检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Alexander Munteanu Simon Omlor Dortmund Data Science Center Faculties of Statistics and Computer Science TU Dortmund University Dortmund Germany Faculty of Statistics TU Dortmund University Dortmund Germany and Lamarr-Institute for Machine Learning and Artificial Intelligence Dortmund Germany

The turnstile data stream model offers the most flexible framework where data can be manipulated dynamically, i.e., rows, columns, and even single entries of an input matrix can be added, deleted, or updated multiple times in a data stream. We develop a novel algorithm for sampling rows ai of a matrix A ∈ ℝn×d, proportional to their ℓp norm, when A is presented in a turnstile data stream. Our algorithm not only returns the set of sampled row indexes, it also returns slightly perturbed rows ãi ≈ ai, and approximates their sampling probabilities up to e relative error. When combined with preconditioning techniques, our algorithm extends to ℓp leverage score sampling over turnstile data streams. With these properties in place, it allows us to simulate subsampling constructions of coresets for important regression problems to operate over turnstile data streams with very little overhead compared to their respective off-line subsampling algorithms. For logistic regression, our framework yields the first algorithm that achieves a (1 + ε) approximation and works in a turnstile data stream using polynomial sketch/subsample size, improving over O(1) approximations, or exp(1/ε) sketch size of previous work. We compare experimentally to plain oblivious sketching and plain leverage score sampling algorithms for ℓp and logistic regression.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Investigating and Implementing the Efficiency of Image Restoration Techniques in Digital Image Processing 3

Investigating and Implementing the Efficiency of Image Resto...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Acharjya, Kalyan Yuvaraj, S. Jadhav, Varsha D. Sidhu, Amritpal Sinha, Deepak Kumar Kaneria, Ojasvee Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electronics and Communication Engineering Chennai127 India Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Computer Science and Engineering Faculty of Engineering and Technology Karnataka Bangalore India Vivekananda Global University Department of Computer Science & Engineering Jaipur India

ISBN: (纸本)9798350319125

This look at explores the efficiency of diverse photo recovery strategies, inclusive of noise reduction, histogram change, facet enhancement, polishing, and smoothing, in digital picture processing. An extensive evaluation of the techniques becomes conducted to assess their effectiveness in restoring degraded virtual pictures. Numerous objective metrics, together with Structural Similarity (SSIM) Index, peak sign-to-Noise Ratio (PSNR), and mean Squared blunders (MSE), have been used to quantitatively examine the first-rate of the restored photographs. Effects indicated that noise discount and area enhancement furnished the finest improvements within the snap shots. Histogram changes and sprucing also stepped forward the high-quality of the pictures, at the same time as the smoothing technique ended in a moderate lower in pleasant. This examines offers a detailed insight into the efficiency of various photo healing techniques and can serve as a reference for in addition investigations. © 2023 IEEE.

关键词： Investigations Smoothing Strategies Structural Techniques

来源：评论

学校读者我要写书评

暂无评论

Enhancing data Visualization in Real-Time with Machine Learning 3

Enhancing Data Visualization in Real-Time with Machine Learn...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Sripriya, T. Kachhoria, Renu Dev, Sudhanshu Mahesh, T.R. Nivesh Acharjya, Kalyan Prince Shri Venkateshwara Padmavathy Engineering College Department of Electronics and Communication Engineering Chennai127 India Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Chitkara University Institute of Engineering and Technology Chitkara University Centre of Interdisciplinary Research in Business and Technology Punjab India Computer Science and Engineering Faculty of Engineering and Technology Karnataka Bangalore India Vivekananda Global University Department of Computer Science & Engineering Jaipur India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India

ISBN: (纸本)9798350319125

Statistics visualization is an effective tool for information and communicating insights from massive facts sets. However, giving complicated records in a correct and complete style becomes challenging, mainly when the statistics are dynamic and change rapidly in real time. Device learning may be leveraged to enhance records visualization, making it more particular and comprehensive. This paper discusses the integration of machine learning techniques to enhance data visualization in real-time. The exponential growth of data in recent years has made it challenging for traditional techniques to effectively visualize and interpret data in real-time. Machine learning algorithms offer the ability to analyze and classify data in real-time, providing a more accurate and efficient way to visualize complex datasets. By leveraging machine learning, data visualization can be enhanced by automatically generating visual representations that are tailored to the data and user preferences. This paper presents an overview of the different machine learning techniques that can be applied to data visualization, along with their advantages and limitations. Additionally, a case study is presented to demonstrate the effectiveness of using machine learning for real-time data visualization. Through this study, it is shown that the integration of machine learning can significantly improve the speed, accuracy, and usability of data visualization in real-time scenarios. By using including the strength of machine learning to statistics visualization, such methods can permit quicker and deeper insights into records, taking into consideration higher selection making within the modern-day international wherein facts modifications swiftly. © 2023 IEEE.

