检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Luo, Zihao Gao, Zijun Liao, Wenjun Zhang, Shichuan Wang, Guotai Luo, Xiangde Department of Radiation Oncology Sichuan Cancer Hospital and Institute University of Electronic Science and Technology of China Chengdu China School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Chengdu China Department of Computer Science and Engineering The Chinese University of Hong Kong Sha Tin Hong Kong Shanghai AI Laboratory Shanghai China Department of Radiation Oncology Stanford University School of Medicine Palo AltoCA United States

Accurate lymph node (LN) segmentation is critical in radiotherapy treatment and prognosis analysis, but is limited by the need for large annotated datasets. While deep learning-based segmentation foundation models show potential in developing high-performing models with fewer samples, their medical adaptation faces LN domain-specific prior deficiencies and inefficient few-shot fine-tuning for complex clinical practices, highlighting the necessity of an LN segmentation foundation model. In this work, we annotated 36,106 visible LNs from 3,346 publicly available head-and-neck CT scans to establish a robust LN segmentation model (nnUNetv2). Building on this, we propose Dynamic Gradient Sparsification Training (DGST), a few-shot fine-tuning approach that preserves foundational knowledge while dynamically updating the most critical parameters of the LN segmentation model with few annotations. We validate it on two publicly available LN segmentation datasets: SegRap2023 and LNQ2023. The results show that DGST outperforms existing few-shot fine-tuning methods, achieving satisfactory performance with limited labeled data. We release the dataset, models and all implementations to facilitate relevant research: https://***/Zihaoluoh/LN-Seg-FM. © 2025, CC BY-SA.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Design and Development of a Rescue Robot to Identify Human Presence in Disaster Scenarios by Using Artificial Intelligence Assisted Sensor Support

Design and Development of a Rescue Robot to Identify Human P...

引用

Mobile Computing and Sustainable Informatics (ICMCSI), International Conference on

作者： Umamaheswari U. Sajja Suneel K. Ravikumar D. Baburao Shrikant Upadhyay B. Swapna Saveetha school of law Saveetha Institute of Medical and Technical Sciences SIMATS Chennai Department of CSE(Data Science) Institute of Aeronautical Engineering Dundigal Hyderabad Telangana India Dhanalakshmi Srinivasan College of Engineering and Technology Chennai Computer Science and Engineering Vidya Jyothi Institute of Technology (VJIT) Hyderabad Telangana India Department of Electronics and Communication Engineering MLR Institute of Technology Hyderabad India Department of ECE Dr. MGR Educational and Research Institute Chennai

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

In disaster scenarios, rapid and accurate identification of human presence is critical for effective rescue operations. This study presents the design and development of an AI-assisted rescue robot equipped with advanced sensor support for detecting human presence in various disaster environments. The proposed system integrates multiple sensors, including thermal imaging, LiDAR, ultrasonic sensors, and cameras, to gather comprehensive environmental data. A YOLO-based AI model processes this data to identify human presence with high accuracy. The model was trained and validated on diverse datasets simulating real-world disaster conditions. Results show that the proposed model outperforms nine existing models, achieving an average accuracy of 97.3% across four different disaster scenarios. This accuracy is significantly higher compared to the closest competing models, highlighting the robustness and reliability of the proposed system. Additionally, the model demonstrated a precision of 96.7%, a recall of 96.5%, and a response time of 49.5 ms, all of which contribute to its superior performance in time-sensitive and complex environments. The findings suggest that this AI-assisted rescue robot is a promising solution for enhancing the efficiency and effectiveness of search and rescue operations in disaster scenarios.

