检索结果-内蒙古大学图书馆

International Conference on computer, Electrical & Communication engineering (ICCECE)

作者： K. Rakesh Kumar Reddy K. Abinaya G.L.V. Satya Sai Ram BE CSE IoT Sathyabama Institute of Science and Technology Semmancheri Chennai Tamil Nadu India Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Semmancheri Chennai Tamil Nadu India

ISBN: (数字)9798331513894

ISBN: (纸本)9798331513900

Since sleep disorders can have a major impact on general well-being, classifying them is crucial to enhancing human health. Experts have historically categorized the stages of sleep, but this is a challenging and error-prone process. By more efficiently assessing, tracking, and diagnosing sleep disturbances, accurate machine learning algorithms (MLAs) can be beneficial. This study uses the publicly accessible Sleep Health and Lifestyle Dataset to evaluate deep learning algorithms and traditional MLAs for the categorization of sleep disorders. Thirteen characteristics pertaining to sleep and everyday activities are included in the 400row dataset. A genetic algorithm was employed to adjust the parameters of the machine learning models in order to maximize their performance. The Artificial Neural Network (ANN) method was evaluated in the study. Significant performance differences were found in the results, with the ANN obtaining the best classification accuracy of 92.92%. In addition, it outperformed the other algorithms tested with high precision (92.01%), recall (93.80%), and F1-score (91.93%).

关键词： Deep learning Accuracy Machine learning algorithms Artificial neural networks Manuals Sleep apnea Real-time systems Reliability Monitoring Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

AADS: An Automated Accident Detection and Nighttime Surveillance System Using Fine-Tuned YOLOv10 Deep Learning Techniques

AADS: An Automated Accident Detection and Nighttime Surveill...

引用

2025 International Conference on Intelligent Control, Computing and Communications, IC3 2025

作者： Karthikeyan, M. Kshirsagar, Pravin Ramdas Tak, Tan Kuan Lalit, Keshav Upreti, Kamal Jain, Rituraj School of Computing Srm Institute of Science and Technology Dept. of Computing Technologies Chennai India J.D College of Engg & Mgmt. Department of Electronics Engg. MS Nagpur India Singapore Institute of Technology Singapore Manipal Institute of Technology Dept. of Computer Science & Engineering Karnataka Manipal India Christ University Department of Computer Science Delhi NCR Ghaziabad India Marwadi University Department of Info. Tech. Gujarat Rajkot India

ISBN: (纸本)9798331527495

computer vision-based surveillance is very important today's security systems to detect, track and regulate the security much better than standard cameras. However, like any other performance measurement systems they have potential pitfalls and technical, ethical, and legal implications must be well understood. The continuous rise in connection and interaction implies that safety of the public especially when navigating roads or operating in public domains is paramount. The conventional approaches to accident identification include observation or reporting from witnesses and always record slow and imprecise outcomes. With the improvement of AI and computer visions, especially with deep learning models such as YOLO, accident detection is changing. YOLO v10 which is incorporated in the surveillance systems, performs real time video analysis to provide object and pattern recognition of accidents including car accidents and incidents involving the pedestrians. When applied to the initial set of annotated accident images, the fine-tuning of the YOLO v10 model enhances its detection capability. The system is in watching the video frames that contain aberrations and issues and alarms are issued when the accidents happen and relayed to the monitoring stations or emergency departments for proper response. The optimized YOLOv10 here delivers a meaningful testing score of 72.3% mAP to outperform the regular YOLOv10 efficiency in incident detection. © 2025 IEEE.

关键词： Machine vision

来源：评论

学校读者我要写书评

暂无评论

Energy-efficient and Privacy-preserving Edge Intelligence for 6G-Empowered Intelligent Transportation Systems

引用

IEEE Network 2025年

作者： Zhu, Chenlu Fan, Xiaoxuan Deng, Xianjun Xiao, Ziheng Guo, Tingting Liu, Shenghao Sun, Jiaqi Park, Jong Hyuk Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Wuhan Kedao Geographic Information Engineering Co. Wuhan China Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul Korea Republic of

6G-empowered Intelligent Transportation Systems (ITS) generate large amounts of data through millions of devices and sensors at the terminal and network edge. Edge intelligence advances the frontier of data-driven artificial intelligence (AI) to the network edge, which enables AI applications to better utilize edge data. Broader connectivity, higher device density, and stronger data exchange present challenges for reliable device communication and privacy data protection in 6G-empowered ITS. To address these challenges, this paper proposes an energy-efficient and privacy-preserving edge intelligence framework named EP-EI. EP-EI deploys a deep reinforcement learning-based cluster head selection model at the edge to ensure energy-efficient communication for terminal devices. Meanwhile, EP-EI designs a privacy-aware hierarchical computing framework for terminal-edge-cloud to prevent privacy leakage. Furthermore, the application scenarios, challenges, and future directions of EP-EI are discussed. Finally, simulation experiments in a specific intelligent transportation case study demonstrate that EP-EI can provide energy-efficient and privacy-protecting services. © 2025 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Geneto-Neuro-Fuzzy Solution for Detection of Early Prostate Cancer

Geneto-Neuro-Fuzzy Solution for Detection of Early Prostate ...

