检索结果-内蒙古大学图书馆

2025 International Conference on Multi-Agent systems for Collaborative Intelligence, ICMSCI 2025

作者： Ramanan, S.V. Rajasekar, M. Shanmugapriya, G. Sujitha, R. Akshya, J. Choudhry, Mani Deepak P Pg Institute of Technology Department of Electronics and Communication Engineering Coimbatore India Vsb college of Engineering Department of Computer Science and Engineering Technical Campus Coimbatore India Dr.N G.P Institute of Technology Department of Computer Science and Business Systems Coimbatore India Christ The King Engineering College Department of Information Technology Coimbatore India Srm Institute of Science and Technology Department of Computational Intelligence Chennai India Srm Institute of Science and Technology Department of Computing Technologies Chennai India

ISBN: (纸本)9798331509828

The ability to match features and keep track of objects in changing dynamic environments is still an important problem, particularly due to varying noise levels, diverse datasets, and high dimensional feature spaces. Euclidean Distance and Cosine Similarity based matching are existing methods that commonly do not generalize well, particularly in the case of cross domain scenarios, where noise and motion dynamics are powerful factors to limit the accuracy of tracking. However, Deep Metric Learning approaches can extract robust features at the cost of computational efficiency and are unsuitable for real-time applications. This research proposes a Siamese Network framework to solve these problems by using robust feature matching and multi-object tracking. Based on that, the proposed framework uses a dual-branch network architecture in which feature embeddings extracted from paired inputs are mapped through the same shared latent space. Furthermore, the adaptive learning rate leads to efficient convergence during the training. Experimental results show that the Siamese Network not only achieves better accuracy than the existing methods and the more such as Deep Metric Learning but also performs significantly more efficient computation. With an accuracy of 90.2 % at a precision of 88.5%, the framework's inference time is much faster than that of Deep Metric Learning at 2.0ms. Furthermore, the proposed method performs well on the generalization over datasets with a 15% improvement of cross-domain matching accuracy on Euclidean Distance. By striking this balance between accuracy, efficiency and adaptability, it shows its suitability for dynamic and noisy environments for real-time tracking. The proposed method fills existing gaps and achieves a new state of the art for feature matching and tracking performance. © 2025 IEEE.

关键词： Object tracking

来源：评论

学校读者我要写书评

暂无评论

Two dimensional DOA estimation of coherent signals based on covariance matrix element transformation 24

Two dimensional DOA estimation of coherent signals based on ...

引用

8th International Conference on Electronic Information Technology and computer engineering, EITCE 2024

作者： Qu, Zhiyu Wu, Xu Geng, Zhenya College of Information Science and Engineering Hohai University Jiangsu Nanjing China College of Computer Science and Software Engineering Hohai University Jiangsu Nanjing China The 49th Research Institute of China Electronics Technology Group Corporation Heilongjiang Harbin China

ISBN: (纸本)9798400710094

Traditional Direction of Arrival (DOA) estimation algorithms for coherent signals in uniform circular array (UCA), such as mode space transformation, allow for the adaptation of advanced algorithms initially developed for uniform linear arrays to be applied effectively in UCA. However, after mode space transformation, the array will encounter aperture loss and will also be unable to perform two-dimensional DOA estimation effectively. In this paper, we propose a new method that that integrates covariance matrix element transformation with the Multiple Signal Classification (MUSIC) to estimate the DOA of coherent signals in various symmetric antenna arrays, including UCA. The algorithm leverages the phase difference symmetry of the antenna array to decorrelate the incoming signals, effectively restoring the full rank of the covariance matrix. Subsequently, it employs two-dimensional MUSIC for DOA estimation. Simulation results demonstrate the effectiveness of the proposed algorithm. © 2024 Copyright held by the owner/author(s).

关键词： Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

Leveraging Ensembles of Pre-trained CNNs for Improved Lung Cancer Detection and Classification

引用

Procedia computer science 2025年 260卷 151-159页

作者： Dasari Bhulakshmi Dharmendra singh rajput Vellore Institute of Technology School of Computer Science Engineering and Information Systems Vellore 632014 India

Lung cancer is a serious global health concern, highlighting the importance of early identification to improve patient survival rates. We explore the potential of deep learning(DL) models to improve lung cancer diagnosis through detection and classification models. The performance of pre-trained ResNet50, VGG19, and AlexNet models is evaluated on an augmented lung cancer image dataset to determine their suitability for lung cancer classification. The fine-tuned models are evaluated for their ability to identify and classify lung cancer, achieving high accuracy of 92.88%, 93.06%, and 95.23%. While promising, this approach has limitations. The efficacy of DL models is significantly influenced by both the quality and volume of the training data. Additionally, the ”black box” nature of DL models can make it challenging to understand their decision-making process. However, the results of this study suggest that DL ensembles hold significant potential for lung cancer diagnosis. Further research is necessary to address limitations and explore interpretability techniques for wider clinical acceptance.

