检索结果-内蒙古大学图书馆

2024 International Conference on Machine Learning and Intelligent Computing, MLIC 2024

作者： Hu, Mingjie Zhang, Qihang Ren, Jing Liu, Hengzhu Department of Intelligent Data Science National University of Defense Technology China College of Computer National University of Defense Technology China

Accurate cardinality estimation is crucial for query optimization by guiding plan selection. Traditional cardinality estimation approaches often fail to provide precise estimates, leading to suboptimal query plans. In recent years, learning-based methods have emerged as a promising alternative. For tree-based learning methods, a conventional way to simply encode nearby parent-child pairs and learn by iteratively training hampers the performance. But it leads to a significant loss of structural information and incurs substantial computational overhead by the iterative training process. In this paper, we proposed a tree-structure positional encoding scheme. It can not only extract effective features for each node, but also capture the inherent structural characteristics of the tree. Based on the tree-based feature, we designed a novel transformer-based cardinality estimation model, which enhances the parallelism of the model training process and reduces the overhead caused by iterative training. On real-world datasets, our method beats the current state-of-the-art techniques, QF, by 25% in terms of mean qerror. © 2024 M. Hu, Q. Zhang, J. Ren & H. Liu.

关键词： Cardinality estimation Positional Encoding Tree Transformer

来源：评论

学校读者我要写书评

暂无评论

Toward Responsible Artificial Intelligence Systems: Safety and Trustworthiness 8th

Toward Responsible Artificial Intelligence Systems: Safety a...

引用

8th International Conference on Engineering of computer-Based Systems, ECBS 2023

作者： Herrera, Francisco Department Computer Sciences and Artificial Intelligence Andalusian Research Institute on Data Science and Computational Intelligence University of Granada Granada Spain

ISBN: (纸本)9783031492518

This short paper associated to the invited lectures introduces two key concepts essential to artificial intelligence (AI), the area of trustworthy AI and the concept of responsible AI systems, fundamental to understand the technological, ethical and legal context of the current framework of debate and regulation of AI. The aim is to understand their dimension and their interrelation with the rest of the elements involved in the regulation and auditability of AI algorithms in order to achieve safe and trusted AI. We highlight concepts in bold in order to fix the moment when they are described in context. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions 37

Adversarial Training for Graph Neural Networks: Pitfalls, So...

引用

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Gosch, Lukas Geisler, Simon Sturm, Daniel Charpentier, Bertrand Zügner, Daniel Günnemann, Stephan Department of Computer Science Munich Data Science Institute Technical University of Munich Germany Microsoft Research United States

ISBN: (纸本)9781713899921

Despite its success in the image domain, adversarial training did not (yet) stand out as an effective defense for Graph Neural Networks (GNNs) against graph structure perturbations. In the pursuit of fixing adversarial training (1) we show and overcome fundamental theoretical as well as practical limitations of the adopted graph learning setting in prior work;(2) we reveal that flexible GNNs based on learnable graph diffusion are able to adjust to adversarial perturbations, while the learned message passing scheme is naturally interpretable;(3) we introduce the first attack for structure perturbations that, while targeting multiple nodes at once, is capable of handling global (graph-level) as well as local (node-level) constraints. Including these contributions, we demonstrate that adversarial training is a state-of-the-art defense against adversarial structure perturbations. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Out-of-Distribution Detection with a Single Unconditional Diffusion Model 38

Out-of-Distribution Detection with a Single Unconditional Di...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Heng, Alvin Thiery, Alexandre H. Soh, Harold Department of Computer Science National University of Singapore Singapore Department of Statistics and Data Science National University of Singapore Singapore Smart Systems Institute National University of Singapore Singapore

Out-of-distribution (OOD) detection is a critical task in machine learning that seeks to identify abnormal samples. Traditionally, unsupervised methods utilize a deep generative model for OOD detection. However, such approaches require a new model to be trained for each inlier dataset. This paper explores whether a single model can perform OOD detection across diverse tasks. To that end, we introduce Diffusion Paths (DiffPath), which uses a single diffusion model originally trained to perform unconditional generation for OOD detection. We introduce a novel technique of measuring the rate-of-change and curvature of the diffusion paths connecting samples to the standard normal. Extensive experiments show that with a single model, DiffPath is competitive with prior work using individual models on a variety of OOD tasks involving different distributions. Our code is publicly available at https://***/clear-nus/diffpath. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

