检索结果-内蒙古大学图书馆

3rd International Academic Exchange Conference on Science and technology Innovation, IAECST 2021

作者： Da, Xinmin Zhang, Jingjing Chen, Luyu Ma, Mengting Xinjiang Agricultural University XJAU Network and Information Technology Center Urumqi China Xinjiang Agricultural University XJAU School of Computer and Information Engineering Urumqi China Zhejiang University ZJU College of Computer Science and Technology Hangzhou China

ISBN: (纸本)9781665402675

Semantic segmentation from very high-resolution (VHR) remote sensing images is of great significance in a broad spectrum of applications. In recent years, deep learning techniques have been used to accomplish relevant tasks. Many of such attempts start with selecting only three image channels for fusion, followed by establishing a segmentation model, making it tough to exploit the information of all individual image channels. Consequently, fusing multi-modal data for improving segmentation performance has received considerable research attention. In this article, we propose a novel approach enabling effective feature fusion for better semantic segmentation from VHR remote sensing images. Based on the encoder-decoder model, our approach's encoder comprises two branch networks simultaneously extracting features from heterogeneous image data. In particular, we introduce multi-task attention networks (MTANs) in the encoder to fuse feature maps, enabling both branch networks to complement each other through the task. Experiments demonstrated that our approach outperformed several benchmark models on two image datasets, proving its promise in semantic segmentation from VHR remote sensing images.s given in this document. © 2021 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

ARES-WiGR: An Attention-enhanced ResNet based Wi-Fi Gesture Recognition

ARES-WiGR: An Attention-enhanced ResNet based Wi-Fi Gesture ...

引用

IEEE Conference on computer Communications Workshops, INFOCOM Wksps

作者： Kexin Yao Han Li Ming Liu Bo Gao Ke Xiong Pingyi Fan Engineering Research Center of Network Management Technology for High Speed Railway of Ministry of Education School of Computer and Information Technology Beijing Jiaotong University Beijing China Collaborative Innovation Center of Railway Traffic Safety Beijing Jiaotong University Beijing China National Engineering Research Center of Advanced Network Technologies Beijing Jiaotong University Beijing China Department of Electronic Engineering Tsinghua University Beijing China

This paper proposes an Attention-enhanced ResNet based Wi-Fi Gesture Recognition (ARES-WiGR), in which it first extracts Doppler Frequency Shift (DFS) vector parameters from Channel State Information (CSI) via conjugate multiplication and antenna selection. Then, the DFS spectrogram is obtained by Short Time Fourier Transform (STFT), and the DFS spectrogram features are used as the input of the proposed neural network model. Moreover, with the attention mechanism, ARES-WiGR is able to automatically recognize the important information and achieve better recognition effect. The performance is examined in real environment, which shows that the proposed ARES-WiGR effectively extracts gesture features and improves recognition accuracy to about 96%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Emotion Recognition Empowered Human-computer Interaction with Domain Adaptation network

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Xu, Xu Fu, Chong Chen, Junxin Northeastern University School of Computer Science and Engineering Shenyang110004 China Dalian University of Technology China The School of Software Dalian116621 China Northeastern University School of Computer Science and Engineering Shenyang110004 China Northeastern University Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Shenyang110819 China Ministry of Education Engineering Research Center of Security Technology of Complex Network System Shenyang110004 China Dalian University of Technology School of Software Dalian116621 China

Multi-modal emotion recognition plays a vital role in the human-computer interaction (HCI) for consumer electronics. Nowadays, many studies have developed multi-modal fusion algorithms for this ***, two challenging issues remain unsolved, i.e., inefficient multi-modal feature fusion and unclear distance in feature *** this end, we develop a novel framework, namely LAFDA-Net, for cross-subject emotion recognition using EEG and eye movement *** is based on low-rank fusion and domain adaptation *** specifically, the multi-modal signals are input into the feature extraction branch in parallel to generate ***, these features are fused by the low-rank fusion branch, reducing complexity and avoiding ***, the fused features are flattened and sent to the classification branch to determine the emotion *** training, these features are input into the domain adaptive branch to bridge the gap between the source domain and target *** benchmark datasets, i.e., SEED, SEED-IV, and SEED-V, are employed for performance *** results demonstrate that the proposed LAFDA-Net is robust, effective, and has advantages over peer methods. © 1975-2011 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Sum Computation Rate Maximization in Self-Sustainable RIS-Assisted MEC

Sum Computation Rate Maximization in Self-Sustainable RIS-As...