引用

International Conference on Signal Processing and Communication (ICSC)

作者： Duke Oghorodi Igulu Kingsley Thipendra P Singh Edafe J. Atajeromavwo Wilson Nwankwo Department of Comp. Sc. Delta State University of Science & Technology Ozoro Nigeria Department of Computer Science Kenule Beeson Saro-Wiwa Polytechnic Bori Bori Nigeria School of Computer Science Engineering & Technology Bennett University Greater Noida India Department of Cyber Security Delta State University of Science & Technology Ozoro Nigeria

ISBN: (数字)9798331511890

ISBN: (纸本)9798331511906

This study presents a novel hybrid diagnostic model for early-stage prostate cancer, integrating genetic algorithms, neuro-fuzzy logic, and mobile agent technology. By optimizing the selection of key genetic markers, the system achieves a marked improvement in sensitivity and specificity-up to a 12% increase over conventional diagnostic methods-based on extensive simulations and a controlled clinical dataset. The neuro-fuzzy component adaptively merges genetic, clinical, and historical patient data, refining its predictive accuracy through continuous learning. A decentralized computation strategy enhances scalability and lowers device-level computational overhead, supporting widespread implementation in diverse healthcare environments. While initial results underscore its promise, validation through large-scale clinical trials remains a priority. This approach offers a practical, high-accuracy solution that could significantly reduce late-stage prostate cancer diagnoses, particularly in resourcelimited settings, and stands as a step forward in precision oncology diagnostics. The developed approach can be helpful in diagnosis of the relevant healthcare problem.

关键词： Training Accuracy Sensitivity Scalability Neural networks Refining Genetics Oncology Prostate cancer Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Lorentz-Equivariant Quantum Graph Neural Network for High-Energy Physics

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Jahin, Md Abrar Masud, Md. Akmol Suva, Md Wahiduzzaman Mridha, M.F. Dey, Nilanjan Okinawa Institute of Science and Technology Graduate University Okinawa904-0412 Japan Jahangirnagar University Institute of Information Technology Dhaka1342 Bangladesh American International University-Bangladesh Department of Computer Science Dhaka1229 Bangladesh Techno International New Town Department of Computer Science & Engineering New Town Kolkata700156 India

The rapid data surge from the high-luminosity Large Hadron Collider introduces critical computational challenges requiring novel approaches for efficient data processing in particle physics. Quantum machine learning, with its capability to leverage the extensive Hilbert space of quantum hardware, offers a promising solution. However, current quantum graph neural networks (GNNs) lack robustness to noise and are often constrained by fixed symmetry groups, limiting adaptability in complex particle interaction modeling. This paper demonstrates that replacing the classical Lorentz Group Equivariant Block modules in LorentzNet with a dressed quantum circuit significantly enhances performance despite using ≈5.5 times fewer parameters. Additionally, quantum circuits effectively replace MLPs by inherently preserving symmetries, with Lorentz symmetry integration ensuring robust handling of relativistic invariance. Our Lorentz-Equivariant Quantum Graph Neural Network (Lorentz-EQGNN) achieved 74.00% test accuracy and an AUC of 87.38% on the Quark-Gluon jet tagging dataset, outperforming the classical and quantum GNNs with a reduced architecture using only 4 qubits. On the Electron-Photon dataset, Lorentz-EQGNN reached 67.00% test accuracy and an AUC of 68.20%, demonstrating competitive results with just 800 training samples. Evaluation of our model on generic MNIST and FashionMNIST datasets confirmed Lorentz-EQGNN’s efficiency, achieving 88.10% and 74.80% test accuracy, respectively. Ablation studies validated the impact of quantum components on performance, with notable improvements in background rejection rates over classical counterparts. These results highlight Lorentz-EQGNN’s potential for immediate applications in noise-resilient jet tagging, event classification, and broader data-scarce HEP tasks. © 2020 IEEE.

