检索结果-内蒙古大学图书馆

32nd ACM World Wide Web Conference, WWW 2023

作者： Dong, Zeqian He, Qiang Chen, Feifei Jin, Hai Gu, Tao Yang, Yun School of Computer Science and Technology Huazhong University of Science and Technology China Department of Computing Technologies Swinburne University of Technology Australia School of Information Technology Deakin University Australia School of Computing Macquarie University Australia National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9781450394161

Training machine learning (ML) models on mobile and Web-of-Things (WoT) has been widely acknowledged and employed as a promising solution to privacy-preserving ML. However, these end-devices often suffer from constrained resources and fail to accommodate increasingly large ML models that crave great computation power. Offloading ML models partially to the cloud for training strikes a trade-off between privacy preservation and resource requirements. However, device-cloud training creates communication overheads that delay model training tremendously. This paper presents EdgeMove, the first device-edge training scheme that enables fast pipelined model training across edge devices and edge servers. It employs probing-based mechanisms to tackle the new challenges raised by device-edge training. Before training begins, it probes nearby edge servers' training performance and bootstraps model training by constructing a training pipeline with an approximate model partitioning. During the training process, EdgeMove accommodates user mobility and system dynamics by probing nearby edge servers' training performance adaptively and adapting the training pipeline proactively. Extensive experiments are conducted with two popular DNN models trained on four datasets for three ML tasks. The results demonstrate that EdgeMove achieves a 1.3 × -2.1 × speedup over the state-of-the-art scheme. © 2023 ACM.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Survey of Low-Resource Named Entity Recognition 7th

A Survey of Low-Resource Named Entity Recognition

引用

7th International Conference on Information science, Communication and computing, ISCC 2023

作者： Tang, Xiangyan Xia, Dongwan Li, Yajing Xu, Taixing Xiong, Neal N. School of Computer Science and Technology Hainan University Haikou570228 China College of Intelligence and Computing Tianjin University Tianjin300072 China Hainan Blockchain Technology Engineering Research Center Haikou570228 China Department of Computer Science and Mathematics Sul Ross State University AlpineTX79830 United States

ISBN: (纸本)9789819971602

Named Entity Recognition, as one of the typical tasks of information extraction, has a wide range of applications. However, the difficulty of data collection and the lack of data annotation are common problems in real scenarios. It is difficult for classical named entity recognition methods to fully obtain hidden information when the dataset and data labels are insufficient. In this case, the recognition accuracy will drop significantly. In resource-poor scenarios, the use of multi-task learning, data augmentation, and transfer learning methods can effectively utilize limited data resources or introduce data from other fields to optimize model performance. In this survey, firstly, we introduce the reader to the state of research on named entity recognition, and outline the reasons for the survey and the contribution of this paper. Then, we comprehensively describe the datasets and evaluation methods included in named entity recognition, and propose a Classification of named entity recognition in the case of lack of resources. Finally, we analyze the existing problems on the basis of the above, and further look forward to the future development direction. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

IoT-Enabled Automated Smart Irrigation System Incorporating Sensor Parameters 5th

IoT-Enabled Automated Smart Irrigation System Incorporating ...

引用

5th Doctoral Symposium on Computational Intelligence, DoSCI 2024

作者： Singh, Jagendra Neeraj Srinivas Reddy, P. Hasan, Dler Salih Alsahlanee, Abbas Thajeel Rhaif Shaik, Nazeer Alliance School of Advanced Computing Alliance University Bangalore India School of Computer Science Engineering and Technology Bennett University Greater Noida India Department of Mechanical Engineering CVR College of Engineering Hyderabad India Department of Computer Science and Information Technology University of Salahaddin-Erbil Erbil Iraq Development and Continuous Education Center University of Thi-Qar Thi-Qar Iraq Department of Computer Science and Engineering Srinivasa Ramanujan Institute of Technology—Autonomous Anantapur India

