检索结果-内蒙古大学图书馆

A Robust Autoencoder HBC Transceiver With CGAN-Based Channel Modeling

IEEE Sensors Journal 2025年第9期25卷 15935-15949页

作者： Ali, Abdelhay Abdelrahman, Amr N. Celik, Abdulkadir Fouda, Mohammed E. Eltawil, Ahmed M. King Abdullah University of Science and Technology Computer Electrical and Mathematical Sciences and Engineering Division Thuwal23955-6900 Saudi Arabia Compumacy for Artificial Intelligence Solutions Cairo22303-2839 Egypt

Human body communication (HBC) offers a promising alternative for efficient and secure data transmission in wearable healthcare systems by leveraging the body’s conductive properties. Using the conductive properties of the human body, HBC offers significant advantages over conventional radio frequency wireless communication methods, including ultralow power consumption and minimal interference. However, HBC systems face key challenges in energy efficiency, data rate optimization, channel adaptability, and accurate body channel modeling. In this article, we present a novel dual-mode HBC transceiver architecture designed to overcome these challenges by integrating autoencoder-based signal processing with generative adversarial network (GAN)-driven channel modeling framework to enhance communication reliability. Operating in both broadband and narrowband modes, the transceiver dynamically adjusts its data rate and power efficiency based on application-specific demands. The design process involves first developing a conditional GAN (CGAN)-based channel model from real HBC measurements, and then using this model to train an autoencoder-based transceiver architecture. Our CGAN framework generates realistic synthetic channel responses for training, enabling the autoencoder to learn optimal encoding and decoding strategies that are robust to channel variations. Subsequently, we developed a low-power hardware architecture that supports flexible data rates of the proposed design while ensuring robust performance in diverse scenarios. This systematic approach provides key advantages: improved channel modeling accuracy achieving a 0.9 correlation coefficient between generated and real channels and mean squared error (mse) of 0.0071, reduced hardware complexity through elimination of digital-to-analog converter (DAC)/analog-to-digital converter (ADC), and flexible operation with dual-mode support. Operating at a clock speed of 42 MHz in the narrowband mode, the transceiver achie

关键词： Radio transceivers

来源：评论

学校读者我要写书评

暂无评论

An Optimal Real-Time Routing and Clustering Protocol for UAV Networks Based on Security 4

An Optimal Real-Time Routing and Clustering Protocol for UAV...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Sophia, S. Leelipushpam Paulraj, Getzi Jeba Yuvarajan, D. Karunya Institute of Technology and Sciences Division of Artificial Intelligence and Machine Learning Coimbatore India Karunya Institute of Technology and Sciences Division of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798331523923

Unmanned Aerial Vehicle (UAV) networks play an important role in different application areas such as military surveillance, emergency services, and infrastructure. However, these networks face significant challenges such as data leakage, unauthorized access, limited processing capacity, and energy constraints. Available techniques such as Elliptic Curve Cryptography (ECC), hash-based techniques, and dynamic clustering algorithms have been proposed to enhance security and operational performance;however, they often encounter challenges concerning scalability, adaptability to real-time changes within the network, and resource-related constraints. This research presents a streamlined authentication framework with the intent to facilitate secure and effective functionalities in turbulent and fluctuating settings. The proposed protocol uses Dijkstra's algorithm for optimal real-time routing, Adaptive Optimization Clustering (AOC) for dynamic resource distribution, and K-means clustering for noise classification. The proposed methodology achieves substantial improvements in power efficiency, latency, and Packet Delivery Rate (PDR) due to reduced computational overhead as well as risks such as data interception and replay attacks. Simulation results conclude that the system suggested here would be secure, scalable, and energy-efficient to be used for applications in demanding scenarios, such as mission-critical scenarios. © 2025 IEEE.

关键词： Emergency services

来源：评论

学校读者我要写书评

暂无评论

Personal data sharing model with legal validity in blockchain-based secure environment 27

Personal data sharing model with legal validity in blockchai...