关键词： Accuracy Rapid thermal processing Disasters Robot vision systems Thermal sensors Robustness Time factors Artificial intelligence Mobile computing Rescue robots

来源：评论

学校读者我要写书评

暂无评论

NFR-EDL: Non-linear fuzzy rank-based ensemble deep learning for accurate diagnosis of oral and dental diseases using RGB color photography

引用

computers in Biology and Medicine 2025年第Pt A期192卷 110279-110279页

作者： Razmjouei, Pouyan Moharamkhani, Elaheh Aryanezhad, Seyed Sasan Shokouhifar, Mohammad Hosseinzadeh, Mehdi Zadmehr, Behrouz Department of Electrical & Computer Engineering Valie-e-Asr University of Rafsanjan Kerman Iran IRO Computer Science Department University of Halabja Halabja Iraq Isfahan Iran Duy Tan University Da Nang550000 Viet Nam School of Computer Science Duy Tan University Da Nang550000 Viet Nam Jadara Research Center Jadara University Irbid21110 Jordan Amirkabir University of Technology Tehran Iran

Background: Oral health plays a vital role in our daily lives, affecting essential activities like eating, speaking, and smiling. Poor oral health can lead to significant social, psychological, and physical consequences, which makes early and accurate diagnosis incredibly important. Recent advances in artificial intelligence (AI) are opening new doors in oral health care, offering faster, more accurate ways to identify dental issues and improve overall care. Methods: This paper uses RGB color photography to introduce a non-linear Fuzzy Rank-based Ensemble Deep Learning model (NFR-EDL) for diagnosing oral and dental diseases. The model utilizes four deep Convolutional Neural Network (CNN) base models to analyze high-resolution color images of the oral cavity. The CNN base models are initially trained to generate confidence scores, which are subsequently mapped onto distinct functions with varying concavities, resulting in non-linear fuzzy ranks. Then, these ranks are combined into a final score to minimize the deviation from expected results. This method aims to provide accurate, reliable identification of oral and dental disease diagnosis by fusing many base models and considering uncertainty in decision-making while utilizing the rich visual information available in RGB images. Results: The experimental results demonstrate that the proposed NFR-EDL model achieves accuracies of 97.08 %, 84.00 %, 89.86 %, and 94.66 % on the Kaggle, MOD, ODSI-DB, and OaDD datasets, respectively. These results demonstrate the model's exceptional accuracy and effectiveness in diagnosing oral and dental diseases, outperforming existing techniques and enhancing diagnostic reliability in clinical settings. Conclusion: Deploying the NFR-EDL model in clinical settings offers a highly accurate and reliable tool for diagnosing oral and dental diseases, enhancing early detection, personalizing patient care, and reducing diagnostic errors to ultimately improve patient outcomes and the efficiency

关键词： Dentistry

来源：评论

学校读者我要写书评

暂无评论

PAC-MC: An Efficient Password-Based Access Control Framework for Time Sequence Aware Media Cloud

引用

IEEE Transactions on Mobile Computing 2025年

作者： Wang, Haiyan Liu, Penghui Zhong, Xiaoxiong Luo, Fucai Xiao, Bin Yang, Yuanyuan Peng Cheng Laboratory Department of New Networks Shenzhen518000 China Zhejiang Gongshang University School of Computer Science and Technology Hangzhou China Hong Kong Polytechnic University Department of Computing Hong Kong Stony Brook University Department of Electrical and Computer Engineering Stony BrookNY11794 United States

Cloud storage makes it easier for users to access and share data remotely, but it often requires integration with cryptographic technologies to address consumer-oriented applications, such as fine-grained data access, secure data sharing and retrieval. This paper focuses on the fine-grained access problem of media applications based on time sequence, that is, certain critical media applications based on time sequences should ideally be accessible only to authorized clients. The traditional keyword-based searchable encryption (SE) allows effective search and access over encrypted data while preserving data privacy, but most existing solutions do not support temporal access control (i.e., a mechanism that grants access permissions to users within a specified time range). In this paper, we propose PAC-MC, an efficient password-based access control framework for media cloud relying on content control with the time sequence attribute. PAC-MC not only supports multi-keyword search using any monotonic boolean formulas but also allows media owners to control content-encryption keys for different time periods with an updatable password. Furthermore, it supports the self-retrieval of content-encryption keys. In addition, PAC-MC is provably secure under the standard model. Finally, the detailed performance evaluation results and experimental comparisons indicate that PAC-MC is very efficient and outperforms the previous solutions in terms of computation, communication, and storage costs. © 2025 IEEE.

