检索结果-内蒙古大学图书馆

4th international conference on Artificial Intelligence and signal Processing

作者： Joshi, Mukund Patel, Ayush Tripathy, Asis Kumar Vellore Inst Technol Sch Comp Sci Engn & Informat Syst Vellore Tamil Nadu India

ISBN: (纸本)9798350350661;9798350350654

The internet of Vehicles (IoV) has brought a new era of innovation in transportation and mobility (T&M) in smart cities, made possible by the confluence of IoT and Machine Learning (ML) technology. The capabilities and applications of the internet of Vehicles (IoV) have been greatly expanded by the increasing adoption of IoT, 5G connectivity, and autonomous vehicles. Modern machine learning (ML) approaches used in IoV service delivery are examined in this review paper, emphasizing how they might improve multimedia communication quality of experience (QoE) in vital industries like healthcare. ML-based service provisioning enhances the functionality and customer experience of the automotive sector by delivering tailored, efficient, and predictive services by analyzing data from connected automobiles.

关键词： IoV ML Service Provisioning QoE Intelligent Transportation systems

来源：评论

学校读者我要写书评

暂无评论

Uncertainty Quantification based on Gaussian Processes for image Segmentation Tasks 2

Uncertainty Quantification Based on Gaussian Processes for I...

引用

2nd international conference on Mobile internet, Cloud Computing and Information Security (MICCIS)

作者： Gao, Bing Chen, Rui Yu, Tingting Beijing Inst Control Engn Beijing Sunwise Informat Technol Ltd Beijing Peoples R China

ISBN: (纸本)9798350389913;9798350389906

Over the past several years, deep neural networks have permeated many fields of science research and have become an essential part of real-world applications. However, when the model encounters a test sample with uncertainty, compared with the distribution of the training set data, it is crucial for users to determine which of the model's predicted outputs for those test data are trustworthy and which are not, rather than being forced to give an untrustworthy prediction output. To this end, it is necessary to evaluate the model uncertainty, which enables to improve utilization of the model prediction results, especially some safety-critical systems. For image segmentation tasks of safety-critical systems, this paper proposes an uncertainty quantification method based on Gaussian processes to evaluate the trustworthiness of the output predicted by neural network models for the given input, so as to facilitate the selection and optimization of segmentation models and provide the model interpretability. The simulation results indicate that for the pixel error rate of each image, this method can give the confidence interval of the predicted output and the stability of the predicted output, achieving the objective of quantifying and understanding the confidence level of deep learning models.

关键词： deep learning uncertainty quantification trustworthiness safety-critical systems Gaussian processes image segmentation

来源：评论

学校读者我要写书评

暂无评论

PET image Reconstruction based on Multi-kernel Fusion 16

PET Image Reconstruction based on Multi-kernel Fusion

引用

16th international conference on signal Processing systems, ICSPS 2024

作者： Dong, Yisheng Sheng, Yuxia College of Information Science and Engineering Wuhan University of Science and Technology Wuhan430081 China

ISBN: (纸本)9781510689251

Positron emission tomography (PET) is a commonly used medical imaging modality, but it has high noise at low doses. To further optimize PET image reconstruction, this paper proposes a novel approach that incorporates magnetic resonance (MR) image information into kernel-based PET image reconstruction. This method integrates MR image texture information into the kernel matrix of the PET prior information;the integrated information is subsequently incorporated into the forward projection model of PET. First, Haralick texture features from the MR images are obtained. Then, a kernel function is constructed using prior information from PET images and texture information from MR images. Finally, the kernel-based PET image reconstruction method is utilized to generate the reconstructed images. Experimental results demonstrate that the proposed method exhibits superior reconstruction performance compared to other existing kernel-based PET image reconstruction methods. © 2025 SPIE.

关键词： Positrons

来源：评论

学校读者我要写书评

暂无评论

Emergency rescue system for chemical industrial parks based on IoT 4

Emergency rescue system for chemical industrial parks based ...

引用

4th international conference on Machine Learning and Intelligent systems Engineering (MLISE)

作者： Wei, Zhongxia Liu, Zeliang Xu, Qin Wang, Ying Jiangxi Bros Pharmaceut Co Ltd Jiujiang Peoples R China Jiujiang Univ Jiujiang Peoples R China

ISBN: (纸本)9798350375084;9798350375077

With the advancement of technology, the use of IoT technology for information management of safety production in chemical industrial parks is of great significance. This article designs an emergency rescue system for chemical industrial parks based on the internet of Things, which mainly consists of a main control module, infrared detection module, image acquisition module, voice prompt module, network transmission module, etc. This system adopts Zigbee wireless networking technology, which has the characteristics of easy operation, low power consumption, low cost, easy expansion, and easy maintenance. Practice has shown that in the social environment of energy conservation and emission reduction, the system has high application value.

