检索结果-内蒙古大学图书馆

RDP: Ranked Differential Privacy for Facial Feature Protection in Multiscale Sparsified Subspaces

IEEE Internet of Things Journal 2025年第11期12卷 17333-17348页

作者： Ou, Lu Liao, Shaolin Gao, Shihui Huang, Guandong Qin, Zheng Hunan University School of Journalism and Communication Hunan Changsha410082 China Sun Yat-sen University School of Electronics and Information Technology Guangzhou510275 China Illinois Institute of Technology Department of Electrical and Computer Engineering ChicagoIL60616 United States Purdue University Elmore School of Electrical and Computer Engineering West LafayetteIN47907 United States Hunan University College of Computer Science and Electronic Engineering Hunan Changsha410082 China State Grid Hunan Materials Company Department of Deployment Management Hunan Changsha410118 China

With the widespread sharing of personal face images on the Internet, systems based on face recognition encounter the real threat of being breached by potential adversaries who are able to access individuals’ face images and use them to intrude the systems. In this article, we propose a novel privacy protection method in the sparsified multiscale feature subspaces to protect sensitive facial features, taking care of the influence or weight-ranked subspace coefficients on the privacy budget, named "ranked differential privacy (RDP)." After the multiscale subspaces’ decomposition, the lightweight Laplacian noise is added to the dimension-reduced sparsified subspaces’ coefficients according to the geometric superposition method. Then, we rigorously prove that the RDP satisfies Ε0-differential privacy. After that, the nonlinear Lagrange multiplier method (LM) is formulated for the constraint optimization problem of maximizing the utility of protected face images of high-visualization quality with sanitizing noise, under a given privacy budget Ε0. Then, two methods are proposed to solve the nonlinear Lagrangian multiplier method (LM) problem and obtain the optimal noise scale parameters: 1) the analytical normalization approximation (NA) method with identical average noise scale parameter for real-time online applications and 2) the LM optimization method via gradient descent (LMGD) to obtain the nonlinear solution through iterative updating for more accurate offline applications. Experimental results on two real-world datasets show that our proposed RDP outperforms other state-of-the-art methods: at a privacy budget of Ε0 = 0.2 , the peak signal-to-noise ratio (PSNR) of the optimized RDP is about ~10 dB higher than (10 times as high as) the highest PSNR of all state-of-the-art methods compared. © 2014 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

The Construction and Application of a Blended Teaching Evaluation Index System Based on Mathematical and Statistical Analysis 24

The Construction and Application of a Blended Teaching Evalu...

引用

2024 International Conference on Artificial Intelligence and Future Education, AIFE 2024

作者： Luo, Dingfu Lao, Yuting Liang, Zhuolai Ye, Qing Department of Computer and Information Engineering Guangdong Songshan Polytechnic College Shaoguan Guangdong China Department of Computer and Information Engineering Youngsan University Yangsan-si Korea Republic of Guangdong Huashao Digital Intelligence Technology Co. Ltd Shaoguan Guangdong China Guangdong Yuebei Shuchuang Technology Co. Ltd Shaoguan Guangdong China

ISBN: (纸本)9798400710650

To scientifically evaluate the effectiveness of blended teaching, an evaluation index system was constructed using mathematical and statistical methods. The system systematically analyzed the coverage of teaching content, student participation, and learning outcomes. The study found that the index weights determined by the Analytic Hierarchy Process (AHP) and Principal Component Analysis (PCA) effectively reflect the impact of different dimensions on teaching quality. The results indicate that reasonable selection of indicators and weight distribution can more comprehensively assess the actual effects of the blended teaching model, providing important decision-making support for educational practice. © 2024 Copyright held by the owner/author(s).

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Quantum Q-Learning Model for the Capacitated Vehicle Routing Problem 17

A Quantum Q-Learning Model for the Capacitated Vehicle Routi...