ISBN: (纸本)9789819763177

This article presents the experimental findings of a smart irrigation system evaluated in two separate agricultural settings—small-scale farming and large-scale agriculture. The system combines sensors, microcontrollers, and actuators to precisely monitor and regulate the irrigation process in order to optimum water use and crop output. Water savings range from 20 to 45% when using smart irrigation technology in small-scale agriculture. By only turning on the irrigation pump when necessary, the technology optimizes water use and fosters sustainable farming methods. Furthermore, by sustaining perfect growing conditions, the approach boosts crop output, with yield benefits ranging from 10 to 22%. These improvements assist small-scale farmers in becoming more profitable and raising their level of living. In large-scale agriculture, smart irrigation systems allow excellent water management and resource optimization across huge agricultural fields. The technology consistently saves a large quantity of water, often between 25 and 50%, addressing water scarcity issues. Additionally, this method has led to a 12–25% increase in aggregate crop yields, thereby raising farm income and increasing agricultural firm profitability. Experiments shows that this smart irrigation system could bring cost-effective, sustainable techniques to extensive and intensive agriculture alike. Intelligence-guided decision-making technology is applied here, and cutting-edge technologies are brought to bear on the water use problem. The system conserves precious resources and increases agricultural output at the same time. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Associative Forms for Encoding Multivariate Climate Data 11

Associative Forms for Encoding Multivariate Climate Data

引用

11th IEEE VIS Arts Program, VISAP 2023

作者： Samsel, Francesca Abram, Greg Bowman, Catherine Keefe, Daniel Texas Advanced Computing Center University of Texas at Austin United States Independent Writer Los AlamosNM United States University of Minnesota Department of Computer Science United States

ISBN: (纸本)9798350330229

We are perpetually present in our environment, experiencing it with our senses. Scientific data describes the same environment quantitatively. Our goal is to use scientific and artistic methods to combine these environmental expressions and personal experience through the creation of glyphs visually abstracted from and associated with forms in nature in the representation of climate data. The use of these glyphs removes the distinctions between scientific data and sensory experience, to allow a fuller intuitive association between the two, creating an embodied experience and increasing awareness of the climate effects and changes all around us. © 2023 IEEE.

关键词： art and design principles environmental visualization Glyphs visual association

来源：评论

学校读者我要写书评

暂无评论

Data-Free Network Debiasing for Long-Tailed visual Recognition

Data-Free Network Debiasing for Long-Tailed Visual Recogniti...

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Cai, Jinmian Wang, Zheng Fu, Huazhu Chen, Jingjing Jiang, Yu-Gang School of Computer Science Fudan University Shanghai Key Lab of Intelligent Information Processing China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China Biren Technology IHPC A-STAR

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Real-world data is often unbalanced and exhibits long-tailed distribution over classes. Vanilla classification models trained on imbalanced datasets inherently exhibit bias towards dominant classes. Existing debiasing methods mostly balance the data or the loss during training. Nevertheless, these data-acquiring methods are not suitable for situations where training data are unavailable. In this paper, we appeal to solutions without access to training data and propose a datafree debiasing (Free-D) method that serves as a plug-and-play module for any standard classification model. Specifically, our method adjusts both the feature representation via feature representation shifting and the classifier weight via class prior compensation in a data-free manner. We evaluate and compare our methods on four long-tailed visual recognition datasets, i.e., long-tailed CIFAR-10/-100, ImageNet-LT, and Places-LT. Extensive experiments demonstrate that the proposed data-free method achieves comparable results of other data-acquired methods. © 2022 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

CHILLAX - at Arabic Hate Speech 2022: A Hybrid Machine Learning and Transformers based Model to Detect Arabic Offensive and Hate Speech 5

CHILLAX - at Arabic Hate Speech 2022: A Hybrid Machine Learn...

引用

5th Workshop Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection, OSACT 2022

作者： Makram, Kirollos Hany Nessim, Kirollos George Abd-Almalak, Malak Emad Roshdy, Shady Zekry Salem, Seif Hesham Thabet, Fady Fayek Mohamed, Ensaf Hussein Research Support Center in Computing and Informatics Department of Computer Science Faculty of Computers and Artificial Intelligence Helwan University Cairo Egypt

ISBN: (纸本)9791095546757

Hate speech and offensive language have become a crucial problem nowadays due to the extensive usage of social media by people of different gender, nationality, religion and other types of characteristics, allowing anyone to share their thoughts and opinions. In this research paper, we proposed a hybrid model for the first and second tasks of OSACT2022. This model used the Arabic pre-trained Bert language model MARBERT for feature extraction of the Arabic tweets in the dataset provided by the OSACT2022 shared task, then fed the features to two classic machine learning classifiers (Logistic Regression, Random Forest). The best results achieved for the offensive tweet detection task were achieved by the Logistic Regression model with accuracy, precision, recall, and f1-score of 80%, 78%, 78%, and 78%, respectively. The results for the hate speech tweet detection task were 89%, 72%, 80%, and 76%. © European Language Resources Association (ELRA).

