检索结果-内蒙古大学图书馆

17th Workshop of Hybrid Intelligent Systems, HIS 2024, 17th Workshop on Intelligent Learning Environments, WILE 2024 and 6th Workshop on New Trends in Computational Intelligence and applications, CIAPP 2024, held in conjunction with Mexican International Conference on artificial Intelligence, MICAI 2024

作者： Barradas-Palmeros, Jesús-Arnulfo López-Herrera, Carlos-Alberto Acosta-Mesa, Héctor-Gabriel Mezura-Montes, Efrén Artificial Intelligence Research Institute University of Veracruz Xalapa Mexico

ISBN: (纸本)9783031838811

neural Architecture Search (NAS) aims to automate the design process of Deep neural networks (DNN) without requiring profound domain knowledge. The Deep Genetic Algorithm (DeepGA) was proposed to find the architectures of Convolutional neural networks (CNNs) for image processing, and its applications have covered a variety of data domains. Nonetheless, one of the main impediments of NAS is its computational cost, which is produced by evaluating candidate architectures. This work proposes using two cost-reduction mechanisms applied to DeepGA: using memory to avoid repeated evaluations and reducing the number of epochs for training in a low-fidelity estimation scheme for evaluations. The results indicate that the execution time of the algorithm was extensively reduced without diminishing the accuracy performance of the resulting architecture. The previous derives in a more efficient NAS procedure. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Toward Intrinsic Adversarial Robustness Through Probabilistic Training

引用

IEEE TRANSACTIONS ON image processing 2023年 32卷 3862-3872页

作者： Dong, Junhao Yang, Lingxiao Wang, Yuan Xie, Xiaohua Lai, Jianhuang Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou 510006 Peoples R China Guangdong Prov Key Lab Informat Secur Technol Guangzhou 510006 Peoples R China Minist Educ Key Lab Machine Intelligence & Adv Comp Guangzhou 510006 Peoples R China

Modern deep neural networks have made numerous breakthroughs in real-world applications, yet they remain vulnerable to some imperceptible adversarial perturbations. These tailored perturbations can severely disrupt the inference of current deep learning-based methods and may induce potential security hazards to artificial intelligence applications. So far, adversarial training methods have achieved excellent robustness against various adversarial attacks by involving adversarial examples during the training stage. However, existing methods primarily rely on optimizing injective adversarial examples correspondingly generated from natural examples, ignoring potential adversaries in the adversarial domain. This optimization bias can induce the overfitting of the suboptimal decision boundary, which heavily jeopardizes adversarial robustness. To address this issue, we propose Adversarial Probabilistic Training (APT) to bridge the distribution gap between the natural and adversarial examples via modeling the latent adversarial distribution. Instead of tedious and costly adversary sampling to form the probabilistic domain, we estimate the adversarial distribution parameters in the feature level for efficiency. Moreover, we decouple the distribution alignment based on the adversarial probability model and the original adversarial example. We then devise a novel reweighting mechanism for the distribution alignment by considering the adversarial strength and the domain uncertainty. Extensive experiments demonstrate the superiority of our adversarial probabilistic training method against various types of adversarial attacks in different datasets and scenarios.

关键词： Deep neural networks adversarial perturbations adversarial training probabilistic model uncertainty

来源：评论

学校读者我要写书评

暂无评论

The Past, Present, and Future Role of artificial Intelligence in Ventilation/Perfusion Scintigraphy: A Systematic Review

引用

SEMINARS IN NUCLEAR MEDICINE 2023年第6期53卷 752-765页

作者： Jabbarpour, Amir Ghassel, Siraj Lang, Jochen Leung, Eugene Le Gal, Gr'egoire Klein, Ran Moulton, Eric Carleton Univ Dept Phys Ottawa ON Canada Univ Ottawa Elect Engn & Comp Sci Ottawa ON Canada Univ Ottawa Fac Med Div Nucl Med & Mol Imaging Ottawa ON Canada Univ Ottawa Fac Med Div Hematol Ottawa ON Canada Ottawa Hosp Dept Nucl Med & Mol Imaging Ottawa ON Canada Jubilant DraxImage Inc Kirkland PQ Canada Ottawa Hosp Dept Nucl Med & Mol Imaging POB 2321053 Carling Ave Ottawa ON K1Y 4E9 Canada

