检索结果-内蒙古大学图书馆

A High Destruction-Resistant Resilient Networking Platform for Air-to-Ground Cooperative Communications

China Communications 2025年第4期22卷 27-41页

作者： Dong Ping Ren Jiaxin Guo Jiannan Zhang Yuzhen Liu Qianwen Amr Tolba Huaxin Consultation Design Research Institute Co. Ltd.Hangzhou 310000China School of Communications and Information Engineering Chongqing University of Posts and TelecommunicationsChongqing 400065China China Academy of Information and Communications Technology Beijing 100191China The Computer Science Department Community CollegeKing Saud UniversityRiyadh 11437Saudi Arabia

With the continuous advancement of communication and unmanned aerial vehicle(UAV)technologies,the collaborative operations of diverse platforms,including UAVs and ground vehicles,have been significantly ***,battlefield uncertainties,such as equipment failures and enemy attacks,can impact these collaborative operations'stability and communication *** this end,we design a highly destruction-resistant air-ground cooperative resilient networking platform that aims to enhance the robustness of network communications by integrating ground vehicle information for UAV network *** then incorporates the concept of virtual guiding force,enabling the UAV swarm to adaptively configure its network layout based on ground vehicle information,thereby improving network destruction *** results demonstrate that the UAV swarm involved in the proposed platform exhibits balanced flight energy consumption and excellent performance in network destruction resistance.

关键词： air-to-ground coordination network destruction resistance SpringBoot UAV

来源：评论

学校读者我要写书评

暂无评论

Scalability in Autoencoder-based OFDM Communication System 2

Scalability in Autoencoder-based OFDM Communication System

引用

2nd IEEE International Conference on computer Vision and Machine Intelligence, CVMI 2023

作者： Tsugawa, Seizan Toma, Takao Oshiro, Shiho Wada, Tomohisa University of the Ryukyus Computer Science and Intelligent Systems Program Okinawa Japan Magna Design Net Inc Okinawa Japan University of the Ryukyus Information Technology Center Okinawa Japan University of the Ryukyus Area of Computer Science and Intelligent Systems Dept. of Engineering Okinawa Japan

ISBN: (纸本)9798350305142

This paper proposed Scalability in Autoencoder-based Orthogonal Frequency Division Multiplexing(OFDM) communication system. In the previous research, only the comparison between IEEE802.11a and Autoencoder by the conventional OFDM communication system was performed, and it was proved that the communication system created by Autoencoder exceeded the performance of the conventional system. Therefore, in this paper, it uses IEEE802.11n and compare whether it can be improved by expanding the bandwidth and using ***802.11n standard has an FFT length of 128, a subcarrier number of 114 (108 for data), and modulation schemes of Quadrature Phase Shift Keying(QPSK), 16 Quadrature Amplitude Modulation (16QAM). The GI length is 800ns and the symbol length is 4000ns. In the simulation, a computer simulation was performed using a conventional OFDM communication system and a communication system generated by Autoencoder. Assuming that the simulation environment had an Signal-to-Noise Ratio (SNR) of 0 to 30 and an amplitude r of 0.0 to 1.0, the Symbol Error Rate (SER) status for each SNR was output. As a result of computer simulation, QPSK converged at SNR 27 at IEEE 802.11a, but was able to reduce SER overwhelmingly to SNR 12 at IEEE 802.11n. Also, in 16QAM the convergence at r=0.0 is the same as for SNR22 , but in IEEE 802.11a it does not converge after r=0.6, but in IEEE 802.11n it does not converge only at r=0.9 and r=1.0. As a future task, it will use IEEE802.11ac, which enables communication speeds several times faster than IEEE802.11n, examine whether it is possible to further improve accuracy. And it will continue our research to correspond MIMO communication. © 2023 IEEE.

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

AdaptiveFL: Adaptive Heterogeneous Federated Learning for Resource-Constrained AIoT Systems 24

AdaptiveFL: Adaptive Heterogeneous Federated Learning for Re...