关键词： Hilbert spaces

来源：评论

学校读者我要写书评

暂无评论

Camouflaged Variational Graph AutoEncoder against Attribute Inference Attacks for Cross-Domain Recommendation

引用

IEEE Transactions on Knowledge and Data engineering 2025年

作者： Xiong, Yudi Guo, Yongxin Pan, Weike Yang, Qiang Ming, Zhong Zhang, Xiaojin Yu, Han Lin, Tao Tang, Xiaoying Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China School of Science and Engineering Shenzhen518172 China Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong WeBank Shenzhen China Huazhong University of Science and Technology School of Computer Science and Technology Wuhan430074 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore Westlake University School of Engineering Hangzhou China

Cross-domain recommendation (CDR) aims to alleviate the data sparsity problem by leveraging the benefits of modeling two domains. However, existing research often focuses on the recommendation performance while ignores the privacy leakage issue. We find that an attacker can infer user attribute information from the knowledge (e.g., user preferences) transferred between the source and target domains. For example, in our experiments, the average inference accuracies of attack models on gender and age attributes are 0.8323 and 0.3897. The best-performing attack model achieves accuracies of 0.8847 and 0.4634, exceeding a random inference by 25.10% and 64.04%. We can see that the leakage of user attribute information may significantly exceed what would be expected from random inference. In this paper, we propose a novel recommendation framework named CVGAE (short for camouflaged variational graph autoencoder), which effectively models user behaviors and mitigates the risk of user attribute information leakage at the same time. Specifically, our CVGAE combines the strengths of VAEs in capturing latent features and variability with the ability of GCNs in exploiting high-order relational information. Moreover, to ensure against attribute inference attacks without sacrificing the recommendation performance, we design a user attribute protection module that fuses user attribute-camouflaged information with knowledge transfer during cross-domain processes. We then conduct extensive experiments on three real-world datasets, and find our CVGAE is able to achieve strong privacy protection while making little sacrifices in recommendation accuracy. © 1989-2012 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Dynamic UAV Deployment in Multi-UAV Wireless Networks: A Multi-Modal Feature-Based Deep Reinforcement Learning Approach

引用

IEEE Internet of Things Journal 2025年

作者： Bai, Yu Xie, Boxuan Liu, Ying Chang, Zheng Jäntti, Riku Aalto University Department of Information and Communications Engineering Espoo02150 Finland University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu611731 China University of Jyväskylä Faculty of Information Technology Jyväskylä40014 Finland

The use of Unmanned Aerial Vehicles (UAVs) as aerial base stations has attracted increasing research interest in recent years. A key challenge in this field is determining how to deploy multiple UAVs in dynamic environments, particularly where mobile user demands fluctuate. To address this challenge, this paper presents an adaptive UAV deployment scheme in a dynamic multi-UAV wireless network, considering the mobility of UAVs and users, state variability, and adjustable UAV transmission power. By jointly optimizing the UAVs’ operational modes, transmission power levels, and movement strategies, our objective is to achieve a trade-off between minimizing power consumption and maximizing ground user coverage. A Deep Reinforcement Learning (DRL) approach is proposed to address these challenges. To capture the dynamic variations of users and UAVs in the environment, a multi-modal feature state space is designed, consisting of both a multi-channel image and vectors. The image component integrates real-time data on user distribution and the UAV coverage area, while the vectors represent UAV operational modes, position data, and system temporal information. These multi-modal features are processed using a combination of Convolutional Neural Networks (CNNs) and Multilayer Perceptrons (MLPs) for advanced feature extraction. To enhance training stability and efficiency, the proposed approach updates parameters using the Proximal Policy Optimization (PPO) method. Simulation results demonstrate the effectiveness of the proposed scheme in balancing power consumption and coverage while effectively managing system dynamics. © 2014 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of QoS in MAODV Routing Protocol in MANETS

Performance Evaluation of QoS in MAODV Routing Protocol in M...

引用

International Conference on Machine Learning and Big Data Analytics, ICMLBDA 2023

作者： Dekka, Satish Sambana, Bosubabu Raju, K. Narasimha Sai, D. Manendra Pallavi, M. Reddy, Kuppireddy Krishna Vizianagaram JNTU-GV Andhra Pradesh Vizianagaram India School of Computing Mohan Babu University Andhra Pradesh Tirupathi India Andhra University Andhra Pradesh Visakhapatnam India Department of Computer Science and Engineering Vignan’s Institute of Engineering for Women Visakhapatnam JNTU-GV Andhra Pradesh Vizianagaram India Department of Electrical and Electronics Engineering Mother Theresa Institute of Engineering and Technology Palamaner JNTUA Andhra Pradesh Anantapur India