关键词： Access control content protection media cloud password searchable encryption time sequence

来源：评论

学校读者我要写书评

暂无评论

VGGBM-Net: A Novel Pixel-Based Transfer Features engineering for Automated Coffee Bean Diseases Classification

引用

IEEE Access 2025年 13卷 83580-83590页

作者： Muhammad Shadab Alam Hashmi Azam Mehmood Qadri Ali Raza Saleem Ullah Aseel Smerat Changgyun Kim Muhammad Syafrudin Norma Latif Fitriyani Department of Computer Science Khwaja Fareed University of Engineering and Information Technology Rahim Yar Khan Pakistan Department of Software Engineering The University of Lahore Lahore Pakistan Department of Precision Medicine School of Medicine Sungkyunkwan University Suwon Republic of Korea Faculty of Educational Sciences Al-Ahliyya Amman University Amman Jordan Centre for Research Impact and Outcome Chitkara Institute of Engineering and Technology Chitkara University Rajpura Punjab India Computer Technologies Engineering Mazaya University College Nasiriyah Iraq Department of Electronic and AI System Engineering Kangwon National University Samcheok Republic of Korea Department of Artificial Intelligence and Data Science Sejong University Seoul Republic of Korea

Although coffee is a crucial commodity for developing nations’ economies, processing defects can significantly impact the safety, commercial value, and quality of coffee beans. Traditional coffee bean grading methods are labor-intensive and prone to error, necessitating automated and accurate classification of bean diseases. This study proposes a novel transfer learning-based deep neural network, VGGBM-Net, for classifying coffee bean diseases. It focuses on the timely and precise identification of diseases to improve export quality without compromising safety during production. In this research, the proposed approach is trained using a dataset USK-Coffee of coffee beans to classify healthy and unhealthy beans. The performance of multiple machine learning classifiers, including Random Forest (RF), Logistic Regression (LoR), LightGBM (LGBM), and K-Nearest Neighbor Classifier (KNC), is evaluated alongside neural network techniques such as Convolutional Neural Networks (CNN) and VGG-19. A novel transformation of the VGG-19 model for feature engineering based on transfer learning is introduced, where spatial features extracted from coffee bean images are transformed into class prediction probabilities using LGBM. These enhanced features are then used as inputs for advanced machine-learning algorithms. Unlike traditional models, this feature extraction enhances classification accuracy and robustness. This transformation improves feature extraction by capturing more discriminative patterns, leading to superior performance compared to conventional methods. Experimental results highlight the superior performance of the LGBM classifier, achieving an impressive 99% accuracy, recall, f1, and precision score of 98% with a computational runtime of just 0.084 seconds. K-fold cross-validation ensured the robustness of the models, and optimization techniques were applied to fine-tune parameters for maximum accuracy. This research establishes a highly effective framework for automat

关键词： Accuracy Feature extraction Diseases Deep learning Convolutional neural networks Transfer learning Production Nearest neighbor methods Training Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

Utilizing Transforming Portfolio Management Through Automation Using Advanced Deep Reinforcement Learning Algorithms for Optimized Investment Strategies

Utilizing Transforming Portfolio Management Through Automati...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： D David Winster Praveenraj Hemalatha D Mohammed Al-Farouni S. Priya B. Arunkumar Prakhar Mittal School of Business and Management CHRIST University Bangalore India Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq KCG College of Technology Department of Computer Science Engineering Karpagam Academy of Higher Education Coimbatore India Department of IT Atricure Mason Ohio

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

This paper focuses on the future possibility of enhancing the applications of DRL in autonomously managing a portfolio for better investment plans. Having used past financial data and a highly developed case of DRL, the proposed system shows better performance compared to conventional investment strategies and indices. This process includes data gathering from the financial databases, the steps of preprocessing and feature extraction, and the use of the DQN structure. After that, the system's training and validation are done by a finite portion of real-world data and a large number of synthesized data to improve stability. The result shows that the new method achieves superior cumulative return, Sharpe ratio, maximum drawdown, and annualized volatility; therefore, it suggests that the proposed system can flexibly predict the fluctuating stock market trends and make appropriate investment decisions. Thus, the present research adds importance to the use of DRL in improving return potential and risk management in portfolio management. Thus, this study adds to the existing literature and practice by allowing for the automation of the optimization and testing for investment solutions at a larger scale, while opening up opportunities for future developments in the application of financial technology and investment tools.

