检索结果-内蒙古大学图书馆

SHERA: SHAP-Enhanced Resource Allocation for VM Scheduling and Efficient Cloud computing

IEEE Access 2025年 13卷 92816-92832页

作者： Slathia, Ashwin Singh Sharma, Abhiram Krishna, P.B. Anand, Saksham Rathi, Ayush Joseph, Linda Gao, Xiao-Zhi Vellore Institute of Technology School of Computer Science and Engineering Chennai600127 India University of Eastern Finland School of Computing Kuopio Finland

Cloud computing plays a crucial role in modern technology, providing scalable and on-demand computing resources. However, excessive resource use can result in higher energy demand, higher operating expenses, and a more significant adverse effect on the environment as per study by A. Berl et al. [1]. In order to forecast and maximize the energy efficiency in cloud systems, this paper presents a machine learning based methodology. Using the Cloud Efficiency Dataset from Google Cloud, key performance indicators such as CPU usage, memory consumption, network traffic, and power consumption were analyzed. Three machine learning models—Random Forest, Naïve Bayes, and Support Vector Machine (SVM) were trained and assessed based on Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and an Equivalent Accuracy metric. Among them Random Forest model performed the best, achieving an RMSE of 0.16 and an accuracy of 96.8 %. To improve the interpretability of the model Explainable Artificial Intelligence (XAI) techniques were applied, specifically SHapley Additive exPlanations (SHAP), to evaluate feature importance. The findings demonstrated that the most important variables which influence energy efficiency are CPU usage and memory consumption. This research develops A novel algorithm based on the XAI results. Unlike static thresholding or heuristic schedulers, our SHAP-driven approach dynamically adapts VMplacement decisions with built-in interpretability. It is capable to efficiently schedule and allocateVirtual Machines on the cloud in a live environment. The proposed framework demonstrates tthe high scalability and real time applicability, making it suitable for the deployment in live cloud environments. While the integration of XAI methods like SHAP enhances interpretability, it introduces additional computational overhead—a trade-off that is justified by the improved transparency and decision making support. © 2013 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Out-of-Distribution Data: An Acquaintance of Adversarial Examples - A Survey

引用

ACM computing Surveys 2025年第8期57卷 1-40页

作者： Karunanayake, Naveen Gunawardena, Ravin Seneviratne, Suranga Chawla, Sanjay School of Computer Science The University of Sydney Sydney Australia Computer Science and Engineering University of New South Wales Sydney Australia Qatar Computing Research Institute Doha Qatar and Hamad Bin Khalifa University Doha Qatar

Deep neural networks (DNNs) deployed in real-world applications can encounter out-of-distribution (OOD) data and adversarial examples. These represent distinct forms of distributional shifts that can significantly impact DNNs’ reliability and robustness. Traditionally, research has addressed OOD detection and adversarial robustness as separate challenges. This survey focuses on the intersection of these two areas, examining how the research community has investigated them together. Consequently, we identify two key research directions: robust OOD detection and unified robustness. Robust OOD detection aims to differentiate between in-distribution (ID) data and OOD data, even when they are adversarially manipulated to deceive the OOD detector. Unified robustness seeks a single approach to make DNNs robust against both adversarial attacks and OOD inputs. Accordingly, first, we establish a taxonomy based on the concept of distributional shifts. This framework clarifies how robust OOD detection and unified robustness relate to other research areas addressing distributional shifts, such as OOD detection, open set recognition, and anomaly detection. Subsequently, we review existing work on robust OOD detection and unified robustness. Finally, we highlight the limitations of the existing work and propose promising research directions that explore adversarial and OOD inputs within a unified framework. © 2025 Copyright held by the owner/author(s)

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Potato Farming: A CNN-Powered Approach for Early Blight and Late Blight Detection to Ensure Global Food Security

Revolutionizing Potato Farming: A CNN-Powered Approach for E...

