检索结果-内蒙古大学图书馆

6th International Conference on Intelligent Computing in data sciences, ICDS 2024

作者： Assami, Sara Daoudi, Najima Ajhoun, Rachida Ecole Nationale Supérieure d'Informatique et d'Analyse Des Systèmes of Mohammed v University Department of Computer Science Rabat Morocco Ecole des Sciences de l'Information Department of Data and Knowledge Engineering Rabat Morocco

ISBN: (纸本)9798350351200

Semantic web technologies aim to interconnect objects using descriptors that identify their characteristics and improve information retrieval. In Massive Open Online Courses (MOOCs), the learning contents semantic links and their pertinence for learner needs are essential to motivate learners and reduce dropout rates. This work aims to develop a semantic recommender system prototype that uses external data sources on learners to identify their knowledge, skills, and interests to recommend MOOCs. First, this paper traces the knowledge-based recommendation of MOOCs and its data representation in the literature. Afterward, it explores a dataset of a MOOC platform to extract MOOCs content-related data, and a dataset of a professional social media to extract knowledge-based characteristics of a learner from his/her social profile. For the implementation of the semantic recommender, three different techniques: TF-IDF, GloVe, and USE models are used to compute the semantic similarity of learner needs and MOOCs content. The semantic MOOC recommender system implementation showed the advantages of using different data sources and the increased performance of a MOOC recommender system based on transformer models like the USE model. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Supply Chain Management Using Internet of Things and Blockchain for Smart Meat Packaging

Supply Chain Management Using Internet of Things and Blockch...

引用

data Intelligence and Cognitive Informatics (ICDICI), International Conference on

作者： KanwalPreet Kour S Kanwal Deep Singh Malvinder Singh Bali G S Pradeep Ghantasala Rajesh Sharma R U Ananthanagu School of Computer Science and Engineering Manipal University Jaipur India Department of Computer Science Federation University Australia Department of Data Science and Engineering Manipal University Jaipur Rajasthan India Department of Computer Science and Engineering Alliance College of Engineering and Design Alliance University Bengaluru India

ISBN: (数字)9798350389609

ISBN: (纸本)9798350389616

In recent times, blockchain has evolved the security of traditional supply chain systems. Different issues of supply chain management like flexibility and reliability can be easily addressed using blockchain. Meat Packing Industry involves the complete process of processing, packaging and supplying the meat and its products throughout the world for human consumption. The animals used for the meat supply chain include pigs, sheep, cattle etc. Due to the enormous increase in the number of meat-eaters worldwide, its packing and timely supply are of utmost importance. The meat packing industry has revolutionized a lot by using the latest supply chain methods based on new technologies like blockchain. These include adulteration, long-term delays leading to spoilage of the product, mixing of other similar products which are lower in price etc. All these issues can be easily handled by using blockchain and IoT for meat supply chain management. Using these technologies, the challenges ranging from timely transportation of good quality meat to the best quality meat delivered to the customer can be easily addressed. In this paper, an effective blockchain and IoT-based model has been proposed which will counter the above challenges and improve the reliability and security factor.

关键词： Industries Supply chain management Supply chains Transportation Packaging Blockchains Safety Security Reliability Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Automatic Detection of Waterbodies from Satellite Images Using DeepLabV3+ 1

引用

9th International Conference on Mining Intelligence and Knowledge Exploration, MIKE 2023

作者： Kadry, Seifedine Al-Betar, Mohammed Azmi Yassine, Sahar Mohan, Ramya Arunmozhi, Rama Rajinikanth, Venkatesan Department of Applied Data Science Noroff University College Kristiansand4612 Norway College of Engineering and Information Technology Ajman University Ajman United Arab Emirates Department of Computer Science and Engineering Division of Research and Innovation Saveetha School of Engineering SIMATS Chennai602105 India