Ventilation-perfusion (V/Q) lung scans constitute one of the oldest nuclear medicine procedures, remain one of the few studies performed in the acute setting, and are amongst the few performed in the emergency setting. V/Q studies have witnessed a long fluctuation in adoption rates in parallel to continuous advances in image processing and computer vision techniques. This review provides an overview on the status of artificial intelligence (AI) in V/Q scintigraphy. To clearly assess the past, current, and future role of AI in V/Q scans, we conducted a systematic Ovid MEDLINE(R) literature search from 1946 to August 5, 2022 in addition to a manual search. The literature was reviewed and summarized in terms of methodologies and results for the various applications of AI to V/Q scans. The PRISMA guidelines were followed. Thirty-one publications fulfilled our search criteria and were grouped into two distinct categories: (1) disease diagnosis/detection (N = 22, 71.0%) and (2) cross modality image translation into V/Q images (N = 9, 29.0%). Studies on disease diagnosis and detection relied heavily on shallow artificial neural networks for acute pulmonary embolism (PE) diagnosis and were primarily published between the mid-1990s and early 2000s. Recent applications almost exclusively regard image translation tasks from CT to ventilation or perfusion images with modern algorithms, such as convolutional neural networks, and were published between 2019 and 2022. AI research in V/Q scintigraphy for acute PE diagnosis in the mid-90s to early 2000s yielded promising results but has since been largely neglected and thus have yet to benefit from today's state-of-the art machine-learning techniques, such as deep neural networks. Recently, the main application of AI for V/Q has shifted towards generating synthetic ventilation and perfusion images from CT. There is therefore considerable potential to expand and modernize the use of real V/Q studies with state-of-the-art deep learnin

关键词：

来源：评论

学校读者我要写书评

暂无评论

17th International Workshop on Design and Architecture for Signal and image processing, DASIP 2024

17th International Workshop on Design and Architecture for S...

引用

17th International Workshop on Design and Architecture for Signal and image processing, DASIP 2024

ISBN: (纸本)9783031628733

The proceedings contain 9 papers. The special focus in this conference is on Design and Architecture for Signal and image processing. The topics include: sEMG-Based Gesture Recognition with Spiking neural networks on Low-Power FPGA;A Highly Configurable Platform for Advanced PPG Analysis;preface;Standalone Nested Loop Acceleration on CGRAs for Signal processing applications;optimising Graph Representation for Hardware Implementation of Graph Convolutional networks for Event-Based Vision;Improving the Energy Efficiency of CNN Inference on FPGA Using Partial Reconfiguration;scratchy: A Class of Adaptable Architectures with Software-Managed Communication for Edge Streaming applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On the Analyses of Medical images Using Traditional Machine Learning Techniques and Convolutional neural networks

引用

ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING 2023年第5期30卷 3173-3233页

作者： Iqbal, Saeed Qureshi, Adnan N. Li, Jianqiang Mahmood, Tariq Univ Cent Punjab Fac Informat Technol & Comp Sci Dept Comp Sci Lahore 54000 Punjab Pakistan Beijing Univ Technol Fac Informat Technol Beijing 100124 Peoples R China Beijing Univ Technol Beijing Engn Res Ctr IoT Software & Syst Beijing 100124 Peoples R China Prince Sultan Univ Coll Comp & Informat Sci CCIS Artificial Intelligence & Data Analyt AIDA Lab Riyadh 11586 Saudi Arabia

Convolutional neural network (CNN) has shown dissuasive accomplishment on different areas especially Object Detection, Segmentation, Reconstruction (2D and 3D), Information Retrieval, Medical image Registration, Multi-lingual translation, Local language processing, Anomaly Detection on video and Speech Recognition. CNN is a special type of neural Network, which has compelling and effective learning ability to learn features at several steps during augmentation of the data. Recently, different interesting and inspiring ideas of Deep Learning (DL) such as different activation functions, hyperparameter optimization, regularization, momentum and loss functions has improved the performance, operation and execution of CNN Different internal architecture innovation of CNN and different representational style of CNN has significantly improved the performance. This survey focuses on internal taxonomy of deep learning, different models of vonvolutional neural network, especially depth and width of models and in addition CNN components, applications and current challenges of deep learning.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Complex-Valued Federated Learning with Differential Privacy and MRI applications 9th

Complex-Valued Federated Learning with Differential Privacy ...