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Empowering Donors: How Blockchain Technology Can Help Ensure Their Contributions Reach the Right Recipients 2

Empowering Donors: How Blockchain Technology Can Help Ensure...

引用

2nd International Conference on Business Analytics for Technology and Security, ICBATS 2023

作者： Ajmal, Sahar Muzammil, Muteeb Bin Shoaib, Muhammad Mehmood, Muhammad Hassaan National University of Computer and Emmerging Sciences Department of Software Engineering Faisalabad Pakistan Riphah International University College of Computing Faisalabad Pakistan University of Engineering and Technology Department of Computer Science Lahore Pakistan School of Computer Science NCBA&E Lahore Pakistan Applied School Research Center Applied Science Private University Amman11937 Jordan

ISBN: (纸本)9798350335644

Charity giving is a fundamental aspect of society, but there are concerns about the accountability and transparency of the donation process. Blockchain technology has emerged as a potential solution, offering a secure and auditable platform for managing charitable contributions. In this paper, we explore the concept of empowering donors through blockchain technology and examine how it can help ensure that contributions reach the right recipients. We review existing literature on the topic and identify key areas for future research, including the development of hybrid blockchain solutions along with the implementation of novel consensus mechanisms. Moreover, providing the idea of decentralized autonomous organizations, self-executing smart contracts, and integration of blockchain with artificial intelligence and Internet of things. By providing a comprehensive overview of the current state of the field and outlining a roadmap for future research, we hope to stimulate further exploration of the potential of blockchain technology to revolutionize charity giving, and create a more accountable and transparent system for managing charitable funds. Some research questions are designed for each novel idea. Our analysis suggests that blockchain has the potential to empower donors and ensure that their contributions make a positive impact in the world, but further research is needed to fully realize its potential. © 2023 IEEE.

关键词： Transparency

来源：评论

学校读者我要写书评

暂无评论

Explainable Hybrid Model for Presaging Tumor Stage Classification with Survival Survey

引用

SN computer science 2025年第4期6卷 1-24页

作者： Manna, Sweta Mistry, Sujoy Zhao, Zhongming Dahal, Keshav Department of Computer Science and Engineering Maulana Abul Kalam Azad University of Technology Nadia W.B Kolkata 741249 India Center for Precision Health School of Biomedical Informatics The University of Texas Health Science Center at Houston Houston TX United States School of Engineering and Computing University of the West of Scotland Paisley PA1 2BE United Kingdom

Tumor stage classification with a survival survey during detection time is the most crucial part of cancer treatment. The survivability period is directly associated with the early detection of the stage. This study developed a hybrid model to accurately classify the tumor (T) stages with the survivability analysis. The study aims to provide an explainable Artificial Intelligence framework (such as SHAP, and SHAPASH), through which the trustability and interpretability of the proposed model can increase. Along with the XAI, this hybrid approach uses two statistical models, ANOVA and LASSO with the standard TNM (tumor, node, metastasis) method for the T-stage classification. Afterward, the survivability analysis for each T stage is shown by the Kaplan–Meier (KM) method, proportion hazard ratio (Cox). Where KM is used to represent the survivability of individual tumor stages in months and the Cox regression shows the risk factors of the events. Initially, the proposed model was examined on a full dataset that contained malignant and benign data for evaluating the performance of the model, therefore stage classification for T1, T2, and T3 performs for malignant data. The K-fold and repeated-stratified K-fold cross-validation are used to measure the accuracy of the whole dataset for lung and breast cancer. For lung cancer, maximum accuracy was attained by MLP–97.64 in K-fold cross-validation. In breast cancer maximum accuracy achieved by GPC-99.57 in repeated-stratified K-fold cross validation. The results of both datasets are compared with the state-of-the-art models. The study contributed by representing the significance of individual features for tumor staging using the advanced approach of XAI, the SHAPASH interface. The accuracy of the T1, T2, and T3 stages based on malignant data was demonstrated with various classifier models with cross-validation. Finally, it is expected that executing that approach will improve patient outcomes. By using, advanced artificial in

关键词： ANOVA Breast cancer Deep learning Explainable artificial intelligence F-score Gaussian process classification LASSO Lung cancer Machine learning Random-Forest Shapely additive explanation XGBoost