关键词： interactive interested machine potential visualization

来源：评论

学校读者我要写书评

暂无评论

Discovering Innovative Applications for Real-Time data Analysis with Machine Learning 3

Discovering Innovative Applications for Real-Time Data Analy...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Jadhav, Prranjali Raja Praveen, K.N. Aggarwal, Prateek Gautam, Sandeep Naval, Preeti Nirmala, D. Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Computer Science and Engineering Faculty of Engineering and Technology Karnataka Bangalore India Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Vivekananda Global University Department of Computer Science & Engineering Jaipur India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electronics and Communication Engineering Chennai127 India

ISBN: (纸本)9798350319125

This paper investigates the capability for discovering modern programs for actual-time information analysis the use of system learning. We will take a look at the technology and strategies used in system getting to know and talk their adaptive potential to interpret and analyze dynamically changing facts inputs. Especially, we can examine existing technological methods to understand the capacity of AI to discover creative solutions to complicated challenges. We will also explore capability techniques to contain gadget gaining knowledge of into present real-time records analysis platforms and architectures. Finally, we are able to speak the programs of machine studying in real-time records evaluation and its potential to allow fast and correct decision making. This paper gives a theoretical framework to apprehend and harness the power of device gaining knowledge of to investigate and interpret real-time facts in modern approaches. © 2023 IEEE.

关键词： Information analysis

来源：评论

学校读者我要写书评

暂无评论

Advancements in AI-Driven Cephalometric Analysis for Orthodontic Applications: A Review on Automated Landmark Detection and Angle Assessment

Advancements in AI-Driven Cephalometric Analysis for Orthodo...

引用

Sentiment Analysis and Deep Learning (ICSADL), International Conference on

作者： Viraj Vijay Gurbade Utkarsha Pacharaaney Chetan Puri Department of Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education & Research (DU) Wardha Maharashtra India Department of Computer Science and Design Faculty of Engineering and Technology Datta Meghe Institute of Higher Education & Research (DU) Wardha Maharashtra India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

This is an essential tool used in the orthodontic practice for the assessment of craniofacial structures and as a basis in initiating treatment planning. Within the pre-AI/deep learning era, it was achieved through the procedure of manual tracing on 2D radiographs, individual variability, and quite time-consuming to obtain the established norm but which was susceptible. These technologies apply CNNs to properly detect landmarks and reduce the occurrence of human mistake, ensuring reproducibility of measurements across analyses. Automated systems demonstrated promising performance for landmark detection both on 2D and 3D images, particularly within the history of 3D imaging techniques such as cone-beam computed tomography (CBCT), offering a sweeping view of craniofacial anatomy. Studies show that training these AI models based on large datasets enables generalization to many images, thereby allowing landmark placement in reliable ways, with improved diagnostic accuracy; however, there's a challenge in achieving model robustness across different populations and complex 3D data. Future directions include the integration of AI with augmented reality, enabling real-time diagnostics to further depict and adjust clinicians' abilities to visualize treatment plans. With advancements in AI in cephalometry, the model may be hybrid to combine AI automation with manual verification, thus optimising reliability for clinical use, paving the way for more personalized and accurate orthodontic care.

关键词： Deep learning Solid modeling Three-dimensional displays Accuracy Computational modeling Manuals data models Real-time systems Planning Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Research on Rice Disease Identification Based on Improved ShuffleNet V2 Network

Research on Rice Disease Identification Based on Improved Sh...

