检索结果-内蒙古大学图书馆

Topological Signal processing Over Generalized Cell Complexes

IEEE TRANSACTIONS ON SIGNAL processing 2024年 72卷 687-700页

作者： Sardellitti, Stefania Barbarossa, Sergio Sapienza Univ Rome Dept Informat Engn Elect & Telecommun I-00184 Rome Italy

Topological Signal processing (TSP) over simplicial complexes is a framework that has been recently proposed, as a generalization of graph signal processing (GSP), to extend GSP to analyzing signals defined over sets of any order (i.e., not only vertices of a graph) and to capture multiway relations of any order among the data. However, simplicial complexes are required to satisfy the so-called inclusion property, according to which, if a set belongs to the complex, then all its subsets must also belong to the complex. In some applications, this is a severe limitation. To overcome this limit, in this paper we extend TSP to deal with signals defined over cell complexes and we also generalize the concept of cell complexes to include hollow cells. We show that, even if the algebraic formulation does not change significantly, the extension to the generalized cell complexes considerably broadens the number of applications. Most important, the new representation provides a much better trade-off between the complexity of the representation and its accuracy. In addition, we propose a method to infer the structure of the cell complex from data and we propose distributed filtering strategies, including a method to retrieve the sparsest representation of the harmonic component. We quantify the advantages of using cell complexes instead of simplicial complexes, in terms of the complexity/accuracy trade-off, for different applications such image segmentation and recovering of real flows measured on data traffic and transportation networks.

关键词： Signal processing Data mining Topology Finite impulse response filters artificial neural networks Transportation Partitioning algorithms Topological signal processing algebraic topology cell complexes simplicial complexes FIR filters topology inference

来源：评论

学校读者我要写书评

暂无评论

image Classification with Regularized Likelihood Estimation and Large Interval Discriminant Dimensionality Reduction

引用

JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 2025年第2期41卷 385-400页

作者： Shen, Ying Zhu, Wei-hua Fu, Si-yong Wu, Guang-sheng Xinyu Univ Zhongxing Commun & Informat Coll Xinyu 338004 Peoples R China Xinyu Univ Sch Math & Comp Sci Xinyu 338004 Peoples R China

With the expansion of image application scale and the development of artificial intelligence industry, the demand for high precision and high robustness of image feature expression is gradually increasing. Convolutional neural networks (CNNS) have attracted much attention in the field of computer vision in recent years because of their excellent image feature learning ability. In order to further improve the accuracy and robustness of image classification, a second-order statistical convolutional neural network with multilayer fusion and cross-convolutional layer pooling are proposed in this study to obtain feature information of different dimensions in different convolutional layers. Due to the increase of computing and storage costs, an image classification method based on robust covariance of deep convolution features is proposed, and two regularized maximum likelihood estimators are introduced. Finally, the proposed method is tested by fine-grained experiments, image retrieval experiments and image classification experiments. The results show that MFBP (4,5) structure achieves 92.4%, 74.2% and 72.9% accuracy in finegrained image classification. Compared with MFBP (3,4,5), despite a slight decrease in accuracy, FPS performance is improved by more than 40%, demonstrating the advantages of this method in real-time applications. In addition, RMIE-VND and RMIE-IM methods improved by 4.1%, 8.4%, 7.8% and 7.1%, 12%, 9.8%, respectively, compared with LW methods on different data sets. The experimental results of image classification show that MFBP+RLME (VND+IM) has better performance and applicability than the current mainstream classification methods. This research is of great value for improving the efficiency and accuracy of image processing in big data environment, and provides a new research direction and practical tool for future real-time image application and computer vision system development.