关键词： Training Automation Machine learning algorithms Stability criteria Deep reinforcement learning Risk management Stock markets Portfolios Optimization Investment

来源：评论

学校读者我要写书评

暂无评论

Drone-assisted adaptive object detection and privacy-preserving surveillance in smart cities using whale-optimized deep reinforcement learning techniques

引用

Scientific Reports 2025年第1期15卷 1-20页

作者： Abu-Khadrah, Ahmed Al-Qerem, Ahmad Hassan, Mohammad R. Ali, Ali Mohd Jarrah, Muath Department of Electrical Engineering College of Engineering Technology Al-Balqa Applied University Amman Jordan Department of Computer Science Faculty of Information Technology Zarqa University Zarqa 13132 Jordan Communications and Computer Engineering Department Faculty of Engineering Al-Ahliyya Amman University Amman Jordan School of Computing Skyline University College Sharjah United Arab Emirates

Drone/ unmanned aerial vehicles (UAV) surveillance for object/ human detection is familiar in large gatherings in the modern cities era. Artificial intelligence algorithms and computer-aided processing will handle the images extracted from the surveillance videos to reveal the object. This article proposes a novel object detection technique (ODT) that assimilates whale optimization algorithms and deep reinforcement learning. The optimization algorithm detects spreading image features from the origin to the end of x×y pixels. This feature extraction is performed until the complete image pixels are covered to identify their existence in the least position. The forging behaviour of the whales is implied to identify highly overlapping features for object/ human detection/ classification. If the overlapping features increase, the whale’s movement is updated from the last-known highest pixel position. The reinforcement learning recommends that new whale agents validate the low overlapping features, such that the forging whale agent moves towards the large overlapping feature. Therefore, the highest overlapping feature-based pixel differentiation is pursued using forging and searching whales to identify objects through collated pixels. © The Author(s) 2025.

关键词： DRL Feature overlap Object detection Whale optimization

来源：评论

学校读者我要写书评

暂无评论

A Strong and Adaptable Watermarking Methodology for Relational Databases

A Strong and Adaptable Watermarking Methodology for Relation...

引用

Intelligent Control, Computing and Communications (IC3), International Conference on

作者： Dharmapuri Siri S. Sangeetha P. Kalaiselvi Devayanai V C Haassan M.M. AlJawahry Ritin Behl Department of CSE Gokaraju Rangaraju Institute of Engineering and Technology Hyderabad Telangana India Department of CSE CMR College of Engineering & Technology Hyderabad Telangana Department of Computer Science Engineering Sethu Institute of Technology Kariapatti Tamil Nadu India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai Tamil Nadu India Department of computers Techniques engineering College of technical engineering The Islamic University Najaf Iraq Department of CSE (AIML) ABES Engineering College Ghaziabad

ISBN: (数字)9798331527495

ISBN: (纸本)9798331527501

Watermarking technique refers to discreet embedding of an imprint to establish possession of the plagiarism. The current databases watermarking methods lack the ability to self-adapt to various kinds of information & exhibit inadequate robustness. The article introduces a novel and resilient initiative for watermarking databases. The plan has the capability of adapting the watermarking technique & variables to suit the particular features of quantitative & textual information. We have successfully demonstrated the effectiveness and reliability of our approach through both theoretical analysis & empirical validation, particularly in regards of its resilience & minimal information deformation. This feature renders it appropriate for objectives such as safeguarding plagiarism, identifying owners, or tracking potential traitors.