引用

27th International Conference on Advanced Communications Technology, ICACT 2025

作者： Shin, Su Jin Shin, Sang Uk Department of Information Security Graduate School Pukyong National University Korea Republic of Division of Computer Engineering and Artificial Intelligence Pukyong National University Korea Republic of

ISBN: (纸本)9791188428137

This paper proposes a data sharing model that ensures the legal validity of data provided by individuals as legal evidence within a blockchain environment. The proposed model applies Distributed Pseudo-Random Functions (DPRFs) to prevent all participants, except the data requester, from obtaining the original data. Based on these characteristics, the model guarantees integrity, confidentiality, and non-repudiation, thereby ensuring that data provided by individuals can possess legal validity as evidence. © 2025 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Data integrity

来源：评论

学校读者我要写书评

暂无评论

Deep transfer learning technique to detect white blood cell classification in regular clinical practice using histopathological images

引用

Multimedia Tools and Applications 2025年第9期84卷 5699-5723页

作者： Davamani, K. Anita Jawahar, Malathy Anbarasi, L. Jani Ravi, Vinayakumar Al Mazroa, Alanoud Robin, C. R. Rene Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Leather Process Technology Division CSIR-Central Leather Research Institute Chennai India School of Computing Science and Engineering Vellore Institute of Technology Vellore India Computer Science and Engineering Sri Sairam Engineering College Sirukalathur India Center for Artificial Intelligence Prince Mohammad Bin Fahd University Khobar Saudi Arabia Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh11671 Saudi Arabia

Leukemia, a malignant disease characterized by the rapid proliferation of specific types of white blood cells (WBC), has prompted increased interest in leveraging automatic WBC classification system. This study presents the design of a robust WBC classification system, integrating deep learning with microscopic image analysis. The proposed classification model is designed to categorize blood cells into four distinct groups: eosinophil, lymphocyte, monocyte, and neutrophil. The study employs a Kaggle image dataset for comprehensive learning. The dataset comprises 12,500 microscopic images used to categorize the four blood cell groups. To enhance performance and reduce the likelihood of overfitting, transfer learning techniques are employed. Six deep transfer learning models namely VGG16, ResNet50, AlexNet, MobileNet, GoogLeNet, and EfficientNetBO are used for feature extraction and classification. The results of the experiments show that VGG16 and MobileNet demonstrated enhancements compared to other pre-trained models when evaluated on both augmented and original datasets. A diverse set of evaluation criteria was employed to thoroughly assess the effectiveness of medical image classification. Notably, the VGG16 and MobileNet models accurately predicted Lymphocytes and Monocytes with a 100% accuracy rate, and Eosinophil and Neutrophil with rates of 99.35% and 99.81%, respectively. This research work empower medical practitioners, particularly in the field of pathology and hematology by providing advanced tools for accurate blood cell classification. The proposed VGG16 and MobileNet models hold promise for simplifying WBC classification, improving decision-making processes, and ultimately advancing patient care in the medical domain. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

GACL-Net:Hybrid Deep Learning Framework for Accurate Motor Imagery Classification in Stroke Rehabilitation

引用

computers, Materials & Continua 2025年第4期83卷 517-536页

作者： Chayut Bunterngchit Laith H.Baniata Mohammad H.Baniata Ashraf ALDabbas Mohannad A.Khair Thanaphon Chearanai Sangwoo Kang State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing100190China School of Computing Gachon UniversitySeongnam13120Republic of Korea Computer Science Department Faculty of Information TechnologyThe World Islamic Sciences and Education UniversityAmman11947Jordan Intelligent Systems Department Faculty of Artificial IntelligenceAl-Balqa Applied UniversityAl-Salt19117Jordan IT Infrastructure Department Qatrana Cement CompanyAmman11821Jordan Division of Industrial and Logistics Engineering Technology Faculty of Engineering and TechnologyKing Mongkut’s University of Technology North BangkokRayong CampusRayong21120Thailand

Stroke is a leading cause of death and disability worldwide,significantly impairing motor and cognitive *** rehabilitation is often hindered by the heterogeneity of stroke lesions,variability in recovery patterns,and the complexity of electroencephalography(EEG)signals,which are often contaminated by *** classification of motor imagery(MI)tasks,involving the mental simulation of movements,is crucial for assessing rehabilitation strategies but is challenged by overlapping neural signatures and patient-specific *** address these challenges,this study introduces a graph-attentive convolutional long short-term memory(LSTM)network(GACL-Net),a novel hybrid deep learning model designed to improve MI classification accuracy and ***-Net incorporates multi-scale convolutional blocks for spatial feature extraction,attention fusion layers for adaptive feature prioritization,graph convolutional layers to model inter-channel dependencies,and bidi-rectional LSTM layers with attention to capture temporal *** on an open-source EEG dataset of 50 acute stroke patients performing left and right MI tasks,GACL-Net achieved 99.52%classification accuracy and 97.43%generalization accuracy under leave-one-subject-out cross-validation,outperforming existing state-of-the-art ***,its real-time processing capability,with prediction times of 33–56 ms on a T4 GPU,underscores its clinical potential for real-time neurofeedback and adaptive *** findings highlight the model’s potential for clinical applications in assessing rehabilitation effectiveness and optimizing therapy plans through precise MI classification.

