检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第6期6卷 1472-1487页

作者： Liu, Zhenhong Wang, Xingce Wu, Zhongke Zhu, Yi-Cheng Frangi, Alejandro F. Beijing Normal University School of Artificial Intelligence Beijing China Peking Union Medical College Hospital Department of Neurology Beijing China The University of Manchester Christabel Pankhurst Institute Division of Informatics Imaging and Data Sciences School of Health Sciences Department of Computer Science School of Engineering United Kingdom Department of Cardiovascular Sciences Department of Electrical Engineering Leuven Belgium Alan Turing Institute London United Kingdom

Magnetic resonance imaging (MRI) is often limited by noise and low-resolution (LR), which can impact the precision of the diagnosis and treatment of patients. LR images and mixed noise (e.g., Gaussian noise, Rician noise, and Impulse noise) are inherent in MR images, and current approaches typically address image super-resolution (SR) reconstruction and denoising separately, resulting in a discrepancy between the actual MRI data distribution and the reconstructed images. This research introduces a new algorithm SRDSNF, the stochastic normalizing flow-based MR image SR and denoising model, which tackles SR and denoising simultaneously through a stochastic normalizing flow. Our method integrates the encoded information of the input image as a conditional variable in each reverse step of the stochastic normalizing flow, ensuring a consistent representation of the spatial distribution between the reconstructed image and the original data. Additionally, we incorporate range-null space decomposition and subsequence sampling techniques to increase the consistency between the original and constructed data and accelerate model generation. To assess the efficacy of our approach, we conducted experiments on the BrainWeb and NFBS datasets, which include simultaneous SR and denoising, standalone denoising, and standalone SR tasks. The results of the experiments illustrate that our method achieves superior SR and denoising performance with fewer sampling steps, closely approximating the ground truths. Furthermore, our results surpass those of existing methods in various tasks, showing improvement of up to 4.64 dB in PSNR and 13.8% in SSIM achieved by our SRDSNF model was contextualized against state-of-the-art approaches such as AMIR, SwinIR, and InstructIR. These methods typically report PSNR improvements ranging from 0.5 to 2 dB and SSIM increases of 3-6%, underscoring the potential clinical value of our methodology. © 2020 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Efficient Canine Vision: Accurate Dog Breed Classification with EfficientNet 2

Efficient Canine Vision: Accurate Dog Breed Classification w...

引用

2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Godwin James, T. Prabahar Poonguzhali, C. Selvakumaran, S. Malathi, G. Kaliappan, S. Venu, Nookala Department of Computer Science and Engineering Sri Sairam Institute of Technology India Department of Electronics and Communication Engineering S.A. Engineering College Chennai India Department of Artificial Intelligence and Data Science Rajalakshmi Institute of Technology Chennai India Department of Electrical and Electronics Engineering Kumaraguru College of Technology Saravanampatti Coimbatore India Madhya Pradesh Gwalior India

ISBN: (纸本)9798350384277

Understanding and classifying dog breeds is a fascinating yet challenging task due to the vast diversity within the canine species. In this project, we present a novel approach to dog breed classification utilizing the state-of-the-art Efficient Net architecture. Leveraging a comprehensive dataset comprising 133 distinct breeds, our method aims to accurately identify and categorize each breed with high precision. Efficient Net's innovative scaling method allows us to strike a balance between model complexity and computational efficiency, enabling robust classification performance even with limited computational resources. Through meticulous preprocessing techniques and data augmentation strategies, we enhance the model's ability to generalize across diverse breed characteristics, minimizing the risk of overfitting. Our experimental results demonstrate the efficacy of the proposed approach, achieving impressive classification accuracy on the challenging dog breed dataset. We conduct extensive evaluations and comparisons with existing methodologies, showcasing the superiority of Efficient Net in handling complex classification tasks with large-scale image datasets. Furthermore, we provide insights into the interpretability of the model's predictions, shedding light on the learned representations and key features contributing to breed classification. This project not only advances the state-of-the-art in dog breed classification but also contributes to our understanding of deep learning techniques applied to animal recognition tasks. In sum up, our work highlights the potential of leveraging advanced neural network architectures like Efficient Net for comprehensive and accurate dog breed classification, paving the way for applications in veterinary medicine, pet care, and animal welfare. © 2024 IEEE.

