检索结果-内蒙古大学图书馆

Modified U-Net with attention gate for enhanced automated brain tumor segmentation

Neural Computing and Applications 2025年第7期37卷 5521-5558页

作者： Saifullah, Shoffan Dreżewski, Rafal Yudhana, Anton Wielgosz, Maciej Caesarendra, Wahyu Faculty of Computer Science AGH University of Krakow Krakow30-059 Poland Department of Informatics Universitas Pembangunan Nasional Veteran Yogyakarta Yogyakarta55281 Indonesia Department of Electrical Engineering Universitas Ahmad Dahlan Yogyakarta55191 Indonesia Faculty of Computer Science Electronics and Telecommunications AGH University of Krakow Krakow30-059 Poland Faculty of Mechanical Engineering Opole University of Technology 76 Proszkowska St. Opole45-758 Poland

This study addresses the formidable challenges encountered in automated brain tumor segmentation, including the complexities of irregular shapes, ambiguous boundaries, and intensity variations across MRI modalities. Manual segmentation, plagued by subjectivity and time constraints, further exacerbates the problem. To address these issues, we propose a modified U-Net architecture with an integrated attention gate. The proposed model demonstrates high performance, with notable Dice Similarity Coefficient (DSC) and Jaccard Index (JI) values across various tumor classes, consistently exceeding 0.93 and 0.87, respectively. Incorporating Contrast-Limited Adaptive Histogram Equalization and Histogram Equalization improves segmentation accuracy, particularly in cases of Meningioma. Comparative analyses against established models reveal a DSC of 0.9521 and a JI of 0.9093, underscoring the superiority of our method. Validation in the BraTS 2021 dataset underscores the robustness of the method, achieving high DSC and JI scores in four MRI modalities, with the T2 modality demonstrating the highest performance (DSC: 0.9216, JI: 0.8556). While acknowledging these achievements, we recognize challenges related to dataset specificity and computational intensity associated with the attention gate. Future research efforts should address these issues to improve the generalizability and applicability of the method in real-world scenarios. In addition to presenting a novel automated brain tumor segmentation method, this study contributes comprehensive result values and comparative analyses with previous research, providing valuable insights into the evolving landscape of medical image analysis. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Neural Network Pruning for Lightweight Metal Corrosion Image Segmentation Models

引用

IEEE Access 2025年 13卷 71673-71687页

作者： Yu, Vincent F. Santiyuda, Gemilang Lin, Shih-Wei Pasaribu, Udjianna S. Afrianti, Yuli Sri National Taiwan University of Science and Technology Department of Industrial Management Taipei106335 Taiwan Institut Bisnis dan Teknologi Indonesia Faculty of Technology and Informatics Bali Denpasar80225 Indonesia Chang Gung University Department of Information Management Taoyuan333 Taiwan Ming Chi University of Technology Department of Industrial Engineering and Management Taoyuan333 Taiwan Keelung Chang Gung Memorial Hospital Department of Emergency Medicine Keelung203 Taiwan Bandung Institute of Technology Statistics Research Group Faculty of Mathematics and Natural Sciences Bandung40132 Indonesia

Metal corrosion detection is essential for ensuring structural safety and minimizing economic losses. While deep learning (DL)-based image segmentation has improved corrosion detection accuracy and efficiency, its high computational demands hinder deployment on resource-constrained edge devices. This study investigates lightweight DL models for corrosion segmentation by applying structured pruning to reduce computational costs while maintaining accuracy. We evaluate five segmentation architectures (U-Net, U-Net++, FPN, LinkNet, and MA-Net) and three pruning strategies (linear, automated gradual pruning, and movement pruning) on two corrosion image datasets (NEA and SSCS). Detailed trade-off analysis between model size, computational cost (MAC), and segmentation performance (IoU) reveals that pruning up to 90% sparsity leads to a ≤ 10% IoU drop on SSCS and ≤ 5% on NEA, demonstrating that significant compression is possible with minimal accuracy loss. However, some architectures (e.g., LinkNet) and pruning strategies (e.g., movement pruning) show significant performance deterioration, suggesting that pruning effectiveness varies across models. These findings provide insights into optimizing corrosion segmentation models for efficient deployment on edge devices, balancing accuracy and resource constraints. © 2013 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A Multi-Scale Deep Learning Framework Combining MobileViT-ECA and LSTM for Accurate ECG Analysis