关键词： Emergency rescue system internet of Things ZigBee Intelligent control

来源：评论

学校读者我要写书评

暂无评论

An Algorithm to Reduce Compression Ratio in Multimedia Applications

引用

Computers, Materials & Continua 2023年第1期74卷 539-557页

作者： Dur-e-Jabeen Tahmina Khan Rumaisa Iftikhar Ali Akbar Siddique Samiya Asghar Department of Electronic Engineering Sir Syed University of Engineering&TechnologyKarachiPakistan Department of Information&Computer Science Sir Syed University of Engineering&TechnologyKarachiPakistan

In recent years,it has been evident that internet is the most effective means of transmitting information in the form of documents,photographs,or videos around the *** purpose of an image compression method is to encode a picture with fewer bits while retaining the decompressed image’s visual *** transmission,this massive data necessitates a lot of channel *** order to overcome this problem,an effective visual compression approach is required to resize this large amount of *** work is based on lossy image compression and is offered for static color *** quantization procedure determines the compressed data quality *** images are converted from RGB to international Commission on Illumination CIE La^(∗)b^(∗);and YCbCr color spaces before being *** the transform domain,the color planes are encoded using the proposed quantization *** improve the efficiency and quality of the compressed image,the standard quantization matrix is updated with the respective image *** used seven discrete orthogonal transforms,including five variations of the Complex Hadamard Transform,Discrete Fourier Transform and Discrete Cosine Transform,as well as thresholding,quantization,de-quantization and inverse discrete orthogonal transforms with CIE La^(∗)b^(∗);and YCbCr to RGB *** to signal noise ratio,signal to noise ratio,picture similarity index and compression ratio are all used to assess the quality of compressed *** the relevant transforms,the image size and bits per pixel are also *** the(n,n)block of transform,adaptive scanning is used to acquire the best feasible compression *** of these characteristics,multimedia systems and services have a wide range of possible applications.

关键词： Color image compression color spaces discrete orthogonal transforms(DOTs) peak-to-signal noise ratio(PSNR) similarity index

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based ECG signal processing algorithms and their applications in cardiac health monitoring 4

Deep learning-based ECG signal processing algorithms and the...

引用

4th international conference on Advanced Algorithms and signal image Processing, AASIP 2024

作者： Zhang, Zhiguo Zhonghuan Information College Tianjin University of Technology Tianjin China

ISBN: (数字)9781510682818

ISBN: (纸本)9781510682801

This paper explores deep learning-based algorithms for electrocardiogram (ECG) signal processing and their applications in cardiac health monitoring. Initially, we provide an overview of the fundamental principles of ECG signals and the suitability of deep learning for ECG signal processing. Subsequently, we discuss data preprocessing techniques and the selection and construction of deep learning models aimed at enhancing the accuracy of ECG signal processing. Finally, the focus is on the application of these algorithms in the detection of arrhythmias and the diagnosis of myocardial ischemia, validated through experimental results. The findings of this study offer new technological approaches for cardiac health monitoring and foster the application of deep learning in the field of ECG signal processing. © 2024 SPIE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Key-Independent image Encryption using DNA Encoding and Chaotic Dynamics 10

Key-Independent Image Encryption using DNA Encoding and Chao...

引用

10th international conference on Communication and signal Processing, ICCSP 2024

作者： Maharaja Vannia Moorthi, V. Krishna, Megha R. Kumar, Gopika Anil Thanikaiselvan, V. Subashanthini, S. Amirtharajan, Rengarajan Vellore Institute of Technology School of Electronics Engineering Vellore India Vellore Institute of Technology School of Computer Science Engineering and Information Systems Vellore India Sastra Deemed University School of Electrical & Electronics Engineering Thanjavur613 401 India

ISBN: (纸本)9798350353068

Privacy violations are common in our technology-driven world, where almost everyone interacts with internet-connected electronic devices. To address this, cryptography has emerged, concealing data during transmission to deter hackers. Cryptography involves basic mathematical operations, exchanging data based on a shared key known only to the sender and receiver. However, this method suffers from key dependency at the receiver's end, requiring constant key knowledge. To overcome this issue, a novel image encryption method has been introduced in this paper that is independent of the key on the receiver side. This method leverages techniques such as DNA Encoding, Chaotic Dynamics, and Key Hiding Mechanisms to increase the security of the sent image. The proposed method has been tested experimentally, and the results demonstrate its effectiveness with entropy values exceeding 7.995 and correlation coefficient values below 1% for the vertical, horizontal, and diagonal directions. Overall, the proposed image encryption scheme offers a promising solution for protecting sensitive image data in various applications, combining advanced encryption techniques with key management enhancements to ensure confidentiality and integrity. © 2024 IEEE.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Bearing-crossing Localization technology for UAV Target based on signal Characteristics 16

Bearing-crossing Localization Technology for UAV Target base...