引用

computer Technology and Information science (ISCTIS), International Symposium on

作者： Zhihuan Chen Shenming Gu Minghui Yu Zhaoquan Huang Key Laboratory of Oceanographic Big Data Mining & Application of Zhejiang Province Zhejiang Ocean University Zhoushan China School of Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China College of Mathematics and Computer Science Zhejiang Normal University Jinhua China

ISBN: (数字)9798350354560

ISBN: (纸本)9798350354577

How to efficiently and accurately identify rice diseases plays a crucial role in rice planting and production. Deploying large convolutional neural networks in practical applications is challenging due to their complex model parameters, while lightweight networks often compromise accuracy to reduce model size. In this study, we introduce a lightweight and precise network called GM-ShuffleNet for rice disease recognition. Building upon the ShuffleNet V2 network, we integrated the Ghost module and MCA attention mechanism, adjusted the network structure and number of channels, and replaced the ReLU activation function with Mish. Through comparative experiments, the accuracy of GM-ShuffleNet algorithm proposed in this paper reaches 96.20%, which is superior to ShuffleNet V2 and other excellent lightweight networks. In addition, in terms of model complexity comparison, the number of model parameters and FLOPs decreased by 82.54% and 77.44% respectively compared with the original network.

关键词： Information science Accuracy Attention mechanisms Computational modeling Buildings Production Complexity theory Convolutional neural networks Diseases

来源：评论

学校读者我要写书评

暂无评论

HYSPECNET-11K: A LARGE-SCALE HYPERSPECTRAL dataSET FOR BENCHMARKING LEARNING-BASED HYPERSPECTRAL IMAGE COMPRESSION METHODS

arXiv

引用

arXiv 2023年

作者： Fuchs, Martin Hermann Paul Demir, Begüm Faculty of Electrical Engineering and Computer Science Technische Universität Berlin Germany BIFOLD - Berlin Institute for the Foundations of Learning and Data Germany

The development of learning-based hyperspectral image compression methods has recently attracted great attention in remote sensing. Such methods require a high number of hyperspectral images to be used during training to optimize all parameters and reach a high compression performance. However, existing hyperspectral datasets are not sufficient to train and evaluate learning-based compression methods, which hinders the research in this field. To address this problem, in this paper we present HySpecNet-11k that is a large-scale hyperspectral benchmark dataset made up of 11,483 nonoverlapping image patches. Each patch is a portion of 128 × 128 pixels with 224 spectral bands and a ground sample distance of 30 m. We exploit HySpecNet-11k to benchmark the current state of the art in learning-based hyperspectral image compression by focussing our attention on various 1D, 2D and 3D convolutional autoencoder architectures. Nevertheless, HySpecNet-11k can be used for any unsupervised learning task in the framework of hyperspectral image analysis. The dataset, our code and the pre-trained weights are publicly available at https://***. © 2023, CC BY.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Adaptive Bandwidth Optimization Techniques for Underwater Fiber Optic Networks 3

Adaptive Bandwidth Optimization Techniques for Underwater Fi...

引用

3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023

作者： Kale, Sunil D. Samrat, Bhavuk Varalakshmi, S. Tiwari, Mohit Singh, Vaishali Umamaheswari, B. Vishwakarma Institute of Information Technology Department of Artificial Intelligence & Data Science Pune India Centre of Interdisciplinary Research in Business and Technology Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Center for Management Studies Faculty of Engineering and Technology Karnataka Bangalore India Vivekananda Global University Department of Computer Science & Engineering Jaipur India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Prince Shri Venkateshwara Padmavathy Engineering College Department of Computer Science and Engineering Chennai127 India

ISBN: (纸本)9798350319125

Underwater fiber optic networks provide hyperlinks that permit communiqué among offshore structures, deep-sea bases, and oil rigs. Despite the growing need for better facts costs, the constrained to be had bandwidth in such networks stays a major undertaking for their efficient use. To overcome this task, a variety of adaptive bandwidth optimization techniques were proposed in current years. A number of those strategies involve dynamic modulation and coding, whilst other techniques use adaptive scheduling algorithms. All tactics rely upon dynamic replace of bandwidth allocation to make the only use of the underlying fiber hyperlink. Within the case of dynamic modulation and coding, modifications are made to the physical layer configuration of the hyperlink to conform to converting conditions on the hyperlink. On the other hand, adaptive scheduling strategies use course optimization algorithms to select the maximum green route for records to tour, re-allocating bandwidth as had to accommodate heavy loads. Subsequently, new techniques such as EQUINOX are also being explored to further optimize bandwidth usage on underwater fiber optic networks by means of combining elements of each dynamic modulation and coding and adaptive scheduling. © 2023 IEEE.