引用

2024 IEEE International Students' Conference on Electrical, Electronics and computer science, SCEECS 2024

作者： Ponnuru, Mahesh Datta Sai Amasala, Likhitha Srm Institute of Science and Technology School of Computing Chennai India Vellore Institute of Technology School of Computer Science and Engineering Amaravathi India

ISBN: (纸本)9798350348460

Potato, a crucial global food crop, faces persistent threats from diseases like early blight and late blight, jeopardizing both yields and economic stability. In response, we present an innovative approach using CNN for early disease detection in potato crops. Our objective is to empower farmers with rapid and accurate disease identification, facilitating timely treatments to prevent economic losses and reduce agricultural waste. Our CNN model achieved a remarkable validation accuracy of 99.59%, outperforming conventional methods. With 183,747 trainable parameters, our efficient and accurate model is set to revolutionize agricultural practices. Furthermore, we are deploying our model to Google Cloud and developing a React Native mobile app for potato prediction. This integration aims to provide farmers with real-time disease insights, preventing economic losses and ensuring global food security, thereby enhancing economic stability in the potato farming sector. © 2024 IEEE.

关键词： Agriculture Convolutional Neural Networks (CNNs) Crop protection Food security Early blight Economic stability Late blight Potato disease detection

来源：评论

学校读者我要写书评

暂无评论

Skyway:Accelerate Graph Applications with a Dual-Path Architecture and Fine-Grained Data Management

引用

Journal of computer science & Technology 2024年第4期39卷 871-894页

作者： Mo Zou Ming-Zhe Zhang Ru-Jia Wang Xian-He Sun Xiao-Chun Ye Dong-Rui Fan Zhi-Min Tang Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China Institute of Information Engineering Chinese Academy of SciencesBeijing 100045China Department of Computer Science Illinois Institute of TechnologyChicagoIL 60616U.S.A.

Graph processing is a vital component of many AI and big data ***,due to its poor locality and complex data access patterns,graph processing is also a known performance killer of AI and big data *** this work,we propose to enhance graph processing applications by leveraging fine-grained memory access patterns with a dual-path architecture on top of existing software-based graph *** first identify that memory accesses to the offset,edge,and state array have distinct locality and impact on *** then introduce the Skyway architecture,which consists of two primary components:1)a dedicated direct data path between the core and memory to transfer state array elements efficiently,and 2)a data-type aware fine-grained memory-side row buffer hardware for both the newly designed direct data path and the regular memory hierarchy data *** proposed Skyway architecture is able to improve the overall performance by reducing the memory access interference and improving data access efficiency with a minimal *** evaluate Skyway on a set of diverse algorithms using large real-world *** a simulated fourcore system,Skyway improves the performance by 23%on average over the best-performing graph-specialized hardware optimizations.

关键词： graph application computer architecture memory hierarchy

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey of federated transfer learning:challenges,methods and applications

引用

Frontiers of computer science 2024年第6期18卷 27-60页

作者： Wei GUO Fuzhen ZHUANG Xiao ZHANG Yiqi TONG Jin DONG Institute of Artificial Intelligence Beihang UniversityBeijing 100191China SKLSDE School of Computer ScienceBeihang UniversityBeijing 100191China School of Computer Science and Technology Shandong UniversityShandong 266237China Beijing Academy of Blockchain and Edge Computing Beijing 100080China

Federated learning(FL)is a novel distributed machine learning paradigm that enables participants to collaboratively train a centralized model with privacy preservation by eliminating the requirement of data *** practice,FL often involves multiple participants and requires the third party to aggregate global information to guide the update of the target ***,many FL methods do not work well due to the training and test data of each participant may not be sampled from the same feature space and the same underlying ***,the differences in their local devices(system heterogeneity),the continuous influx of online data(incremental data),and labeled data scarcity may further influence the performance of these *** solve this problem,federated transfer learning(FTL),which integrates transfer learning(TL)into FL,has attracted the attention of numerous ***,since FL enables a continuous share of knowledge among participants with each communication round while not allowing local data to be accessed by other participants,FTL faces many unique challenges that are not present in *** this survey,we focus on categorizing and reviewing the current progress on federated transfer learning,and outlining corresponding solutions and ***,the common setting of FTL scenarios,available datasets,and significant related research are summarized in this survey.