关键词： Veterinary medicine

来源：评论

学校读者我要写书评

暂无评论

An Integrated Fusion Framework for Ensemble Learning Leveraging Gradient-Boosting and Fuzzy Rule-Based Models

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第11期5卷 5771-5785页

作者： Li, Jinbo Liu, Peng Chen, Long Pedrycz, Witold Ding, Weiping Nantong University School of Artificial Intelligence and Computer Science Nantong226019 China China Unicom Research Institute Beijing100048 China Henan University International Business School Zhengzhou47500 China University of Macau Department of Computer and Information Science 999078 China University of Alberta Department of Electrical and Computer Engineering EdmontonAB T6R 2V4 Canada City University of Macau Faculty of Data Science 999078 China

The integration of different learning paradigms has long been a focus of machine learning research, aimed at overcoming the inherent limitations of individual methods. Fuzzy rule-based models excel in interpretability and have seen widespread application across diverse fields. However, they face challenges such as complex design specifications and scalability issues with large datasets. The fusion of different techniques and strategies, particularly gradient boosting, with fuzzy rule-based models offers a robust solution to these challenges. This article proposes an integrated fusion framework that merges the strengths of both paradigms to enhance model performance and interpretability. At each iteration, a fuzzy rule-based model is constructed and controlled by a dynamic factor to optimize its contribution to the overall ensemble. This control factor serves multiple purposes: it prevents model dominance, encourages diversity, acts as a regularization parameter, and provides a mechanism for dynamic tuning based on model performance, thus mitigating the risk of overfitting. Additionally, the framework incorporates a sample-based correction mechanism that allows for adaptive adjustments based on feedback from a validation set. Experimental results substantiate the efficacy of the presented gradient-boosting framework for fuzzy rule-based models, demonstrating performance enhancement, especially in terms of mitigating overfitting and complexity typically associated with many rules. By leveraging an optimal factor to govern the contribution of each model, the framework improves performance, maintains interpretability, and simplifies the maintenance and update of the models. © 2024 IEEE.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond

引用

Journal of Machine Learning Research 2023年第1期24卷 1-11页

作者： Hedström, Anna Weber, Leander Bareeva, Dilyara Krakowczyk, Daniel Motzkus, Franz Samek, Wojciech Lapuschkin, Sebastian Höhne, Marina M.-C. Understandable Machine Intelligence Lab TU Berlin Berlin10587 Germany Department of Electrical Engineering and Computer Science TU Berlin Berlin10587 Germany Department of Artificial Intelligence Fraunhofer Heinrich-Hertz-Institute Berlin10587 Germany Department of Computer Science University of Potsdam Potsdam14476 Germany BIFOLD – Berlin Institute for the Foundations of Learning and Data Berlin10587 Germany

The evaluation of explanation methods is a research topic that has not yet been explored deeply, however, since explainability is supposed to strengthen trust in artificial intelligence, it is necessary to systematically review and compare explanation methods in order to confirm their correctness. Until now, no tool with focus on XAI evaluation exists that exhaustively and speedily allows researchers to evaluate the performance of explanations of neural network predictions. To increase transparency and reproducibility in the field, we therefore built Quantus—a comprehensive, evaluation toolkit in Python that includes a growing, wellorganised collection of evaluation metrics and tutorials for evaluating explainable methods. The toolkit has been thoroughly tested and is available under an open-source license on PyPi (or on https://***/understandable-machine-intelligence-lab/Quantus/). © 2023 Anna Hedström, Leander Weber, Dilyara Bareeva, Daniel Krakowczyk, Franz Motzkus, Wojciech Samek, Sebastian Lapuschkin, and Marina M.-C. Höhne.

关键词： Open systems

来源：评论

学校读者我要写书评

暂无评论

Cyber Twin Technology for AI-Driven Real-Time Software Security in IoT Ecosystems 4

Cyber Twin Technology for AI-Driven Real-Time Software Secur...

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Sunkara, Krishna Chaitanya Dhasmana, Gulshan Ravi, K.S. Nayana Yadav, M. Desai, Ishan Shankar, Rajmani Oracle Cloud Engineering Data Center NC United States Graphic Era Deemed to be University Department of Computer Science & Engineering Dehradun India Vidyavardhaka College of Engineering Department of Mechanical Engineering Mysuru India Aj Institute of Engineering and Technology Department of Computer Science and Engineering Mangalore India Parul institute of Engineering and Technology Parul University Faculty of Engineering and Technology Department of Electrical Engineering Gujarat India Faculty of Law Pune India

