检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Chen, Ziqin Egerstedt, Magnus Wang, Yongqiang The Department of Electrical and Computer Engineering Clemson University ClemsonSC29634 United States The Department of Electrical Engineering and Computer Science University of California Irvine IrvineCA92697 United States

Distributed aggregative optimization methods are gaining increased traction due to their ability to address cooperative control and optimization problems, where the objective function of each agent depends not only on its own decision variable but also on the aggregation of other agents' decision variables. Nevertheless, existing distributed aggregative optimization methods implicitly assume all agents to be truthful in information sharing, which can be unrealistic in real-world scenarios, where agents may act selfishly or strategically. In fact, an opportunistic agent may deceptively share false information in its own favor to minimize its own loss, which, however, will compromise the network-level global performance. To solve this issue, we propose a new distributed aggregative optimization algorithm that can ensure truthfulness of agents and convergence performance. To the best of our knowledge, this is the first algorithm that ensures truthfulness in a fully distributed setting, where no "centralized" aggregator exists to collect private information/decision variables from participating agents. We systematically characterize the convergence rate of our algorithm under nonconvex/convex/strongly convex objective functions, which generalizes existing distributed aggregative optimization results that only focus on convex objective functions. We also rigorously quantify the tradeoff between convergence performance and the level of enabled truthfulness under different convexity conditions. Numerical simulations using distributed charging of electric vehicles confirm the efficacy of our algorithm. Copyright © 2025, The Authors. All rights reserved.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Pro-CHASER: A Prototype testbed for Car Hacking Attack Simulation and Evaluation using Raspberry Pi to Investigate Threat Landscape

引用

IEEE Access 2025年 13卷 36401-36420页

作者： Vanajakshi, J. Renuka, A. Kamath, Vidya Adesh, N.D. Manipal Academy of Higher Education Manipal Institute of Technology Department of Computer Science and Engineering Karnataka Manipal576104 India Manipal Academy of Higher Education Manipal Institute of Technology Department of Information and Communication Technology Karnataka Manipal576104 India

Recent advancements in transportation technology have necessitated a seamless integration of sensors, cameras, and communication protocols for autonomous vehicles. Ensuring cybersecurity for these vehicles has become critical, as they are vulnerable to attacks that could jeopardize safety and performance. While machine learning and deep learning models could be developed to address cybersecurity issues in autonomous vehicles, developing these models requires large datasets for training. Obtaining real-world data from actual vehicles also presents significant challenges. To address these limitations, a low-cost Pro-CHASER testbed - Prototype testbed for Car Hacking Attack Simulation and Evaluation using Raspberry Pi - was developed using a Controller Area Network (CAN) bus network with CAN-HAT (Hardware Attached on Top). This testbed utilized CAN to simulate autonomous vehicle functions and explore attack vectors. Microsoft Threat Modelling Tool, and MITRE ATT&CK framework were used to identify the vulnerabilities in the context of autonomous vehicles. The identified attacks were exploited using the designed testbed by employing many security testing tools to simulate CAN message injection attacks, USB exploits, and ROS-based fake image publisher attack, respectively. Through these attack simulations, the testbed functionalities were successfully compromised. The results demonstrated that message injection into the CAN bus manipulated sensor data that led to erroneous decision-making. Unauthorized access to the physical access points led to the injection of a malicious payload via a USB port. The computer vision system's response to the false data ultimately compromised the vehicle's perception and control. The findings highlight the capability of Pro-CHASER in identifying cyber security risks in autonomous vehicles, which offers a practical and low-cost platform for threat simulation and evaluation. © 2013 IEEE.

关键词： Testbeds

来源：评论

学校读者我要写书评

暂无评论

Enhancing Grayscale Image Clarity Through Blind Deconvolution and PSF Estimation With Total Variation Regularization 3rd

Enhancing Grayscale Image Clarity Through Blind Deconvolutio...