引用

IEEE Conference on computer Communications Workshops, INFOCOM Wksps

作者： Han Li Ming Liu Bo Gao Ke Xiong Pingyi Fan Khaled B. Letaief Engineering Research Center of Network Management Technology for High Speed Railway of Ministry of Education School of Computer and Information Technology Beijing Jiaotong University Beijing China Collaborative Innovation Center of Railway Traffic Safety Beijing Jiaotong University Beijing China Department of Electronic Engineering Tsinghua University Beijing China Department of Electrical and Computer Engineering Hong Kong University of Science and Technology Hong Kong

This paper studies a self-sustainable reconfigurable intelligent surface (SRIS)-assisted mobile edge computing (MEC) network, where a SRIS first harvests energy from a hybrid access point (HAP), and then enhances the users' offloading performance with the harvested energy. To improve computing efficiency, a sum computation rate maximization problem is formulated. Based on the alternating optimization (AO) method, an efficient algorithm is proposed to solve the formulated non-convex problem. Simulations show that when the SRIS is deployed closer to the HAP, a higher performance gain can be achieved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semantic Structural and Occlusive Feature Fusion for Pedestrian Detection 18th

Semantic Structural and Occlusive Feature Fusion for Pedestr...

引用

18th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2021

作者： Wang, Hui Zhang, Yu Ke, Hongchang Wei, Ning Xu, Zhongyu The College of Computer Science and Engineering Changchun University of Technology Changchun130012 China The School of Computer Technology and Engineering Changchun Institute of Technology Changchun130012 China National and Local Joint Engineering Research Center for Intelligent Distribution Network Measurement Organization Control and Safe Operation Technology of National Development and Reform Commission Changchun Institute of Technology Changchun130012 China

ISBN: (纸本)9783030891879

Pedestrian detection under occlusion scenes remains a formidable challenge in computer vision. Recently, anchor-free approach has been raised on the object detection and pedestrian detection field, anchor-free detector center and Scale Prediction (CSP) has been proposed in pedestrian detection without special measures for occlusion. In this paper, we propose an anchor-free detector named OCSP with power ful occlusion handling ability to existing anchor-free detection network. OCSP integrates prior information into the network to handle occlusion. This high-fusion prior information gives the detector a hint about identifying the structural features of pedestrians. OCSP becomes more robust with the prior information which fusion the semantic head, the visible part, and the size and center body for each pedestrian. The detector enhances the perception of occlusion by predicting the semantic head and visible part. Besides, we design a head branch and add predicting the visible box to achieve a similar result. Experiments show that this fusion of prior information represents a suitable combination. We compare our OCSP with state-of-arts models on the Citypersons dataset, the proposed OCSP detector achieves the state-of-arts result on the CityPersons benchmark. © 2021, Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Risk Modeling and Traceability of Boundary Attacks on Internet of Power Systems Based on Complex networks 9

Risk Modeling and Traceability of Boundary Attacks on Intern...

