检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Heidari, Moein Kazerouni, Amirhossein Soltany, Milad Azad, Reza Aghdam, Ehsan Khodapanah Cohen-Adad, Julien Merhof, Dorit School of Electrical Engineering Iran University of Science and Technology Tehran Iran Institute of Imaging and Computer Vision RWTH Aachen University Aachen Germany Department of Electrical Engineering Shahid Beheshti University Tehran Iran Functional Neuroimaging Unit CRIUGM University of Montreal Canada NeuroPoly Lab Institute of Biomedical Engineering Polytechnique Montreal Canada MILA Quebec AI Institute Montreal Canada Faculty of Informatics and Data Science University of Regensburg Regensburg Germany Fraunhofer Institute for Digital Medicine MEVIS Bremen Germany

Convolutional neural networks (CNNs) have been the consensus for medical image segmentation tasks. However, they suffer from the limitation in modeling long-range dependencies and spatial correlations due to the nature of convolution operation. Although transformers were first developed to address this issue, they fail to capture low-level features. In contrast, it is demonstrated that both local and global features are crucial for dense prediction, such as segmenting in challenging contexts. In this paper, we propose HiFormer, a novel method that efficiently bridges a CNN and a transformer for medical image segmentation. Specifically, we design two multi-scale feature representations using the seminal Swin Transformer module and a CNN-based encoder. To secure a fine fusion of global and local features obtained from the two aforementioned representations, we propose a Double-Level Fusion (DLF) module in the skip connection of the encoder-decoder structure. Extensive experiments on various medical image segmentation datasets demonstrate the effectiveness of HiFormer over other CNN-based, transformer-based, and hybrid methods in terms of computational complexity, quantitative and qualitative results. Our code is publicly available at GitHub. © 2022, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Scribble2Label: Scribble-Supervised Cell Segmentation via Self-Generating Pseudo-Labels with Consistency

arXiv

引用

arXiv 2020年

作者： Lee, Hyeonsoo Jeong, Won-Ki Ulsan National Institute of Science and Technology School of Electrical and Computer Engineering Korea Republic of Korea University College of Informatics Department of Computer Science and Engineering Korea Republic of

Segmentation is a fundamental process in microscopic cell image analysis. With the advent of recent advances in deep learning, more accurate and high-throughput cell segmentation has become feasible. However, most existing deep learning-based cell segmentation algorithms require fully annotated ground-truth cell labels, which are time-consuming and labor-intensive to generate. In this paper, we introduce Scribble2Label, a novel weakly-supervised cell segmentation framework that exploits only a handful of scribble annotations without full segmentation labels. The core idea is to combine pseudo-labeling and label filtering to generate reliable labels from weak supervision. For this, we leverage the consistency of predictions by iteratively averaging the predictions to improve pseudo labels. We demonstrate the performance of Scribble2Label by comparing it to several state-of-the-art cell segmentation methods with various cell image modalities, including bright-field, fluorescence, and electron microscopy. We also show that our method performs robustly across different levels of scribble details, which confirms that only a few scribble annotations are required in real-use cases. Copyright © 2020, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

CVM-Cervix: A Hybrid Cervical Pap-Smear Image Classification Framework Using CNN, Visual Transformer and Multilayer Perceptron

arXiv

引用

arXiv 2022年

作者： Liu, Wanli Li, Chen Xu, Ning Jiang, Tao Rahaman, Md Mamunur Sun, Hongzan Wu, Xiangchen Hu, Weiming Chen, Haoyuan Sun, Changhao Yao, Yudong Grzegorzek, Marcin Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information Engineering Northeastern University Shenyang China Liaoning Petrochemical University Fushun China School of Control Engineering Chengdu University of Information Technology Chengdu China Shengjing Hospital China Medical University Shenyang China Suzhou Ruiqian Technology Company Ltd. Suzhou China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China Department of Electrical and Computer Engineering Stevens Institute of Technology Hoboken United States Institute of Medical Informatics University of Luebeck Luebeck Germany

