检索结果-内蒙古大学图书馆

Hybrid AI-Electronic Systems for Real-Time Edge Processing in IoT Networks 3

Hybrid AI-Electronic Systems for Real-Time Edge Processing i...

3rd International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, IITCEE 2025

作者： Sweety Prasanna Kiruba, G. Esakki Madura, E. Kumar, Bura Vijay Kavitha, M. Reddy, T. Srinivas Athiraja, A. Bannari Amman Institute of Technology Department of Computer Technology Tamil Nadu Sathyamangalam India Bannari Amman Institute of Technology Department of Artificial Intelligence and Data Science Tamil Nadu Sathyamangalam India School of Computer Science and Artificial Intelligence Sr University Warangal India Kathir College of Engineering Department of Artificial Intelligence and Data Science Neelambur Coimbatore India Malla Reddy Engineering College Department of Ece Main Campus Maisammaguda Telangana Medchal India Hyderabad India

ISBN: (纸本)9798331515911

Real-time data processing is facing many issues as a result of the Internet of Things' rapid expansion, especially at the network's edge where latency, bandwidth, and compute resources are limited. The creation of hybrid AI-electronic systems for real-time edge processing is investigated as a solution to these problems. To improve the effectiveness and precision of data processing in Internet of Things contexts, the research combines machine learning algorithms with sophisticated electronic circuits. The techniques include creating a brand-new hybrid framework that blends edge computing and AI models and focuses for low latency and low power consumption. When compared to conventional edge processing systems, extensive simulations and real-world research show a 25% reduction in processing latency and a 15% gain in data categorization accuracy. According to the findings, the suggested hybrid AI-electronic system can successfully handle the requirements of contemporary IoT networks and offer a scalable real-time edge processing solution. This strategy has potential for use in smart city applications, industrial automation, and other fields in the future. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Supply Chain Operations through Machine Learning: Opportunities and Challenges

Optimizing Supply Chain Operations through Machine Learning:...

引用

2025 International Conference on Pervasive Computational Technologies, ICPCT 2025

作者： Santhakumar, D. Soundararajan, Gopalakrishnan Chintala, Suman Bharath, E. Murthy Inumula, Krishna Chouhan, Kuldeep Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Thandalam Tamil Nadu Chennai602105 India Muscat College Ruwi Oman Business Intelligence Architect United States C K College of Engineering & Technology Anna University Department of Artificial Intelligence & Data Science Tamil Nadu Cuddalore India Maharashtra Pune411057 India Sharda School of Engineering and Technology Sharda University Department of Computer Science and Applications Greater Noida201310 India

ISBN: (纸本)9798331508685

In order to create enduring partnerships that are essential to attaining long-term economic success, supply chain management, or SCM, is essential. Strict standards and decision-making procedures are necessary for efficient SCM, and they have a big influence on the final results. In order to efficiently manage inventory levels and logistical procedures, this study offers a complex ML system that combines demand forecasts and optimisation methods. For predicting demand, the approach uses a Generative Adversarial Networks (GAN) model, taking advantage of its capacity to process time-series data and identify intricate trends. The algorithm achieves an impressive 96.4% forecasting of demand accuracy by examining extensive historical sales data and a variety of supply chain variables. In order to optimise inventory rules, the investigation also uses optimisation techniques, particularly Genetic Algorithms (GA) in conjunction with Simulated Annealing (SA). The model demonstrated significant improvements when implemented to an actual commercial logistics system. Notably, it reduced storage expenses by 19% and increased order fulfillment rates by 24%, proving its capacity for combining service standards with financial efficiency. The findings highlight the significant impact of ML on improving supply chain efficiency and show how it can result in significant cost savings and improve service quality. © 2025 IEEE.

关键词： Simulated annealing

来源：评论

学校读者我要写书评

暂无评论

AccelES: Accelerating Top-K SpMV for Embedding Similarity via Low-bit Pruning 31

AccelES: Accelerating Top-K SpMV for Embedding Similarity vi...