关键词： image classification image dimensionality reduction convolutional neural net- work bilinear pooling regularized likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

From methods to datasets: A survey on image-Caption Generators

引用

MULTIMEDIA TOOLS AND applications 2024年第9期83卷 28077-28123页

作者： Agarwal, Lakshita Verma, Bindu Delhi Technol Univ Dept Informat Technol Delhi 110042 India

image - Caption Generator is a popular artificial Intelligence research tool that works with image comprehension and language definition. Creating well-structured sentences requires a thorough understanding of language in a systematic and semantic way. Being able to describe the substance of an image using well-structured phrases is a difficult undertaking, but it can have a significant impact in terms of assisting visually impaired people in better understanding the images' content. image captions has gained a lot of attention as a study subject for various computer vision and natural language processing (NLP) applications. The goal of image captions is to create logical and accurate natural language phrases that describes an image. It relies on the caption model to see items and appropriately characterise their relationships. Intuitively, it is also difficult for a machine to see a typical image in the same way that humans do. It does, however, provide the foundation for intelligent exploration in deep learning. In this review paper, we will focus on the latest in-depth advanced captions techniques for image captioning. This paper highlights related methodologies and focuses on aspects that are crucial in computer recognition, as well as on the numerous strategies and procedures being developed for the development of image captions. It was also observed that Recurrent neural networks (RNNs) are used in the bulk of research works (45%), followed by attention-based models (30%), transformer-based models (15%) and other methods (10%). An overview of the approaches utilised in image captioning research is discussed in this paper. Furthermore, the benefits and drawbacks of these methodologies are explored, as well as the most regularly used data sets and evaluation processes in this sector are being studied.

关键词： image- Caption Generator Natural language processing Computer vision Intelligent exploration Deep learning

来源：评论

学校读者我要写书评

暂无评论

Role of Convolutional neural networks in Hyperspectral Imaging applications: A Review 1

引用

4th Congress on Intelligent Systems (CIS)

作者： Lanke, Neha P. Chandak, M. B. Shri Ramdeobaba Coll Engn & Management Nagpur Maharashtra India

ISBN: (数字)9789819990405

ISBN: (纸本)9789819990399;9789819990405

In last few years, considerable improvements have been made in digital image acquisition and processing, improving image quality and results. However, hyperspectral imaging techniques evolved to gain more valuable information from images that integrate digital spectroscopy and imaging to generate information in special and spectral dimensions. HSI is a powerful tool for image analysis in potential application areas, including remote sensing, agriculture, horticulture, food quality assessment, medical imaging, forensic science, etc. artificial intelligence technologies are used as an important tool in many research areas. As a result, image analysis and classification studies are carried out on HSI with various ML techniques. Lately, deep learning with convolutional neural networks has emerged as an important tool for dealing with hyperspectral images' high dimensionality. In this paper, we review work done on different hyperspectral imaging applications using convolutional neural networks, which shows that deep learning using convolutional neural networks can be a powerful tool for hyperspectral image analysis and classification.

关键词： Hyperspectral imaging (HSI) Deep learning (DL) Convolutional neural network (CNN)

来源：评论

学校读者我要写书评

暂无评论

Software vulnerability detection under poisoning attacks using CNN-based image processing

引用

INTERNATIONAL JOURNAL OF INFORMATION SECURITY 2025年第2期24卷 1-22页

作者： Gonzalez-Manzano, Lorena Garcia-Alfaro, Joaquin Univ Carlos III Madrid Leganes Spain Inst Polytech Paris SAMOVAR Telecom SudParis F-91120 Palaiseau France

Design flows, code errors, or inadequate countermeasures may occur in software development. Some of them lead to vulnerabilities in the code, opening the door to attacks. Assorted techniques are developed to detect vulnerable code samples, making artificial intelligence techniques, such as Machine Learning (ML), a common practice. Nonetheless, the security of ML is a major concern. This includes the the case of ML-based detection whose training process is affected by data poisoning. More generally, vulnerability detection can be evaded unless poisoning attacks are properly handled. This paper tackles this problem. A novel vulnerability detection system based on ML-based image processing, using Convolutional neural Network (CNN), is proposed. The system, hereinafter called IVul, is evaluated under the presence of backdoor attacks, a precise type of poisoning in which a pattern is introduced in the training data to alter the expected behavior of the learned models. IVul is evaluated with more than three thousand code samples associated with two representative programming languages (C# and PHP). IVul outperforms other comparable state-of-the-art vulnerability detectors in the literature, reaching 82%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$82\%$$\end{document} to 99%\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$99\%$$\end{document} detection accuracy. Besides, results show that the type of attack may affect a particular language more than another, though, in general, PHP is more resilient to proposed attacks than C#.

