检索结果-内蒙古大学图书馆

作者： Xu, Xiaolong Cao, Hao Geng, Qingfan Liu, Xihua Dai, Fei Wang, Chuanjian School of Computer and Software Nanjing University of Information Science and Technology Nanjing China Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and Technology Nanjing China Nanjing University of Information Science and Technology Nanjing China Engineering Research Center of Digital Forensics Ministry of Education Nanjing China School of Big Data and Intelligence Engineering Southwest Forestry University Kunming China College of Information Science and Technology Shihezi University Xinjiang China

Edge computing, an extension of cloud computing, is introduced to provide sufficient computing and storage resources for mobile devices. Moreover, a series of computing tasks in a mobile device are set as structured computing processes and flows to achieve effective management by the workflow. However, the execution uncertainty caused by performance degradation, service failure, and new service additions remains a huge challenge to the user's service experience. In order to address the uncertainty, a software-defined network (SDN)-based edge computing framework and a dynamic resource provisioning (UARP) method are proposed in this paper. The UARP method is implemented in the proposed framework and addresses the uncertainty through the advantages of SDN. In addition, the nondominated sorting genetic algorithm-III is employed to optimize two goals, that is, the energy consumption and the completion time, to obtain balanced scheduling strategies. The comparative experiments are performed and the results show that the UARP method is superior to other methods in addressing the uncertainty, while reducing energy consumption and shortening the completion time. © 2020 John Wiley & Sons, Ltd.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Federated Learning-Based Intelligent Indoor Smoke and Fire Detection System for Smart Buildings

Federated Learning-Based Intelligent Indoor Smoke and Fire D...

引用

2024 International Conference on Telecommunications and Intelligent Systems, ICTIS 2024

作者： Aymene Berkani, Mohamed Rafik Chouchane, Ammar Himeur, Yassine Abdennebi, Anes Sagiroglu, Seref Amira, Abbes Medea Algeria University Biskra University Center of Barika Laboratory of LI3C Amdoukal Road Barika05001 Algeria University of Dubai College of Engineering and Information Technology Dubai United Arab Emirates École de Technologie Supérieure Software and Information Technology Engineering Montréal Canada Analytics Security R&D Center Gazi University Artificial Intelligence and Big Data Ankara Turkey University of Sharjah Department of Computer Science Sharjah United Arab Emirates

ISBN: (纸本)9798331527396

Ensuring safety in smart buildings is crucial due to the increasing prevalence of smoke and fire hazards in modern environments. This paper introduces a novel privacy-preserving FL approach based on a CNN1D for smoke and fire detection in smart buildings. Our system integrates data from wearable environmental sensors to train a lightweight, edge-deployable DL-CNN1D model, ensuring data privacy while enabling collaborative learning across distributed clients using Federated Averaging (FedAvg) aggregation. Experiments conducted on a comprehensive air measurement dataset for smoke and fire detection demonstrate exceptional performance, with the global model achieving 99.97% accuracy, 99.96% precision, in smoke and fire recognition. Our model demonstrates a low communication cost of 0.4 MB, underscoring its efficiency for real-time applications. Our FL-based approach represents a significant step towards balancing the need for robust safety systems with growing privacy concerns in smart building environments. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

An Experimental Analysis on Mining Proportional Process Models from Process Logs

An Experimental Analysis on Mining Proportional Process Mode...

引用

IEEE/ACM International Symposium on Big data Computing (BDC)

作者： Joo-Eun Bae Jin-Hyong Lee Young-In Park So-Hyang Park Kyoung-Sook Kim Kwanghoon Pio Kim Data & Process Engineering Research Laboratory Divison of AI Computer Science and Engineering College of Software & Management Kyonggi University Suwon-si Republic of Korea

In this paper, we carry out an experimental analysis to show how much perfectly the conceptual mining framework is working on mining process patterns and their enacted proportions from the business process enactment event histories logged with the IEEE-XES standardized format. In principle, the framework must be able to properly handle all the process patterns based upon the four types of control-flow primitives, such as linear (sequential), disjunctive (selective), conjunctive (parallel), and iterative (loop) patterns, together with the execution proportions. The paper focuses on not only verifying the conceptual feasibility of the procedural process mining framework through a series of experimental activities by using the implemented algorithmic mining framework and system, but also proving the functional correctness of the implemented process mining framework by applying to the real process instance enactment event histories of 10,000 workcases instantiated from the Large Bank Transaction Process Model and visualizing the details of the analytical artifacts and results, as well.

