检索结果-内蒙古大学图书馆

Efficiency-optimized 6G:A virtual network resource orchestration strategy by enhanced particle swarm optimization

Digital Communications and Networks 2024年第5期10卷 1221-1233页

作者： Sai Zou Junrui Wu Haisheng Yu Wenyong Wang Lisheng Huang Wei Ni Yan Liu College of Big Data and Information Engineering Guizhou UniversityGuiyangChina Prospective Technology Lab of the China Future Internet Engineering Center BeijingChina College of Computer Science and Engineering University of Electronic Science and TechnologyChengduChina International Institute for Next Generation Internet Macao University of Science and TechnologyMacaoChina Data61 Business Unit CSIROAustralia

The future Sixth-Generation (6G) wireless systems are expected to encounter emerging services with diverserequirements. In this paper, 6G network resource orchestration is optimized to support customized networkslicing of services, and place network functions generated by heterogeneous devices into available *** is a combinatorial optimization problem that is solved by developing a Particle Swarm Optimization (PSO)based scheduling strategy with enhanced inertia weight, particle variation, and nonlinear learning factor, therebybalancing the local and global solutions and improving the convergence speed to globally near-optimal *** show that the method improves the convergence speed and the utilization of network resourcescompared with other variants of PSO.

关键词： Virtualization Network function orchestration Network resource virtualized orchestration (NRVO) Particle swarm optimization(PSO)

来源：评论

学校读者我要写书评

暂无评论

QuMIN: quantum multi-modal data fusion for humor detection

引用

Multimedia Tools and Applications 2025年第18期84卷 18855-18872页

作者： Phukan, Arpan Haq Khan, Anas Anwarul Ekbal, Asif Department of Computer Science and Engineering Indian Institute of Technology Patna Bihta Bihar Patna801106 India Kalinga Institute of Industrial Technology Odisha Bhubaneswar751024 India School of AI and Data Science Indian Institute of Technology Jodhpur Rajasthan Jodhpur342030 India

Humour detection has attracted considerable attention due to its significance in interpreting dialogues across text, visual, and acoustic modalities. However, effective methods to map correlations among different modalities remain an active area of research. In this study, we go beyond traditional machine learning techniques by introducing a Variational Quantum Circuit (VQC) that capitalizes on the inherent quantum properties of superposition, entanglement, and interference. Our proposed model, Quantum Multi-Modal data Fusion (QuMIN), is designed to better capture and reproduce the interaction across modalities, as well as the internal correlations within each modality. Our introduction of the novel VQC, which augments the DialogueRNN baseline with only an additional 4,809 parameters, signifies a substantial advancement in multi-modal humor detection with improvements of 12.34% in precision, 8.84% in recall and 10.57% in F1 score compared to the state-of-the-art methods. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

FedLRes: enhancing lung cancer detection using federated learning with convolution neural network (ResNet50)

引用

Neural Computing and Applications 2025年第14期37卷 8273-8284页

作者： Usharani, C. Selvapandian, A. Department of Artificial Intelligence and Data Science Ramco Institute of Technology Rajapalayam India Department of Electronics and Communication Engineering Gnanamani College of Technology Namakkal India

Lung cancer remains a leading global cause of mortality, necessitating efficient early detection. Lung cancer image analysis plays a pivotal role, yet current manual segmentation by oncologists is laborious. Our innovative (FedLRes) approach proposes a comprehensive system for automated diagnoses of lung cancer using federated learning with ResNet50. The lung cancer dataset from the Iraq-Oncology Teaching Hospital/National Centre for Cancer Diseases was gathered by the IQ-OTH/NCCD. The dataset consists of 1097 images, split into training (822 images) and validation (275 images) sets. The training set includes 312 normal, 420 malignant, and 90 benign cases. The training set's data are further enhanced by using data augmentation techniques, which are then applied to normalise images differences before being fed into the federated learning with ResNet50 architecture. This approach combines deep learning models trained on different datasets allowing for improvising accuracy and generalisation. The federated learning approach enables the use of distributed data while ensuring data privacy and security. The proposed approach compared with different state of art algorithms. Through rigorous experimentation, our system showcases remarkable advancements a classification accuracy of 99.40%. This innovative approach, utilising 3D input CT scan data, offers a potent and precise tool for early detection and effective treatment strategies against the scourge of lung cancer. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

StealthFace:Transfer Learning-Based Ensemble Model for Disguised Face Recognition using Skin-Segmented Images

IAENG International Journal of Computer Science

引用

IAENG International Journal of Computer science 2025年第4期52卷 1244-1260页

作者： Padmashree, G. Kotegar, Karunakar A Department of Data Science and Computer Applications Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal576104 India