关键词： federated transfer learning federated learning transfer learning survey

来源：评论

学校读者我要写书评

暂无评论

Systematic Review of Emerging Deep Learning approaches for Crop Diseases detection 7

Systematic Review of Emerging Deep Learning approaches for C...

引用

7th International Conference on Circuit Power and computing Technologies, ICCPCT 2024

作者： Vasuki Rohinidevi, V. Deeban Chakravarthy, V. Deepak, S. Prem Kumar SRM Institute of Science and Technology School of Computing Department of Computing Technologies Chennai India B V Raju Institute of Technology Department of Computer Science and Engineering Narsapur India

ISBN: (纸本)9798350372816

Deep learning, a branch of artificial intelligence, has drawn interest from the academic and corporate realms, especially in areas like speech and image analysis, video processing, and natural language processing. Its use in agricultural plant protection has expanded to include the diagnosis and evaluation of pests and plant diseases. In this situation, there are several benefits to using deep learning. It removes the biases related to manually chosen pathogen properties, improves objectivity when determining disease characteristics, and hastens the advancement of contemporary technology. In order to diagnose agricultural leaf illnesses, this study explores the most recent developments in deep learning methods, including CNN, DENSNET, InceptionV3, VGG16, Resnet50, and MobileNet, in addition to a variety of sensors. This project aims to aid scientists in the field by tackling challenges in merging deep learning and cutting-edge imaging tools to enhance illness identification. It addresses current trends and barriers, shedding light on unresolved issues and paving the way for further research. By clarifying persistent problems and posing new questions, it fosters progress and innovation in the field of medical imaging and diagnosis. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

An Assessment Towards 2D and 3D Human Pose Estimation and its Applications to Activity Recognition: A Review

引用

SN computer science 2025年第2期6卷 1-24页

作者： Verma, Pratishtha Srivastava, Rajeev Tripathy, Santosh Kumar Department of Computer Engineering National Institute of Technology Haryana Kurukshetra India Computer Science and Engineering IIT BHU Varanasi India Department of Computing Science and Engineering National Institute of Technology Patna Bihar Patna India

Human pose estimation (HPE) from images or video is not only a major issue of computer vision, but also it plays a vital role in many real-world applications. The most challenging problems of human pose estimation are the disparity of poses, disturbing background clutter, different camera views, changes in scene lighting conditions, and occlusion. To solve these issues, a significant amount of research effort has been considered in the past. In this paper, we explore various vision-based activity recognition using 2D and 3D human pose estimations. We explore the conventional system, which includes both statistical and deep learning-based approaches for HPE, and then explore the current progress of each one in comparison to existing ones. At last, we also present various current state-of-the-art human activity recognition (HAR) techniques that use HPE for recognition. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Human activity recognition (HAR) Human body model (HBM) Human pose estimation (HPE)

来源：评论

学校读者我要写书评

暂无评论

Which is more faithful,seeing or saying? Multimodal sarcasm detection exploiting contrasting sentiment knowledge

引用

CAAI Transactions on Intelligence Technology 2025年第2期10卷 375-386页

作者： Yutao Chen Shumin Shi Heyan Huang School of Computer Science and Technology Beijing Institute of TechnologyBeijingChina Beijing Engineering Research Center of High Volume Language Information Processing and Cloud Computing Applications BeijingChina

Using sarcasm on social media platforms to express negative opinions towards a person or object has become increasingly ***,detecting sarcasm in various forms of communication can be difficult due to conflicting *** this paper,we introduce a contrasting sentiment-based model for multimodal sarcasm detection(CS4MSD),which identifies inconsistent emotions by leveraging the CLIP knowledge module to produce sentiment features in both text and ***,five external sentiments are introduced to prompt the model learning sentimental preferences among ***,we highlight the importance of verbal descriptions embedded in illustrations and incorporate additional knowledge-sharing modules to fuse such imagelike *** results demonstrate that our model achieves state-of-the-art performance on the public multimodal sarcasm dataset.