引用

9th IEEE International Conference on Data Science in Cyberspace, DSC 2024

作者： Li, Xin Qu, Zhaoyang Yu, Tong Xie, Ming Yu, Fu Ding, Wei Northeast Electric Power University School of Electrical Engineering Jilin132012 China People's Bank of China Qinghai Provincial Branch Xining810000 China China Southern Power Grid Guangxi Power Grid Co. Ltd. Research Institute Nanning530023 China China Guizhou Power Grid Co. Ltd. Bijie Power Supply Bureau Bijie551700 China Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Jinan250014 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan250014 China

ISBN: (纸本)9798350391367

With the increasing intelligence of power IoT terminal devices, the massive volume of data transmission, and the widespread adoption of shared services, traditional terminal boundary security mechanisms are unable to keep up with the rapid development of network technologies and applications. Additionally, they fail to trace and source network attacks, leading to frequent organized and purposeful malicious attack incidents. To address these issues, this paper proposes a research method for risk modeling and traceability of boundary attacks on power IoT terminals based on complex networks. First, based on the node information of power IoT terminal devices and complex network theory, a terminal boundary attack network (TBAN) is established. Next, using indicators related to complex network theory, such as degree, in-degree, and out-degree, the terminal boundary attack network is analyzed. Furthermore, a staged TBAN is proposed to analyze the attack risks at different times. Then, combining causal theory, a method for tracing and sourcing terminal boundary attacks based on a causal Bayesian network is proposed to identify and trace malicious attacks. Finally, validation and testing analysis are conducted using the actual deployment of power IoT terminal devices. The proposed analysis method transforms the spatial characteristics of the power IoT terminal boundary into a temporally sequential TBAN, which not only visually reflects attack risks but also reveals the temporal relationships of terminal boundary attacks between lines. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Robotics Architectures Based Machine Learning and Deep Learning Approaches 8

Robotics Architectures Based Machine Learning and Deep Learn...

引用

8th International Conference on Mechatronics engineering, ICOM 2022

作者： Alatabani, Lina E. Ali, E.S. Mokhtar, R.A. Khalifa, Othman O. Saeed, Rashid A. Department of Data Communications & Network Engineering Faculty of Telecommunications The Future University Khartoum Sudan port Sudan Sudan Khartoum Sudan Department of Computer Engineering College of Computers and Information Technology Taif University P.O. Box 11099 Taif21944 Saudi Arabia Department of Electrical and Electronics Engineering Faculty of Engineering International Islamic University Malaysia Malaysia The Libyan Center for Engineering Research and Information Technology Bani Walid Libya

ISBN: (数字)9781839538063

ISBN: (纸本)9781839538063

Robotics has been playing a vital role in our daily lives with a wide range of applications to improve the quality of life. With a variety of usable applications in the medical, manufacturing, and transportation industries, there is a continuous need for improving the performance of robotics for the importance of precision in executing commands and tasks. The implementation of precise commands has led to intense research on approaches to improve the performance of robotics. Machine Learning (ML) and Deep Learning (DL) have been drawing attention to applying architectures and algorithms to robotics which imposed a positive impact on the field of robotics. ML and DL applications in robotics include areas of computer vision, imitation learning, self-supervised learning, assistive and medical technologies, multi-agent learning, and manufacturing. This paper provides a comprehensive review of autonomous vs automatic robotics, robotic applications, extreme learning machine methods, and ML for soft robotics applications, in addition, to discussing the challenges, and future trends for AI applications in robotics applications. © 2022 IET Conference Proceedings. All rights reserved.

关键词： Robotics

来源：评论

学校读者我要写书评

暂无评论

Objective quality assessment of generated high-resolution human face images

Objective quality assessment of generated high-resolution hu...

引用

International Conference on Identification, Information and Knowledge in the Internet of Things (IIKI)

作者： Jiacheng Gu Ding Yue Shaode Yu Peng Zhang Qiurui Sun School of Computer Science Beijing Institute of Technology Beijing China School of Info. and Comm. Engineering Communication University of China Beijing China Education Management Information Center Ministry of Education of the PRC Beijing China Center of Information & Network Technology Beijing Normal University Beijing China