引用

IEEE Access 2025年 13卷 85473-85492页

作者： Ba Mahel, Abduljabbar S. Al-Gaashani, Mehdhar S. A. M. Alkanhel, Reem Ibrahim Hassan, Dina S. M. Muthanna, Mohammed Saleh Ali Muthanna, Ammar Aziz, Ahmed University of Electronic Science and Technology of China School of Life Science and Technology Chengdu610054 China University of Electronic Science and Technology of China School of Resources and Environment Chengdu610056 China Princess Nourah bint Abdulrahman University College of Computer and Information Sciences Department of Information Technology P.O. Box 84428 Riyadh11671 Saudi Arabia Tashkent State University of Economics Department of International Business Management Tashkent Uzbekistan RUDN University Department of Applied Probability and Informatics Peoples’Friendship University of Russia 6 Miklukho-Maklaya St Moscow117198 Russia Faculty of Computer and Artificial Intelligence Benha University Department of Computer Science Egypt Central Asian University Engineering school Tashkent Uzbekistan

Electrocardiogram (ECG) analysis is crucial for diagnosing cardiovascular diseases (CVD), especially atrial fibrillation (AF), a prevalent cardiac rhythm abnormality. However, the variability and complexity of ECG signals make AF classification challenging, highlighting the need for more accurate and reliable methods. This paper introduces a novel deep learning (DL) architecture designed to enhance the processing, feature extraction, and analysis of ECG signals. The proposed model utilizes a hybrid framework that combines standard and dilated convolutional networks, advanced attention mechanisms, and temporal sequence learning to address the complexities of ECG data. A parallel architecture integrates a MobileViT block for efficient spatial feature extraction and an Efficient Channel Attention (ECA) module to refine feature representations. Simultaneously, a Long Short-Term Memory (LSTM) network captures temporal dependencies in the data. The concatenation of the outputs from both the MobileViT-ECA block and the LSTM network allows for the extraction of both local and global features. Fully connected layers, along with dropout regularization, ensure robust performance and effective classification. We analyzed ECG signals of three different lengths (1, 2, and 3 seconds) to investigate how segment length affects model performance. Additionally, we conducted various classification scenarios and an ablation study to simulate real-world conditions and identify key components of the architecture. Our experimental findings show that the model attains high accuracy in ECG classification and AF identification, with average metrics including accuracy of 87.80%, recall of 87.80%, F1-score of 87.45%, and specificity of 95.66%. The proposed model outperforms existing methods on the same AF dataset, demonstrating its superior performance. This method accurately classifies ECG signals and detects AF, highlighting its potential for clinical application. The results help move forwar

关键词： Electrocardiography

来源：评论

学校读者我要写书评

暂无评论

Physics-Inspired Generative Models in Medical Imaging

引用

Annual review of biomedical engineering 2025年第1期27卷 499-525页

作者： Hein, Dennis Bozorgpour, Afshin Merhof, Dorit Wang, Ge Department of Physics KTH Royal Institute of Technology Stockholm Sweden Karolinska University Hospital Stockholm Sweden Faculty of Informatics and Data Science University of Regensburg Regensburg Germany email: dorit.merhof@ur.de Faculty of Informatics and Data Science University of Regensburg Regensburg Germany email: Department of Biomedical Engineering School of Engineering Biomedical Imaging Center Center for Biotechnology and Interdisciplinary Studies Rensselaer Polytechnic Institute Troy New York USA email:

Physics-inspired generative models (GMs), in particular diffusion models and Poisson flow models, enhance Bayesian methods and promise great utility in medical imaging. This review examines the transformative role of such generative methods. First, a variety of physics-inspired GMs, including denoising diffusion probabilistic models, score-based diffusion models, and Poisson flow generative models (including PFGM++), are revisited, with an emphasis on their accuracy, robustness and acceleration. Then, major applications of physics-inspired GMs in medical imaging are presented, comprising image reconstruction, image generation, and image analysis. Finally, future research directions are brainstormed, including unification of physics-inspired GMs, integration with vision-language models, and potential novel applications of GMs. Since the development of generative methods has been rapid, it is hoped that this review will give peers and learners a timely snapshot of this new family of physics-driven GMs and help capitalize their enormous potential for medical imaging.