关键词： Motor imagery EEG stroke rehabilitation deep learning brain-computer interface

来源：评论

学校读者我要写书评

暂无评论

EchoNet Dynamic: Deep Learning-driven Advancements in Dynamic Heart Function Analysis through Echocardiography 3

EchoNet Dynamic: Deep Learning-driven Advancements in Dynami...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Vidhya, K. Nagarajan, B. Jenefa, A. Catherine Joy, R. Cherian, Minu Franz Kingstein, N. School of CST Karunya Institute of Tech. and Sci Coimbatore India Artificial Intelligence and Data Science KPR Institute of Engineering and Technology Coimbatore India Division of ECE Karunya Institute of Tech. and Sci Coimbatore India Computer science and engineering department Amal Jyothi college of engineering kanjirapally Kottayam India

ISBN: (纸本)9798331527549

Advances in echocardiography have significantly improved the diagnostic processes for heart function analysis. However, traditional imaging techniques often struggle with the dynamic complexities of cardiac activities. Existing methods fail to capture detailed variations in cardiac function over time, leading to suboptimal clinical decision-making and patient outcomes. Traditional echocardiography relies heavily on manual interpretation, which can be subjective and varies significantly between observers. This research presents EchoNet Dynamic, a novel method for improving echocardiographic data analysis and interpretation based on deep learning and the Transformer model. The EchoNet Dynamic dataset used in this study comprises 15,000 B-mode echocardiographic images from 750 patients, divided into training, validation, and testing sets for comprehensive model evaluation. The Transformer model demonstrated remarkable effectiveness, achieving an accuracy of 98.5%, an AUC of 0.992, and an F1 score of 0.972, surpassing traditional diagnostic tools by a significant margin. The EchoNet Dynamic model demonstrates a promising enhancement in detecting and diagnosing cardiac functions, offering substantial improvements over conventional echocardiographic methods and setting a new benchmark in cardiac healthcare. © 2025 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

ParkinSense: A Tri-Sensory AI-Powered Framework for Early Detection of Parkinson’s Disease 9th

ParkinSense: A Tri-Sensory AI-Powered Framework for Early De...

引用

9th International Conference on Information, Communication and Computing Technology, ICICCT 2024

作者： Akshaya, M. Joy, Emmanuel Division of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (纸本)9783031724824

Parkinson’s disease (PD) is a brain dysfunction condition that affects thousands of people across the globe. Early detection of Parkinson’s disease is crucial for effective treatment and control of symptoms. This study employs a multi-modal methodology coded as ParkinSense that combines spiral drawings, gait analysis, and Magnetic Resonance Imaging (MRI) analysis for timely Parkinson’s disease identification. MRI analysis provides insight into structural and functional changes in the brain, revealing potential anomalies. GAIT analysis assesses alterations in walking patterns, such as reduced arm swing and slow gait velocity. Spiral drawings, serve as a surrogate for motor dexterity and fine motor control, both of which are compromised in Parkinson’s disease. In this study, data from Parkinson’s patients and healthy candidates are collected and analyzed using advanced machine-learning techniques to create models for accurate disease prediction and classification. Specifically, the gait analysis is conducted using a Support Vector Machine and XGBoost algorithm. The spiral drawings are analyzed using a Convolutional Neural Network. The MRI data is processed using a MobileNet-based neural network. These algorithms are integrated to create models for accurate disease prediction and classification. The results demonstrate that this multimodal technique is equipped to identify Parkinson’s disease with an accuracy rate of more than 90%. Early detection using speech analysis, gait analysis, and spiral drawings can lead to earlier intervention and treatment, resulting in a better excellence of life for those affected. This study adds to the expanding body of knowledge about non-invasive, cost-effective approaches for the timely identification of Parkinson’s disease. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

An Optimal Real-Time Routing and Clustering Protocol for UAV Networks Based on Security

An Optimal Real-Time Routing and Clustering Protocol for UAV...