关键词： Analytical models Visualization Computational modeling Process control Big data Knowledge discovery data models

来源：评论

学校读者我要写书评

暂无评论

Audio Steganography Based Backdoor Attack for Speech Recognition software

Audio Steganography Based Backdoor Attack for Speech Recogni...

引用

IEEE Annual International Computer software and Applications Conference (COMPSAC)

作者： Mengyuan Zhang Shunhui Ji Hanbo Cai Hai Dong Pengcheng Zhang Yunhe Li Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China College of Computer Science and Software Engineering Hohai University Nanjing China School of Computing Technologies RMIT University Melbourne Australia

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

With the growing prevalence of deep learning in the speech area, speech recognition, voice control, and related applications have become integral parts of people's lives. However, the rise of malicious third-party platforms has introduced significant security concerns, particularly through backdoor attacks. These attacks implant triggers that manipulate speech recognition models to produce specific labels, thereby compromising the system's integrity. Studying speech backdoor attacks is crucial for evaluating the security of speech recognition software, and iden-tifying and addressing potential vulnerabilities. Existing methods for speech backdoor attacks usually employ fixed perturbations as triggers. However, these perturbations may be discernible to the human ear, making them easily detectable. To address this issue, we propose a frequency domain-embedded backdoor attack method based on echo hiding. Echo hiding is a steganography technique based on audio. This method embeds hidden information into the frequency spectrum of the echo signal, leveraging the masking property of the human auditory system. It is difficult to arouse suspicion or detect the presence of hidden information since echo is perceived as a natural phenomenon in auditory perception. Furthermore, it does not cause a significant decrease in audio quality. Experimental results show the effectiveness of our method in different settings.

关键词： Training Steganography Perturbation methods Frequency-domain analysis Speech recognition Ear Implants

来源：评论

学校读者我要写书评

暂无评论

Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Large Language Models 39

Divide, Conquer and Combine: A Training-Free Framework for H...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Wenbin Ding, Liang Zeng, Minyan Zhou, Xiabin Shen, Li Luo, Yong Yu, Wei Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China The University of Sydney Australia Jiangsu University China Shenzhen Campus of Sun Yat-sen University China College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)157735897X

Multimodal large language models (MLLMs) have experienced significant advancements recently, but still struggle to recognize and interpret intricate details in high-resolution (HR) images effectively. While state-of-the-art (SOTA) MLLMs claim to process images at 4K resolution, existing MLLM benchmarks only support up to 2K, leaving the capabilities of SOTA models on true HR images largely untested. Furthermore, existing methods for enhancing HR image perception in MLLMs rely on computationally expensive visual instruction tuning. To address these limitations, we introduce HR-Bench, the first deliberately designed benchmark to rigorously evaluate MLLM performance on 4K&8K images. Through extensive experiments, we demonstrate that while downsampling HR images leads to vision information loss, leveraging complementary modalities, e.g., text, can effectively compensate for this loss. Building upon this insight, we propose Divide, Conquer and Combine, a novel training-free framework for enhancing MLLM perception of HR images. Our method follows a three-staged approach: 1) Divide: recursively partitioning the HR image into patches and merging similar patches to minimize computational overhead, 2) Conquer: leveraging the MLLM to generate accurate textual descriptions for each image patch, and 3) Combine: utilizing the generated text descriptions to enhance the MLLM's understanding of the overall HR image. Extensive experiments show that: 1) the SOTA MLLM achieves 63% accuracy, which is markedly lower than the 87% accuracy achieved by humans on HR-Bench;2) our method brings consistent and significant improvements (a relative increase of +6% on HR-Bench and +8% on general multimodal benchmarks). Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

Gradient-Guided Test Case Generation for Image Classification software

Gradient-Guided Test Case Generation for Image Classificatio...

