检索结果-内蒙古大学图书馆

3rd International Conference on Emerging Electronics and Automation, E2A 2023

作者： Dhar, Prasenjit Singh, Mohit Kumar Ahmed, Tanveer Suganya, Devi K. Medical Imaging Laboratory Computer Science and Engineering Department National Institute of Technology Silchar Assam India

ISBN: (纸本)9789819768011

Red blood cells (RBCs) also known as erythrocytes are an essential component of the human body that play several important roles. RBCs transport oxygen (O2) from the lungs to the body’s tissues, remove carbon dioxide (CO2), regulate pH balance, support the immune system, and provide diagnostic information. The abnormal shapes of RBCs (signified as poikilocytosis) are unable to carry O2 and CO2, leading to decreased O2 delivery to the tissues and an increased workload on the heart and lungs. Anemia, thalassemia, and other blood-related illnesses affect the body for insufficient replenishment (oxygen, protein, nutrients). Hematologists take more time to examine RBC shapes manually using a microscope. In this study ensemble deep learning technique was introduced to examine poikilocytosis abnormality accurately and efficiently. The proposed ensemble model outperforms state-of-the-art approaches with an excellent accuracy and F1-score of 98.77%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

More Accurate Constraints for Self-Supervised Learning in Remote Sensing Images based Object Detection

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 12303-12314页

作者： Zheng, Shangdong Wu, Zebin Xu, Yang Liu, Qian Wei, Zhihui Nanjing University of Posts and Telecommunications School of Computer Science Nanjing210023 China Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China Nanjing University of Science and Technology Jiangsu Key Laboratory of Spectral Imaging & Intelligent Sense China Anhui Agricultural University School of Information and Artificial Intelligence Hefei230036 China

Self-supervised learning (SSL) automatically generates internal labels by exploring the potential auxiliary task of the network itself, and trains the same model through these annotations to learn the latent representation of the data, which greatly improves the accuracy of object detection in remote sensing images (RSIs). However, most existing methods suffer from guaranteeing the quality of the generated SSL pseudo annotations, and the constructed auxiliary tasks are not detectionoriented, which is difficult to enhance the feature representations that are beneficial for object detection. In this paper, we focus on generating more accurate constraints by excavating the intercorrelation between fully and weakly-supervised learning to improve the performance of object detection in RSIs. Initially, weakly-supervised learning (WSL) assigns the pseudo instancelevel annotations for the high-scoring positive bags to model the detector, which can be regarded as a weakened version of the region proposal network (RPN). Fortunately, RPN can be constrained by the ground truth of bounding boxes in fullysupervised learning (FSL), and the high-quality supervisions it provides are unavailable in any WSL methods. Moreover, we construct a proposal generation module (PGM), which further filters the unreliable bounding boxes, predicted by RPN, to supplement high-quality constraints into the ground truth and SS generated candidate boxes to supervise the optimization of WSL branch. By constructing an interactive learning paradigm of WSL and FSL, the former has more accurate constraints to learn an efficient auxiliary task, while the latter enjoys a richer representation form of data provided by WSL, which is undoubtedly a win-win process. Finally, we cascade the losses of WSL and FSL to further explore the intrinsic correlation between them by sharing the same feature extraction network. Experimental comparisons on DOTA and DIOR datasets demonstrate that our method achieves superior per

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Delay-Sensitive Task Offloading: A Multi-agent Deep Reinforcement Learning Algorithm for MEC-Based AIoT Systems 24th

Enhancing Delay-Sensitive Task Offloading: A Multi-agent Dee...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Tang, Fengjie Xu, Jia Liu, Xiao Yao, Aiting Fang, Mingyan Li, Xuejun Anhui Provincial International Joint Research Center for Advanced Technology in Medical Imaging School of Computer Science and Technology Anhui University Hefei China School of Information Technology Deakin University Geelong Australia