关键词： Deformation Plagiarism Watermarking Relational databases Reliability theory Robustness Object recognition Resilience Intelligent control

来源：评论

学校读者我要写书评

暂无评论

Bilateral Multi-Subarray Padded Coprime Array Configuration for DOA Estimation in MIMO Radar

引用

IEEE Transactions on Vehicular technology 2025年

作者： Chen, Hua Li, Jiajie Yang, Songjie Liu, Wei Yuen, Chau So, Hing Cheung Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo315211 China University of Electronic Science and Technology of China National Key Laboratory of Wireless Communications Chengdu610054 China The Hong Kong Polytechnic University Department of Electrical and Electronic Engineering Kowloon Hong Kong Nanyang Technological University School of Electrical and Electronics Engineering 639798 Singapore Department of Electrical Engineering City University of Hong Kong Hong Kong

Simultaneous consideration of uniform degrees of freedom (uDOF) and mutual coupling is a key focus in sparse array design. To reduce mutual coupling and increase degrees of freedom (DOF), a bilateral multi-subarray coprime array (BMSCA) is proposed with its specific hole locations in the difference co-array (DCA). To address the holes in the central DCA, an additional subarray is incorporated, resulting in the bilateral multi-subarray padded coprime array (BMSPCA), which substantially increases both DOF and uDOF. Additionally, the first three weight functions and the optimal structure are determined for BMSPCA. As an application, BMSPCA is applied to multiple-input multiple-output (MIMO) radar with sum-difference co-array, where the holes in DCA and virtual sparse sensors can be divided into similar layers and exhibit symmetry;specific sparse arrays that exhibit similar symmetrical properties are then identified, which can fundamentally enhance the uDOF of MIMO radar. Simulation results demonstrate the superior performance of both the proposed array and the sparse MIMO array in scenarios with strong mutual coupling. © 1967-2012 IEEE.

关键词： Direction of arrival

来源：评论

学校读者我要写书评

暂无评论

Unmanned aerial vehicle based multi-person detection via deep neural network models

引用

Frontiers in Neurorobotics 2025年 19卷 1582995页

作者： Alshehri, Mohammed Zahoor, Laiba AlQahtani, Yahya Alshahrani, Abdulmonem AlHammadi, Dina Abdulaziz Jalal, Ahmad Liu, Hui Department of Computer Science King Khalid University Abha Saudi Arabia Faculty of Computer Science Air University Islamabad Pakistan Department of Informatics and Computer Systems King Khalid University Abha Saudi Arabia Department of Information Systems College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University Riyadh Saudi Arabia Department of Computer Science and Engineering College of Informatics Korea University Seoul Korea Republic of Cognitive Systems Lab University of Bremen Bremen Germany Guodian Nanjing Automation Company Ltd. Nanjing China Jiangsu Key Laboratory of Intelligent Medical Image Computing School of Future Technology Nanjing University of Information Science and Technology Nanjing China

Introduction: Understanding human actions in complex environments is crucial for advancing applications in areas such as surveillance, robotics, and autonomous systems. Identifying actions from UAV-recorded videos becomes more challenging as the task presents unique challenges, including motion blur, dynamic background, lighting variations, and varying viewpoints. The presented work develops a deep learning system that recognizes multi-person behaviors from data gathered by UAVs. The proposed system provides higher recognition accuracy while maintaining robustness along with dynamic environmental adaptability through the integration of different features and neural network models. The study supports the wider development of neural network systems utilized in complicated contexts while creating intelligent UAV applications utilizing neural networks. Method: The proposed study uses deep learning and feature extraction approaches to create a novel method to recognize various actions in UAV-recorded video. The proposed model improves identification capacities and system robustness by addressing motion dynamic problems and intricate environmental constraints, encouraging advancements in UAV-based neural network systems. Results: We proposed a deep learning-based framework with feature extraction approaches that may effectively increase the accuracy and robustness of multi-person action recognition in the challenging scenarios. Compared to the existing approaches, our system achieved 91.50% on MOD20 dataset and 89.71% on Okutama-Action. These results do, in fact, show how useful neural network-based methods are for managing the limitations of UAV-based application. Discussion: Results how that the proposed framework is indeed effective at multi-person action recognition under difficult UAV conditions. Copyright © 2025 Alshehri, Zahoor, AlQahtani, Alshahrani, AlHammadi, Jalal and Liu.

关键词： Drones

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：