Cervical cancer is the seventh most common cancer among all the cancers worldwide and the fourth most common cancer among women. Cervical cytopathology image classification is an important method to diagnose cervical cancer. Manual screening of cytopathology images is time-consuming and error-prone. The emergence of the automatic computer-aided diagnosis system solves this problem. This paper proposes a framework called CVM-Cervix based on deep learning to perform cervical cell classification tasks. It can analyze pap slides quickly and accurately. CVM-Cervix first proposes a Convolutional Neural Network module and a Visual Transformer module for local and global feature extraction respectively, then a Multilayer Perceptron module is designed to fuse the local and global features for the final classification. Experimental results show the effectiveness and potential of the proposed CVM-Cervix in the field of cervical Pap smear image classification. In addition, according to the practical needs of clinical work, we perform a lightweight post-processing to compress the model. Copyright © 2022, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Adaptive AGV fleet management in a dynamically changing production environment

引用

Procedia Manufacturing 2021年 54卷 148-153页

作者： Júlia Bergmann Dávid Gyulai József Váncza EPIC Center of Excellence in Production Informatics and Control Institute for Computer Science and Control (SZTAKI) Eötvös Loránd Research Network (ELKH) Budapest Hungary Doctoral School of Informatics Eötvos Lóránd University Budapest Hungary Department of Manufacturing Science and Engineering Budapest University of Technology and Economics Budapest Hungary

In the era of smart manufacturing, autonomous mobile robots have become affordable for numerous companies, although the fleet management remains a challenging problem. A novel approach is proposed, supporting the solution of vehicle assignment problem. The method relies on adaptive workstation clustering that considers not only complex environment layout, but also the main characteristics of the material flow. The technique combines network analytical and optimization tools with a greedy algorithm of refinement. The implementation is presented, and the impact of clustering techniques on selected performance metrics are analyzed within a series of experiments, taken from an industrial case study.

关键词： internal logistics AGV network modularity MIQP

来源：评论

学校读者我要写书评

暂无评论

Experimental Analysis for Position Estimation using Trilateration and RSSI in Industry 4.0

Experimental Analysis for Position Estimation using Trilater...

引用

International Conference on System Modeling & Advancement in Research Trends (SMART)

作者： Robin Singh Chouhan Anand Singh Rajawat S.B. Goyal Pradeep Bedi Neagu Bogdan Constantin Maria Simona Raboaca Chaman Verma Shri Vaishnav Institute of Information Technology Shri Vaishnav Vidyapeeth Vishwavidyalaya Indore India School of Computer Science and engineering Sandip University Nashik India Faculty of Information Technology City University Petaling Jaya Malaysia Galgotais University Greater Noida Department of Power Engineering “Gheorghe Asachi” Technical University of Iasi Iasi ICSI Energy Department National Research and Development Institute for Cryogenics and Isotopic Technologies Ramnicu Valcea Romania Faculty of Informatics University of Eötvös Loránd Budapest Hungary

ISBN: (纸本)9781665487351

With the introduction of industry 4.0, the role of robots especially autonomous bots has increased exponentially. The next thing in order to improve the navigation for these bots is the need for a proper indoor navigation system. The paper proposes experimental analysis for estimating the position using trilateration. The experiment includes three wifi nodes operating at 2.4GHz working as wifi beacons. The paper provides an efficient and cost-effective solution to estimate the approximate position of the node in terms of coordinates. The paper also includes a working mobile application to showcase the node's position in real-time in the form of a 2d map.

关键词： Visualization Time-frequency analysis Coordinate measuring machines Service robots Extraterrestrial measurements Chatbots Mathematical models

来源：评论

学校读者我要写书评

暂无评论

Using Machine Learning for Industry 5.0 Efficiency Prediction Based on Security and Proposing Models to Enhance Efficiency

Using Machine Learning for Industry 5.0 Efficiency Predictio...

引用

International Conference on System Modeling & Advancement in Research Trends (SMART)

作者： Piyush Pant Anand Singh Rajawat S.B. Goyal Deepmala Singh Neagu Bogdan Constantin Maria Simona Raboaca Chaman Verma School of Computer Sciences and Engineering Sandip University Nashik India School of Computer Science and engineering Sandip University Nashik India Faculty of Information Technology City University Petaling Jaya Malaysia Symbiosis Centre of Management Studies (SCMS) Nagpur Symbiosis International (Deemed University)(SIU) India Department of Power Engineering “Gheorghe Asachi” Technical University of Iasi Iasi ICSI Energy Department National Research and Development Institute for Cryogenics and Isotopic Technologies Ramnicu Valcea Romania Faculty of Informatics University of Eötvös Loránd Budapest Hungary