ISBN: (纸本)9798350352931

As Internet of Things (IoT) ecosystems grow more complex, ensuring real-time security has become a major challenge. Traditional security approaches are insufficient for handling dynamic and interconnected IoT networks, which are increasingly targeted by sophisticated cyber-attacks. To address these issues, new methodologies that combine real-time monitoring and adaptive security mechanisms are needed. Cyber Twin technology, an innovative extension of digital twin technology, presents a promising solution by creating AI-driven digital replicas of IoT devices and software systems for continuous security monitoring and management. This paper introduces a Cyber Twin Technology Framework for AI-driven real-time software security in IoT ecosystems. The framework employs advanced AI models, including Convolutional Neural Networks (CNNs) for anomaly detection and Generative Adversarial Networks (GANs) for synthetic data generation to simulate potential attack scenarios. A dynamic reinforcement learning module is integrated to optimize threat response strategies based on evolving threat patterns. By creating real-time digital replicas of IoT components, the Cyber Twin framework continuously monitors device behaviors, identifies anomalies, and autonomously initiates mitigation actions. The system is evaluated in a simulated IoT environment with over 500 interconnected devices. Experimental results demonstrate that the Cyber Twin framework achieved a 99.2% detection accuracy in identifying cyber threats, with a false positive rate of 1.3%. The dynamic response module reduced incident response time by 35% compared to traditional methods, enhancing the system's ability to neutralize potential threats in real-time. The use of GAN-based synthetic data also enabled proactive defense strategies, reducing attack success rates by 40% during testing. The Cyber Twin Technology Framework provides a robust solution for real-time software security in complex IoT ecosystems. By leveraging A

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Graph-based deep learning models in the prediction of early-stage Alzheimers 46

Graph-based deep learning models in the prediction of early-...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Thapaliya, Bishal Wu, Zundong Sapkota, Ram Ray, Bhaskar Suresh, Pranav Ghimire, Santosh Calhoun, Vince Liu, Jingyu Georgia State University Department of Computer Science Atlanta United States Tri-Institutional Center for Translational Research in Neuroimaging and Data Science United States Georgia Institute of Technology School of Electrical and Computer Engineering Atlanta United States Tribhuvan University Department of Applied Sciences and Chemical Engineering Nepal

ISBN: (纸本)9798350371499

Alzheimer's disease is the most common age-related problem and progresses in different stages, from cognitively normal to early mild cognitive impairment, and severe dementia. This study investigates the predictive potential of resting-state functional magnetic resonance imaging (rs-fMRI) and its derived functional connectivity (FC) in understanding Alzheimer's progression. Leveraging deep learning and graph-based models, we introduce two key contributions: 1) a comparative analysis of rs-fMRI time points and FC for Alzheimer's prediction. 2) an innovative graph transformer variant incorporating self-clustering for enhanced prediction accuracy. Experiments on the Alzheimer's Disease Neuroimaging Initiative dataset with 830 subjects reveal two notable conclusions. Firstly, rs-fMRI time points offer limited utility compared to functional network connectivity for transformer-based models, even when considering temporal information. Secondly, a clustering-based attention module proves effective for classifying brain networks in predicting Alzheimer's disease progression, providing valuable insights for future research and clinical applications. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

FastPlane: A Fully Convolutional Network for Real-time 3D Plane Segmentation

FastPlane: A Fully Convolutional Network for Real-time 3D Pl...

引用

2024 IEEE International Conference on Consumer Electronics, ICCE 2024

作者： Zhang, Haijun Ren, Qingji Dong, Li Tsang, Kim Fung Harbin Institute of Technology Shenzhen China Department of Computer Science Shenzhen China Shenzhen Technology University The College of Big Data and Internet Shenzhen China School of Electrical and Computer Engineering Nanfang College Guangzhou Guangzhou China

ISBN: (纸本)9798350324136

3D plane segmentation is a challenging computer vision task that involves the detection of planar regions in a scene and the prediction of their spatial position. Recent methods have addressed this problem as a multi-task learning problem in which convolutional neural networks with separate branches predict the plane segmentation mask and the dense depth maps, or plane parameters. However, existing methods often rely on a multi-stage object detection framework for plane segmentation, resulting in slow inference speeds that hinder real-time applications. To address this issue, we propose FastPlane, a real-time 3D plane segmentation network based on a fully convolutional structure. FastPlane comprises a shared backbone, a fully convolutional plane segmentation network, and a lightweight depth estimation network. Given a single image as input, FastPlane outputs both the plane segmentation mask and dense depth maps. Extensive experiments on public datasets demonstrate the effectiveness and efficiency of FastPlane, outperforming existing methods in terms of plane segmentation and depth estimation metrics. Notably, FastPlane achieves an impressive inference speed of 45.0 FPS, making it suitable for real-time applications in robotics, augmented reality, and virtual reality. © 2024 IEEE.