ISBN: (数字)9783031440847

ISBN: (纸本)9783031440830

In recent times, it has become increasingly popular to examine a wide range of environmental and earth data using remote sensing schemes supported by satellite images (SI). Due to the complex nature of spatial, spectral, and temporal characteristics of SI, it is quite difficult for automatic analysis to be performed as it requires specially designed algorithms. As part of the research proposal, an enhanced deep-learning scheme will be implemented in order to extract the waterbodies from the chosen SIs. The phases involved in this scheme includes;(i) the collection and resizing of images, (ii) Shannon's Entropy preprocessing, (iii) DeepLabV3+ extraction of waterbodies, (iv) the comparison of extracted sections with ground truth (GT) and the calculation of performance metrics, and (v) validation of the effectiveness of the implemented scheme. In the proposed work, the proposed multi-thresholding approach is combined with DeepLabV3+ in order to get the waterbodies to be extracted from the chosen test images. DeepLabV3 is demonstrated to have excellent segmentation performance when it is compared to UNet and SegNet. The experimental results of this scheme indicate that DeepLabV3+ results in higher Jaccard value (>89%), Dice value (>93%), and segmentation accuracy value (>97%) when compared to other pretrained segmentation schemes. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

ISUAM: Intelligent and Safe UAM with Deep Reinforcement Learning 29

ISUAM: Intelligent and Safe UAM with Deep Reinforcement Lear...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Garcia, Cristiano P. Weigang, Li Hirata, Nina S. T. Neumann, Clovis University of Brasilia Computer Science Department Brasília Brazil University of São Paulo Institute of Mathematics and Statistics São Paulo Brazil University of Brasilia Production Engineering Department Brasília Brazil

ISBN: (纸本)9798350330717

Urban air mobility (UAM) is on the verge of a fast-growing expansion as the major aircraft manufacturers are in the late-stage development of various Electric Vertical Take-Off and Landing (eVTOL) aircraft models. In recent decades, conflict detection and resolution (CD&R) in air traffic management has been widely studied. However, factors such as the wide availability of unmanned aerial vehicles (UAV), the expected use of eVTOL, and the latest development of groundbreaking deep reinforcement learning (DRL) have generated new interest in this research field. Some characteristics of this new aircraft type, such as weight, speed, and maneuverability, require a revisit of the CD&R for adaptation to the new paradigm. We propose an Intelligent and Safe UAM with Deep Reinforcement Learning (ISUAM) system that can perform tactical deviation maneuvers in the UAM environment using some latest DRL models. After extensive testing, including various DRL agents, Dueling Deep Q Networks (Dueling DQN) has provided the best performance and proved its ability to provide satisfactory conflict resolution. © 2023 IEEE.

关键词： Air Traffic Management eVTOL Leamig Reinforcement UAM

来源：评论

学校读者我要写书评

暂无评论

Once read is enough: domain-specific pretraining-free language models with cluster-guided sparse experts for long-tail domain knowledge 24

Once read is enough: domain-specific pretraining-free langua...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Fang Dong Mengyi Chen Jixian Zhou Yubin Shi Yixuan Chen Mingzhi Dong Yujiang Wang Dongsheng Li Xiaochen Yang Rui Zhu Robert Dick Qin Lv Fan Yang Tun Lu Ning Gu Li Shang China and Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Oxford Suzhou Centre for Advanced Research Suzhou China University of Bath and China and Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Microsoft Research Asia Shanghai China School of Mathematics & Statistics University of Glasgow Bayes Business School City St George's University of London Department of Electrical Engineering and Computer Science University of Michigan Department of Computer Science University of Colorado Boulder School of Microelectronics Fudan University

ISBN: (纸本)9798331314385

Language models (LMs) only pretrained on a general and massive corpus usually cannot attain satisfying performance on domain-specific downstream tasks, and hence, applying domain-specific pretraining to LMs is a common and indispensable practice. However, domain-specific pretraining can be costly and time-consuming, hindering LMs' deployment in real-world applications. In this work, we consider the incapability to memorize domain-specific knowledge embedded in the general corpus with rare occurrences and "long-tail" distributions as the leading cause for pretrained LMs' inferior downstream performance. Analysis of Neural Tangent Kernels (NTKs) reveals that those long-tail data are commonly overlooked in the model's gradient updates and, consequently, are not effectively memorized, leading to poor domain-specific downstream performance. Based on the intuition that data with similar semantic meaning are closer in the embedding space, we devise a Cluster-guided Sparse Expert (CSE) layer to actively learn long-tail domain knowledge typically neglected in previous pretrained LMs. During pretraining, a CSE layer efficiently clusters domain knowledge together and assigns long-tail knowledge to designate extra experts. CSE is also a lightweight structure that only needs to be incorporated in several deep layers. With our training strategy, we found that during pretraining, data of long-tail knowledge gradually formulate isolated, "outlier" clusters in an LM's representation spaces, especially in deeper layers. Our experimental results show that only pretraining CSE-based LMs is enough to achieve superior performance than regularly pretrained-finetuned LMs on various downstream tasks, implying the prospects of domain-specific-pretraining-free language models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unleashing the Potential of Women in Leadership Roles within the Evolving Landscape of Machine Learning and Technology

