检索结果-内蒙古大学图书馆

2024 IEEE international conference on Consumer Electronics-Asia, ICCE-Asia 2024

作者： Huang, Xiang-Rui Chen, Yi-Cheng Chen, Liang-Bi Hu, Wu-Chih National Penghu University of Science and Technology Master Program in Electrical Engineering and Computer Science Department of Electrical Engineering Penghu Taiwan National Penghu University of Science and Technology Department of Computer Science and Information Engineering Penghu Taiwan

ISBN: (纸本)9798331530839

In offshore aquaculture operations, personnel equipped with diving gear are often necessary to inspect the underwater net cages for damage, particularly on the sea floor. This manual inspection process is time-consuming and complex. To overcome this problem, this paper proposes a computer vision solution for identifying damage in underwater net cages to address the inefficiencies and challenges of traditional manual inspections. The proposed scheme utilizes a high-performance multi-branch computational architecture designed based on ShuffleNet architecture to detect net cage damage more efficiently. Experimental results demonstrate that this work performs well on the ImageNet ILSVRC-2010 dataset and achieves an accuracy of 88.54% in underwater net damage detection. © 2024 IEEE.

关键词： Aquaculture

来源：评论

学校读者我要写书评

暂无评论

Combining Global Contextual and multi-Scale Features in ACSOA based multi-Branch Deep Learning for Sensor based HAR 10

Combining Global Contextual and Multi-Scale Features in ACSO...

引用

10th international conference on Electrical Energy Systems, ICEES 2024

作者： Anitha, Cuddapah Mahaveerakannan, R. Archana Jenis, R.M. Sathyendra Kumar, V. Mohan Babu University Erstwhile Sree Vidyanikethan Engineering College School of Computing Department of Computer Science and Engineering Andhra Pradesh Tirupati India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India St.Joseph's College of Engineering OMR Computer Science and Engineering Chennai600 119 India Dept. of CSE Andhra Pradesh India

ISBN: (纸本)9798350353778

Research in human-cyber-physical systems is seeing a substantial push towards human activity recognition (HAR) using smartphone sensors. In computer vision, HAR is still an important but difficult topic to solve. Healthcare and eldercare are two areas where HAR is most suited for integration with other machineries like the Internet of Things. Thanks to advancements in deep learning, HAR presentation optimisation is now possible through automated high-level feature extraction. This study introduces a novel multi-branch deep learning framework that combines global contextual information with multi-scale features to reduce feature redundancy and enhance recognition accuracy. The framework includes two branches: one for extracting global context and another for capturing multi-scale local features using a fully convolutional network (FCN). The advanced crow search optimization algorithm (ACSOA) selects the most relevant features, further boosting classification accuracy. Human activities are classified based on prediction scores from both branches. The study also examines the impact of feature maps, filter sizes, decision fusion strategies, and convolution layers on recognition accuracy. The proposed method achieves approximately 98% accuracy on the UCI HAR and WIDSM datasets, outperforming single-layer decision fusion approaches. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Reviewing Facial Insight - A Smart Approach to Identity Unveiling Through Active Facial Patches and multi-Task Cascaded Convolutional Networks 5

Reviewing Facial Insight - A Smart Approach to Identity Unve...

引用

5th international conference on Sustainable Communication Networks and Application, ICSCNA 2024

作者： Kavin, F. Pradeepa, K. Selvalakshmi, B. Anitha, P. Subashini, K. Vijayalakshmi, P. Cyient Maharashtra Navi Mumbai India St. Michael College of Engineering & Technology Department of Computer Science and Engineering Tamil Nadu Sivaganga India Tagore Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India Sri Sai Renganathan Engineering College Department of ECE Tamil Nadu Coimbatore India Tagore Engineering College Dept. of Information Technology Tamil Nadu Chennai India Knowledge Institute of Technology Department of Computer Science and Engineering Salem Tamil Nadu Chennai India

ISBN: (数字)9798331530013

ISBN: (纸本)9798331530013

This research work proposes an innovative method for enhancing facial recognition accuracy and efficiency by leveraging active facial patches and a multi-Task Cascaded Convolutional Network (MTCNN). The review assesses the paper's contributions, methodology, experimental results, and potential impact on advancing facial recognition technology. It highlights the strengths of the proposed approach, including its clear problem statement, thorough methodology, compelling experimental results, and potential for real-world application. Additionally, the review offers recommendations for improvement, such as further exploration of potential biases and scalability considerations. Overall, Facial Insight presents a promising advancement in identity unveiling within facial recognition systems, contributing to the broader field of biometrics and computer vision. © 2024 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Distributed Hierarchical multi-Agent Reinforcement Learning for Real-World Adversarial Team Games 21

Distributed Hierarchical Multi-Agent Reinforcement Learning ...