ISBN: (纸本)9781665487351

Machine learning, with its huge untapped potential, is being researched all over the world to develop truly intelligent systems. Its applications are not enclosed in just one domain but in almost everything, from prediction models, recommender systems, and anomaly detection to automation and teaching a computer how to fly a helicopter. In this research, Multivariate Linear regression of supervised machine learning is studied to predict the efficiency of Industry 5.0, however, the efficiency of the model would be dependent on many factors and components such as security protocols and models, Industrial IoT - performance, connectivity, reachability, availability and many more. These factors and components would be categorized as the features of the algorithm which would be assigned weight ‘w’ and bias ‘b’. To improve the efficiency of the model, these components could be changed and updated in order to enhance the overall model. Previous research papers discussed the integration of “hot” technologies like 5G, Blockchain, AI, and IIoT in the industry 5.0 model, but this research is presented as their future work as it proposes to determine the efficiency of the model based on the features provided so that ultimate and optimal model could be determined. Later it proposes security and IIoT models that could improve the overall Industry 5.0. Quorum blockchain is proposed by the research in order to implement the ultimate security in the Industry 5.0.

关键词： Industries Protocols Machine learning algorithms Computational modeling Machine learning Predictive models Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Correction to: A novel driver emotion recognition system based on deep ensemble classification

引用

Complex & Intelligent Systems 2024年第3期10卷 4657-4657页

作者： Zaman, Khalid Zhaoyun, Sun Shah, Babar Hussain, Tariq Shah, Sayyed Mudassar Ali, Farman Khan, Umer Sadiq Information Engineering School Chang’an University Xi’an China College of Technological Innovation Zayed University Dubai UAE School of Computer Science and Technology Zhejiang Gongshang University Hangzhou China Department of Computer Science and Engineering School of Convergence College of Computing and Informatics Sungkyunkwan University Seoul South Korea School of Computer and Information Science Hubei Engineering University Xiaogan Hubei China Institute for AI Industrial Technology Research Hubei Engineering University Xiaogan Hubei China

来源：评论

学校读者我要写书评

暂无评论

Federated learning in network traffic classification: Taxonomy of implementation, application, and impact on sixth-generation wireless networks

引用

engineering Applications of Artificial Intelligence 2025年 158卷

作者： Azizi Ariffin Firdaus Afifi Faiz Zaki Hazim Hanif Nor Badrul Anuar Department of Computer System and Technology Faculty of Computer Science and Information Technology Universiti Malaya 50603 Kuala Lumpur Malaysia School of Computing Sciences College of Computing Informatics and Mathematics Universiti Teknologi MARA 40450 Shah Alam Selangor Malaysia Faculty of Computer Science and Mathematics Universiti Malaysia Terengganu Kuala Nerus Terengganu 21030 Malaysia Department of Software Engineering Faculty of Computer Science and Information Technology Universiti Malaya 50603 Kuala Lumpur Malaysia Centre of Research for Cyber Security and Network (CSNET) Faculty of Computer Science and Information Technology Universiti Malaya 50603 Kuala Lumpur Malaysia Institute of Informatics & Computing in Energy Universiti Tenaga Nasional Putrajaya Kampus 43000 Kajang Selangor Malaysia

Objectives Network traffic classification (NTC) is crucial for network management. However, the surge in Internet traffic poses scalability and privacy issues. Researchers are turning to federated learning (FL) to tackle these issues. Despite the importance of FL, there is lack of literature that comprehensively reviews its implementation and application within NTC and its impact on Sixth-Generation Wireless (6G) networks. Current surveys cover the technical aspects of NTC without fully addressing the integration of FL and its broader implications. This study aims to review the technical implementation of FL in NTC and its application to various network-related areas, including 6G. Methods This study presents a taxonomy for FL implementation in NTC, considering aspects such as learning and aggregation approaches, topology, and client operations. It examines the limitations of these elements and their effects on performance, efficiency, scalability, and their impact on 6G. This study outlines a taxonomy for FL applications, focusing on privacy preservation, scalable classification, and shared security intelligence. Novelty The proposed taxonomy provides insights into research landscape and highlights its limitations. The analysis of the impact of FL-based NTC on 6G provides insight into its integration and implementation challenges. This study discusses open issues and advocates for future research directions in FL for NTC, including 6G. Findings The study identifies areas needing improvement such as privacy, addressing security, single-point-of-failure, hardware limitations, delays and heterogeneity concerns. The findings of this paper show that an optimal implementation approach is essential to cater for heterogeneity and real-time requirements of the network environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Assistive Technical Communication of Montenegrin eServices: a Case Study

Assistive Technical Communication of Montenegrin eServices: ...