引用

16th international conference on signal Processing systems, ICSPS 2024

作者： Lu, Shanshan Wu, Kun Dai, Wenrui PLA Army Academy of Artillery and Air Defense China

ISBN: (纸本)9781510689251

Passive bearing-crossing localization technology has an important application in the scenario of UAV (Unmanned Aerial Vehicle) target positioning, in which the removal of false intersection points in the process of multi-target location is a key issue. To address this problem, a bearing-crossing localization technology based on the signal characteristics of UAVs is proposed. Firstly, the algorithm analyzes the characteristic parameters of the image transmission signal of UAV. Then, according to the characteristic parameters, the correlation between the signal and the corresponding UAV target is established, and the multi-target bearing-crossing localization problem is transformed into multiple single-target location problems, so as to eliminate false intersection points. Finally, the pseudo-linear least squares method is used to complete the bearing-crossing localization of multiple UAV targets. Simulation results show that the algorithm has good positioning effects and reliability in the positioning of multiple UAV targets. © 2025 SPIE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Research on cryptographic medical image information hiding method based on chaotic system 24

Research on cryptographic medical image information hiding m...

引用

2024 international conference on Virtual Reality, image and signal Processing, ICVISP 2024

作者： Liu, Zilong Haikou University of Economics Hainan Haikou China

ISBN: (纸本)9798400710926

With the continuous advancement of internet technology, the transmission and storage of medical images in the network environment are becoming increasingly frequent. Ensuring the security of these image data has become an urgent and critical task in the field of medical information management today. This paper proposed a medical image encryption method with"numerical invariance" using the Kent chaotic system. Additionally, the paper explores methods for embedding text information within encrypted medical images. Experimental results indicated that the encryption scheme proposed in this study could restore the original medical images and their sensitive information without any damage during the decryption process, and effectively embedded and extracted text information within the encrypted medical images. © 2024 Copyright held by the owner/author(s).

关键词： Information hiding

来源：评论

学校读者我要写书评

暂无评论

Spread-Spectrum based a New Secured Robust imageWatermarking Scheme 3rd

Spread-Spectrum Based a New Secured Robust ImageWatermarking...

引用

3rd international conference on Network Security and Blockchain technology

作者： De, Supriyo Maity, Soumalya Bhaumik, Jaydeb Pal, Pabitra Giri, Debasis Maulana Abul Kalam Azad Univ Technol Dept Comp Applicat Nadia 741249 India Maulana Abul Kalam Azad Univ Technol Dept Informat Sci PG Nadia 741249 India Jadavpur Univ Dept Elect & Telecommun Engn Kolkata 700032 India Maulana Abul Kalam Azad Univ Technol Dept Informat Technol Nadia 741249 India

ISBN: (纸本)9789819780501;9789819780518

Nowadays, the advancement of modern communication systems, along with internet usability, enhances the application of multimedia data in various fields. In this context, security in multimedia data is highly demanding to prevent unauthorized access, as well as to ensure confidentiality. This paper introduces a new reversible blind imagewatermarking scheme to validate the image authentication and confidentiality for secret information. To address this aim, a spread-spectrum-based message hiding technique is developed. The reduced Lorenz map combined with the sine-cos map is employed here to produce a key-dependent pseudo-random number (PRN), which is directly mapped into the cover image according to the bit pattern of the secret message. On the other hand, the message hiding has been performed in the cover image by decomposing it using a two-level integer wavelet transform (IWT). The robustness of the scheme is further improved by employing Hamming (7, 4) code and a geometric distortion correction module. Several cover images are used to examine the effectiveness of the proposed scheme. The experimental results present that this approach has better or equivalent robustness against common sig-D nal processing distortions and geometric distortions compared to relevant existing schemes.

关键词： Blind image watermarking Reversible IWT Chaos-based PRN Spread-spectrum Robustness Imperceptibility

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：