ISBN: (纸本)9789819615414

Artificial Intelligence of Things (AIoT) systems are widely utilized in various domains such as smart logistics and smart health. In AIoT systems, computational tasks earmarked for offloading by IoT devices often have different task priorities and heterogeneous resource requirements. However, these factors will affect the QoS of the solution and the task response time. Therefore, motivated by a typical smart warehouse system, a Multi-access Edge Computing (MEC) based distributed task offloading framework is proposed. Afterward, a delay-sensitive mixed-integer programming model is defined to address the imbalanced utilization of computing resources between edge and cloud servers during the offloading process. Finally, based on the attention mechanism, a Priority-Driven Multi-Agent Deep Reinforcement Learning algorithm (PDMA-DRL) is proposed to fulfill real-time resource requirements while reducing the task response time. The PDMA-DRL algorithm consists of two agents, and each agent corresponds to a sub-problem. Comprehensive experimental results demonstrate that our proposed PDMA-DRL algorithm can outperform representative existing methods in generating delay-sensitive task offloading plans and effectively reducing the task response time. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Fast alternating minimization algorithm for coded aperture snapshot spectral imaging based on sparsity and deep image priors

引用

Applied Optics 2025年第14期64卷 4121-4131页

作者： Zhao, Qile Zhao, Xianhong Ma, Xu Chen, Xudong Arce, Gonzalo R. Key Laboratory of Photoelectronic Imaging Technology System of Ministry of Education of China School of Optics and Photonics Beijing Institute of Technology Beijing100081 China Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore Department of Electrical and Computer Engineering University of Delaware NewarkDE19716 United States

Coded aperture snapshot spectral imaging is a computational imaging technique used to reconstruct three-dimensional hyperspectral images from one or several two-dimensional projection measurements. However, fewer projection measurements or more spectral channels lead to a severely ill-posed problem, in which case regularization methods have to be applied. In order to significantly improve the accuracy of reconstruction, this paper proposes a fast alternating minimization algorithm based on the sparsity and deep image priors of natural images. By integrating deep image prior into the principle of compressive sensing reconstruction, the proposed algorithm can achieve state-of-the-art results without any training dataset. Extensive experiments show that the Fama-SDIP method significantly outperforms prevailing methods on simulation and real HSI datasets. © 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved. © 2025 Optica Publishing Group (formerly OSA). All rights reserved.

关键词： Computational imaging

来源：评论

学校读者我要写书评

暂无评论

Observer Performance and Eye-Tracking Variations as a Function of AI Output Format

Observer Performance and Eye-Tracking Variations as a Functi...

引用

Medical imaging 2025: Image Perception, Observer Performance, and technology Assessment

作者： Krupinski, Elizabeth A. van Assen, Marly De Cecco, Carlo N. Mullins, Siobhan Gabriel, Roy M. Zandehshahvar, Mohammadreza Kittisut, Nattakorn Adibi, Ali Baird, Grayson L. Department of Radiology & Imaging Sciences Emory University United States School of Electrical & Computer Engineering Georgia Institute of Technology United States Department of Diagnostic Imaging Brown University United States

ISBN: (纸本)9781510685963

Artificial intelligence (AI) tools are designed to improve the efficacy and efficiency of data analysis and interpretation by the human decision maker. However, we know little about the optimal ways to present AI output to providers. This study used radiology image interpretation with AI-based decision support to explore the impact of different forms of AI output on reader performance. Readers included 5 experienced radiologists and 3 radiology residents reporting on a series of COVID chest x-ray images. Four different forms (1 word summarizing diagnoses (normal, mild, moderate, severe), probability graph, heatmap, heatmap plus probability graph) of AI outputs (plus no AI feedback) were evaluated. Results reveal that most decisions regarding presence/absence of COVID without AI were correct and overall remained unchanged across all types of AI outputs. Fewer than 1% of decisions that were changed as a function of seeing the AI output were negative (true positive to false negative or true negative to false positive) regarding presence/absence of COVID;and about 1% were positive (false negative to true positive, false positive to true negative). More complex output formats (e.g., heat map plus a probability graph) tend to increase reading time and the number of scans between the clinical image and the AI outputs as revealed through eye-tracking. The key to the success of AI tools in medical imaging will be to incorporate the human into the overall process to optimize and synergize the human-computer dyad, since at least for the foreseeable future, the human is and will be the ultimate decision maker. Our results demonstrate that the form of the AI output is important as it can impact clinical decision making and efficiency. © 2025 SPIE.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

A Graph Structure-Feature Learning Network for Diagnosing Alzheimer’s Disease Based on Multi-modal Brain Biometric Feature 18th

A Graph Structure-Feature Learning Network for Diagnosing A...