引用

IEEE Annual International Computer software and Applications Conference (COMPSAC)

作者： Shunhui Ji Yunhe Li Hai Dong Mingxuan Xiao Pengcheng Zhang Mengyuan Zhang Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China College of Computer Science and Software Engineering Hohai University Nanjing China School of Computing Technologies RMIT University Melbourne Australia

ISBN: (数字)9798350376968

ISBN: (纸本)9798350376975

The widespread use of deep neural networks (DNNs) in image classification sofwares underlines the importance of the robustness. Researchers have proposed sparse adversarial attack methods for generating test cases, which add pixel-level perturbations to construct the test case to mislead the target model. However, the existing methods have certain limitations, such as high time cost, poor flexibility, and poor quality of the test cases. To address these issues, we propose a gradient-guided test case generation method (GGTM) to evaluate the robustness of image classification software. The method firstly identifies the key region in the image based on the gradient-weighted class activation mapping (Grad-CAM) and the prediction confidence of the target model on the input image. In the key region, it selects a set of pixels as candidate perturbation pixels according to the gradient value and the change of loss function. Then perturbations are added to the candidate perturbation pixels after applying a random dropout strategy to reduce some candidate perturbation pixels which is used to avoid local optimum. For the initially constructed test case which can mislead the target model, after removing redundant and unimportant perturbations, perturbations are re-added to optimize the test case. Experiments show the effectiveness of GGTM, which achieves 100% attack success rate. And the test cases generated by GGTM have the best perturbation sparsity. Furthermore, compared with the baseline method SparseAG which achieves optimal perturbation sparsity among the baseline methods, GGTM significantly improves the efficiency.

关键词： Costs Perturbation methods Artificial neural networks Predictive models software Robustness Image classification

来源：评论

学校读者我要写书评

暂无评论

A Novel AI-based Hybrid Ensemble Segmentation CAD System for Lumber Spine Stenosis pathological Regions Using MRI Axial Images

A Novel AI-based Hybrid Ensemble Segmentation CAD System for...

引用

International Artificial Intelligence and data Processing Symposium (IDAP)

作者： Saied Salem Raza Mukhlis Oguzhan Katar Bilal Ertuğrul Ozal Yildirim Mugahed A. Al-Antari Department of Artificial Intelligence and Data Science College of AI Convergence Sejong University Seoul Korea Department of Software Engineering Faculty of Technology Firat University Elazig Turkey Department of Neurosurgery Faculty of Medicine Firat University Elazığ Turkey

ISBN: (数字)9798331531492

ISBN: (纸本)9798331531508

Lumbar Spinal Stenosis (LSS) is a condition where the spinal canal in the lower back becomes narrower, resulting in pressure on the spinal cord and nearby nerves. To predict LSS, neurologists focus on four key regions in MRI axial scans: the Intervertebral Disc (IVD), Thecal Sac (TS), Posterior Element (PE), and the Area between the Anterior and Posterior (AAP) vertebrae. To delineate these regions, we present a novel hybrid ensemble deep learning CAD system for multi-class segmentation, encompassing data collection, preprocessing, automated hyperparameter optimization and selection, segmentation ensemble learning, and both qualitative and quantitative performance evaluation. The core of the proposed pipeline features two ensemble phases: (1) ensemble learning through feature space fusion of three distinct AI models (SwinUNETR, Attention Unet, and UNet++), and (2) ensemble learning via a stacking method of the feature maps outputs from the same AI models used in phase 1. The Mendeley benchmark dataset is employed to train and assess both CAD systems, while a private dataset from Firat University Hospital in Turkey is used for verification and validation. The best achieved results via FFA’s mean dice score is 93.1% and mean IoU is 87.76%. showing the usefulness of using ensemble methods to capture different features from the trained models.

