检索结果-内蒙古大学图书馆

5th international conference on Computer Information and Big Data Applications, CIBDA 2024

作者： Wu, Zhengnan Wuhan Donghu University Hubei Wuhan430212 China

ISBN: (纸本)9798400718106

In the rapid development of the internet of Things technology, image recognition and detection technology is used in all walks of life. In order to solve the limitations of traditional image detection methods in practical application, such as slow efficiency, low precision and lack of in-depth analysis, this study will design an artificial intelligence image detection system based on the internet of Things, starting from the requirements of synthetic signal images, image features acquisition and cloud image processing functions. Complete the design of image analysis system, image feature acquisition system and image integration system. Finally, the artificial intelligence image detection system is simulated and debugging. The test results prove that the artificial intelligence image detection system based on the internet of Things has the advantages of fast detection speed, high recognition accuracy and big data integration analysis, and can meet the stable operation of any configuration computer platform, providing new ideas for the development and research of image detection system. © 2024 ACM.

关键词： internet of things

来源：评论

学校读者我要写书评

暂无评论

An image encryption algorithm based on non-degenerate chaos and dynamic Bi-directional permutation 16

An image encryption algorithm based on non-degenerate chaos ...

引用

16th international conference on signal Processing systems, ICSPS 2024

作者： Liao, Yunlong Xu, Qingyang Zhang, Qiyuan Xing, Zheng Yuan, Xiaochen Faculty of Applied Sciences Macao Polytechnic University China

ISBN: (纸本)9781510689251

In the wake of the accelerated advancement of internet of Things(IoT) technology, a significant volume of multimedia information is emerging as the dominant component of IoT applications. However, this information also led to big security risks. Therefore, a secure and reliable image encryption scheme based on non-degenerate hyper chaos and dynamic bidirectional permutation is proposed for the characteristic of digital images which the primary information carrier in the IoT communication environment. The scheme uses non-degenerate discrete chaos to generate pseudo-random sequences and applies them to the encryption process involving image confusion, dynamic permutation, and dynamic diffusion. Through theoretical analysis and experimental verification, the algorithm exhibits high sensitivity to both the plaintext images and the ciphertext images. Concurrently, it can effectively resist common noise attacks and cryptographic attacks. In conclusion, the proposed scheme offers superior encryption capabilities and stands as a secure solution, compatible with a diverse range of IoT environments. © 2025 SPIE.

关键词： Chaos theory

来源：评论

学校读者我要写书评

暂无评论

Skeleton-based Human Activities Fine-grained Recognition with RFID technology

Skeleton-Based Human Activities Fine-grained Recognition wit...

引用

9th international conference on signal and image Processing (ICSIP)

作者： Liu, Meng Chen, Yihong Zheng, Hao Huang, Lingbo Zhao, Kun Zhao, Yilin China West Normal Univ Internet Things Percept & Big Data Anal Key Lab N Nanchong Peoples R China

ISBN: (纸本)9798350350920

Human activity recognition(HAR) has received increasing attention and has been applied in multiple fields such as healthcare and human-computer interaction. Previous activity recognition methods have problems such as privacy leakage, strong intrusion on users, and coarse detection granularity. Therefore, we propose a privacy protection, easy-to-use, identifiability, lightweight, and fine-grained human activity recognition method based on bound-RFID technology. Firstly, we utilize the fundamental physical characteristics of radio frequency signals, such as doppler frequency (DF), received signal strength indicator (RSSI), and phase, which reflect human activity. Analyze the correlation between these data and human activities, establish a graphical relationship between data changes and activities, and generate human postures through posture time windows. Secondly, we integrate tags information to model human activities by establishing spatio-temporal skeleton graphs with temporal and spatial information. Finally, we model the spatio-temporal skeleton graph convolutional neural network to classify these graphs. As far as we know, this is the most refined HAR based on bound-RFID tags.

关键词： RFID GCN HAR Skeleton-based

来源：评论

学校读者我要写书评

暂无评论

Self-Supervised Cross-Scale Nonlocal Attention Network for Blind image Super-Resolution 21

Self-Supervised Cross-Scale Nonlocal Attention Network for B...

引用

21st IEEE international conference on Mobile Ad-Hoc and Smart systems (MASS)

作者： Li, Yinong Yu, Jing Xiao, Chuangbai Beijing Univ Technol Comp Coll Beijing Peoples R China

ISBN: (纸本)9798350363999;9798350364002

Most existing image super-resolution (SR) methods commonly assume that the degradation kernel is fixed and known. Blind SR aims to handle various unknown degradation processes closer to real-world applications and more generalizations. We propose a self-supervised cross-scale nonlocal attention network for blind SR (CNSR) which jointly models a blur kernel estimation module (KEM) based on a regularization model and a high-resolution image reconstruction module (HRM) based on a deep neural network. The low-resolution (LR) image is used as the supervision signal, and the blur kernel and high-resolution image are estimated simultaneously by iterating the two modules alternately. In HRM, we introduce a cross-scale nonlocal correspondence aggregation module (CNCAM) that uses the cross-scale self-similarity of images to provide additional information for image reconstruction. Experimental results show that CNSR can effectively improve image reconstruction performance.