引用

61st ACM/IEEE design Automation Conference, DAC 2024

作者： Jia, Chentao Hu, Ming Chen, Zekai Yang, Yanxin Xie, Xiaofei Liu, Yang Chen, Mingsong MoE Engineering Research Center of SW/HW Co-Design Tech. and App. East China Normal University China School of Computer Science and Engineering Nanyang Technological University Singapore School of Computing and Information Systems Singapore Management University Singapore

ISBN: (纸本)9798400706011

Although Federated Learning (FL) is promising to enable collaborative learning among Artificial Intelligence of Things (AIoT) devices, it suffers from the problem of low classification performance due to various heterogeneity factors (e.g., computing capacity, memory size) of devices and uncertain operating environments. To address these issues, this paper introduces an effective FL approach named AdaptiveFL based on a novel fine-grained width-wise model pruning mechanism, which can generate various heterogeneous local models for heterogeneous AIoT devices. By using our proposed reinforcement learning-based device selection strategy, AdaptiveFL can adaptively dispatch suitable heterogeneous models to corresponding AIoT devices based on their available resources for local training. Experimental results show that, compared to state-of-the-art methods, AdaptiveFL can achieve up to 8.94% inference improvements for both IID and non-IID scenarios. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Railway Passenger Flow and Sales Prediction Using Advanced Machine Learning Techniques

Railway Passenger Flow and Sales Prediction Using Advanced M...

引用

BIT Conference (BITCON), International

作者： Nalli Vinaya Kumari G S Pradeep Ghantasala Rajesh Sharma R Pellakuri Vidyullatha Ananthanagu U Saliha Bathool Department of Computer Science and Engineering Malla Reddy Engineering College for Women JNTUH Hyderabad Department of Computer Science and Engineering Alliance College of Engineering and Design Alliance University Bengaluru India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Guntur Andhra Pradesh India

ISBN: (数字)9798331518394

ISBN: (纸本)9798331518400

Effective passenger waft control is pivotal for the highest quality operation of railway structure, impacting each operational performance and passenger satisfaction. This study delves into the software of system gaining knowledge of strategies to investigate and forecast passenger waft and price tag income inside railway networks. Utilizing historic tour statistics, sensor statistics, and outside influences, we increase predictive fashions that offer treasured insights into passenger conduct and decorate operational decision-making. Our findings spotlight the extensive enhancements in prediction accuracy and operational performance that system gaining knowledge of can deliver, providing sizeable blessings for railway control.

关键词： Support vector machines Knowledge engineering Accuracy Decision making Transportation Predictive models Rail transportation Software Real-time systems Random forests

来源：评论

学校读者我要写书评

暂无评论

Efficient Machine Learning and Factional Calculus Based Mathematical Model for Early COVID Prediction

引用

Human-Centric Intelligent Systems 2023年第4期3卷 508-520页

作者： Chandra, Saroj Kumar Bajpai, Manish Kumar Center of Excellence in Industry 4.0 Computer Science and Engineering OP Jindal University Raigarh India Computer Science and Engineering PDPM-Indian Institute of Information Technology Design and Manufacturing Jabalpur India

Diseases are increasing with exponential rate worldwide. Its detection is challenging task due to unavailability of the experts. Machine learning models provide automated mechanism to detect diseases once trained. It has been used to predict and detect many diseases such as cancer, heart attack, liver infections, kidney infections. The new coronavirus has become one of the deadliest diseases. Its case escalated in unexpected ways. In the literature, many machine learning models such as Extreme Gradient Boosting (XGBoosting), Support Vector Machine (SVM), regression, and Logistic regression have been used. It has been observed that these models can predict COVID cases early but are unable to find the peak point and deadline of the disease. Hence, mathematical models have been designed to early predict and find peak point and dead-line in disease prediction. These mathematical models use integral calculus-based Ordinary Differential Equations (ODEs) to predict COVID cases. Governments are dependent on these models’ pre- diction for early preparation of hospitalization, medicines, and many more. Hence, higher prediction accuracy is required. It has been found in the literature that fractional calculus-based models are more accurate in disease prediction and detection. Fractional models provides to choose order of derivative with fractional value due to which information processing capability increases. In the present work, mathematical model using fractional calculus has been devised for prediction of COVID cases. In the model, quarantine, symptomatic and asymptomatic cases have been incorporated for accurate prediction. It is found that the proposed fractional model not only predicts COVID cases more accurately but also gives peak point and dead-line of the disease.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Deep Drive Analysis Framework on Emotions of Users in Attention Driven Systems 8