关键词： Deep learning Solid modeling Image segmentation Pathology Hospitals Magnetic resonance imaging Stacking Benchmark testing Ensemble learning Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Scribble-supervised semantic segmentation with prototype-based feature augmentation 24

Scribble-supervised semantic segmentation with prototype-bas...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Guiyang Chan Pengcheng Zhang Hai Dong Shunhui Ji Bainian Chen Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China and College of Computer Science and Software Engineering Hohai University Nanjing China School of Computing Technologies RMIT University Melbourne Australia

Scribble-supervised semantic segmentation presents a cost-effective training method that utilizes annotations generated through scribbling. It is valued in attaining high performance while minimizing annotation costs, which has made it highly regarded among researchers. Scribble supervision propagates information from labeled pixels to the surrounding unlabeled pixels, enabling semantic segmentation for the entire image. However, existing methods often ignore the features of classified pixels during feature propagation. To address these limitations, this paper proposes a prototype-based feature augmentation method that leverages feature prototypes to augment scribble supervision. Experimental results demonstrate that our approach achieves state-of-the-art performance on the PASCAL VOC 2012 dataset in scribble-supervised semantic segmentation tasks. The code is available at https://***/TranquilChan/PFA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intelligent Gen: An Efficient On-Demand Access Protocol in MANETs using Network Simulator - 2

Intelligent Gen: An Efficient On-Demand Access Protocol in M...

引用

International Conference on Computing for Sustainable Global Development (INDIACom)

作者： T. Ganesan N. Murali S. Palani Murugan M. Chandrakumar Peter P. Anand Raj S. Manikandan Department of Computer Science & Engineering E.G.S. Pillay Engineering College Nagapattinam Tamil Nadu India Department of Artificial Intelligence & Data Science E.G.S. Pillay Engineering College Nagapattinam Tamil Nadu India Department of Software Engineering Periyar Maniammai Institute of Science & Technology Thanjavur Tamil Nadu India Department of Computer Science and Business Systems E.G.S. Pillay Engineering College Nagapattinam Tamil Nadu India Department of Information Technology E.G.S. Pillay Engineering College Nagapattinam Tamil Nadu India

Mobile Ad-Hoc network is a self-configuring and multi-hop collection of mobile devices for making successful communication. The wireless and mobile communication process are encountered based on bandwidth, process control and energy conception. Energy conception is considered and dynamically changed to rely on life time of batteries and power. The life time of battery get exhausted very quickly the nodes are moved and changed rapidly across the network. This paper noticed the problem of life time of power, batteries and energy consumption problem in various routing stages. The proposed Intelligent Gen Algorithm is used to get optimal solution for ensuring high robustness, flexibility and Energy consumption factor. It presents a common framework to balance various routing requirements in MANETs dynamically. The following are the main contributions includes, i. introducing Intelligent GEN Algorithms to classify the throughout bandwidth, delay, data ratio. ii. Various routing performance are evaluated and viewed by speed, packetize and simulation time. The comparison evaluated by select routing algorithm using NS-2. The simulation results are recorded and the performance is monitored by using on demand access protocl. The result clearly demonstrated the proposed Intelligent Gen algorithm used in self-organized manner by wireless channel.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhance Learning Efficiency of Oblique Decision Tree via Feature Concatenation

arXiv

引用

arXiv 2025年

作者： Lyu, Shen-Huan He, Yi-Xiao Wang, Yanyan Qu, Zhihao Tang, Bin Ye, Baoliu Key Laboratory of Water Big Data Technology of Ministry of Water Resources College of Computer Science and Software Engineering Hohai University Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China School of Artificial Intelligence and Information Technology Nanjing University of Chinese Medicine Nanjing China

Oblique Decision Tree (ODT) separates the feature space by linear projections, as opposed to the conventional Decision Tree (DT) that forces axis-parallel splits. ODT has been proven to have a stronger representation ability than DT, as it provides a way to create shallower tree structures while still approximating complex decision boundaries. However, its learning efficiency is still insufficient, since the linear projections cannot be transmitted to the child nodes, resulting in a waste of model parameters. In this work, we propose an enhanced ODT method with Feature Concatenation (FC-ODT), which enables in-model feature transformation to transmit the projections along the decision paths. Theoretically, we prove that our method enjoys a faster consistency rate w.r.t. the tree depth, indicating that our method possesses a significant advantage in generalization performance, especially for shallow trees. Experiments show that FC-ODT can outperform the other state-of-the-art decision trees with a limited tree depth. Copyright © 2025, The Authors. All rights reserved.

关键词： Efficiency

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：