关键词： Bayesian theorem consistency model diffusion model image analysis image reconstruction image/data synthesis medical imaging PFGM++ physics-inspired generative models Poisson flow generative model

来源：评论

学校读者我要写书评

暂无评论

Clustering Single-Cell RNA-seq Data: Impact of Data Binarization on Algorithmic Performance

Clustering Single-Cell RNA-seq Data: Impact of Data Binariza...

引用

18th International Joint Conference on Biomedical engineering Systems and Technologies, BIOSTEC 2025

作者： Widzisz, Karolina Kania, Mateusz Zyla, Joanna Polański, Andrzej Department of Computer Graphics Vision and Digital Systems Silesian University of Technology Akademicka 16 Gliwice Poland Department of Applied Informatics Silesian University of Technology Akademicka 16 Gliwice Poland Department of Data Science and Engineering Silesian University of Technology Akademicka 16 Gliwice Poland

The primary objective of this study was to test the hypothesis that the binary information on the presence or absence of gene expression can sufficiently capture the inherent heterogeneity within single-cell RNA se quencing (scRNA-seq) data. This hypothesis posits that even without detailed expression levels, valuable insights about cellular diversity can be obtained. Utilizing this method can be particularly advantageous when analyzing large datasets, a common scenario in the field of scRNA-seq. In this paper, we evaluate clustering performance and cluster separability of a variety of model-based algorithms and distance-based methods to an alyze both expression level data and threshold-encoded binarized data. We examined the performance of the Bernoulli-mixture model and Gaussian-mixture model. These were compared against traditional clustering techniques such as hierarchical clustering, K-means, and the Louvain algorithm on a range of scRNA-seq datasets. Our findings reveal that mixture models exhibit a lower dependence on the specific dataset compared to distance-based methods. Mixture models, particularly, demonstrate greater efficacy in accurately estimat ing the number of clusters present within the data. Among analyzed algorithms, the Bernoulli-mixture model stands out, outperforming distance-based approaches in several key aspects. Binary data, presence/absence of gene expression, seem to be indeed adequate to capture the heterogeneity of scRNA-seq data when clus tering with methods specifically designed for binary datasets. The implications of this finding are significant, as it opens up new possibilities for simplifying data analysis in scRNA-seq studies without compromising the accuracy of the results. © 2025 by SCITEPRESS– science and technology Publications, Lda.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

Exploring Children’s Strategies in Response to Robot’s Advice During a Group Task with iCub and Nao 16th

Exploring Children’s Strategies in Response to Robot’s A...

引用

16th International Conference on Social Robotics, ICSR + AI 2024

作者： Pusceddu, Giulia Sangineto, Mariapia Cocchella, Francesca Bogliolo, Michela Belgiovine, Giulia Lastrico, Linda Casadio, Maura Rea, Francesco Gena, Cristina Sciutti, Alessandra Robotics Brain and Cognitive Science Department Italian Institute of Technology Genoa Italy Department of Informatics Bioengineering Robotics and Systems Engineering University of Genoa Genoa Italy Department of Computer Science University of Turin Turin Italy Cognitive Architecture for Collaborative Technologies Unit Italian Institute of Technology Genoa Italy Scuola di Robotica Genoa Italy

ISBN: (纸本)9789819635184

This study investigates children’s trust in two humanoid robots, Nao and iCub, through a cooperative game designed to elicit spontaneous behaviors and group dynamics. We investigate whether participants change their choices after hearing advice from a robot, considering rounds where the advice is correct or incorrect, with the robot apologizing for its mistakes. Results reveal that, in most cases, participants prefer not to change their moves after the robot’s advice. Additionally, after the robots made mistakes, participants are less likely to actively follow their advice and more likely to reject it. No significant differences in strategies among the iCub and Nao samples are evidenced. Furthermore, we examine the influence of group dynamics, identifying "Proactive Players" who consistently initiated moves. A significant association between the strategies of this player and their teammates is found, suggesting potential influence. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based Framework for Enhancing Cybersecurity