A Deep Drive Analysis Framework on Emotions of Users in Atte...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Dharshini, S. Akshita, Ravula Panigrahi, Suman Varma, Nadimpalli Sai Kiran Kumar Thangavel, Senthil Somasudaram, K. Abel Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Tamil Nadu Coimbatore India Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Coimbatore India Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Mathematics Tamil Nadu India Cape Peninsula University of Technology Faculty of Informatic and Design Department of Information Technology South Africa

ISBN: (纸本)9798350376425

One of the ways humans communicate is by using facial expressions. In psychology, the detection of emotions or facial expressions requires analysis and assessment of decisions in predicting a person's emotions or group of people in communicating. Emotion is powerful in many ways because it can influence a decision and urge people to act. This emotion like anger, happiness, sadness, disgust, fear, surprise, and neutral detection is used for human behaviour and understanding, action of mental disorders, and synthetic human expressions. This can be used in healthcare, marketing, and manufacturing. Here the paper is based on marketing where we can detect the emotions of the people watching the ads. This emotion detection for the ads can be used for predictions like whether customers will like the product or not, whether the sales will increase or not, etc. The methodology used to predict human emotion through the face is CNN and MobileNetV2 with LSTM which is a pretrained model. The architecture involves pre-processing of the data, feature detection, face detection, and detection of emotion. There are various datasets used for detecting emotions like FER-2013, JAFFE, CK+, etc. Here the FER-2013 is used. The performance of the model is measured by using confusion matrix, recall, precision, f1-score, and accuracy. © 2024 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Facemask Detection System using CNN Model

Facemask Detection System using CNN Model

引用

Recent Advances in science and engineering Technology (ICRASET), International Conference on

作者： Senbagavalli M Saswati Debnath Rajagopal R Kishkind Ghildial Computer Science & Engineering and IT Department Alliance College of Engineering & Design Alliance University Bangalore Karnataka India Computer Science & Engineering Department Alliance College of Engineering & Design Alliance University Bangalore Karnataka India

Global trade and transportation have been impacted by the COVID-19 epidemic, which has quickly affected our everyday activities. One of the best ways to stop the Covid-19 virus from transmitting is to wear a face mask. As a result, the World Health Organization (WHO) advised wearing masks as a precaution in crowded areas. Not only COVID-19, wearing mask can reduce the risk of many infectious diseases. In certain places, diseases caused by bacteria, viruses, fungi, or parasites spread quickly due to the inappropriate usage of face masks. Many public services providers demand that their clientele participate in their services while suitably dressed in masks. Therefore, identifying face masks has become a crucial duty in supporting global civilization. This paper develops face mask detection system with an alert that detects the presence of a mask in real-time. The proposed system accurately examines the face from the picture and then determines whether it is covered by a mask or not. A notification can be issued to the administrator if the camera records an unrecognizable face. After that, the administrator will be able to track down the infringer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review of Sensor-Based Smart Packaging Technology

A Comprehensive Review of Sensor-Based Smart Packaging Techn...