引用

31st IEEE International Symposium on High Performance computer Architecture, HPCA 2025

作者： Zhai, Jiaqi Shi, Xuanhua Huang, Kaiyi Ye, Chencheng Hu, Weifang He, Bingsheng Jin, Hai Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Wuhan430074 China National University of Singapore School of Computing 119077 Singapore

ISBN: (纸本)9798331506476

In the realm of recommendation systems, achieving real-time performance in embedding similarity tasks is often hindered by the limitations of traditional Top-K sparse matrix-vector multiplication (SpMV) methods, which suffer from high latency due to inefficient memory access patterns. This paper identifies these critical gaps and introduces AccelES, a novel approach that significantly enhances the efficiency of Top-K SpMV. Our method employs a two-stage calculation scheme: the first stage utilizes a compact, low-bit dataset to quickly identify the most relevant entries, while the second stage performs full-precision calculations solely on this pruned subset, thereby minimizing computational overhead. Furthermore, AccelES incorporates innovative matrix representations, Ultra-CSR and Random-CSR, which optimize memory bandwidth utilization. Experimental results demonstrate that AccelES accelerates performance, surpassing state-of-the-art FPGA, GPU, and CPU solutions by factors of 3.4×, 2.5×, and 153.3×, respectively, under controlled conditions. These advancements not only enhance processing speed but also significantly improve real-time performance in recommendation systems, establishing AccelES as a pivotal contribution to the field of Top-K sparse matrix-vector multiplication. © 2025 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Triple voting: hybrid cardiovascular diseases prediction model

引用

International Journal of Applied Decision Sciences 2025年第3期18卷 257-281页

作者： Solomon, Dahlak Daniel Kumar, Karan Sonia Kanwar, Kushal Polat, Kemal Yogananda School of AI Computers and Data Science Shoolini University Himachal Pradesh Solan India Mullana Ambala133207 India Department of Computer Science and Engineering and Information Technology Jaypee University of Information and Technology Himachal Pradish Solan India Department of Electrical and Electronics Engineering Bolu Abant Izzet Baysal University Bolu Turkey

Currently, cardiovascular diseases are a high-risk cause of death in both developed and developing countries. Thus, heart disease prognosis has received substantial interest in the medical field worldwide. The incidence of heart disorders is escalating at an alarming rate, and it is crucial and worrisome to anticipate their occurrence. Predicting and detecting cardiovascular disease using machine learning and data mining might be clinically useful, but difficult. There are numerous machine learning algorithms accessible, several studies have developed machine learning algorithms for early cardiac disease prediction to help physicians suggest medical treatments. The accuracy of the model will be evaluated to determine whether the performance of the model is accurate or not. Seven machine learning methods are compared in this study, with the data obtained from the UCI Laboratory’s cardiovascular patient database. In essence, this research presents a majority voting-based hybrid model which is called triple voting. The hybrid model uses voting of Naïve Bayes, logistic regression (LR) and support vector machines (SVM) experimental outcomes show the proposed triple voting model’s accuracy is 89%, which is higher than the individual models and other proposed hybrid models. Copyright © 2025 Inderscience Enterprises Ltd.

关键词： Pulmonary diseases

来源：评论

学校读者我要写书评

暂无评论

AI-Enhanced Public Safety Lighting for Smart Sustainable Cities Using Cloud Computing

AI-Enhanced Public Safety Lighting for Smart Sustainable Cit...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Tidke, Bharat Pragadeeswaran, S. Lakshmi, R. Poornima Bhuvaneswari, G. Manikandan, G. Murugan, S. University Nagpur Campus Pune India School of Computing Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Chennai Institute of Technology Department of Computer Science and Engineering Chennai India Saveetha Engineering college Department of Computer Science and Engineering Thandalam Tamil Nadu Chennai India Rmk Engineering College Department of Artificial Intelligence and Data Science RSM Nagar Kavaraipettai Tamil Nadu Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Biomedical Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331509828

This paper presents a novel method that combines cloud computing infrastructure and Reinforcement Learning (RL) algorithms to improve public safety lighting in smart cities. By dynamically adjusting lighting levels in response to real-time sensor inputs, the proposed system aims to maximize visibility while minimizing energy consumption. The cloud-based framework's RL agents continuously interact with the environment and human activity patterns to learn the best lighting policies. The system utilizes data from multiple sensors, including ambient light and motion detectors, to adjust real-time to daylight levels, weather, and pedestrian traffic variations. By integrating RL, the lighting system can adapt to changing urban dynamics and safety requirements over time, all while reducing energy waste. Compared to conventional static lighting systems, case studies and simulations show how the system can significantly improve visibility and response times while enhancing safety in various urban settings. RL algorithms can be easily deployed and managed throughout extensive smart city networks due to cloud computing network scalability and adaptability. This study advances sustainable urban infrastructure by showcasing the effectiveness of RL-based artificial intelligence (AI) solutions in public safety lighting optimization, thereby laying the groundwork for future smarter and safer cities. © 2025 IEEE.