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2025年第3期19卷 170-190页

作者： Al-Nawashi, Malek M. Al-Hazaimeh, Obaida M. Tahat, Nedal M. Gharaibeh, Nasr Abu-Ain, Waleed A. Abu-Ain, Tarik Al-Huson University College Al-Balqa Applied University Irbid Jordan Faculty of Information Technology Department of Information Security and Cybersecurity Philadelphia University Amman Jordan Faculty of Science The Hashemite University Zarqa Jordan College of Science and Computer Engineering Taibah University Yanbu Saudi Arabia College of Computing and Informatics Saudi Electronic University Riyadh Saudi Arabia

The detection of cyberattacks has been increasingly emphasized in recent years, focusing on both infrastructure and people. Conventional security measures such as intrusion detection, firewalls, and encryption are insufficient in protecting cyber systems against growing and changing threats. In order to address this problem, scholars have explored reinforcement learning (i.e., RL) as a potential solution for intricate cybersecurity decision-making difficulties. Nevertheless, the use of RL faces several obstacles, including dynamic attack scenarios, insufficient training data, and the challenge of replicating real-world complexities. This study presents a novel framework that uses deep reinforcement learning (i.e., DRL) to simulate harmful cyberattacks and improve cybersecurity. This study presents an agent-based framework that is capable of ongoing learning and adaptation in a dynamic network security environment. The agent determines the optimal course of action by considering the current state of the network and the rewards it receives for its decisions. The CIC-IDS-2018 database, constructed using Python 3.7 programming, was used. The conducted studies yielded outstanding results, with a detection accuracy of 98.82% achieved for the CIC-IDS-2018 database in cyber-attack classification. © 2025 by the authors of this article. Published under CC-BY.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Progressive Semantic-Visual Alignment and Refinement for Vision-Language Tracking

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第5期35卷 4271-4286页

作者： Liang, Yanjie Wu, Qiangqiang Cheng, Lin Xia, Changqun Li, Jia Peng Cheng Laboratory Shenzhen518000 China City University of Hong Kong Department of Computer Science Hong Kong Xiamen University Fujian Key Laboratory of Sensing and Computing for Smart City School of Informatics Xiamen361005 China Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China

In recent years, vision-language tracking has drawn emerging attention in the tracking field. The critical challenge for the task is to fuse semantic representations of language information and visual representations of vision information. For this purpose, several vision-language tracking methods perform early or late fusion to fuse visual and semantic features. However, these methods cannot take full advantage of the transformer architecture to excavate useful cross-modal context at various levels. To this end, we propose a new progressive joint vision-language transformer (PJVLT) to progressively align and refine visual embedding with semantic embedding for vision-language tracking. Specifically, to align visual signals with semantic signals, we propose to insert a semantic-aware instance encoder layer (SAIEL) into each intermediate layer of transformer encoder to perform progressive alignment of visual and semantic features. Furthermore, to highlight the multi-modal feature channels and patches corresponding to target objects, we propose a unified channel communication patch interaction layer (CCPIL), which is plugged into each intermediate layer of transformer encoder to progressively activate target-aware channels and patches of aligned multi-modal features for fine-grained tracking. In general, by progressively aligning and refining visual features with semantic features in the transformer encoder, our PJVLT can adaptively excavate well-aligned vision-language context at coarse-to-fine levels, therefore highlighting target objects at various levels for more discriminative tracking. Experiments on several tracking datasets show that the proposed PJVLT can achieve favorable performance in comparison with both conventional trackers and other vision-language trackers. © 1991-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Pose Estimation of Spacecraft Using Dual Transformers and Efficient Bayesian Hyperparameter Optimization

引用

International Journal of Advanced Computer science and Applications 2025年第4期16卷 629-644页

作者： Raja, N. Kannaiya Ramesh, Janjhyam Venkata Naga El-Ebiary, Yousef A. Baker Muniyandy, Elangovan Reddy, N. Konda Kumar, Vanipenta Ravi Devarasetty, Prasad School of Computing Science and Engineering VIT Bhopal University Madhya Pradesh Bhopal466114 India Department of CSE Graphic Era Hill University Dehradun248002 India Department of CSE Graphic Era Deemed To Be University Uttarakhand Dehradun248002 India Faculty of Informatics and Computing UniSZA University Malaysia Department of Biosciences Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai602 105 India Applied Science Research Center Applied Science Private University Amman Jordan Department of Engineering Mathematics K L University Greenfields Guntur Dist Andhra Pradesh Vaddeswaram522302 India Department of Mathematics Annamacharya University New Boyanapalli Rajampet India Department of Computer Science and Engineering DVR & Dr HS MIC College of Technology Andhra Pradesh Kanchikacherla India

