logic operators with various neural networks. However, they are bottlenecked by the inability to share world knowledge to improve logical reasoning, thus resulting in suboptimal performance. In this paper, we propose a complex reasoning schema over KG upon large language models (LLMs), containing a curriculum-based logical-aware instruction tuning framework, named LACT. Specifically, we augment the arbitrary first-order logical queries via binary tree decomposition, to stimulate the reasoning capability of LLMs. To address the difficulty gap among different types of complex queries, we design a simple and flexible logic-aware curriculum learning framework. Experiments across widely used datasets demonstrate that LACT has substantial improvements (brings an average +5.5% MRR score) over advanced methods, achieving the new state-of-the-art. Copyright © 2024, The Authors. All rights reserved.

关键词： Binary trees

来源：评论

学校读者我要写书评

暂无评论

High-dimensional Feature Selection in Classification: A Length-Adaptive Evolutionary Approach

High-dimensional Feature Selection in Classification: A Leng...

引用

IEEE International Conference on Networking, Sensing and Control

作者： Junhai Zhou Jianyun Lu Quanwang Wu Junhao Wen College of Computer Science Chongqing University Chongqing China School of Artificial Intelligence and Big Data Chongqing College of Electronic Engineering Chongqing China College of Software Engineering Chongqing University Chongqing China

ISBN: (纸本)9781665472449

Feature selection is an essential technique which has been widely applied in data mining. Recent research has shown that a good feature subset can be obtained by using evolutionary computing (EC) approaches as a wrapper. However, most feature selection methods based on EC use a fixed-length encoding to represent feature subsets. When this fixed length representation is applied to high-dimensional data, it requires a large amount of memory space as well as a high computational cost. Moreover, this representation is inflexible and may limit the performance of EC because of a too huge search space. In this paper, we propose an Adaptive- Variable-Length Genetic Algorithm (A VLGA), which adopts a variable-length individual encoding and enables individuals with different lengths in a population to evolve in their own search space. An adaptive length changing mechanism is introduced which can extend or shorten an individual to guide it to explore in a better search space. Thus, A VLGA is able to adaptively concentrate on a smaller but more fruitful search space and yield better solutions more quickly. Experimental results on 6 high-dimensional datasets reveal that A VLGA performs significantly better than existing methods.

关键词： Training Sociology Memory management Process control Feature extraction Encoding Sensors

来源：评论

学校读者我要写书评

暂无评论

Optimization Study of BP Neural Network Based on Genetic Algorithm

Optimization Study of BP Neural Network Based on Genetic Alg...

引用

Electrical, Automation and Computer engineering (ICEACE), International Conference on

作者： Yongheng Cai Zhuye Zhou Zehui Li School of Computing Zhuhai College of Science and Technology Zhuhai China School of Data Sciences Zhejiang University of Finance & Economics Hangzhou China School of Automation and Software Engineering Shanxi University Taiyuan China

In today's era of big data, neural networks play a pivotal role in fields such as image recognition and natural language processing. However, traditional Backpropagation (BP) neural networks often encounter challenges when dealing with complex problems, including slow convergence and getting stuck in local optima. To address these issues, this study employs a genetic algorithm as an optimization technique to optimize the weights and thresholds of BP neural networks. Training is conducted on a set of highly nonlinear mapping datasets to obtain the optimal weight and threshold configurations for the GA-BP model. Experimental results demonstrate that compared to traditional BP neural networks, the GA-BP model exhibits a 19.8% improvement in prediction accuracy, an approximately 9.20% increase in the coefficient of determination (R 2 ), a reduction of approximately 62.50% in mean squared error (MSE), and a decrease of about 38.76% in root mean squared error (RMSE). Furthermore, the GA-BP model displays significantly accelerated convergence. The contribution of this research lies in proposing an optimization method that combines genetic algorithms with BP neural networks. This model not only enhances prediction accuracy compared to the standalone BP neural network but also significantly strengthens its generalization capabilities. As a result, it demonstrates substantial practical application potential across diverse datasets and application scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DAMPER: A Dual-Stage Medical Report Generation Framework with Coarse-Grained MeSH Alignment and Fine-Grained Hypergraph Matching 39

DAMPER: A Dual-Stage Medical Report Generation Framework wit...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Huang, Xiaofei Chen, Wenting Liu, Jie Lu, Qisheng Luo, Xiaoling Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Electrical Engineering City University of Hong Kong Kowloon Hong Kong National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

ISBN: (纸本)157735897X

Medical report generation is crucial for clinical diagnosis and patient management, summarizing diagnoses and recommendations based on medical imaging. However, existing work often overlook the clinical pipeline involved in report writing, where physicians typically conduct an initial quick review followed by a detailed examination. Moreover, current alignment methods may lead to misaligned relationships. To address these issues, we propose DAMPER, a dual-stage framework for medical report generation that mimics the clinical pipeline of report writing in two stages. In the first stage, a MeSH-Guided Coarse-Grained Alignment (MCG) stage that aligns chest X-ray (CXR) image features with medical subject headings (MeSH) features to generate a rough keyphrase representation of the overall impression. In the second stage, a Hypergraph-Enhanced Fine-Grained Alignment (HFG) stage that constructs hypergraphs for image patches and report annotations, modeling high-order relationships within each modality and performing hypergraph matching to capture semantic correlations between image regions and textual phrases. Finally,the coarse-grained visual features, generated MeSH representations, and visual hypergraph features are fed into a report decoder to produce the final medical report. Extensive experiments on public datasets demonstrate the effectiveness of DAMPER in generating comprehensive and accurate medical reports, outperforming state-of-the-art methods across various evaluation metrics. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Diagnosis

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：