Unleashing the Potential of Women in Leadership Roles within...

引用

2024 IEEE International Conference on Intelligent Systems and Advanced Applications, ICISAA 2024

作者： Tiwari, Madhuri Giri, Neeraj Suman, Sanjay Kumar Chandanan, Amit Kumar Peneti, Subhashini Choudhury, Shibanjali GGITS Dept of Data Science MP Jabalpur India IES Institute of Technology and Management IES University Department of Computer Science and Engineering MP Bhopal462044 India St. Martin's Engineering College Dept. of ECE Telangana Secunderabad India Department of Computer Science and Engineering C G Bilaspur India MLR Institute of Technology Dept. of CSE Telangana Hyderabad India Techno College of Engineering Dept. of CSE Tripura Agartala India

ISBN: (纸本)9798331539948

The innovative Gender-Empowered Leadership Development (GELD) programme promotes gender equality in fast-paced technology and machine learning leadership positions. This was a US government initiative. BiasMitigator, Skillenhancer, and CultureCatalyst work together to eliminate gender prejudice, improve employee skills, and improve workplace morale. Programs collaborate to achieve these aims. CultureCatalyst promotes a pleasant environment, SkillEnhancer improves skills over time, and BiasMitigator eliminates gender prejudice across the firm. All three projects assist the organization achieve its aims. This study compares GELD to normal approaches to better understand the situation. This illustrates how intricate its procedure is. © 2024 IEEE.

关键词： BiasMitigator CultureCatalyst GenderEmpowered Leadership Development Inclusion Leadership Development Machine Learning SkillEnhancer Technology Traditional Methods Women in Leadership

来源：评论

学校读者我要写书评

暂无评论

Failures and Successes of Cross-Validation for Early-Stopped Gradient Descent

arXiv

引用

arXiv 2024年

作者： Patil, Pratik Wu, Yuchen Tibshirani, Ryan J. Department of Statistics University of California BerkeleyCA94720 United States Department of Statistics and Data Science Wharton School University of Pennsylvania PA19104 United States

We analyze the statistical properties of generalized cross-validation (GCV) and leave-one-out cross-validation (LOOCV) applied to early-stopped gradient descent (GD) in high-dimensional least squares regression. We prove that GCV is generically inconsistent as an estimator of the prediction risk of early-stopped GD, even for a well-specified linear model with isotropic features. In contrast, we show that LOOCV converges uniformly along the GD trajectory to the prediction risk. Our theory requires only mild assumptions on the data distribution and does not require the underlying regression function to be linear. Furthermore, by leveraging the individual LOOCV errors, we construct consistent estimators for the entire prediction error distribution along the GD trajectory and consistent estimators for a wide class of error functionals. This in particular enables the construction of pathwise prediction intervals based on GD iterates that have asymptotically correct nominal coverage conditional on the training data. Copyright © 2024, The Authors. All rights reserved.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Robust Federated Learning for Privacy Preservation and Efficiency in Edge Computing

引用

IEEE Transactions on Services Computing 2025年第03期18卷 1739-1752页

作者： Zhou, Hao Dai, Hua Yang, Geng Xiang, Yang Nanjing University of Posts and Telecommunications School of Computer Science Jiangsu Security and Intelligent Processing Lab of Big Data Nanjing210023 China Swinburne University of Technology Department of Computer Science HawthornVIC3122 Australia