引用

3rd International Conference on Intelligent Systems and Sustainable Computing, ICISSC 2023

作者： Narasimharao, Jonnadula Kumar, Voruganti Naresh Kirankumar, Adepu Pooja, Bejjanki Rambabu, D. Joshi, Ganpat Department of CSE CMR Technical Campus Telangana Hyderabad India Sreenidhi Institute of Science and Technology Telangana Hyderabad India Department of Computer Science and Engineering Madhav University Rajasthan India

ISBN: (纸本)9789819783540

Nowadays, the usage of digital cameras in daily life has increased, leading to a growing demand for enhancing the quality of captured images. One of the most challenging problems in image processing is the restoration of blurred or out-of-focus images. This paper presents Enhancing grayscale image clarity through blind deconvolution and PSF estimation with total variation regularization. This blind deconvolution approach is used to handle the problem of removing blur from acquired photos, making it easier to restore defocused grayscale photographs. Determining the ideal picture and the point spread function (PSF) may be challenging when using blind deconvolution, which aims to recreate a clear ideal image from a single fuzzy image. As a result, this work also introduces a unique PSF estimate technique that makes use of an adaptive filter and total variation regularization. Finally, the results obtained after implementation are demonstrated based on the blur type and performance metrics, which include the mean square error and the peak signal-to-noise ratio. The experimental outcomes indicate that our method is the best among various other methods in terms of deblurring performance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adaptive filtering

来源：评论

学校读者我要写书评

暂无评论

Enhanced Layer Extraction for Efficient Plant Disease Classification using Efficientnet B1

引用

SN computer science 2025年第4期6卷 1-15页

作者： Thakur, Arastu Thakur, Abhilasha Vivek, V. Mahesh, T.R. Krishna, K. Murali Department of Computer Science and Engineering Faculty of Engineering and Technology JAIN (Deemed-to-Be University) Bangalore 562112 India Department of Agriculture Marwadi University Gujarat Rajkot India Alliance School of Advanced Computing Alliance University Chandapura - Anekal Main Road Bengaluru Anekal 562106 India Department of Electrical and Electronics Engineering Faculty of Engineering and Technology JAIN (Deemed-to-Be University) Bangalore 562112 India

Agriculture is crucial for the global economy, providing sustenance and resources for various industries. However, plant diseases threaten crop quality and yield, risking severe economic impacts. Traditional plant disease diagnosis methods, like manual inspection or basic machine learning, are slow, require expertise, and struggle with scalability and adapting to new diseases. This study introduces a deep learning model using convolutional neural networks (cnns) to autonomously detect and classify plant diseases from images, enhancing speed, scalability, and accuracy. We utilize the efficientnetb1 architecture, pretrained on imagenet and fine-tuned on a dataset of bell pepper, potato, and tomato diseases, recognizing 14 diseases plus healthy plants. The model achieves 98.80% accuracy on the test dataset, with high precision, recall, and F1-scores, demonstrating its effectiveness in plant disease diagnosis. This advancement marks a significant step in automating plant disease diagnosis, offering a robust tool for effective disease management in agriculture. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Agriculture Automated diagnosis Deep learning Disease management Efficientnetb1 Image classification Plant disease detection Transfer learning

来源：评论

学校读者我要写书评

暂无评论

HyperSteiner: Computing Heuristic Hyperbolic Steiner Minimal Trees

HyperSteiner: Computing Heuristic Hyperbolic Steiner Minimal...

引用

2025 SIAM Symposium on Algorithm engineering and Experiments, ALENEX 2025

作者： García-Castellanos, Alejandro Medbouhi, Aniss Aiman Marchetti, Giovanni Luca Bekkers, Erik J. Kragic, Danica Amsterdam Machine Learning Lab University of Amsterdam Netherlands School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden School of Engineering Sciences KTH Royal Institute of Technology Sweden

ISBN: (纸本)9798331311995

We propose HyperSteiner – an efficient heuristic algorithm for computing Steiner minimal trees in the hyperbolic space. HyperSteiner extends the Euclidean Smith-Lee-Liebman algorithm, which is grounded in a divide-and-conquer approach involving the Delaunay triangulation. The central idea is rephrasing Steiner tree problems with three terminals as a system of equations in the Klein-Beltrami model. Motivated by the fact that hyperbolic geometry is well-suited for representing hierarchies, we explore applications to hierarchy discovery in data. Results show that HyperSteiner infers more realistic hierarchies than the Minimum Spanning Tree and is more scalable to large datasets than Neighbor Joining. Copyright © 2025 by SIAM.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Deep Learning Framework for Pneumonia Detection in Chest X-rays