IoT-Based Smart Wearable Devices Using Very Large Scale Integration (VLSI) Technology 1

引用

6th International Conference on Soft Computing and Signal Processing, ICSCSP 2023

作者： Ashwin, M. Naidu, R. Ch. A. Ramamoorthy, Raghu Kumar, E. Saravana Department of Artificial Intelligence and Data Science Koneru Lakshmaiah Education Foundation Andhra Pradesh India Department of Computer Science and Engineering The Oxford College of Engineering Karnataka Bengaluru India

ISBN: (数字)9789819984510

ISBN: (纸本)9789819984503

People’s usage of smart wearable devices and sensors plays a crucial role in VLSI technology. The wearable devices are embedded in clothes, smartwatches, and accessories. The wear gadgets like smart rings, smartwatches, and smart spectacles are associated with human healthcare monitoring, actual period location discovery and portable online games, etc. This paper presents a survey of the recent usage of wearable devices and sensors with VLSI technology. Three key features considered to make user-friendly smart wearable devices: They are security, performance, and deployment cost. Almost all wearable devices are equipped with Bluetooth communication and screen displays like smartwatches and smartphones. The primary goal of this research is to minimize the power consumption for wearable devices. Smart wearable devices are utilized for a wide range of applications like medicine, sports, fitness, business, etc. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Enhancing Residential Real Estate Search with Classification Strategies Using Diffusion and CLIP

Enhancing Residential Real Estate Search with Classification...

引用

2024 IEEE International Conference on Consumer Electronics, ICCE 2024

作者： Deng, Haojin Zhang, Wandong Yang, Yimin Nejad, Eman Western University Department of Electrical and Computer Engineering London Canada Wahi Realty Inc. Data Science Toronto Canada

ISBN: (纸本)9798350324136

The significance of the real estate search engine in the economy necessitates the development of a reliable room image luxury level annotation method that addresses current limitations, including the inability to assess room quality, underutilization of deep network capacities, and the need for more annotated house images. This paper proposes a novel real estate image annotation model, leveraging the diffusion model and contrastive language-image pre-Training (CLIP) network, through a multi-stage algorithm. First, the diffusion network is employed as a data augmentation technique to generate additional real estate images for network training. Then, a CLIP model is utilized to categorize images into the kitchen, bathroom, dining room, living room, and foyer. Finally, five CLIP models assess the condition of each room, categorizing it as contemporary and standard. Experimental results on a newly collected real estate image dataset demonstrate that the proposed approach surpasses existing house image classification algorithms. © 2024 IEEE.

关键词： contrastive language-image pre-Training image classification luxury level annotation Real-estate image

来源：评论

学校读者我要写书评

暂无评论

Heart disease prediction using machine learning, deep Learning and optimization techniques-A semantic review

引用

Multimedia Tools and Applications 2024年第39期83卷 86895-86922页

作者： Bhavekar, Girish Shrikrushnarao Das Goswami, Agam Vasantrao, Chafle Pratiksha Gaikwad, Amit K. Zade, Amol V. Vyawahare, Harsha Department of Artificial Intelligence & Data Science CSMSS Chh. Shahu College of Engineering Aurangabad431136 India Department of SENSE VIT-AP University Andhra Pradesh 522237 India Department of AI & DS CSMSS Chh. Shahu College of Engineering Maharashtra Aurangabad431136 India Department of Computer Science & Engineering GH Raisoni University Maharashtra Amravati444701 India Department of Computer Science & Engineering Sipna College of Engineering & Technology Maharashtra Amravati444701 India