引用

21st international computer conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2024

作者： Wei, Li Bei, Hui Ke, Lu School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu611731 China

ISBN: (纸本)9798331519254

Real-world applications often require teams of agents to coordinate strategies against adversaries. However, existing MARL models overlook resource constraints and task complexity, limiting their practical use. To address this, we propose the Distributed Hierarchical multi-agent Learning (DHML) framework, which uses distributed neural networks for efficient computation. A mean-field mechanism and an attentional communication module are further incorporated for scalability, and a hierarchical task decomposition is adopted based on the option-critic framework for handling complexity. Experiments on a simulation platform modeling real communication networks demonstrate DHML's effectiveness across various adversarial scenarios. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Analysis of an Intelligent Pulse Monitoring Beat Wiser System using Machine Learning Classifiers

Analysis of an Intelligent Pulse Monitoring Beat Wiser Syste...

引用

2024 international conference on Distributed Systems, computer Networks and Cybersecurity, ICDSCNC 2024

作者： Jain, Sanat Jain, Garima Phulre, Ajay Kumar Pagare, Shreyas Singh Mathur, Jitendra Pratap Singh Bhati, Vishal Vit Bhopal University Kothri-Kalan School of Computer Science and Engineering Sehore India Chameli Devi Group of Institutions Computer Science Engineering Department Indore India

ISBN: (纸本)9798350375442

In recent decades, vascular disease - which includes a variety of heart-related conditions - has emerged as the primary cause of death worldwide. There are numerous risks associated with heart disease, and it is important to have accurate, trustworthy, and sensible techniques for early detection in order to promptly manage the condition. One popular technique for analyzing large volumes of data in the healthcare industry is machine learning. Machine learning is a widely employed method for analyzing vast amounts of data in the field of healthcare. This paper focused on hyper parameter tuning of multi-classifiers to forecast the occurrence of various heart illnesses in patients and reduce the problem of over fitting. The dataset comprises 14 primary attributes with a proposed framework driven by multi classifier to get predictions. The results indicate that the LGBM classifier achieves the highest accuracy score with 99.7%. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Formation Control of Heterogeneous multi-Agent Systems Under Fixed and Switching Hierarchies

引用

IEEE Access 2024年 12卷 97868-97882页

作者： Shamrooz Aslam, Muhammad Bilal, Hazrat Chang, Wen-Jer Yahya, Abid Anjum Badruddin, Irfan Kamangar, Sarfaraz Hussien, Mohamed China University of Mining and Technology Artificial Intelligence Research Institute Xuzhou221116 China University of Science and Technology of China Department of Automation Hefei230026 China Department of Marine Engineering Keelung202 Taiwan Botswana International University of Science and Technology Department of Electrical Computer and Telecommunications Engineering Palapye Botswana King Khalid University College of Engineering Department of Mechanical Engineering Abha Saudi Arabia King Khalid University Faculty of Science Department of Chemistry Abha61413 Saudi Arabia

Modern information technology is driving the rapid development of the information and automation industry through the combination of computer technology, communication technology, and control technology. Inspired by nature's cluster movement, such as birds, people proposed the concept of multi-Agent Systems (MASs). This paper deals with the formation control problem for a class of heterogeneous multi-agent systems with time-delays. First, the formation control of heterogeneous multi-agent systems with communication delay in fixed and switching topologies is investigated. A heterogeneous multi-agent system model with input delay and communication delay is established. Furthermore, based on this model, the formation control protocol is designed and the stability of the proposed control protocol in fixed and switched topologies is analyzed. The first- and second-order multi-agent control system was formulated for both fixed and switched topology, respectively. Then, using the new LMI toolbox, the feasibility of the parameters is obtained and the example is created by MATLAB. The simulation results show that the proposed formation control protocol with delay in this paper can make the systems converge to the expected value under fixed and switched hierarchies. © 2013 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Vision Based Littering Detection and Face Tagging using multi-model Architecture 4

Vision Based Littering Detection and Face Tagging using mult...