引用

International Conference on Power engineering and Intelligent Systems, PEIS 2023

作者： Aniruddha Prabhu, B.P. Dani, Rakesh Abdullah, Khairul Hafezad Sharma, Tushar Bhatt, Chandradeep Chauhan, Rahul Alliance College of Engineering and Design Alliance University Bangalore India University Dehradun India Department of Academic Affair UniversitiTeknologi MARA Perlis Branch Arau Campus Shah Alam Malaysia Department of computer Science and Engineering Graphic Era Hill University Dehradun India

ISBN: (纸本)9789819972159

Economic growth for good quality food contributed to packaging advancements. The topic of discussion in this research paper is intelligent packaging technologies, their applications in food packaging, as well as research and breakthroughs in the packaging industry. Food products with more intelligent and active packaging are both healthier and of higher quality. Active packaging makes use of additives to maintain or extend the quality and freshness of the food inside. During the entire process of storage and transportation, intelligent systems check packed foods for correct information. These advances satisfy the demand for foods that are healthier and can be stored for longer. It is anticipated that the market would expand as a result of the incorporation of active and intelligent packaging technologies. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Additives

来源：评论

学校读者我要写书评

暂无评论

Temporal-aware Mechanism with Bidirectional Complementarity for Video Q&A

Temporal-aware Mechanism with Bidirectional Complementarity ...

引用

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Luo, Yuanmao Wang, Ruomei Zhang, Fuwei Zhou, Fan Lin, Shujin School of Computer Science and Engineering National Engineering Research Center of Digital Life Sun Yat-sen University School of Communication and Design Guangzhou China

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Video question answering (Video Q&A) is a challenging task as it requires a sufficient understanding of the video and question information. Video is composed of frame sequence, which contains multi-scale temporal relationships and corresponding contextual information. A model competently tackle Video Q&A task that needs to be able to: 1) construct long-term and neighborhood dependencies in frame sequences to extract global and local contextual features that can reflect multi-scale temporal dependencies, and deduce the temporal-aware refined features, and 2) identify static and dynamic features from pertinent moments of a video, while filtering away question-irrelated dependencies of feature sequences, to yield the most precise and reasonable temporal-aware overall contextual features. In response to the above requirements, we propose a novel Video Q&A mechanism which consists of Bidirectional Complementary Attention(BCA) module and Adaptive Temporal-aware(ATA) module. Bidirectional complementary attention module stacks multi-head self-attention layer and convolutional layer in different orders to designed two kinds of attention units, which is able to make bidirectional multi-step reasoning based on complete global information and accurate local information to obtain temporal-aware refined features. Adaptive temporal-aware module is used to filter away question-irrelated dependencies in the feature sequence to yield the most precise and reasonable temporal-aware overall contextual features. Comprehensive comparative experiments are conducted on publicly available benchmark datasets. An extended ablation study is further conducted to show the usefulness of each module of the solution in acquiring its computational Q&A capabilities. © 2022 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

ELU-GCN: EFFECTIVELY LABEL-UTILIZING GRAPH CONVOLUTIONAL NETWORK

arXiv

引用

arXiv 2024年

作者： Huang, Jincheng Mo, Yujie Shi, Xiaoshuang Feng, Lei Zhu, Xiaofeng School of Computer Science and Engineering University of Electronic Science and Technology of China China Information Systems Technology and Design Pillar Singapore University of Technology and Design Singapore

The message-passing mechanism of graph convolutional networks (i.e., GCNs) enables label information to be propagated to a broader range of neighbors, thereby increasing the utilization of labels. However, the label information is not always effectively utilized in the traditional GCN framework. To address this issue, we propose a new two-step framework called ELU-GCN. In the first stage, ELU-GCN conducts graph learning to learn a new graph structure (i.e., ELU-graph), which enables GCNs to effectively utilize label information. In the second stage, we design a new graph contrastive learning on the GCN framework for representation learning by exploring the consistency and mutually exclusive information between the learned ELU graph and the original graph. Moreover, we theoretically demonstrate that the proposed method can ensure the generalization ability of GCNs. Extensive experiments validate the superiority of the proposed method. Copyright © 2024, The Authors. 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

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：