引用

17th IEEE International Symposium on Embedded Multicore/Many-core Systems-on-Chip, MCSoC 2024

作者： Xu, Jiahua Xie, Ningyi Lee, Xinwei Saito, Yoshiyuki Asai, Nobuyoshi Cai, Dongsheng University of Tsukuba Graduate School of Science and Technology Japan Singapore Management University School of Computing and Information Systems Singapore University of Aizu Graduate School of Computer Science and Engineering Japan University of Aizu School of Computer Science and Engineering Japan University of Tsukuba Faculty of Engineering Information and Systems Japan

ISBN: (纸本)9798331530471

The research on Variational Quantum Algorithms (VQAs) has gained significant momentum because of their promising practicality in the noisy intermediate-scale quantum (NISQ) era. Recent studies highlight the potential of VQAs in reinforcement learning (RL) by replacing classical components with parameterized quantum circuits (PQCs). Building on this, we propose a quantum Q-learning model for the Capacitated Vehicle Routing Problem (CVRP), combining a PQC with an RL training process. We present a PQC for embedding both static and dynamic states in RL environments. The proposed PQC approximates the Q-value function by using the expectation values of different observables. Experimental results demonstrate that the proposed PQC outperforms the existing PQC for the CVRP with fewer quantum resources. Furthermore, our method shows competitive performance compared to the classical counterpart. © 2024 IEEE.

关键词： Vehicle routing

来源：评论

学校读者我要写书评

暂无评论

Intelligent Risk-Identification Algorithm with Vision and 3D LiDAR Patterns at Damaged Buildings

引用

Intelligent Automation & Soft Computing 2023年第5期36卷 2315-2331页

作者： Dahyeon Kim Jiyoung Min Yongwoo Song Chulsu Kim Junho Ahn Computer Information Technology Korea National University of TransportationChungju27469Korea Department of Railway Vehicle System Engineering Korea National University of TransportationUiwang16106Korea

Existingﬁreﬁghting robots are focused on simple storage orﬁre sup-pression outside buildings rather than detection or *** a large number of robots using expensive equipment is *** study aims to increase the efﬁciency of search and rescue operations and the safety ofﬁreﬁgh-ters by detecting and identifying the disaster site by recognizing collapsed areas,obstacles,and rescuers on-site.A fusion algorithm combining a camera and three-dimension light detection and ranging(3D LiDAR)is proposed to detect and loca-lize the interiors of disaster *** algorithm detects obstacles by analyzingﬂoor segmentation and edge patterns using a mask regional convolutional neural network(mask R-CNN)features model based on the visual data collected from a parallelly connected camera and 3D *** as objects are detected using you only look once version 4(YOLOv4)in the image data to localize persons requiring *** point cloud data based on 3D LiDAR cluster the objects using the density-based spatial clustering of applications with noise(DBSCAN)clustering algorithm and estimate the distance to the actual object using the center point of the clustering *** proposed artiﬁcial intelligence(AI)algorithm was veriﬁed based on individual sensors using a sensor-mounted robot in an actual building to detectﬂoor surfaces,atypical obstacles,and persons requiring ***,the fused AI algorithm was comparatively veriﬁed.

关键词： Three-dimension light detection and ranging vision risk identiﬁcation damaged building robot

来源：评论

学校读者我要写书评

暂无评论

Dual-Model Approach for Lung Disease Classification using Convolutional Neural Networks and Support Vector Machines 2

Dual-Model Approach for Lung Disease Classification using Co...

引用

2nd IEEE International Conference on Integrated Intelligence and Communication Systems, ICIICS 2024

作者： Shaik, Mohammed Ali Fatima, Afshan Parveen, Masrath Rani, A. Soumya Mohammad, Akheel Rahim, Abdul School of Computer Science & Artificial Intelligence SR University Warangal India Department of Computer Science & Engineering CMR Institute of Technology Hyderabad India Department of Information Technology Vidya Jyothi Institute of Technology Hyderabad India Hyderabad India Department of Computer Science & Engineering Dr. Vrk women's College of Engineering and Technology Hyderabad India Department of Electronics and Communication Engineering Malla Reddy Engineering College for Women Secunderabad India

ISBN: (纸本)9798331504960

This paper proposes a solution of integrating the use of Support Vector Machine (SVM) and Convolutional Neural Networks (CNNs) for categorizing lung conditions of people with and without lung disease. The proposed model has achieved a high F1-Score of 97.4%, a high Precision of 93.17% and high Recall of 93. 63 for the Healthy class. The F1 Scores of this study for the Infected Lung class were as follows: the accuracy of F1 Score was 97.4%;Precision was 94.12%;and Recall was 92.06%. The combining of SVM and CNN model was quite accurate with the accuracy of 97% and the model was accurate in multiple domains of assessment. These results suggest that the application of CNNs and SVMs to the task of medical image analysis constitutes a promising and accurate approach for diagnosing lung diseases. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

A Transformer-based method for non-contact heart rate estimation from facial videos recorded in realistic environment 3

A Transformer-based method for non-contact heart rate estima...