Federated Learning (FL) has emerged as a key enabler of privacy-preserving distributed model training in edge computing environments, crucial for service-oriented applications such as personalized healthcare, smart cities, and intelligent assistants. However, existing privacy-preserving FL methods are susceptible to multiple privacy leakage attacks (MPLA), where adversaries infer sensitive information through repeated gradient updates. This paper proposes a Robust and Communication-Efficient Federated Learning (RCFL) framework designed to enhance privacy protection and communication efficiency in edge-based service environments. RCFL integrates a global privacy-preserving mechanism with an innovative privacy encoding strategy that minimizes privacy risks over multiple data releases while significantly reducing communication overhead. The proposed framework's theoretical analysis demonstrates its ability to maintain differential privacy across numerous interactions, ensuring robust model convergence and efficiency. Experimental results using MNIST and CIFAR-10 datasets reveal that RCFL can lower the MPLA success rate from 88.56% to 42.57% compared to state-of-the-art methods, while reducing communication costs by over 90%. These findings underscore RCFL's potential to enhance security, efficiency, and scalability in service-oriented edge computing applications. © 2008-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Detecting Bipolar Disorder based on Crowdsourced Symptoms using Machine Learning with Shapley Additive Explanations

引用

Procedia computer science 2024年 245卷 290-298页

作者： Marvel Martawidjaja Matthew Lefrandt Ni Luh Putu Satyaning Pradnya Paramita Rongfang Zhan Renata Komalasari Felix Indra Kurniadi Erna Fransisca Angela Sihotang Maria Susan Anggreainy Dwy Bagus Cahyono Putu Hadi Purnama Jati Computer Science Department School of Computer Science Bina Nusantara University Jakarta 11530 Indonesia Department of Rehabilitation and Health Services University of North Texas Denton 76203 United States of America College of Nursing Pennsylvania State University State College 16802 United States of America Statistics Department School of Computer Science Bina Nusantara University Jakarta 11530 Indonesia Computer Science Department BINUS Graduate Program Doctor of Computer Science Bina Nusantara University Jakarta 11530 Indonesia Meta Lab Jakarta 10310 Indonesia

Bipolar disorder is a mental health condition characterized by extreme mental states ranging from manic highs to depressive lows. Early intervention is crucial to prevent progression and complications of bipolar disorder, which can lead to significant loss. This study proposes a framework to detect bipolar disorder based on crowdsourced symptoms in the form of free texts. We extract the features by transforming these free-text symptoms into binary features using a set of natural language processing techniques. We build support vector machine models with different kernel functions and penalized logistic regression models with different penalty functions, where the best models have a precision of 0.7, recall of 0.78, F1 score of 0.74, and accuracy of 0.88. Moreover, the models are explainable since we incorporate a model-agnostic explanation method called Shapley additive explanations to understand the symptoms that mostly contributed to the prediction of bipolar disorder. The models presented in this study can be implemented in the initial screening process of bipolar disorder for further examination.

关键词： bipolar disorder crowdsourcing explainable machine learning support vector machine penalized logistic regression natural language processing

来源：评论

学校读者我要写书评

暂无评论

Retraction Note: A Systematic Survey on Implementation of Fuzzy Regression Models for Real Life Applications

引用

Archives of Computational Methods in Engineering 2025年 1-2页

作者： Khan, Mufala Kumar, Rakesh Aledaily, Arwa N. Kariri, Elham Viriyasitavat, Wattana Yadav, Kusum Dhiman, Gaurav Kaur, Amandeep Sharma, Ashutosh Vimal, S. Department of Mathematics Lovely Professional University Phagwara India College of Computer Science and Engineering University of Ha’il Hail Saudi Arabia College of Computer Science and Engineering Prince Sattam Bin Abdulaziz University Al‑Kharj Saudi Arabia Business Information Technology Division Department of Statistics Faculty of Commerce and Accountancy Chulalongkorn University Bangkok Thailand Department of Computer Science Government Bikram College of Commerce Patiala India Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon University Centre for Research and Development Department of Computer Science and Engineering Chandigarh University Gharuan India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India Chitkara University Institute of Engineering and Technology Chitkara University Rajpura India School of Computer Science University of Petroleum and Energy Studies Dehradun India Department of Artificial Intelligence and Data Science Ramco Institute of Technology Rajaplayam India

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：