关键词： Software vulnerability detection Poisoning attack artificial Intelligence Machine learning Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

The use of physics-informed neural network approach to image restoration via nonlinear PDE tools

引用

COMPUTERS & MATHEMATICS WITH applications 2023年 152卷 355-363页

作者： Namaki, Neda Eslahchi, M. R. Salehi, Rezvan Tarbiat Modares Univ Fac Math Sci Dept Appl Math POB 14115134 Tehran Iran

In this work, we propose a physics-informed solution for a blending PDE model with application in image denoising and edge-preserving. The blending model contains isotropic diffusion (ID) model and the modified Perona-Malik model introduced by Catte et al. Then we solve this model applying a physics-informed approach. Solving the new blending model is done using DeepXDE, which is a deep learning library for solving differential equations, by considering the image as input. Error analysis for neural network approximations of the new PDE model is shown. Applying PSNR criteria for some images, it can be seen that the proposed method can compete with solving denoising PDE models using finite difference method (FDM).

关键词： Isotropic diffusion model Perona-Malik model Physics-informed Deep learning artificial neural networks image processing

来源：评论

学校读者我要写书评

暂无评论

RCT: Resource Constrained Training for Edge AI

引用

IEEE TRANSACTIONS ON neural networks AND LEARNING SYSTEMS 2024年第2期35卷 2575-2587页

作者： Huang, Tian Luo, Tao Yan, Ming Zhou, Joey Tianyi Goh, Rick ASTAR Inst High Performance Comp Singapore 138632 Singapore ASTAR Ctr Frontier AI Res Singapore 138632 Singapore

Efficient neural network training is essential for in situ training of edge artificial intelligence (AI) and carbon footprint reduction in general. Train neural network on the edge is challenging because there is a large gap between limited resources on edge and the resource requirement of current training methods. Existing training methods are based on the assumption that the underlying computing infrastructure has sufficient memory and energy supplies. These methods involve two copies of the model parameters, which is usually beyond the capacity of on-chip memory in processors. The data movement between off-chip and on-chip memory incurs large amounts of energy. We propose resource constrained training (RCT) to realize resource-efficient training for edge devices and servers. RCT only keeps a quantized model throughout the training so that the memory requirement for model parameters in training is reduced. It adjusts per-layer bitwidth dynamically to save energy when a model can learn effectively with lower precision. We carry out experiments with representative models and tasks in image classification, natural language processing, and crowd counting applications. Experiments show that on average, 8-15-bit weight update is sufficient for achieving SOTA performance in these applications. RCT saves 63.5%-80% memory for model parameters and saves more energy for communications. Through experiments, we observe that the common practice on the first/last layer in model compression does not apply to efficient training. Also, interestingly, the more challenging a dataset is, the lower bitwidth is required for efficient training.

关键词： Training Quantization (signal) Memory management neural networks Computational modeling System-on-chip Program processors Efficient training memory efficient neural network quantization weight update

来源：评论

学校读者我要写书评

暂无评论

Exploring the power of photoplethysmogram matrix for atrial fibrillation detection with integrated explainability

引用

ENGINEERING applications OF artificial INTELLIGENCE 2024年第PartD期133卷

作者： Fuster-Barcelo, Caterina Guerrero-Lopez, Alejandro Camara, Carmen Peris-Lopez, Pedro Carlos III Univ Madrid UC3M Dept Bioengn Madrid Spain Univ Politecn Madrid UPM Escuela Tecn Super Ingn & Sistemas Telecomuniac Madrid Spain Carlos III Univ Madrid UC3M Dept Comp Sci Madrid Spain