引用

27th International Conference on Medical image Computing and Computer Assisted Intervention (MICCAI)

作者： Riess, Anneliese Ziller, Alexander Kolek, Stefan Rueckert, Daniel Schnabel, Julia Kaissis, Georgios Helmholtz Munich Inst Machine Learning Biomed Imaging Neuherberg Germany Tech Univ Munich Sch Computat Informat & Technol Munich Germany Helmholtz Munich Helmholtz AI Oberschleissheim Germany Tech Univ Munich Artificial Intelligence Healthcare & Med Munich Germany Ludwig Maximilians Univ Munchen Math Foundat AI Munich Germany Imperial Coll London Dept Comp London England Kings Coll London Sch Biomed Engn & Imaging Sci London England Tech Univ Munich Inst Diagnost & Intervent Radiol Munich Germany

ISBN: (纸本)9783031776090;9783031776106

Federated learning enhanced with Differential Privacy (DP) is a powerful privacy-preserving strategy to protect individuals sharing their sensitive data for processing in fields such as medicine and healthcare. Many medical applications, for example magnetic resonance imaging (MRI), rely on complex-valued signal processing techniques for data acquisition and analysis. However, the appropriate application of DP to complex-valued data is still underexplored. To address this issue, from the theoretical side, we introduce the complex-valued Gaussian mechanism, whose behaviour we characterise in terms of f-DP, (epsilon, delta)-DP and Renyi-DP. Moreover, we generalise the fundamental algorithm DP stochastic gradient descent to complex-valued neural networks and present novel complex-valued neural network primitives compatible with DP. Experimentally, we showcase a proof-of-concept by training federated complex-valued neural networks with DP on a real-world task (MRI pulse sequence classification in k-space), yielding excellent utility and privacy. Our results highlight the relevance of combining federated learning with robust privacy-preserving techniques in the MRI context.

关键词： Federated learning Differential Privacy Complex Numbers

来源：评论

学校读者我要写书评

暂无评论

image Super-Resolution With Content-Aware Feature processing

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on artificial Intelligence 2024年第1期5卷 179-191页

作者： Mehta, Nancy Murala, Subrahmanyam Indian Institute of Technology Ropar Department of Electrical Engineering Rupnagar140001 India

image super-resolution (SR) is currently a very active research topic with applications spanning from computer vision to videos and graphic industries. The top performers in SR field usually employ deep or wide convolutional neural networks (CNNs) to restore the lost textures from low-resolution images. However, most of these methods adopt pixel shuffle and deconvolution as their upsampling techniques and often generate conspicuous artifacts in the reconstructed image. In addition, the ongoing trend of directly portraying the degraded low-resolution image to a high-resolution image via complex deep CNNs improves the reconstruction performance, but at the cost of high computational complexity. In this article, we propose a multilevel bicubic upsampler network for reconstructing high-quality SR image with a restricted number of parameters. A novel content-aware feature difference (CAFD) block is presented to reform the network by focusing on contextual information. The proposed CAFD block consists of four multilevel attention blocks for a better extraction of low-level features at different scales. Furthermore, we design an innovative upsampling layer that consistently outperforms the traditional upsampling methods. These components collaboratively endow our proposed network with a great performance boost, helping it achieve state-of-the-art accuracy on five synthetic benchmark datasets, both qualitatively and quantitatively. In addition, a detailed ablation study has been accomplished to scrutinize the improvements obtained by different modules in the proposed method. © 2020 IEEE.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

FlowgateUNet: Dental CT image segmentation network based on FlowFormer and gated attention

引用

SIGNAL image AND VIDEO processing 2024年第2期18卷 1175-1182页

作者： Cao, Danhua Cai, Biao Liu, Mingzhe Chengdu Univ Technol Coll Comp Sci & Cyber Secur Chengdu 610059 Peoples R China Chengdu Univ Technol Coll Ind Technol Yibin 644000 Peoples R China Wenzhou Univ Technol Sch Data Sci & Artificial Intelligence Wenzhou 325035 Peoples R China