Cardiovascular disease holds the position of being the foremost cause of death worldwide. Heart Disease Prediction (HDP) is a difficult task as it needs advanced knowledge with better experience. Moreover, it encounters numerous significant challenges in clinical data analysis. While many researchers have focused on predicting heart disease, the performance metric, namely prediction accuracy, remains suboptimal. The accurate HDP can help the person to prevent himself from life threats and at the same time, inaccurate prediction can prove to be fatal. To solve these issues, in this review work several Deep Learning (DL), Machine Learning (ML) and optimization based HDP techniques are discussed. In recent times, many researchers have been utilizing different DL and ML algorithms to help the professionals and health care industry for the prediction of heart disease. Further, it discussed about various optimization-based algorithms and its performance analysis. Therefore, this review paper suggests that the optimization-based HDP algorithm could assist doctors in predicting the occurrence of heart disease in advance and offering suitable treatment. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Enhanced Clickbait Detection through Ensemble Machine Learning Techniques

引用

Procedia computer science 2025年 258卷 599-608页

作者： Neetu Sardana Deepika Varshney Seema Luthra Department of Computer Science & Engineering-Data Science ABES Engineering College Ghaziabad India

Nowadays online news websites are one of the quickest ways to get information. However, the credibility of news from these sources is sometimes questioned. One common problem with online news is the prevalence of clickbait. Clickbait uses exaggerated headlines to lure people to click the suspected link, but the content often disappoints the reader and degrades user experience it may also hamper public emotions. The proposed work aims to examine diverse set of models for clickbait detection. The models are formed by integration of Machine learning (ML) and Ensemble learning methods (EL) with Term Frequency and Inverse Document Frequency (TF-IDF) & Embedding technique. Five ML and three EL are analysed &compared. Random Forest along with TF-IDF gave the best results of 85%. The resultant model shows significant improvements with a minimal false-positives.

关键词： Clickbait Detection Machine Learning text classification NLP Ensemble learning Stacking classifir

来源：评论

学校读者我要写书评

暂无评论

AI - Based Aircraft Recognition System 3

AI - Based Aircraft Recognition System

引用

3rd International Conference on Artificial Intelligence, Computational Electronics and Communication System, AICECS 2024

作者： Shiva Chandra, N.K. Rajath Anirudhan Manipal Institute of Technology Manipal Academy of Higher Education Department of Data Science and Computer Applications Karnataka Manipal576104 India

ISBN: (纸本)9798350391244

The project 'AI-Based Aircraft Recognition System' aims to develop an advanced system for automatically recognizing and identifying aircraft using AI techniques. The increasing role of artificial intelligence (AI) in various sectors, including aviation, has driven the need for more efficient and accurate recognition systems. Aircraft recognition has attracted attention due to its potential uses in areas like military operations, air traffic control, and aviation surveillance. This project proposes the use of advanced AI algorithms to address gaps in current aircraft recognition systems by enhancing accuracy, performance, and real-time application. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

On the Effect of Cross-Channel Normalization on Wide-Shallow Convolutional Networks 26

On the Effect of Cross-Channel Normalization on Wide-Shallow...

引用

26th Irish Machine Vision and Image Processing Conference, IMVIP 2024

作者： Alakkari, Salaheddin Mileo, Alessandra Department of Computer Science and Information Systems University of Limerick Ireland Insight Centre for Data Analytics Dublin City University Ireland

ISBN: (纸本)9781837242672

Cross-channel Normalization (CN) was first proposed in AlexNet paper as a biologically inspired normalization process mimicking the lateral inhibition phenomenon in biological neurons. However, the effect of such a normalization was not well explored in the literature due to the wide popularity of batch normalization. In this paper, we show that such a type of normalization can significantly enhance the network accuracy when applied to wide-shallow convolutional networks. Wide-shallow networks are more advantageous compared to deep CNNs since they significantly increase parallelism and reduce the sequential computation across layers. Our experiments show that using cross-channel normalization not only improves the accuracy of residual and standard convolutional networks on benchmark datasets but also significantly enhances the performance when considering limited and reduced representation examples. © This is an open access article published by the IET under the Creative Commons Attribution License (http://***/licenses/by/3.0/)

关键词： Convolution

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：