Atrial Fibrillation (AF) detection is paramount for cardiovascular health due to its potential complications. In this study, we investigate the utility of Photoplethysmogram (PPG) for continuous heart rate monitoring and detection of patients with AF. Our approach centres on creating PhotoplethysmoMatrices (PPMs) and leverages Explainable artificial Intelligence (XAI) techniques to enable accurate AF patient classification with interpretability. Our method involves transforming PPG data into multiple PPM images, which represent aligned peaks within the PPG signal, presented as heatmaps. The diagnostic architecture is a lightweight and efficient Convolutional neural Network (CNN) combined with attention mechanisms for model transparency. Remarkably, our approach achieves a 100% classification accuracy across multiple experiments, even with variations in the number of users and training images. Furthermore, the attention module underscores the significance of peak positioning and shifting in AF patient detection. Overall, our research makes a substantial contribution to the field of AF patient classification using PPG signals. The combination of image -based preprocessing techniques and explainable architectures enhances accuracy and interpretability, promising improved diagnostic capabilities in clinical settings.

关键词： Photoplethysmogram Convolutional neural networks Atrial fibrillation Explainable artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Deep CNN, YOLO, and LeNet for Handwritten Digit Classification 1

引用

International Conference on artificial Intelligence: Theory and applications (AITA)

作者： Sarmah, Jibok Saini, Madan Lal Kumar, Ankush Chasta, Vidhan Chandigarh Univ Dept CSE Apex Inst Technol Mohali Punjab India

ISBN: (数字)9789819984794

ISBN: (纸本)9789819984787;9789819984794

The fundamental applications of handwritten digit classification are in the fields of optical reorganization of digits, bank check processing, recognizing zip codes on mail for postal, processing bank check amounts, and numeric entries in forms filled up by hand. For processing these types of tasks, different kinds of learning algorithms are used. A comparative study on performance analysis was done for convolutional neural network, LeNet-5, and YOLOv7. Publically available MNIST, DIDA, and MNIST MIX handwritten digit dataset were used in experimental work. The objective of this study is to find the best algorithm which can give an acceptable accuracy. To implement the model, this paper uses a deep neural network CNN and its architecture LeNet-5 and YOLOv7 which have become a potent tool for image categorization problems in recent years. This paper demonstrates the efficacy of deep learning approaches for effective and precise digit recognition, which can be expanded to numerous real-world applications needing accurate and dependable recognition of digits written on paper. This research has achieved the highest accuracy of 99.38% for LeNet-5.

关键词： Handwritten digit recognition Convolutional neural networks LeNet-5 YOLOv7 MNIST

来源：评论

学校读者我要写书评

暂无评论

SoN: Selective Optimal Network for smartphone-based indoor localization in real-time

引用

EXPERT SYSTEMS WITH applications 2025年 272卷

作者： Lee, Kyungsu Lee, Haeyun Hwang, Jae Youn Jeonbuk Natl Univ Dept Comp Sci & Artificial Intelligence Jeonju 54896 South Korea Korea Univ Technol & Educ Sch Comp Sci & Engn Cheonan 31253 South Korea Daegu Gyeongbuk Inst Sci & Technol DGIST Dept Elect Engn & Comp Sci Interdisciplinary Studies Artificial Intelligence Daegu 42988 South Korea

Deep learning-based scene recognition algorithms have been developed for real-time application in indoor localization systems. However, owing to the slow calculation time resulting from the deep structure of convolutional neural networks, deep learning-based algorithms have limitations in the usage of real-time applications, despite their high accuracy in classification tasks. To significantly reduce the computation time of these algorithms and slightly improve their accuracy, we thus propose a path-selective deep learning network, denoted as Selective Optimal Network (SoN). The SoN selectively uses the depth-variable networks depending on anew indicator, denoted as the classification-complexity of a source image. The SoN reduces the prediction time by selecting optimal depth for the baseline networks corresponding to the input samples. The network was evaluated using two public datasets and two custom datasets for indoor localization and scene classification, respectively. The experimental results indicated that, compared to other deep learning models, the SoN exhibited improved accuracy and enhanced the processing speed by up to 78.59%. Additionally, the SoN was applied to a smartphone-based indoor positioning system in real-time. The results indicated that the SoN shows excellent performance for rapid and accurate classification in real-time applications of indoor localization systems.

关键词： Deep learning Semi-supervised learning Efficient learning Scene recognition Indoor localization

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：