Spacecraft pose estimation is an essential contribution to facilitating central space mission activities like autonomous navigation, rendezvous, docking, and on-orbit servicing. Nonetheless, methods like Convolutional Neural Networks (CNNs), Simultaneous Localization and Mapping (SLAM), and Particle Filtering suffer significant drawbacks when implemented in space. Such techniques tend to have high computational complexity, low domain generalization capacity for varied or unknown conditions (domain generalization problem), and accuracy loss with noise from the space environment causes such as fluctuating lighting, sensor limitations, and background interference. In order to overcome these challenges, this study suggests a new solution through the combination of a Dual-Channel Transformer Network with Bayesian Optimization methods. The innovation is at the center with the utilization of EfficientNet, augmented with squeeze-and-excitation attention modules, to extract feature-rich representations without sacrificing computational efficiency. The dual-channel architecture dissects satellite pose estimation into two dedicated streams—translational data prediction and orientation estimation via quaternion-based activation functions for rotational precision. Activation maps are transformed into transformer-compatible sequences via 1×1 convolutions, allowing successful learning in the transformer's encoder-decoder system. To maximize model performance, Bayesian Optimization with Gaussian Process Regression and the Upper Confidence Bound (UCB) acquisition function makes the optimal hyperparameter selection with fewer queries, conserving time and resources. This entire framework, used here in Python and verified with the SLAB Satellite Pose Estimation Challenge dataset, had an outstanding Mean IOU of 0.9610, reflecting higher accuracy compared to standard models. In total, this research sets a new standard for spacecraft pose estimation, by marrying the versatility of deep le

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Insights into acoustic beams in nonlinear, weakly dispersive and dissipative media

引用

Optical and Quantum Electronics 2025年第5期57卷 1-18页

作者： Khater, Mostafa M. A. Wang, Heng Alfalqi, Suleman H. Vokhmintsev, Aleksander Owyed, Saud School of Information Engineering Yango University Fuzhou350015 China Engineering School of Digital Technologies Yugra State University Khanty-Mansiysk628012 Russia Department of Basic Science The Higher Institute for Engineering & Technology Al-Obour Cairo10587 Egypt School of Medical Informatics and Engineering Xuzhou Medical University Jiangsu Province Xuzhou221004 China Department of Mathematics Faculty of Science and Arts in Mahayil Asir King Khalid University Abha Saudi Arabia Institute of Information Technology Chelyabinsk State University Chelyabinsk Russia Department of Mathematics College of Sciences University of Bisha Bisha61922 Saudi Arabia

This study examines the (2+1)–dimensional dissipative Zabolotskaya–Khokhlov equation, a fundamental nonlinear wave model with broad applications in diverse physical domains, such as acoustic wave propagation, nonlinear optics, and fluid dynamics. This equation exhibits profound connections with other nonlinear evolution equations, particularly in describing wave interactions in dispersive and dissipative media, highlighting its significance in characterizing complex wave phenomena. The principal objective of this work is to derive both closed-form and numerical solutions to gain deeper insight into the equation’s underlying dynamics. To this end, we employ the Khater II and the modified Kudryashov approaches-two systematic mathematical techniques for obtaining explicit solutions. Additionally, He’s variational iteration method is implemented as a numerical scheme to evaluate the reliability and precision of the derived exact solutions. A comparative assessment of the analytical and numerical results underscores the accuracy of the obtained solutions and the effectiveness of the employed methods in handling highly nonlinear wave systems. This investigation provides novel perspectives on dissipative wave dynamics and illustrates the advantages of integrating exact and numerical methodologies. The findings hold substantial implications for applications in fluid mechanics, nonlinear optics, and acoustic wave theory, fostering a more comprehensive understanding of nonlinear dissipative structures. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Nonlinear optics

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：