关键词： CLIP image-text classification knowledge fusion multi-modal sarcasm detection

来源：评论

学校读者我要写书评

暂无评论

Focus Your Attention: Multiple Instance Learning with Attention Modification for Whole Slide Pathological Image Classification

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年第6期35卷 5791-5804页

作者： Cheng, Hailun Huang, Shenjin Cai, Linghan Xu, Yangfan Wang, Runming Zhang, Yongbing Tsinghua University Institute of Biopharmaceutical and Health Engineering Shenzhen International Graduate School Shenzhen518055 China Harbin Institute of Technology Faculty of Computing Harbin150001 China Harbin Institute of Technology School of Computer Science and Technology Shenzhen518055 China

computer-aided pathology diagnosis based on whole slide images, which is often formulated as a weakly supervised multiple instance learning (MIL) paradigm. Current approaches generally employ attention mechanisms to aggregate instance-level features. However, the weakly supervised signal and the imbalanced instance distribution often lead to inaccurate attention localization, compromising the performance and generalization capability of the MIL framework. To address these problems, this paper presents a novel MIL framework called FAMIL that focuses on inaccurate attention and refines them. FAMIL adopts a dual-branch structure and incorporates two innovative online data augmentation strategies: attention-based Mixup (ABMix) and attention-based Masking (ABMask). ABMix emphasizes the significance of positive instances, generalizing Mixup in the MIL scenarios, while ABMask flexibly identifies challenging positive instances to optimize the feature representation. Moreover, these two methods are plug-and-play and can be easily embedded into attention-based MIL methods. Extensive experiments on three public benchmarks demonstrate the superiority of our FAMIL, outperforming current state-of-the-art methods. The test AUC for the binary tumor classification can be up to 92.61% over CAMELYON16. And the AUC over the cancer subtype classification can be up to 93.81% and 98.41% on TCGA-NSCLC and TCGA-RCC datasets, respectively. © 1991-2012 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Enabled Decentralized Trust Management and Secure Voting system 7

Blockchain-Enabled Decentralized Trust Management and Secure...

引用

7th International Conference on Circuit Power and computing Technologies, ICCPCT 2024

作者： Minu, R.I. Nagarajan, G. SRM Institute of Science and Technology Department of Computing Technologies Kattankulathur India Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350372816

In the era of digital transformation, trust and security are paramount in ensuring the integrity of various online transactions and processes, including voting systems. Traditional centralized trust management and voting systems have faced challenges related to security, transparency, and accountability. To address these issues, this research introduces a novel Blockchain-Enabled Decentralized Trust Management and Secure Voting System. It leverages blockchain technology, a decentralized and immutable ledger, to enhance trust, transparency, and security in trust management and voting processes. This system combines several key components, including smart contracts, cryptographic techniques, and distributed ledger technology, to create a robust and tamper-resistant infrastructure. In the trust management aspect, the proposed system employs a decentralized reputation system where individuals and entities can build trust through transparent and verifiable interactions. Smart contracts automate trust-building processes and provide a reliable mechanism for dispute resolution. This system allows for trust to be quantified and established in a trustless environment. The secure voting component introduces a tamper-proof and transparent voting system. Through the use of cryptographic keys and digital signatures, voters can securely cast their votes while ensuring anonymity and integrity. All voting transactions are recorded on the blockchain, providing a permanent and auditable record of the election process. Verification of election results becomes accessible to all stakeholders, enhancing transparency and trust in the electoral process. The Blockchain-Enabled Decentralized Trust Management and Secure Voting System represents a significant step towards enhancing trust and security in critical online processes, such as voting. By combining blockchain technology, cryptography, and decentralized trust mechanisms, it offers a promising solution to address the challenges associat

关键词： Decentralized finance

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：