ISBN: (数字)9798331510633

ISBN: (纸本)9798331510640

Human face image generation can be used in media, marketing, education, creativity, research and privacy protection. Many deep learning networks have been proposed for generating high-resolution human face images, while the quality of generated human face images are not fully investigated. To bridge this gap, 11 StyleGAN-based networks are firstly trained via the database Flickr-Faces-HQ (FFHQ). Then, each network produces 10,000 high-resolution (1024 × 1024) human face images. After that, the quality of these generated images are evaluated with 6 Face Image Quality Assessment (FIQA) metrics. The average metric values suggest that the generated human face images are with higher quality than the realistic images in the FFHQ database. However, the failure cases of generated images remind us that artifacts and distortions exist, and unreasonable combinations and meaningless contents are produced. Therefore, significant progress is still required for achieving reliable quality assessment and high-accuracy generation of human faces.

关键词： Measurement Image quality Training Image synthesis Databases Face recognition Quality assessment Reliability Protection Faces

来源：评论

学校读者我要写书评

暂无评论

Research on technology Against Deepfake

Research on Technology Against Deepfake

引用

Mobile networks and Wireless Communications (ICMNWC), IEEE International Conference on

作者： Xia Wei Wenjun Zhang Guozhu Bai Bo Li School of Information Engineering Xi ‘an Mingde Institute of Technology Xi'an China Shaanxi Branch of National Computer Emergency Network Response Technical Team Coordination Center of China Xi'an China

With the help of social networks, Deepfakes enable false information to be presented to netizens in a highly credible manner, which will have a huge impact on individuals, organizations, and countries. It will also pose huge information security risks to individuals, organizations, and countries. Some countries are even seeking to weaponize “deep counterfeiting technology”, which poses significant security risks and has become a focus and difficulty of research both domestically and internationally. Scholars both domestically and internationally are exploring different deep forgery detection countermeasures to eliminate negative impacts. It was found that at the technical level, it can be divided into two types based on processing methods: passive detection algorithms and active defense technologies. According to the different processing objects, passive detection algorithms can be divided into two categories: deep forged image detection and deep forged video detection. In terms of active defense technology, content traceability technology is mainly used to build a trusted system for digital content in the internet to ensure the source security of content. This paper summarizes the current research situation of combating deepfake technology based on blockchain technology from three aspects of building a trusted network, tracing deepfake and content Tamper resistance prevention, analyzes the limitations and risks of using blockchain technology against deepfake technology, and discusses the future research direction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Load Balancing in Small-Cell Access Point Placement

Load Balancing in Small-Cell Access Point Placement

引用

IEEE Conference on Vehicular technology (VTC)

作者： Govind R. Gopal Bhaskar D. Rao Gabriel Porto Villardi Department of Electrical and Computer Engineering University of California San Diego La Jolla United States Wireless Network Research Center National Institute of Information and Communications Technology Yokosuka Japan

We address the uplink small-cell access point (AP) placement problem for optimal throughput, while considering load balancing (LB) among the APs. To consider LB and consequently incorporate fairness in user spectral access, i.e., the frequency of user-to-AP communications, we modify the Lloyd algorithm from vector quantization so that delays incurred by the existence of a large number of users in a cell are accounted for in the AP placement process. Accordingly, we present two methods, the first of which involves the incorporation of weights proportional to the cell occupancy, hence called the Occupancy Weighted Lloyd algorithm (OWLA). The second method adds a new step to the Lloyd algorithm, which involves re-assigning users from higher to lower occupancy cells, and the adoption of a distance threshold to cap the throughput lost in the assignment process. This formulated Lloyd-type algorithm is called the Cell Equalized Lloyd Algorithm-α (CELA-α) where α is a factor that allows for throughput and spectrum access delay trade-off. Extensive simulations show that both CELA-α and OWLA algorithms provide significant gains, in comparison to the standard Lloyd algorithm, in 95%-likely user spectral access. For the α values considered in this paper, CELA-α achieves gains up to 20.83%, while OWLA yields a gain of 12.5%. Both algorithms incur minimal throughput losses of different degrees, and the choice of using one algorithm over the other for AP placement depends on system LB as well as throughput requirements.

关键词：

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：