关键词： 3D plane segmentation depth estimation multitask learning scene reconstructing

来源：评论

学校读者我要写书评

暂无评论

Hybrid Blockchain and IoT Driven Framework for Supply Chain Optimization by Enhancing Transparency, Efficiency and Cost Reduction 3

Hybrid Blockchain and IoT Driven Framework for Supply Chain ...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Pradeep Kumar, S. Basha, C.H. Hussaian Prasath, C. Arun Amirthayogam, G. Lathif, Syed Ismail Abdul Leelavathi, R. Rajalakshmi Engineering College Computer Science Design Department Thandalam Chennai602105 India Sr University Department of Electrical and Electronics Engineering Warangal506371 India Mahendra Engineering College Department of Ece Namakkal637503 India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology School of Computing Department of Computer Science and Engineering Chennai600062 India Srm Institute of Science and Technology Department of Data Science and Business Systems Chennai603203 India Velalar College of Engineering and Technology Department of Biomedical Engineering Erode638012 India

ISBN: (纸本)9798331509675

Blockchain technology represents a modern supply chain management revolution which fixes operational challenges while providing enhanced transparency at reduced costs. The research develops HB-SCOF (Hybrid Blockchain-Enabled Supply Chain Optimization Framework) which combines blockchain self-verification databases with automatic smart contracts to maintain continuous supply chain observation and evaluate data credibility. The framework integrates tamper-proof transaction tracking mechanisms with unified supply chain network connectivity for securing data transmission as a trust delivery method through unbreakable shared databases. The retail-industry case study demonstrated a 25% decrease in expenses stemming from agency elimination alongside enhanced flow management and better stock distribution. The system demonstrates its effectiveness through assessments of key performance indicators including transaction speed and data accuracy together with business cost efficiency. This part looks at implementation methods through training stakeholders in addition to transforming organizational policies which produce successful outcomes. Blockchain technology labs verify its capability to enhance supply chain management efficiency while showing realistic deployment methods. © 2025 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Self-Transriber: Few-Shot Lyrics Transcription With Self-Training 48

Self-Transriber: Few-Shot Lyrics Transcription With Self-Tra...

引用

48th IEEE International Conference on Acoustics, Speech and Signal processing, ICASSP 2023

作者： Gao, Xiaoxue Yue, Xianghu Li, Haizhou National University of Singapore Department of Electrical and Computer Engineering Singapore Shenzhen Research Institute of Big Data Shenzhen China The Chinese University of Hong Kong School of Data Science Shenzhen China

ISBN: (纸本)9781728163277

The current lyrics transcription approaches heavily rely on supervised learning with labeled data, but such data are scarce and manual labeling of singing is expensive. How to benefit from unlabeled data and alleviate limited data problem have not been explored for lyrics transcription. We propose the first semi-supervised lyrics transcription paradigm, Self-Transcriber, by leveraging on unlabeled data using selftraining with noisy student augmentation. We attempt to demonstrate the possibility of lyrics transcription with a few amount of labeled data. Self-Transcriber generates pseudo labels of the unlabeled singing using teacher model, and augments pseudo-labels to the labeled data for student model update with both self-training and supervised training losses. This work closes the gap between supervised and semi- supervised learning as well as opens doors for few-shot learning of lyrics transcription. Our experiments show that our approach using only 12.7 hours of labeled data achieves competitive performance compared with the supervised approaches trained on 149.1 hours of labeled data for lyrics transcription. © 2023 IEEE.

关键词： Lyrics transcription music information retrieval singing processing and self-training

来源：评论

学校读者我要写书评

暂无评论

Ultrasound Elasticity reconstruction with inaccurate forward model using integrated data-driven correction of data-fidelity gradient 21

Ultrasound Elasticity reconstruction with inaccurate forward...

引用

IS and T International Symposium on Electronic Imaging: 21st Computational Imaging, COIMG 2023

作者： Mohammadi, Narges Doyley, Marvin M. Cetin, Mujdat Department of Electrical and Computer Engineering University of Rochester RochesterNY United States Goergen Institute for Data Science University of Rochester RochesterNY United States

Ultrasound elasticity images which provide quantitative visualization of tissue stiffness are reconstructed based on solving an inverse problem. Classical model-based methods are usually formulated in terms of constrained optimization problems composed of a data-fidelity term and a regularization term. The data-fidelity term incorporates the physical forward model which arises from the governing equilibrium equation discretized by finite element methods (FEMs). In elastography, the physical forward model is directly governed by the measured displacement image which leads to an inaccurate forward model in the presence of an intermediate level of noise. To tackle this issue, in the first step, we utilize a statistical representation of the physical forward model which incorporates the noise statistics with a signal-dependent correlated noise model. Next, for compensating the inaccurate forward operator error, we introduce an explicit data-driven approach for correcting the data-fidelity gradient, which can be integrated with any regularization term. The constrained optimization problem is solved using the fixed-point gradient descent where the analytical gradient of the data-fidelity term is corrected using the nonlinear mapping of a deep neural network (DNN). Finally, the proposed approach is integrated with a data-driven regularizer based on REgularization by Denoising (RED) for incorporating the prior information about the underlying elasticity patterns. Our simulation and experimental results demonstrate the improved performance of the proposed approach in various scenarios. © 2023, Society for Imaging science and Technology.

关键词： Ultrasonics

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：