引用

SN computer science 2025年第5期6卷 1-25页

作者： Rashid, Asma Binte Asma, Jannatul Barua, Krittika Das, Dhrubajyoti Department of Computer Science and Engineering Premier University Chattogram 4000 Bangladesh

Pneumonia is a particularly serious lung condition that can be caused by bacteria, viruses, or fungus. Pus and other fluids are deposited in the air sacs of the lungs as a result of this sickness. This illness presents a substantial worldwide health problem, specifically impacting young children and populations that are susceptible. Timely identification and prompt medical intervention are essential in order to avoid serious complications and loss of life. Out of all the diagnostic tools available, chest X-rays are among the most frequently utilized to detect pneumonia. This study introduces an enhanced deep learning framework for pneumonia detection, integrating the Convolutional Block Attention Module (CBAM) with DenseNet-121 to optimize feature extraction through channel and spatial attention. Utilizing the Kermany dataset, comprising 5856 chest X-ray images, the study achieves a test accuracy of 95.57% with baseline DenseNet-121, improving to 98.64% with CBAM integration on a 1056-image test set. The model’s decision-making process was made more understandable by using Grad-CAM visualization, which highlighted the key parts of the lungs where pneumonia patterns were discovered. Models were assessed using a range of metrics, such as accuracy, precision, F1-score, recall, and area under the ROC curve (AUC). On top of that, we benchmarked our proposed architecture against the most advanced pneumonia detection models currently available. Our DenseNet-121 with CBAM achieved better results than other improved models, including complex ensembles, with a far lower number of parameters. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Attention module (CBAM) CNN DenseNet-121 Grad-CAM Pneumonia detection

来源：评论

学校读者我要写书评

暂无评论

Enhancing Building Safety Through Machine Learning-Based Smoke Detection 5

Enhancing Building Safety Through Machine Learning-Based Smo...

引用

5th IEEE International Conference on Advances in electrical, Computing, Communication and Sustainable Technologies, ICAECT 2025

作者： Mohamed, Sulaiman Syed Judeson Antony Kovilpillai, J. Pragya Mir, Mahmood Hussain Golda Brunet, R. Mir, Tawseef Ahmad Alliance School of Advanced Computing Alliance University Bangalore India Government College of Engineering Department of Computer Science & Engineering Thanjavur India

ISBN: (纸本)9798350356236

Smoke detection in surveillance systems plays a crucial role in ensuring the safety and security of various environments, including buildings, forests, and industrial sites. In this paper, a comprehensive analysis of machine learning algorithms applied to smoke detection is presented. The proposed technique is validated using the Smoke Detection Dataset from Kaggle. The dataset comprises a diverse collection of images captured in different scenarios, including both smoke and non-smoke instances. The performance of various machine learning classifiers was evaluated. This included ensemble methods Random Forest (RF), Gradient Boosting (GB), AdaBoost (AB), linear models Logistic Regression (LR), kernel methods Support Vector Machine (SVM), decision-based methods Decision Tree (DT), and nearest neighbor methods K-Nearest Neighbors (KNN). Their precision, recall, AUC-ROC score, and Intersection over Union (IoU) are measured to assess their effectiveness in smoke detection. The results highlight that classifiers such as RF, DT, KNN, GB and AdaBoost achieve outstanding performance, with perfect scores in multiple metrics. © 2025 IEEE.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

Energy-Free Sensing and Context Recognition Using Photovoltaic Cells

引用

IEEE Sensors Journal 2025年第9期25卷 15598-15611页

作者： Shintani, Kaede Rizk, Hamada Yamaguchi, Hirozumi Osaka University Graduate School of Information Science and Technology Department of Information Networking Suita565-0871 Japan Tanta University Tanta31733 Egypt RIKEN Center for Computational Science Kobe650-0047 Japan RIKEN Center for Computational Science Department of Computer and Control Engineering Kobe650-0047 Japan