Disguised face identification is challenging since people cover their identities by wearing masks, hats, sunglasses, or other disguises. These disguises dramatically modify face features, making identifying individuals a difficult task. In this study, we introduce StealthFace, an ensemble model that utilizes transfer learning and skin-segmented images to improve the recognition of disguised faces. To improve the accuracy and resilience of disguised face recognition, StealthFace leverages the power of deep learning algorithms, transfer learning, and ensemble methods. The framework employs pre-trained convolutional neural network models, such as ResNet50 and DenseNet121 for feature extraction and to learn discriminative features that are important in identifying individuals despite the disguises. The ensemble approach combines models’ predictions, utilizing their collective expertise and capturing multiple perspectives on disguised faces. Our ensemble model outperforms other state-of-the-art methods with an overall accuracy of 99.24% and contributes to enhancing security measures and advancing the development of face recognition systems. © (2025), (International Association of Engineers). All Rights Reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Novel Rifle Number Recognition Based on Improved YOLO in Military Environment

引用

Computers, Materials & Continua 2024年第1期78卷 249-263页

作者： Hyun Kwon Sanghyun Lee Department of Artificial Intelligence and Data Science Korea Military AcademySeoulKorea Graduate School of Information Security Korea Advanced Institute of Science and TechnologyDaejeonKorea

Deep neural networks perform well in image recognition,object recognition,pattern analysis,and speech *** military applications,deep neural networks can detect equipment and recognize *** military equipment,it is necessary to detect and recognize rifle management,which is an important piece of equipment,using deep neural *** have been no previous studies on the detection of real rifle numbers using real rifle image *** this study,we propose a method for detecting and recognizing rifle numbers when rifle image data are *** proposed method was designed to improve the recognition rate of a specific dataset using data fusion and transfer *** the proposed method,real rifle images and existing digit images are fusedas trainingdata,andthe final layer is transferredto theYolov5 *** detectionand recognition performance of rifle numbers was improved and analyzed using rifle image and numerical *** used actual rifle image data(K-2 rifle)and numeric image datasets,as an experimental *** was used as the machine learning *** results show that the proposed method maintains 84.42% accuracy,73.54% precision,81.81% recall,and 77.46% F1-score in detecting and recognizing rifle *** proposed method is effective in detecting rifle numbers.

关键词： Machine learning deep neural network rifle number recognition detection

来源：评论

学校读者我要写书评

暂无评论

Understanding the Aftermath of COVID-19: A data-Driven Exploration of Health Effects 3

Understanding the Aftermath of COVID-19: A Data-Driven Explo...

引用

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

作者： Selvaraj, Arikumar K. Naveen Akash, P. Venkata Swamy, B. Department of Data Science and Business Systems SRM Institute of Science and Technology Kattankulathur India

ISBN: (纸本)9798331527549

The COVID-19 pandemic has ravaged public health in a manner that is unprecedented: millions of infections and fatalities worldwide. Now that the immediate crisis seems to recede, there is growing concern over long-term health consequences faced by survivors, commonly referred to as "long COVID." This study aims to systematically explore the multifaceted health effects experienced by individuals who have recovered from COVID-19, focusing on physical, mental, and cognitive health issues that have emerged in the aftermath of the infection. Employing a data-driven approach, the collected extensive survey data from a diverse cohort of COVID-19 survivors to assess their post-recovery health status. The survey included questions targeting various health dimensions, such as fatigue, pain, anxiety, depression, and cognitive function. To analyze the data, utilized several machine learning algorithms to identify significant health complications and to determine the interrelationships among various health factors. © 2025 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

H2O Guard: Predicting Water Potability with Machine Learning and Blockchain Integration 3

H2O Guard: Predicting Water Potability with Machine Learning...

引用

3rd International Conference on Electronics and Renewable Systems, ICEARS 2025

作者： Nair, Rahul Aalim, Ansab Manhaas, Ishaan Rastogi, Kshitij Kalpana, A.V. Srm Institute of Science and Technology Department of Data Science and Business Systems Kattankulathur India

ISBN: (纸本)9798331509675

Access to clean drinking water is critical to public health and well - being. Water compatibility refers to the safety of drinking water for human consumption and includes various physical, chemical and biological parameters. Contaminated water can cause serious health problems, particularly among vulnerable populations due to water-borne diseases. Traditionally, water quality assessment relies on time - consuming laboratory tests that can delay responses to contamination. The H2OGuard project presents a novel approach: It uses deep learning and machine learning algorithms to predict water sustainability based on key environmental factors such as pH, turbidity and chemical contaminants. With these advanced methods, we aim to improve the efficiency and accuracy of water quality testing. In addition, the integration of blockchain technology is intended to ensure secure and immutable storage of water quality data and promote integrity and transparency. This paper discusses the methods of the H2OGuard project, evaluates the performance of various predictive models, and highlights the critical importance of blockchain in securing data. With this innovative framework, we aim to enable more efficient and timely assessment of drinking water safety, ultimately contributing to improved public health outcomes. © 2025 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Mechanical properties of thermoelectric generators