来源：评论

学校读者我要写书评

暂无评论

Modeling and Clustering of Parabolic Granular Data

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第7期5卷 3728-3742页

作者： Tang, Yiming Gao, Jianwei Pedrycz, Witold Hu, Xianghui Xi, Lei Ren, Fuji Hu, Min Hefei University of Technology Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computer and Information Hefei230601 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6R 2V4 Canada Hefei University of Technology School of Computer and Information Hefei230601 China University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 2R3 Canada Polish Academy of Sciences Systems Research Institute Warsaw00-901 Poland Istinye University Research Center of Performance and Productivity Analysis Istanbul34010 Turkey Southeast University School of Computer Science and Engineering Nanjing211189 China University of Electronic Science and Technology of China School of Computer Science and Engineering Sichuan Chengdu611731 China

At present, there exist some problems in granular clustering methods, such as lack of nonlinear membership description and global optimization of granular data boundaries. To address these issues, in this study, revolving around the parabolic granular data, we propose an overall architecture for parabolic granular modeling and clustering. To begin with, novel coverage and specificity functions are established, and then a parabolic granular data structure is proposed. The fuzzy c-means (FCM) algorithm is used to obtain the numeric prototypes, and then particle swarm optimization (PSO) is introduced to construct the parabolic granular data from the global perspective under the guidance of principle of justifiable granularity (PJG). Combining the advantages of FCM and PSO, we propose the parabolic granular modeling and optimization (PGMO) method. Moreover, we put forward attribute weights and sample weights as well as a distance measure induced by the Gaussian kernel similarity, and then come up with the algorithm of weighted kernel fuzzy clustering for parabolic granularity (WKFC-PG). In addition, the assessment mechanism of parabolic granular clustering is discussed. In summary, we set up an overall architecture including parabolic granular modeling, clustering, and assessment. Finally, comparative experiments on artificial, UCI, and high-dimensional datasets validate that our overall architecture delivers a good improvement over previous strategies. The parameter analysis and time complexity are also given for WKFC-PG. In contrast with related granular clustering algorithms, it is observed that WKFC-PG performs better than other granular clustering algorithms and has superior stability in handling outliers, especially on high-dimensional datasets. © 2020 IEEE.

关键词： Fuzzy clustering

来源：评论

学校读者我要写书评

暂无评论

DaC-GANSAEBF:Divide and Conquer-Generative Adversarial Network-Squeeze and Excitation-Based Framework for Spam Email Identification

引用

computer Modeling in Engineering & sciences 2025年第3期142卷 3181-3212页

作者： Tawfeeq Shawly Ahmed A.Alsheikhy Yahia Said Shaaban M.Shaaban Husam Lahza Aws I.Abu Eid Abdulrahman Alzahrani Department of Electrical Engineering Faculty of Engineering at RabighKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Electrical Engineering College of EngineeringNorthern Border UniversityArar91431Saudi Arabia Center for Scientific Research and Entrepreneurship Northern Border UniversityArar73213Saudi Arabia Department of Information Technology College of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Information and Communication Technology College of Computing StudiesArab Open UniversityKuwait BranchKuwait City13033Al-SafatState of Kuwait Department of Information Systems and Technology College of Computer Science and EngineeringUniversity of JeddahJeddah23218Saudi Arabia

Email communication plays a crucial role in both personal and professional contexts;however,it is frequently compromised by the ongoing challenge of spam,which detracts from productivity and introduces considerable security *** spam detection techniques often struggle to keep pace with the evolving tactics employed by spammers,resulting in user dissatisfaction and potential data *** address this issue,we introduce the Divide and Conquer-Generative Adversarial Network Squeeze and Excitation-Based Framework(DaC-GANSAEBF),an innovative deep-learning model designed to identify spam *** framework incorporates cutting-edge technologies,such as Generative Adversarial Networks(GAN),Squeeze and Excitation(SAE)modules,and a newly formulated Light Dual Attention(LDA)mechanism,which effectively utilizes both global and local attention to discern intricate patterns within textual *** approach significantly improves efficiency and accuracy by segmenting scanned email content into smaller,independently evaluated *** model underwent training and validation using four publicly available benchmark datasets,achieving an impressive average accuracy of 98.87%,outperforming leading methods in the *** findings underscore the resilience and scalability of DaC-GANSAEBF,positioning it as a viable solution for contemporary spam detection *** framework can be easily integrated into existing technologies to enhance user security and reduce the risks associated with spam.

关键词： Email spam fraud light dual attention squeeze and excitation divide and conquer-generative adversarial network-squeeze and excitation-based framework security

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：