引用

3rd Vision-Based Remote Physiological Signal Sensing Challenge and Workshop, RePSS 2024

作者： Hu, Yi Liu, Xuenan Rao, Xinlong Li, Bojing School of Computer Science and Information Engineering Hefei University of Technology Anhui Hefei230601 China School of Software Hefei University of Technology Anhui Hefei230601 China

The Video Photoplethysmography (VPPG) technique, while increasingly popular due to its convenience and cost-effectiveness, faces challenges in handling continuous head movements and vigorous motion interferences encountered in real-life scenarios. In this paper, we present a Transformer-based approach aimed at enhancing the robustness of heart rate estimation from facial videos. Leveraging the selfattention mechanism inherent in Transformers, our method adeptly captures both temporal dependencies and spatial information, thereby elevating the accuracy and resilience of heart rate estimation, even in challenging conditions. Through extensive experiments conducted on real-world face video datasets, we illustrate the effectiveness of our approach. Our results demonstrate significant improvements over existing methods in mitigating motion artifacts and enhancing the reliability of non-contact heart rate estimation in practical environments. © 2024 Copyright for this paper by its authors.

关键词： heart rate detection non-contact type Transformer Video Photoplethysmography

来源：评论

学校读者我要写书评

暂无评论

4D-Rossler Hyperchaotic System for Image Encryption and Decryption with High Security 10

4D-Rossler Hyperchaotic System for Image Encryption and Decr...

引用

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Agarwal, Soumil Byramdharmika, M. Dhathri, Sree Thanikaiselvan, V. Subashanthini, S. Amirtharajan, Rengarajan Vellore Institute of Technology School of Electronics Engineering Vellore India Engineering and Information Systems Vellore Institute of Technology School of Computer Science Vellore India Sastra Deemed University School of Electrical & Electronics Engineering Thanjavur India

ISBN: (纸本)9798350353068

In today's digital world, safeguarding data at all times is important, especially with the widespread use of images across various processes. Image encryption is vital in concealing sensitive information through cryptographic techniques, rendering data indecipherable to unauthorized parties. However, existing encryption systems often fall short in terms of both efficiency and security. This research explores chaos theory for image encryption methodologies to address these limitations. A comprehensive study of image encryption fundamentals was conducted, including chaos theory, various chaotic maps, DNA encoding, and encryption system evaluation metrics. Implementation of different chaotic maps such as the logistic map, tent map, and combined logistic-tent map, along with 3D chaotic systems like the Lorenz and Rossler systems, was performed for encryption purposes. Additionally, the 4D extension of the Rossler hyperchaotic system was introduced for enhanced encryption capabilities. Encryption methods were evaluated using metrics such as UACI, NPCR, correlation coefficients, image entropy and histogram analysis, with results compared and tabulated. This research advances image encryption techniques by leveraging chaos theory to achieve heightened security and efficiency in safeguarding image data. © 2024 IEEE.

关键词： Chaotic systems

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Computation Offloading for DNN Tasks in Semantic-Assisted Mobile Edge Computing Systems 24

Energy Efficient Computation Offloading for DNN Tasks in Sem...

引用

24th IEEE International Conference on Communication technology, ICCT 2024

作者： Zheng, Guangyuan Wen, Miaowen Tao, Yiwei Li, Qiang Ding, Zhiguo South China University of Technology School of Electronic and Information Engineering Guangzhou510640 China Khalifa University Department of Electrical Engineering and Computer Science Abu Dhabi United Arab Emirates Jinan University College of Information Science and Technology Guangzhou510632 China