关键词： Sustainable city

来源：评论

学校读者我要写书评

暂无评论

ABIDS-VEM: leveraging an equilibrium optimizer and data ramification in association with ensemble learning for anomaly-based intrusion detection system

引用

Journal of Supercomputing 2025年第7期81卷 1-35页

作者： Verma, Priyanka O’Shea, Donna Newe, Thomas Mehta, Nakul Bharot, Nitesh Breslin, John G. School of Computer Science University of Galway University road GalwayH91TK33 Ireland Department of Computer Science Munster Technological University Rossa Ave Bishopstown CorkT12 P928 Ireland Department of Electronics and Computer Engineering University of Limerick Castletroy LimerickV94 T9PX Ireland Data Science Institute University of Galway University road GalwayH91TK33 Ireland Digital Engineering University of Limerick Castletroy LimerickV94 T9PX Ireland

The convergence of the Internet of Things (IoT) and Industrial Internet of Things (IIoT) within the Industry 4.0 paradigm leverages software-defined networking, multi-cloud architectures, and edge/fog computing to enhance industrial processes. However, this digital transformation introduces significant cybersecurity and privacy vulnerabilities within the complex, data-intensive IoT/IIoT ecosystems. To mitigate these risks, this research proposes a novel Anomaly-based Intrusion Detection System using Voting-based Ensemble Model (ABIDS-VEM) in Industry 4.0 environments. The VEM architecture synergistically combines multiple machine learning algorithms and gradient boosting frameworks, including CatBoost (CB), XGBoost (XGB), LightGBM (LGBM), Logistic Regression (LR), and Random Forest (RF), to enhance the precision and computational efficiency of intrusion detection systems (IDS) in IoT/IIoT contexts. The proposed framework incorporates a data ramification process, in which the data is divided into multiple parts, feature selection process which is optimized through the Equilibrium Optimizer (EO) algorithm, and outlier detection utilizing the Isolation Forest (IF) method. Comprehensive empirical evaluations were conducted using three benchmark datasets: XIIoTID, NSL-KDD, and UNSW-NB15, to validate the efficacy of the proposed system. The model achieves high accuracy across datasets: 98.1476% for XIIoT-ID, an impressive accuracy of 98.9671% for NSL-KDD, and 94.1327% for UNSW-NB15 dataset. These experimental results demonstrate the potential of this approach to significantly enhance the resilience of critical industrial systems and data against evolving cyber threats, thereby supporting the continued evolution of Industry 4.0 technologies and bolstering the security posture of IoT/IIoT ecosystems. This research contributes to the ongoing efforts to secure the rapidly expanding digital industrial landscape, offering a robust solution for detecting and mitigating sophistic

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

A Model Inference Attack Based on Random Sampling in DLaaS 24th

A Model Inference Attack Based on Random Sampling in DLaaS

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Wu, Feng Sun, Shouyue Yang, Jiaxun Wu, Liwen Cui, Lei Qu, Youyang Yao, Shaowen Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Engineering Research Center of Cyberspace Yunnan University Kunming China School of Information Science and Engineering Yunnan University Kunming China Data61 Commonwealth Scientific and Industrial Research Organization BurwoodVIC3166 Australia

ISBN: (纸本)9789819615506

Deep learning as a service (DLaaS) has become an effective business solution in numerous domains. Nevertheless, its service form has been proven vulnerable to model inference by previous research. Existing work on model inference attack relies on strong assumptions, such as the attacker knows the sample variance and model structure, which may not thoroughly reflect the attack’s potential threats. In this paper, we propose MC-infer, a zero-knowledge, real-data-free, and black-box model inference method inspired by Monte-Carlo sampling. In particular, MC-infer feeds random noises obtained from different distributions to the target model, and sniffs the corresponding target distributions according to its feedback. Then many samples are taken in these distributions to obtain enough robust noises. Finally, the distribution represented by the target model is fitted through these noises to perform model inference. Our extensive evaluations demonstrate that MC-infer can effectively infer the target model with less information, and general noise perturbation on the model’s outputs cannot defend against MC-infer. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