引用

4th IEEE international conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2024

作者： Kumar, Ananya Tripathi, Uday Kaushik, Vikram Gambo, Abdul Saddam Singh, Jaspreet Agrawal, Adarsh Kaur, Jaspreet Lovely Professional University School of Computer Science and Engineering Phagwara India Lovely Professional University Department of Computer Science & Technology Phagwara India

ISBN: (纸本)9798350360165

In this research, a new framework has been introduced to detect illegitimate littering action using multi-model architecture based on computer vision methods. The methodology aims to address the pervasive issue of littering by leveraging computer vision techniques. It utilizes a multi-model architecture, integrating pose detection, object detection and face recognition algorithms to identify relation between joints of a person and object held by them. Also, face tagging method is performed to mark the person as potential litterer which was not previously introduced in existing literature. This study conducted multiple trials which showed effectiveness of the model in real-world instance. Results showed overall precision of 0.947 and recall of 0.857 over a significant number of trials. The experimental analysis for individual components of this model has been discussed in ablation. With its potential to significantly mitigate the impact of littering, this innovative approach holds great promise for creating cleaner and more sustainable communities. © 2024 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Guest Editorial: Special Issue of Selected Extended Papers From the IEEE international conference on Flexible, Printable Sensors and Systems (FLEPS) 2024

IEEE Journal on Flexible Electronics

引用

IEEE Journal on Flexible Electronics 2025年第1期4卷 2-3页

作者： Mantysalo, Matti Marrocco, Gaetano Agarwale, Shweta Grau, Gerd Gao, Wei Tampere University Faculty of Information Technology and Communication Sciences Tampere33720 Finland University of Roma Tor Vergata Dipartimento di Ingegneria Civile ed ed Ingegneria Informatica Rome00133 Italy Aarhus University Department of Electrical and Computer Engineering Aarhus8200 Denmark York University Department of Electrical Engineering and Computer Science TorontoONM3J 1P3 Canada Caltech Department of Engineering and Applied Science PasadenaCA91125 United States

来源：评论

学校读者我要写书评

暂无评论

Risk prediction method of multi-source network information cross-space fusion based on reinforcement learning 2

Risk prediction method of multi-source network information c...

引用

2nd IEEE international conference on Sensors, Electronics and computer engineering, ICSECE 2024

作者： Chen, Yiping Zheng, Yingzi Guangzhou Institute of Science and Technology Department of Computer Science and Engineering Guangzhou510540 China

ISBN: (纸本)9798350373646

In order to improve the level of cross-space transmission and sharing of multi-source network information, it is necessary to effectively predict the process risk of fusion, and a risk prediction method of cross-space fusion of multi-source network information based on reinforcement learning is proposed. A cross-spatial dimension construction and transformation model of multi-source network information is constructed, and a feature-tag correlation selection model is established. Combined with the maximum feature-tag correlation identification method, the cross-spatial transformation and reinforcement tracking learning of multi-source network information are realized, and the redundancy test in the process of information cross-spatial fusion is realized by reinforcement learning. The frame structure model of network topology transmission is established according to the self-organized decentralized distributed networking mode of multi-source network space, and the reinforcement learning of information fusion risk prediction is realized by using the replacement parameter configuration and protocol configuration of channel resources, according to the reinforcement learning results. The simulation results show that the proposed method has a high degree of fitness for risk prediction of cross-space fusion of multi-source network information, improves the utilization rate of networking channels, and has good reliability in the process of channel access and resource allocation, effectively reducing the fusion risk, thus improving the transmission channel balance of multi-source networks. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Abstract Thinking of Beginning Electrical engineering and computer science Students 26th

Abstract Thinking of Beginning Electrical Engineering and Co...

引用

26th international conference on Interactive Collaborative Learning (ICL) - Towards a Hybrid, Flexible and Socially Engaged Higher Education / 52nd IGIP international conference on engineering Pedagogy

作者： Gero, Aharon Hadish, Mohammed Ali Kvatinsky, Shahar Technion Israel Inst Technol Haifa Israel

ISBN: (纸本)9783031530210;9783031530227

The Abstract thinking is the capability to deal with relevant information for a given phase while temporarily disregarding the irrelevant details for the current step. Abstract thinking is required in a wide variety of disciplines. It is of special importance in engineering, where examining many topics at different detail levels is needed. However, the literature implies that the abstract thinking of beginning students is insufficient. In light of the above, the research aimed to assess the abstract thinking of beginning electrical engineering and computer science students. The study used closed and open-ended instruments, and involved 64 undergraduate students at the Technion - Israel Institute of Technology. According to the findings, the average abstract thinking of the participants is moderate, with no significant difference between the two groups of students.

关键词： Abstract Thinking Electrical engineering Students computer science Students

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：