The field of energy-free sensing and context recognition has recently gained significant attention as it allows operating systems without external power sources. Photovoltaic cells can convert light energy into electrical energy to power sensing devices, but their power may not be sufficient to ensure energy-free sensing due to the varying power needs of sensors and high computational demands. In this article, we propose the use of photovoltaic cells as a standalone sensor for the recognition of different contexts, including user identification, step counting, and location tracking. The system utilizes the photocurrent readings generated by the photovoltaic cells to capture the unique mobility patterns of different users. By analyzing these patterns, the system can accurately identify the user, count the number of steps taken, and track the user’s location. We propose a computationally efficient dynamic time warping (DTW) to match the variable length sequences of photocurrent readings to a database of known patterns and identify the closest subject and location matches. The system was rigorously evaluated in a realistic environment, and the results indicate that it can accurately estimate step count, identify subjects, and localize them with an accuracy of 88%, 90%, and 43 cm, respectively. This is achieved while the proposed system is nonintrusive and can operate without external power sources, making it a promising technology for energy-free sensing and context recognition. © 2001-2012 IEEE.

关键词： Photovoltaics

来源：评论

学校读者我要写书评

暂无评论

SafeLight: Enhancing Security in Optical Convolutional Neural Network Accelerators

SafeLight: Enhancing Security in Optical Convolutional Neura...

引用

Design, Automation and Test in Europe Conference and Exhibition

作者： Salma Afifi Ishan Thakkar Sudeep Pasricha Department of Electrical and Computer Engineering Colorado State University Fort Collins USA Department of Electrical and Computer Engineering University of Kentucky Lexington USA

ISBN: (数字)9783982674100

ISBN: (纸本)9798331534646

The rapid proliferation of deep learning has revolutionized computing hardware, driving innovations to improve computationally expensive multiply-accumulate operations in deep neural networks. Among these innovations are integrated silicon-photonic systems that have emerged as energy-efficient platforms capable of achieving light speed computation and communication, positioning optical neural network (ONN) platforms as a transformative technology for accelerating deep learning models such as convolutional neural networks (CNNs). However, the increasing complexity of optical hardware introduces new vulnerabilities, notably the risk of hardware trojan (HT) attacks. Despite the growing interest in ONN platforms, little attention has been given to how HT-induced threats can compromise performance and security. This paper presents an in-depth analysis of the impact of such attacks on the performance of CNN models accelerated by ONN accelerators. Specifically, we show how HTs can compromise microring resonators (MRs) in a state-of-the-art non-coherent ONN accelerator and reduce classification accuracy across CNN models by up to 7.49% to 80.46% by just targeting 10% of MRs. We then propose techniques to enhance ONN accelerator robustness against these attacks and show how the best techniques can effectively recover the accuracy drops.

关键词： Deep learning Technological innovation Analytical models Accuracy Optical resonators Optical computing Optical fiber networks Convolutional neural networks Trojan horses Security

来源：评论

学校读者我要写书评

暂无评论

Optimizing Data Center Power Usage: Server Consolidation and Efficient Cooling Techniques 7th

Optimizing Data Center Power Usage: Server Consolidation and...

引用

7th International Conference on Communication, Device and Networking, ICCDN 2024

作者： Bose, Rajesh Mondal, Haraprasad Sutradhar, Shrabani Roy, Sandip Department of Computer Science & Engineering JIS University West Bengal Kolkata India Institute of Engineering and Technology Dibrugarh University Assam786001 India Department of Computational Science Brainware University West Bengal Kolkata India

ISBN: (纸本)9789819753369

Data centers’ high energy consumption necessitates essential power-saving techniques for optimization. This paper proposes two effective strategies: server consolidation and precise air conditioning units. Server consolidation combines multiple servers into a single server or cluster, reducing energy usage, carbon footprint, and cutting hardware and maintenance costs. Additionally, a virtualized task scheduling algorithm enhances server utilization and data center performance. The second technique involves using computer room air conditioning (CRAC) units to regulate temperature, air distribution, and humidity, leading to reduced energy consumption and preventing overheating-related equipment failure. Studies confirm significant reductions in data center power consumption and carbon footprint through these techniques. For instance, a study showed savings of 41,000 kWh of electric power and 16 tons of carbon footprint. Implementing these methods allows data center operators to achieve substantial energy savings and environmental impact minimization. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Carbon footprint

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：