关键词： Hyperlinks Modulation Optimization Scheduling Techniques

来源：评论

学校读者我要写书评

暂无评论

Sustainable North-South Africa Collaboration for Disaster and Crisis Management: A Strategic Capacity Development Framework using Open science, Artificial Intelligence and Geoinformatics

引用

data science Journal 2025年 24卷

作者： Ibrahim, Rania Elsayed Motshegwa, Tshiamo Benouar, Djillali Khodja, Mohamed Ead, Hamed Zhang, Lili Crawley, Francais McHunu, Nokuthula P. Hachigonta, Sepo Hodson, Simon McBride, Vanessa Yohannes, Teketel National Authority for Remote Sensing and Space Sciences Egypt National Research Foundation South Africa Department of Computer Science University of Botswana Botswana Algerian Academy for Science and Technology Algeria Faculty of Science Cairo University Egypt Egyptian Embassy in Morocco Morocco Computer Network Information Center Chinese Academy of Sciences China CODATA International Data Policy Committee Belgium University of KwaZulu Natal South Africa CODATA France International Science Council South Africa

Background: This paper explores strategies to enhance North-South collaboration to foster multi-and trans-disciplinary research in disaster risk reduction (DRR) and crisis management, emphasizing the role of open science, Artificial Intelligence (AI) and geoinformatics in developing a resilient and proactive approach to these challenges, as well as drawing on lessons learned from the COVID-19 pandemic, the paper highlights how collaboration and data sharing can enhance preparedness, response, and recovery in future crises. Methods: The study uses a mixed approach to gather and analyze information. Qualitative methods focus on gathering descriptive data through engaging with experts and a structured review. By investigating literature, a comprehensive strategic framework for minimizing disaster risk, and for crisis management, is developed to provide adequate guidance to policymakers on implementation strategies and the application of how to build the human, institutional, and technological capacity required for effective disaster and crisis management (DCM). The events were used to engage with experts to provide recommendations and opportunities to enhance crisis response, capacity development and policy. Findings: By presenting a comprehensive framework that bridges theoretical knowledge with practical application, our findings indicate that governments must address the challenges of DCM to minimize losses. The practices surrounding disaster recovery can provide opportunities for policymakers to reassess priorities and redirect resources toward building sustainable communities. Originality: There is no strategic framework that provides adequate guidance to policymakers on implementation strategies or the application of how to build the human, institutional and technological capacity required for effective DCM. This article develops a Decision Support Framework for DCM. We outline how open science promotes cross-disciplinary collaboration and the sharing of knowledg

关键词： Risk management

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approach 39

Personalized Federated Collaborative Filtering: A Variationa...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Li, Zhiwei Long, Guodong Zhou, Tianyi Jiang, Jing Zhang, Chengqi Australian Artificial Intelligence Institute Faculty of Engineering and IT University of Technology Sydney Australia Department of Computer Science University of Maryland College Park United States Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University Hong Kong

ISBN: (纸本)157735897X

Federated Collaborative Filtering (FedCF) is an emerging field focused on developing a new recommendation framework with preserving privacy in a federated setting. Existing FedCF methods typically combine distributed Collaborative Filtering (CF) algorithms with privacy-preserving mechanisms, and then preserve personalized information into a user embedding vector. However, the user embedding is usually insufficient to preserve the rich information of the fine-grained personalization across heterogeneous clients. This paper proposes a novel personalized FedCF method by preserving users' personalized information into a latent variable and a neural model simultaneously. Specifically, we decompose the modeling of user knowledge into two encoders, each designed to capture shared knowledge and personalized knowledge separately. A personalized gating network is then applied to balance personalization and generalization between the global and local encoders. Moreover, to effectively train the proposed framework, we model the CF problem as a specialized Variational AutoEncoder (VAE) task by integrating user interaction vector reconstruction with missing value prediction. The decoder is trained to reconstruct the implicit feedback from items the user has interacted with, while also predicting items the user might be interested in but has not yet interacted with. Experimental results on benchmark datasets demonstrate that the proposed method outperforms other baseline methods, showcasing superior performance. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Variational techniques

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：