引用

Journal of Materials science & technology 2023年第17期148卷 64-74页

作者： Xin Bao Shuaihang Hou Zhixin Wu Xiaodong Wang Li Yin Yijie Liu Huolun He Sichen Duan Baolin Wang Jun Mao Feng Cao Qian Zhang School of Materials Science and Engineering and Institute of Materials Genome&Big DataHarbin Institute of TechnologyShenzhen518055China State Key Laboratory of Advanced Welding and Joining Harbin Institute of TechnologyHarbin150001China School of Science Harbin Institute of TechnologyShenzhen518055China

To satisfy the requirements of practical applications,thermoelectric generators should be highly efficient and mechanically ***,progress in designing high-performance thermoelectric generators has been ***,the mechanical properties of thermoelectric generators are still *** this review,studies on the mechanical properties of thermoelectric generators are *** me-chanical properties of bulk thermoelectric generators will be first *** this section,the mechan-ical properties of thermoelectric materials and the strategies for improving their mechanical properties are *** the device’s failure usually occurs at the interface between the thermoelectric ma-terials and electrode,the joint strength of electrodes and thermoelectric materials will be *** that,the mechanical properties of the inorganic thin-film thermoelectric devices will be *** the figure of merit for the flexibility of thermoelectric materials depends on the film thickness,elastic modulus,and yield strength,the synthesis methods of thin-film thermoelectric materials will be ***,this review will be concluded with a discussion on flexible organic thermoelectric de-vices and flexible devices using bulk legs.

关键词： Thermoelectric generator Mechanical properties Interface Joint strength

来源：评论

学校读者我要写书评

暂无评论

A Contemporary CNN Implanted Deep Learning Framework for Crop Protection from Animal Intrusion in Farming Environment

A Contemporary CNN Implanted Deep Learning Framework for Cro...

引用

2024 International Conference on Advances in data Engineering and Intelligent Computing Systems, ADICS 2024

作者： Pavitra, A.Rehash Rushmi Panimalar, K. Rajalakshmi, D. Chinnasamy, A. Srm Institute Of Science And Technology Data Science And Business Systems Chennai India

ISBN: (纸本)9798350364828

In general, monitoring wild animal behavior at reasonable outlay is necessary for both managing human wildlife conflicts and protecting wildlife thereby reliable method is needed to detect wild animals. On the other side, Indian farmers endure severe risks from pests, natural disasters and animal damage resulting decreases the production process. To inspect crops and prevent animals from roaming farmers find it difficult to hire security and their standard approaches tend to be highly effective. Therefore, by applying efficient Deep Learning (DL) framework facilitate to develop Convolutional Neural Network CNN algorithm that can identify wild animal intrusion and provide an indication to end user. Further research highlights smart agriculture applications that significantly minimize losses in production by utilizing DL to make digital notifications that protect fields against mammalian attack. In addition to implementing into consideration the constraints imposed by the farming environment in terms of power supply and network connection, the proposed system is built on image processing platform that provide an optimal combination of efficiency, expense, and power consumption. Ultimately, significant advancement toward cutting-edge technology and sustainable crop protection offers farmers can able to minimize the negative effects of wildlife on the farming industry while reducing adverse ecological implications. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Explainability of Deep Learning-Based ECG Diagnosis Using Large Language Models 24

Enhancing Explainability of Deep Learning-Based ECG Diagnosi...

引用

8th International Conference on Advances in Artificial Intelligence, ICAAI 2024

作者： Wu, Shi Zhou, Jianlong Dong, Yifei Chen, Fang Data Science Institute University of Technology Sydney SydneyNSW Australia

ISBN: (纸本)9798400718014

The electrocardiogram (ECG) is an essential diagnostic tool for monitoring heart health. Traditional manual methods for ECG interpretation are increasingly challenged by the complexity of heart diseases and the volume of ECG data. Recent advancements in artificial intelligence (AI), particularly deep learning, have improved the efficiency and accuracy of ECG diagnostics. However, the "black-box" nature of AI models poses trust and verification challenges. To address this, we propose a novel approach integrating Explainable AI (XAI) techniques with multimodal large language models to enhance ECG diagnostic interpretability. Our methodology employs a 2D convolutional neural network (CNN) to classify ECG signals, followed by Grad-CAM to generate heatmaps highlighting critical areas influencing AI decisions. These enhanced ECG images and their classifications are then input into a multimodal large language model to produce comprehensive explanatory outputs. This approach combines the visual processing power of CNNs with the contextual understanding of multimodal models, offering clearer insights into AI reasoning. Our research demonstrates improved diagnostic accuracy and interpretability, setting a new standard for AI integration in clinical practices. Specifically, our method achieved an F1-score of 0.67 for ECG classification using Inception and a BERT-Score of 0.818 for text generation using Gemini_GradCAM. © 2024 Copyright held by the owner/author(s).

关键词： Convolutional neural networks

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：