ISBN: (纸本)9783031513374

A Mobile Ad-hoc Network (MANET) is a wirelessly connected network of mobile devices that configures itself without the need for infrastructure. With the freedom to travel in any direction, every device within a MANET will regularly switch links with other devices. Each device operates as a router. The key difficulty in developing a MANET is ensuring that every device has the means to constantly update the data needed for accurate traffic routing. These networks can function alone or they can be linked to the wider Internet. Since MAODV is the reactive protocol linked to the Ad hoc On-Demand Distance Vector (AODV) routing protocol, it is comparable to AODV in terms of packet formats. The unicast Route Table and the packet types for the Route Request and Route Reply are derived from those used by AODV. In a similar vein, AODV defines a large number of the configuration settings that MAODV uses. A mobile node that wants to join or participate in a group inside an ad hoc network can do so dynamically, autonomously, and across several hops using the Modified Ad hoc On-Demand Distance Vector (MAODV) protocol. For managing routing in a mobile setting, there are various protocols. The MAODV (Modified Ad hoc On-Demand Distance Vector) routing protocol used in MANETs is therefore presented here. Packet delivery ratio, average end-to-end delay, and throughput are the measures utilized in simulation. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Mobile ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Falcon Optimized CNN for the Detection of Alzheimer's Disease in MRI Image

Falcon Optimized CNN for the Detection of Alzheimer's Diseas...

引用

Smart Systems for applications in Electrical sciences (ICSSES), International Conference on

作者： S. Febeena Ezhil Jothi L. Mahalakshmi P. Elamurugan Naveenkumar Kaliyan J. Swapna R. Rajeshwari Department of Artificial Intelligence and Data Science Adhi College of Engineering And Technology Kanchipuram Department of Biomedical Engineering Kongunadu College of Engineering and Technology Trichy Department of Instrumentation and Control Engineering Sri Manakula Vinayagar Engineering College Puducherry Department of Computer science and Engineering Veltech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai Tamilnadu India Department of Electrical and Electronics Engineering J.P. College of Engineering Ayikudi Tenkasi

ISBN: (数字)9798331507671

ISBN: (纸本)9798331507688

Degenerative illnesses that lead to the eventual death of brain neurons afflict a large number of people. Compared to the traditional Machine Learning (ML) approach, the recent success in the medical community of classifying Alzheimer's Disease (AD) utilized a Deep Learning (DL) technique eliminates the necessity for manual feature extraction techniques. Although DL methods are widely used, there is currently a dearth of trustworthy and comprehensive research on the quantitative analysis of brain Magnetic Resonance Image (MRI) data. In this paper, an effective AD classification approach is proposed that use MRI to classify brain structure and diagnose AD. Gaussian filter is used to eliminate noises at different degrees of complexity, noisy backgrounds, low contrast, and partial volume effect in the original input image. Next, K-Means clustering segmentation is useful for dividing image into different regions based on pixel intensity values. Key features for categorization are extracted using the Gray Level Co-Occurrence Matrix (GLCM) method. A Convolutional Neural Network (CNN), enhanced by Falcon Optimization Algorithm (FOA), is employed for AD categorization. The proposed system, implemented on the Python platform using the best Alzheimer's MRI dataset, demonstrates an enhanced accuracy of 93.21 %. Additionally, this model-based approach provides a capable avenue for advancing research in the early detection of AD and holds substantial potential in differentiating AD patients from healthy individuals.

关键词： Training Accuracy Magnetic resonance imaging Neurons Magnetic resonance Feature extraction Convolutional neural networks Alzheimer's disease Optimization Testing

来源：评论

学校读者我要写书评

暂无评论

Advancing Visual Marketing Strategies Through Deep Learning-Based Image Recognition for Improved Customer Engagement and Brand Visibility 3

Advancing Visual Marketing Strategies Through Deep Learning-...

引用

3rd IEEE International Conference on Automation and Computation, AUTOCOM 2025

作者： Pandiri, Ramu Nnadhini, T.J. Velmurugan, R. Menaga, A. Karpagam, J. Vinothkumar, K. Infomatics Corp DallasTX United States Department of Computer Science and Engineering Chennai India Karpagam Academy of Higher Education Coimbatore India St Joseph's College of Engineering Department of Mba Chennai India Karpagam Academy of Higher Education Department of Electrical and Electronics Engineering Coimbatore India Psna College of Engineering and Technology Department of Ece Dindigul India

ISBN: (纸本)9798331542375

This paper aims at analyzing the effectiveness of utilizing deep learning-based image recognition in enhancing the visual marketing thereby determining the extent to which clients' attention and brand awareness are likely to be affected. It uses convolutional neural networking (CNN) to analyze and classify the visual content and the models used include VGG16, ResNet50, InceptionV3. An effective implementation of the data gathering, feature engineering, and algorithm development can be seen in the enhancing of the marketing effectiveness. This entails better accuracy of images in classification. This involves gaining high engagement rates from the customers. probabilities of high visibility of the brands across the various platforms. The study points at the possibility of deep learning technologies in changing visual marketing practices and therefore serves as a useful reference guide to business entity that wish to align themselves with adequate marketing practices in the growing digital landscape. © 2025 IEEE.

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：