引用

18th Chinese Conference on Biometric Recognition, CCBR 2024

作者： Shang, Dongxu Wang, Huabin Zhang, Mengxin Peng, Yuhang Ye, Xingjian Wang, Zilin Anhui Provincial International Joint Research Center for Advanced Technology in Medical Imaging School of Computer Science and Technology Anhui University Anhui Hefei China Stony Brook Institute at Anhui University Anhui Hefei China

ISBN: (纸本)9789819610709

Alzheimer’s Disease (AD) is a neurodegenerative disease, typically identified and diagnosed through brain biometric feature. However, certain common brain biometric feature exist among patients in different stages of AD, which result in incorrect edges within the graph structure. To address above issues, this paper proposes a Graph Structure-Feature Learning Network (GSFLN) model. The model simultaneously learns a graph structure that appropriately represents the relationships among patients and selects the significant pathogenic brain biometric feature of patients. Firstly, a Graph Convolutional Clustering (GCC) module is designed to capture the relationships between non-image data of patients. Secondly, a Pathogenic Feature Selection (PFS) module is designed to capture the relationships between image data of patients and select the pathogenic brain biometric feature. Thirdly, an Unsupervised Predictive Clustering (UPC) module is designed to control the above two modules. Our proposed model has surpassed the current state-of-the-art level in diagnostic performance on both the NACC and Tadpole datasets. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Alzheimer’s Disease brain biometric feature Feature Selection Graph Convolutional Network Graph Structure Learning

来源：评论

学校读者我要写书评

暂无评论

NETrack: A Lightweight Attention-Based Network for Real-Time Pose Tracking of Nasal Endoscope Based on Endoscopic Image 21st

NETrack: A Lightweight Attention-Based Network for Real-Tim...

引用

21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024

作者： Shao, Liangjing Chen, Benshuang Chen, Xinrong Academy for Engineering and Technology Fudan University Shanghai200438 China Shanghai Key Laboratory for Medical Imaging Computing and Computer Assisted Intervention Fudan University Shanghai200032 China

ISBN: (纸本)9789819601271

Vision-based real-time pose tracking of endoscope is significant for navigation and automation of endoscopy. In this work, a deep learning-based framework is proposed for vision-based real-time pose tracking of nasal endoscope based on endoscopic images. Specifically, an attention-based module is introduced into the feature encoder to extract and integrate multi-dimensional and multi-scale information. Furthermore, a novel pose encoder is proposed to extract more complicated representation from the feature map for pose vector prediction. The proposed method is compared with state-of-the-art methods on the dataset, which consists of endoscopic videos and endoscope poses obtaining by an optical tracking system. The experimental results demonstrate that the proposed network achieves better performance than state-of-the-art works for real-time nasal endoscope pose estimation. The average tracking error of our method is 5.78 mm, while the relative translation error and rotation error are respectively 0.48 mm and 0.22 degree on average. In addition, the average inference speed of our network is 46 fps, which achieves the real-time requirement. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Endoscopy

来源：评论

学校读者我要写书评

暂无评论

An Ensemble-Based Approach for Smart Detection of Heart Diseases Symptoms 3rd

An Ensemble-Based Approach for Smart Detection of Heart Dise...

引用

3rd International Conference on Computing and Communication Networks, ICCCN 2023

作者： Balaji, Prasanalakshmi Bansal, Shivam Banerjee, Subham Mishra, Sushruta Sridevi, R. Department of Computer Science College of Computer Science King Khalid University Abha Saudi Arabia Kalinga Institute of Industrial Technology Deemed to be University Bhubaneswar India Medical Imaging Research Lab Research Associate SCRA Chennai India