ISBN: (纸本)9798350363760

In this paper, we focus on semantic-aware computation offloading for executing the deep neural network (DNN) inference tasks in a mobile edge computing (MEC) system. To cope with the challenges of insufficient wireless resources during task offloading, we propose a compress-then-offload mode, in which each user first compresses its raw large-size task data into a small-size semantic feature and then uploads it to the edge server for remote execution. Specifically, we establish the relationship between the compression ratio and computation ratio for different DNN tasks. To achieve energy-efficient offloading, we formulate an optimization problem to minimize the energy consumption of all users by jointly optimizing the compression ratio, computation allocation, uploading time, and DNN layer selection. We propose a low-complexity iterative algorithm to solve the original non-convex problem. Simulation results demonstrate that our proposed semantic-aware computation offloading scheme can substantially reduce users' energy consumption compared to the conventional offloading, especially with scarce wireless resources. © 2024 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Utilization of Processing of Images in Bio-Acoustics

Utilization of Processing of Images in Bio-Acoustics

引用

2023 International Conference on Power Energy, Environment and Intelligent Control, PEEIC 2023

作者： Raja Praveen, K.N. Shrimal, Gajendra Shukla, Meenu Computer Science Department Bangalore India Vivekananda Global University Department of Computer Science & Engineering Jaipur India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India

ISBN: (纸本)9798350357769

The present research examines how the Felsenstein approach might be improved in light of huge data and evolutionary inference. The Felsenstein approach, phylogeny starting points, huge data, statistical techniques, and testing hypotheses are among the important ideas and terms covered in the overview. It emphasizes the importance of repeatability in evolutionary inferences as well as the difficulties brought on by rogue genera and bootstrapping proportions. The article suggests a brand-new strategy to increase the accuracy of phylogenetic investigations that makes use of transfer separation and bipartition distance. The abstract's conclusion emphasizes the need of better methods for managing huge datasets and for recognizing instability taxonomic. This study dives into the refining of the Felsenstein technique within the setting of vast data and evolution prediction. Essential ideas comprise the Felsenstein method, evolutionary points of departure, problems associated with huge datasets, methods in statistics, and testing hypotheses. Noteworthy focus is made on the relevance of reproducibility in phylogenetic conclusions, along with the complexity provided by rogue families and ramping percentages. The article provides a unique technique targeted at boosting the accuracy of phylogenetic studies, utilising transfer isolation and bipartition distances. The summary continues by highlighting the essential need for sophisticated approaches capable of successfully handling big datasets and spotting taxonomic fragility. © 2023 IEEE.

关键词： ABC Big data Bipartition distance Bootstrap Confidence intervals Felsenstein method Homogenization Hypothesis testing Phylogenetic estimation Phylogenetic starting Reboot method Rogue taxa Statistical approach Taxonomic units Transfer distance

来源：评论

学校读者我要写书评

暂无评论

Multi-scale Feature Fusion for Enhanced Person Re-identification 3rd

Multi-scale Feature Fusion for Enhanced Person Re-identific...

引用

3rd International Conference on Machine Learning, Cloud Computing and Intelligent Mining, MLCCIM 2024

作者： Wang, XiaoHui Sun, Yulin Zou, Zhipeng Liang, Xiaoyang Sun, Zhenyu Liu, Wei Shandong Business Institute Yantai China Shandong Xuewen Information Technology Co. Ltd. Jining China Technology of Computer Application Yantai Engineering and Technology College Yantai China School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou China

ISBN: (纸本)9789819624676

In the realm of surveillance and security, person re-identification (Re-ID) stands as a critical challenge, particularly across non-overlapping camera networks. The essence of this challenge lies in the accurate and efficient identification of individuals by leveraging features captured from multiple perspectives. Addressing this, we introduce the Contextual Multi-Scale Network (Asy-CMSNet), a novel framework designed to enhance the Re-ID process through the integration of asymmetrical convolution and an innovative loss function, the Enhanced TriHard (E-TriHard). Unlike traditional approaches that rely on the stacking of convolutional layers, Asy-CMSNet employs a sophisticated mechanism that allows for the nuanced extraction and integration of multi-scale features, thereby optimizing the identification process across diverse pedestrian appearances. Central to our framework is the notion that effective person Re-ID necessitates the consideration of both global and localized pedestrian details, ranging from broad clothing characteristics to subtle accessories, which our model adeptly captures and utilizes. Through extensive experimentation across several benchmark datasets, Asy-CMSNet demonstrates superior performance in person Re-ID challenges, highlighting a substantial progression in the area. Our findings not only set new performance benchmarks but also pave the way for future research into more efficient, scalable, and robust person Re-ID systems. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Benchmarking

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：