引用

Sentiment Analysis and Deep Learning (ICSADL), International Conference on

作者： Sophia S Getzi Jeba Leelipushpam Paulraj Yuvarajan D Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Coimbatore India Division of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

Unmanned Aerial Vehicle (UAV) networks play an important role in different application areas such as military surveillance, emergency services, and infrastructure. However, these networks face significant challenges such as data leakage, unauthorized access, limited processing capacity, and energy constraints. Available techniques such as Elliptic Curve Cryptography (ECC), hash-based techniques, and dynamic clustering algorithms have been proposed to enhance security and operational performance; however, they often encounter challenges concerning scalability, adaptability to real-time changes within the network, and resource-related constraints. This research presents a streamlined authentication framework with the intent to facilitate secure and effective functionalities in turbulent and fluctuating settings. The proposed protocol uses Dijkstra's algorithm for optimal real-time routing, Adaptive Optimization Clustering (AOC) for dynamic resource distribution, and K-means clustering for noise classification. The proposed methodology achieves substantial improvements in power efficiency, latency, and Packet Delivery Rate (PDR) due to reduced computational overhead as well as risks such as data interception and replay attacks. Simulation results conclude that the system suggested here would be secure, scalable, and energy-efficient to be used for applications in demanding scenarios, such as mission-critical scenarios.

关键词： Protocols Heuristic algorithms Clustering algorithms Autonomous aerial vehicles Routing Elliptic curve cryptography Real-time systems Security Vehicle dynamics Optimization

来源：评论

学校读者我要写书评

暂无评论

An Enhancement of Object Detection Using YOLO V8 and Mobile Net in Challenging Conditions

引用

SN computer Science 2025年第4期6卷 1-20页

作者： Pasupuleti, Shailaja Ramalakshmi, K. Gunasekaran, Hemalatha Arokiaraj, Rex Macedo Debnath, Saswati Jebaseeli, T. Jemima Department of Computer Science and Engineering Alliance University Karnataka Anekal Bangalore India AU-Centre of Excellence Department of Computer Vision Alliance University Karnataka Anekal Bangalore India College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Oman Department of Information Technology College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Oman Department of Computer Science and Engineering Alliance University Karnataka Bangalore India Division of Artificial Intelligence and Machine Learning Karunya Institute of Technology and Sciences Coimbatore India

Autonomous drones and deep learning neural networks are becoming popular tools to revolutionize aircraft operations by partially automating visual inspection processes in aircraft maintenance. The research aims to provide a trustworthy method for locating and classifying surface flaws on aircraft, such as dents, fractures, corrosion, and a few other anomalies. To assess the model performance with and without a lightweight network integration, the implementation merges YOLOv8 and Mobile Net architectures, using dropout regularization and data augmentation approaches. To guarantee the model's performance in low-light situations, the dataset has been carefully selected to contain images replicating such settings. Annotation, environment setup, model training, and online dataset scraping are all covered by the thorough technique. A web-scraped dataset is used to train and validate two popular semantic segmentation algorithms, YOLOv8 and Mobile Net, which show enough performance for segmenting and grading aircraft surface problems in practical settings. The results show that precision and recall values are improved using a hybrid technique that ensembles trained Mobile Net and YOLOv8 models. Using COCO metrics, in the proposed approach an assessment of Ensemble WBF, Mobile Net-YOLO, and YOLOv8 outcomes on test and validation sets, guaranteed reliable object recognition and classification abilities. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Aircraft Classification Mobile-Net Object detection Weighted Box Fusion YOLOv8

来源：评论

学校读者我要写书评

暂无评论

Personal data sharing model with legal validity in blockchain-based secure environment

Personal data sharing model with legal validity in blockchai...

引用

International Conference on Advanced Communication Technology (ICACT)

作者： Su Jin Shin Sang Uk Shin Department of Information Security Graduate School Pukyong National University Republic of Korea Division of Computer Engineering and Artificial Intelligence Pukyong National University Republic of Korea

ISBN: (数字)9791188428137

ISBN: (纸本)9798331507602

关键词： Law Computational modeling Data security Non-repudiation Data models Communications technology Blockchains Encryption Digital signatures

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：