引用

International Scientific-Professional Conference on Information technology (IT)

作者： Aniko Simon Luka Laković Pavle Kovačević Peter A. Kara Ivana Ognjanović Ramo Šendelj Christoph Reich Milovan Roganović John Mantas Laszlo Bokor Sigma Technology 1093 Budapest Hungary Faculty for Information Systems and Technologies University of Donja Gorica 81000 Podgorica Montenegro Budapest University of Technology and Economics 1111 Budapest Hungary Department of Networked Systems and Services Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics 1111 Budapest Hungary Department of Computer Science School of Computer Science and Mathematics Faculty of Science Engineering and Computing Wireless Multimedia and Networking Research Group Kingston University London KT1 2EE UK Humanistic Studies University of Donja Gorica 81000 Podgorica Montenegro Institute of Data Science Cloud Computing and IT Security Furtwangen University 78120 Furtwangen Germany Clinic for Neurology Clinical Centre of Montenegro 81000 Podgorica Montenegro Faculty of Nursing School of Health Sciences National and Kapodistrian University of Athens 11527 Goudi Greece

With the advancement of information technology in the recent decades, digital and online services have become essential components of everyday life in Europe. Montenegro is no different in this regard. However, as digital literacy in the country is still in a developing phase in comparison with most countries of the EU, a higher portion of its citizens may rely on assistive technical communication. In this paper, we provide a case study on the assistive technical communication of Montenegrin eServices. The work addresses the sectors of online banking, healthcare services, higher education, national administrative services, and utilities. Our findings highlight the diversity in terms of implemented assistive technical communication, and distinguish usage contexts on the level of adequacy. Yet as the functionalities of Montenegrin eServices are expected to gradually expand in the upcoming years, assistive technical communication must aim to handle the higher extents of service complexity.

关键词： Online banking Education Europe Medical services Complexity theory Information technology

来源：评论

学校读者我要写书评

暂无评论

Video Forgery Detection for Surveillance Cameras: A Review

arXiv

引用

arXiv 2025年

作者： Tayfor, Noor B. Rashid, Tarik A. Qader, Shko M. Hassan, Bryar A. Abdalla, Mohammed H. Majidpour, Jafar Ahmed, Aram M. Ali, Hussein M. Aladdin, Aso M. Abdullah, Abdulhady A. Shamsaldin, Ahmed S. Sidqi, Haval M. Salih, Abdulrahman Yaseen, Zaher M. Ameen, Azad A. Nayak, Janmenjoy Hamza, Mahmood Yashar Department of Information Technology Kurdistan Technical Institute Sulaimani Iraq Computer Science and Engineering Department University of Kurdistan Hewlêr Erbil Iraq Department of Computer Science Kurdistan Technical Institute Sulaimani Iraq Department of Computer Science University of Raparin Rania Iraq Artificial Intelligence and Innovation Centre University of Kurdistan Hewler Erbil Iraq Department of Software Engineering College of Engineering and Computational Science Charmo University Chamchamal46023 Iraq Department of Database College of Informatics Sulaimani Polytechnic University Sulaimani Iraq Northumbria University London United Kingdom Civil and Environmental Engineering Department King Fahd University of Petroleum and Minerals Dhah-ran31261 Saudi Arabia Department of Computer Science Maharaja Sriram Chandra Bhanja Deo University Odisha Baripada India Department of Computer Engineering Tishk International University Erbil Iraq

The widespread availability of video recording through smartphones and digital devices has made video-based evidence more accessible than ever. Surveillance footage plays a crucial role in security, law enforcement, and judicial processes. However, with the rise of advanced video editing tools, tampering with digital recordings has become increasingly easy, raising concerns about their authenticity. Ensuring the integrity of surveillance videos is essential, as manipulated footage can lead to misinformation and undermine judicial decisions. This paper provides a comprehensive review of existing forensic techniques used to detect video forgery, focusing on their effectiveness in verifying the authenticity of surveillance recordings. Various methods, including compression-based analysis, frame duplication detection, and machine learning-based approaches, are explored. The findings highlight the growing necessity for more robust forensic techniques to counteract evolving forgery methods. Strengthening video forensic capabilities will ensure that surveillance recordings remain credible and admissible as legal evidence. © 2025, CC BY.

关键词： CCD cameras

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：