关键词： blind super-resolution kernel estimation cross-scale self-similarity nonlocal attention self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent ID System for the Industrial internet of Things Using Machine Learning Algorithms

Intelligent ID System for the Industrial Internet of Things ...

引用

international conference on Advanced systems and Emergent Technologies (ICASET)

作者： Sawssen, Bacha Noureeddine, Liouane Univ Monastir Natl Engn Sch Monastir Lab Automat Signal & Image Proc Monastir Tunisia

ISBN: (纸本)9798350384901;9798350384895

The Industrial internet of Things offers modern industrial firms numerous opportunities for significant growth. The internet of Things technology utilized in the sector has developed into a large-scale network as a result of the increasing amount of data and devices. Industrial IoT networks are by nature susceptible to hacking and intrusions. Thus, in order to ensure the security of IIoT networks, intrusion detection system IDS development is essential. This study proposes an IDS to defeat a variety of cyberattacks in industrial internet of things environments. The suggested approach reduces the dimension of the data characteristics and enhances the performance of anomaly identification by using the kernel principal component analysis technique. For binary classification, we use the kernel extreme learning machine to identify if the traffic flow is benign or attack. We use it to multiclass classification in order to classify the set of attacks based on the specific type of attack. The performance results are assessed and analyzed using the X-IIoTDS dataset in order to prove the effectiveness of the suggested anomaly detection approach. The evaluation's findings show that the suggested anomaly detection strategy may greatly raise detection performance outcomes in terms of specificity, accuracy, sensitivity, and F1-score while also successfully increasing detection efficiency.

关键词： cybersecurity internet of Things (IoT) industrial intrusion detection feature selection

来源：评论

学校读者我要写书评

暂无评论

Robust image watermarking scheme based on orientation of local image texture 16

Robust image watermarking scheme based on orientation of loc...

引用

16th international conference on signal Processing systems, ICSPS 2024

作者： Li, Qiutong Zhang, Qiyuan Yuan, Xiaochen Faculty of Applied Sciences Macao Polytechnic University China

ISBN: (纸本)9781510689251

With the rapid development of big data and internet of Things (IoT), more and more digital products are emerging. However, this has also brought about a growing problem of copyright violation. Digital image robust watermarking technology can effectively resist various attacks and protect image copyright. Most of the existing robust watermarking schemes generally adopt the global embedding method and often ignore the texture orientation of the cover image itself leading to poor imperceptibility and robustness. In this paper, we propose an innovative digital image robust watermarking scheme. Firstly, we conduct the Oriented FAST and Rotated BRIEF (ORB) and Speeded Up Robust Features (SURF) feature point detection algorithms, combined with the texture complexity of the cover image to select the most complex texture region as the local embedding location of the watermark. Secondly, to further improve the robustness of the watermarked image, we conduct the Discrete Cosine Transform (DCT) adaptive inter-block correlation algorithm. We embed the watermark into the cover image by adjusting the difference between the image embedding block and the adjacent block. We have tested a dataset containing multiple images, in which various common attacks are simulated and multiple cover images are tested. By comparing the experimental results, our scheme performs better regarding robustness and imperceptibility. © 2025 SPIE.

关键词： Cosine transforms

来源：评论

学校读者我要写书评

暂无评论

MultiView Markerless MoCap - MultiView Performance Capture, 3D Pose Motion Reconstruction and Comparison 17

MultiView Markerless MoCap - MultiView Performance Capture, ...

引用

17th international conference on signal-image technology and internet-based systems, SITIS 2023

作者： Bisht, Pratik Singh Colantoni, Philippe Muselet, Damien Tremeau, Alain Université de Lyon Université Jean Monnet Laboratoire Hubert Curien Umr 5516 France

ISBN: (纸本)9798350370911

This article explores the challenges and advancements in multi-view camera systems, 2D pose estimation, and 3D reconstruction for capturing and reconstructing live performances. It conducts a comparative analysis of methodologies at each stage of the pipeline, identifying strengths, weaknesses, and effective techniques. The study addresses the robustness of existing techniques in diverse scenarios and aims to integrate these fields into a unified framework for high-quality reconstructions. It contributes to the development of advanced multi-camera systems applicable across domains and serves as a valuable resource for future research in the field of performance capture and analysis. © 2023 IEEE.