Segmentation of cone-beam computed tomography (CBCT) images plays an important role in clinical treatment as well as teaching. Traditional manual segmentation of dental CBCT images requires tools such as mimics and is time-consuming. With the development of deep learning, the U-shaped network, represented by UNet, has shown good results. Due to the significant improvement brought by various applications of Transformers to image tasks, more and more models try to combine attention mechanism with traditional convolutional neural networks. To further improve the performance of dental CBCT segmentation, this paper proposes an improved FlowgateUNet segmentation network, which uses the FlowFormer instead of Transformer in the encoder to achieve attention computation with nearly linear complexity. It also uses the feature map containing global information as the gating signal in the skip connections to further extract relevant features and fuses the results from multiple decoders as the output. Compared to TransUnet, the proposed FlowgateUnet model improved the Dice similarity coefficient (DSC) by 1% on the dental CBCT image dataset, by 0.7% on the dental microCT dataset, and by 2% on the Synapse dataset.

关键词： Medical image segmentation Dental CBCT Semantic segmentation Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Trans-IFFT-FGSM: a novel fast gradient sign method for adversarial attacks

引用

MULTIMEDIA TOOLS AND applications 2024年第29期83卷 72279-72299页

作者： Naseem, Muhammad Luqman Northeastern Univ Software Coll Shenyang 110169 Liaoning Peoples R China

Deep neural networks (DNNs) are popular in image processing but are vulnerable to adversarial attacks, which makes their deployment in security-sensitive systems risky. Adversarial attacks reduce the performance of DNNs by generating adversarial examples (AEs). In this paper, we propose a novel method called Trans-IFFT-FGSM (Transformer Inverse Finite Fourier Transform Fast Gradient Sign Method) to generate adversarial examples. Unlike others, we apply multiple steps, adding imperceptible perturbation and saving input noise information to create strong AEs, while emphasizing simplicity, efficiency, robustness through iterations, and analytical precision on specific models. We evaluate and compare perturbation generated by Trans-IFFT-FGSM and other attack methods, including FGSM, PGD, DeepFool, and C &W on imageNet and MNIST, and evaluation results suggest that Trans-IFFT-FGSM achieves a high attack success rate (ASR) and attack accuracy. In addition, we compare Trans-IFFT-FGSM and other attack methods under the existence of a defense method, which denoises the AEs generated by these methods, and the evaluation results also suggest Trans-IFFT-FGSM outperforms other methods.

关键词： artificial intelligence security Adversarial attack Adversarial examples Defense Perturbation

来源：评论

学校读者我要写书评

暂无评论

High-quality color image restoration from a disturbed graded-index imaging system by deep neural networks

引用

OPTICS EXPRESS 2023年第13期31卷 20616-20628页

作者： Hu, Xuanyu Duan, Zaipeng Yang, Yang Tan, Yehong Zhou, Ruiqi Xiao, Jiong Zeng, Jinwei Wang, Jian Huazhong Univ Sci & Technol Wuhan Natl Lab Optoelect Wuhan 430074 Hubei Peoples R China Huazhong Univ Sci & Technol Sch Opt & Elect Informat Wuhan 430074 Hubei Peoples R China Opt Valley Lab Wuhan 430074 Hubei Peoples R China Huazhong Univ Sci & Technol Shenzhen Inst Shenzhen 518000 Peoples R China Huazhong Univ Sci & Technol Natl Key Lab Sci & Technol Multispectral Informat Wuhan 430074 Hubei Peoples R China Huazhong Univ Sci & Technol Sch Artificial Intelligence & Automat Wuhan 430074 Hubei Peoples R China

Imaging transmission plays an important role in endoscopic clinical diagnosis involved in modern medical treatment. However, image distortion due to various reasons has been a major obstacle to state-of-art endoscopic development. Here, as a preliminary study we demonstrate ultra-efficient recovery of exemplary 2D color images transmitted by a disturbed graded-index (GRIN) imaging system through the deep neural networks (DNNs). Indeed, the GRIN imaging system can preserve analog images through the GRIN waveguides with high quality, while the DNNs serve as an efficient tool for imaging distortion correction. Combining GRIN imaging systems and DNNs can greatly reduce the training process and achieve ideal imaging transmission. We consider imaging distortion under different realistic conditions and use both pix2pix and U-net type DNNs to restore the images, indicating the suitable network in each condition. This method can automatically cleanse the distorted images with superior robustness and accuracy, which can potentially be used in minimally invasive medical applications. & COPY;2023 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

关键词： image metrics image processing image quality image transmission Imaging systems Medical image processing

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：