ISBN: (纸本)9789819726707

Machine learning is widely used in health care. Heart disease is the world's most dangerous chronic life-threatening disease, and with heart disease rates on the rise, we need to set up a system that can detect and prevent heart disease symptoms early on. Various and many algorithms in machine learning are being used to predict the early symptoms of coronary heart disease. But the majority of those suffer from low accuracy rates. In this particular study, an ensemble-based approach is utilized to train the model using the dataset on heart diseases obtained from the UCI repository. The model captures various heart disease data from different sensors and then uses an ensemble-based random forest algorithm to accurately detect the symptoms pertaining to heart disease risks in patients. The model’s accuracy is quite satisfactory at 93.8% with the use of 40 decision trees in random forest. Thus, the proposed model can serve as a reliable tool for medical experts in detecting heart disease symptoms with greater accuracy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Healthcare Heart disease Internet of Things Machine learning Random forest

来源：评论

学校读者我要写书评

暂无评论

A Dual-Defense Self-balancing Framework Against Bilateral Model Attacks in Federated Learning 24th

A Dual-Defense Self-balancing Framework Against Bilateral Mo...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Wu, Xiang Yao, Aiting Pal, Shantanu Jiang, Frank Li, Xuejun Xu, Jia Dong, Chengzu Chen, Xuefei Zhang, Xiuyi Liu, Xiao Anhui Provincial International Joint Research Center for Advanced Technology in Medical Imaging School of Computer Science and Technology Anhui University Anhui China Deakin University Melbourne Australia School of Data Science Lingnan University Hong Kong

ISBN: (纸本)9789819615247

With the rapid expansion of Artificial Intelligence (AI) services, smart devices generate a large amount of user data at the edge network, which urgently needs to be protected while effectively extracting information. Federated learning (FL) is an important technology for handling dispersed data and strict privacy requirements in this context. However, the security threats caused by model inversion attacks and poisoning attacks can affect the mutual trust between the client and server. Yet, for these two types of attacks, the existing defense mechanisms are contradictory in terms of whether the model parameters are publicly disclosed. In addition, the data distribution of the clients is imbalanced which will increase the bias of model, reducing its practicality. To address this issue, this study proposes a dual defense self-balanced federated learning (DDSFL) framework, aiming to introduce a novel lightweight defense mechanism during the model parameter aggregation stage, combating these two types of attacks simultaneously by applying differential privacy and adjusting learning rates. In addition, this method also integrates a middleware-based reordering algorithm to enhance the robustness of the framework. Experimental results show that DDSFL effectively improves the ability to resist imbalanced data, forged data, and malicious behavior, significantly enhancing the generalization performance and security of the FL system. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Domain Aware Multi-task Pretraining of 3D Swin Transformer for T1-Weighted Brain MRI 17th

Domain Aware Multi-task Pretraining of 3D Swin Transformer ...

引用

17th Asian Conference on computer Vision, ACCV 2024

作者： Kim, Jonghun Kim, Mansu Park, Hyunjin Department of Electrical and Computer Engineering Sungkyunkwan University Suwon Korea Republic of Center for Neuroscience Imaging Research Institute for Basic Science Suwon Korea Republic of AI Graduate School Gwangju Institute of Science and Technology Gwangju Korea Republic of

ISBN: (纸本)9789819609000

The scarcity of annotated medical images is a major bottleneck in developing learning models for medical image analysis. Hence, recent studies have focused on pretrained models with fewer annotation requirements that can be fine-tuned for various downstream tasks. However, existing approaches are mainly 3D adaptions of 2D approaches ill-suited for 3D medical imaging data. Motivated by this gap, we propose novel domain-aware multi-task learning tasks to pretrain a 3D Swin Transformer for brain magnetic resonance imaging (MRI). Our method considers the domain knowledge in brain MRI by incorporating brain anatomy and morphology as well as standard pretext tasks adapted for 3D imaging in a contrastive learning setting. We pretrain our model using large-scale brain MRI data of 13,687 samples spanning several large-scale databases. Our method outperforms existing supervised and self-supervised methods in three downstream tasks of Alzheimer’s disease classification, Parkinson’s disease classification, and age prediction tasks. The ablation study of the proposed pretext tasks shows the effectiveness of our pretext tasks. Our code is available at ***/jongdory/DAMT. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Neurodegenerative diseases

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：