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Lightweight image Encryption Using a Novel Chaotic Technique for the Safe internet of Things

引用

international JOURNAL OF COMPUTATIONAL INTELLIGENCE systems 2024年第1期17卷 1-21页

作者： Gilmolk, Ali Mohammad Norouzzadeh Aref, Mohammad Reza Sharif Univ Technol Dept Elect Engn ISSL Lab Tehran Iran

Recently, the field of lightweight cryptography (LWC) has emerged in response to the security needs of low-cost, widely used technology. It is essential to implement an encryption approach with access control to give less complex, more flexible, and safe access to sensitive data. In this work, a novel lightweight chaotic encryption approach with fuzzy access control is presented to encrypt light images in the IoT domain, while maintaining image quality. With the aid of multiplexer modeling and information shift register technology, the algorithm's design combines random and chaotic mapping approach based on a specific password key with a predetermined number of fuzzy logic shifts on the password key for the image pixels. Further, to extract the private key with complexity and boost defense against attacks, a shift register and logical xor combination is employed. The simulation of the proposed model for AVR microcontroller has been done under MATLAB software and the design of various encryption components has been used to implement lightweight mapping. The proposed system has been evaluated in terms of histogram analysis, adjacent pixel correlation analysis, contrast analysis, homogeneity analysis, energy analysis, NIST analysis, error mean square analysis, information entropy, pixel number change rate, integrated mean change intensity, peak signal-to-noise ratio, and time complexity. Remarkably, the proposed technique has demonstrated high efficiency. The simulation results show that the homogeneity, energy, contrast, NPCR, and UACI criteria have improved by 11.5%, 13.1%, 19%, 0.53%, and 0.12%, respectively, compared to other methods in other articles.

关键词： Lightweight image encryption internet of Things Fuzzy logic Security Chaotic mapping MATLAB

来源：评论

学校读者我要写书评

暂无评论

REINFORCEMENT LEARNING-based SECURE VIDEO TRANSMISSION FOR IOV systems 31

REINFORCEMENT LEARNING-BASED SECURE VIDEO TRANSMISSION FOR I...

引用

2024 international conference on image Processing

作者： Liu, Lixin Liu, Zhibo Lu, Luxiaozhen Bu, Yanling Han, Bin Xiao, Liang Nanjing Univ Aeronaut & Astronaut Coll Comp Sci & Technol Nanjing Peoples R China Nanjing Univ Posts & Telecommun Sch Communicat & Informat Engn Nanjing Peoples R China Xiamen Univ Dept Informat & Commun Engn Xiamen Peoples R China

ISBN: (纸本)9798350349405;9798350349399

The rapid growth in the number of vehicles and types of services such as video transmission improves the quality-of-service (QoS) requirements and increases the difficulty in resisting eavesdropping attacks on the internet of Vehicles (IoV). Existing video transmission schemes that either ignore the impact of eavesdropping attacks or have the full knowledge of the attack model have performance degradation in highly dynamic IoV systems. In this paper, we propose a reinforcement learning-based secure video transmission scheme for IoV systems, which jointly optimizes the access control policy for each vehicle (i.e., the selection of access nodes such as the base stations or unmanned aerial vehicles) and the corresponding transmit power level against active eavesdropping. This scheme uses the QoS and eavesdropping rate as the criteria to evaluate the long-term risk of each state-action pair, which is estimated by a designed deep Q-network to avoid the risky access control policies that cause severe data leakage or video transmission failure. Simulation results show that our scheme reduces the energy consumption, transmission latency, and eavesdropping rate compared with the benchmark.

关键词： internet of Vehicles video transmission eavesdropping reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning-based Intelligent ID System for the internet of Things

A Machine Learning-based Intelligent ID System for the Inter...

引用

2024 IEEE international conference on Advanced systems and Emergent Technologies, IC_ASET 2024

作者： Sawssen, Bacha Noureeddine, Liouane Laboratory of Automatic Signal and Image Processing National Engineering School of Monastir University of Monastir Tunisia

ISBN: (纸本)9798350384895

The internet of Things, or loT, is a rapidly expanding field that has been integrated into numerous different industries. Thanks to this technology, devices may send, receive, and analyze data without the assistance of a human. loT security and privacy concerns continue to be a significant obstacle, despite the fact that it has gained widespread acceptance in a number of important domains due to its ability to simplify human life and enhance service quality. To protect loT networks from different attacks, an anomaly-based intrusion detection system (IDS) can be included as a security feature. In order to combat various cyberattacks in internet of Things environments, this study suggests an anomaly-based intrusion detection system (IDS). The suggested approach makes use of in order to enhance anomaly identification performance and reduce the dimension of the data characteristics.. © 2024 IEEE.

关键词： Intrusion detection

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：