HyperDiff: Masked Diffusion Model with High-efficient Transformer for Hyperspectral Image Cross-Scene Classification

HyperDiff: Masked Diffusion Model with High-efficient Transf...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhang, Pei Wang, Dong Wu, Chanyue Yang, Jing Kang, Lei Bai, Zongwen Li, Ying Shen, Qiang School of Computer Science Northwestern Polytechnical University Xi'an China Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data Yan'an University Yan'an China School of Automation and Software Engineering Shanxi University Taiyuan China Qingdao Topscomm Communication Co. Ltd. Qingdao China Department of Computer Science Aberystwyth University Aberystwyth United Kingdom

ISBN: (纸本)9798350368741

Hyperspectral Image (HSI) cross-scene classification is a challenging task in remote sensing, particularly when real-time processing of Target Domain (TD) HSI is required, and data cannot be reused for training. While deep learning methods have shown promising results, the generalization ability of HSI representations remains limited, mainly due to class label imbalance. This paper introduces a dual-stage learning framework based on transfer learning to enhance classification accuracy in the TD. The framework includes a self-supervised learning stage and a supervised fine-tuning stage. The self-supervised stage focuses on learning robust representations by leveraging inherent structures within HSI data, while the fine-tuning stage uses training labels to extract semantic information. A masked diffusion model predicts masked tokens from unmasked ones, capturing both high-level structures and fine details in HSI data. An efficient spatiospectral Transformer, which removes self-attention from the decoder, is proposed to enhance the self-supervised process. This design allows mask tokens to obtain information from visible tokens without interacting with each other, reducing sequence length and computational costs. By decoding each mask token conditionally independently, only a subset of masked tokens is processed. Extensive experiments on two public HSI datasets demonstrate that the proposed method outperforms state-of-the-art techniques. © 2025 IEEE.

关键词： Cross-scene classification Diffusion model Hyperspectral image Transformer

来源：评论

学校读者我要写书评

暂无评论

Enhancing Subsequent Video Retrieval via Vision-Language Models (VLMs)

arXiv

引用

arXiv 2025年

作者： Duan, Yicheng Huang, Xi Chen, Duo Computer and Data Sciences School of Engineering Case Western Reserve University ClevelandOH44106 United States

The rapid growth of video content demands efficient and precise retrieval systems. While vision-language models (VLMs) excel in representation learning, they often struggle with adaptive, time-sensitive video retrieval. This paper introduces a novel framework that combines vector similarity search with graph-based data structures. By leveraging VLM embeddings for initial retrieval and modeling contextual relationships among video segments, our approach enables adaptive query refinement and improves retrieval accuracy. Experiments demonstrate its precision, scalability, and robustness, offering an effective solution for interactive video retrieval in dynamic environments. © 2025, CC BY.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

MP-DPCC: A Motion Proxy-Based Dynamic Point Cloud Compression Framework

MP-DPCC: A Motion Proxy-Based Dynamic Point Cloud Compressio...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Jiang, ZhaoYi Han, Dong Song, Cao Nan, FangZhe Yang, Bailin School of Computer Science and Technolgy Zhejiang Gongshang University China School of Statistics and Mathematics Zhejiang Gongshang University China Economic Forecasting and Policy Simulation Laboratory Zhejiang Gongshang University China Collaborative Innovation Center of Statistical Data Engineering Technology & Application Zhejiang Gongshang University China

ISBN: (纸本)9798350368741

The increasing data volume and the demand for real-time transmission highlight the necessity for efficient compression of dynamic point cloud data. Existing methods primarily focus on reducing inter-frame redundancy by calculating per-point motion information, overlooking the computational and storage costs involved. In this paper, we propose a novel motion proxy-based dynamic point cloud compression framework to enhance the efficiency and accuracy of motion information utilization. Specifically, we introduce a feature proxy module to adaptively locate proxy points, which represent the overall motion through the motion of proxy points. Additionally, a motion enhancement module is employed to refine motion details and prevent local information loss caused by dense motion trajectories. Extensive experiments demonstrate the superiority of our approach. Compared with baseline methods, it achieves an average BD-rate improvement of 12.07% (D1) and 11.90% (D2). © 2025 IEEE.

关键词： compression deep learning neural network point cloud

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：