关键词： Deep Learning Machine Learning convolutional neural networks Artificial Intelligence

来源：评论

学校读者我要写书评

暂无评论

When Generative AI Meets Semantic Communication: Optimizing Radio Map Construction and Distribution in Future Mobile Networks

引用

IEEE Network 2025年第3期39卷 47-55页

作者： Zhou, Li Deng, Xinfeng Ning, Zhaolong Zhao, Haitao Wei, Jibo Leung, Victor C. M. National University of Defense Technology College of Electronic Science and Technology Changsha410073 China Chongqing University of Posts and Telecommunications School of Communications and Information Engineering Chongqing400065 China Shenzhen MSU-BIT University AI Research Institute Shenzhen518000 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518000 China The University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T 1Z4 Canada

With the rapid development of the internet of things and smart cities, the demand for effective spectrum collaboration has grown *** maps play a crucial role in understanding the spatial radio environment, which is essential for wireless applications such as cell planning and radio resource management. However, generating radio maps is a resource-intensive task, as the construction process is complex and the distribution process consumes substantial bandwidth. This article proposes a method that combines semantic communication (SemCom) and generative artificial intelligence (GAI) to optimize the construction and distribution processes of radio maps. By incorporating SemCom, our method transmits only key semantic information during the distribution process, significantly reducing bandwidth usage while ensuring accurate and efficient information transfer. While the diverse generative capabilities of GAI introduce some instability, which could be a limitation in radio map construction, this article achieves precise content decoding through prompts based on multi-modal semantic information, enabling accurate construction and restoration of radio maps. By utilizing SemCom and GAI technologies, the cost of applications of radio maps can be significantly reduced, which is beneficial for stimulating the pace of intelligence evolution in future mobile networks. © 1986-2012 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

computer Vision and Control Algorithm for Sustainable and Precision Agriculture

引用

SN computer science 2025年第4期6卷 1-13页

作者： Adebayo, Segun Aworinde, Halleluyah O. Ojerinde, Stephen A. Oyedoja, Kayode O. Adeniyi, Abidemi Emmanuel Olanloye, Odunayo Dauda Osueke, Christian O. Ogundokun, Roseline Oluwaseun Das, Abhishek Mechatronics Engineering Bowen University Iwo Nigeria Computer Science Bowen University Iwo Nigeria Computer Science Western Illinois University IL United States Technology Education Emmanuel Alayande University of Education Oyo Nigeria Department of Software Engineering Kaunas University of Technology Kaunas Lithuania Department of Computer Science Landmark University Omu-Aran Kwara State Nigeria Department of Computer Science and Engineering Aliah University Kolkata India Tshwane University of Technology Pretoria South Africa Durban University of Technology Durban South Africa Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

The world population continues to increase with a large proportion of this increase happening in Africa just as predicated by Food and Agriculture Organization of the United Nation. To meet the demand of feeding this increasing population, innovative farming practices are being developed to increase the yield of the major stable food supply. This research developed a computer vision and control algorithm on a quadcopter for farm surveillance, crop protection from the invasion of pest, early disease detection as well as crop yield estimation. A process of developing a model capable of detecting and classifying these pests in the environment was presented in this study. The process involves selecting, preprocess and transforming the sensed data from a vision sensor to train classification algorithm and to detect and track object of interest in the environment. This study addresses a notable research gap in computer vision, control systems, big data analytics, and robotics, specifically within the context of smart farming. It primarily utilizes conventional learning algorithms, including Artificial Neural Networks and Support Vector Machines, typically found in widely-used commercial software. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Algorithm computer vision Machine learning Quadcopter UAV

来源：评论

学校读者我要写书评

暂无评论

Adaptive Quantum and Graph-Attentive Security Framework for DoS Attack Mitigation in VANETs 2

Adaptive Quantum and Graph-Attentive Security Framework for ...

引用

2nd International Conference on Machine Learning and Autonomous systems, ICMLAS 2025

作者： Anjum, Asma Rao, P. S. V. Srinivasa Sindhu, M. Bhatt, Pooja Priya, M.R. Maranan, Ramya HKBK College of Engineering Department of Computer Science and Engineering Karnataka Bengaluru560045 India Joginpally B R Engineering College Department of Computer Science and Engineering Telangana Hyderabad500075 India R.M.K Engineering College Department of Computer Science and Business Systems Tamil Nadu Thiruvallur601206 India Parul institute of Engineering and Technology Parul University Computer Science and Engineering Faculty of Engineering and Technology Post Limda Gujarat 391760 India NIE First Grade College Department of Computer Science Karnataka Mysuru570008 India Saveetha School of Engineering SIMATS Department of Research and Innovation Tamil Nadu Chennai602105 India

ISBN: (纸本)9798331505745

Vehicular Ad Hoc Networks (VANETs) are considered crucial for real-time vehicle-to-vehicle communication, which in turn enhances the efficiency of traffic and road safety. VANETs are very vulnerable to Denial-of-Service (DoS) attacks, which seriously disrupt communication and degrade network performance. This paper introduces a high-performance neural network-based detection and prevention mechanism that can effectively counter DoS attacks. The proposed method is initiated with the real-time monitoring of the network. Data collection and preprocessing through the Adaptive Self-Guided Loop Filter (ASGLF) are used to filter out noise from the data. The Fast Hybrid Vision Transformer (FHVT) conducts feature extraction for network traffic to effectively preserve the spatial and temporal relationships. Using the Reflecting Equivariant Quantum Neural Network (REQNN) integrated with Heterogeneous Edge-Enhanced Graph Attention Network (HEEGAT) ensures timely anomaly detection accuracy of attacks. Subtraction-Average-Based Optimizer (SAO) optimizes the detection parameters to effectively utilize resources. The experimental results have shown accuracy in the detection of DoS attacks as 99.9% with a PDR of 99.9% and also improved throughput efficiency by 99.8%. These results validate the effectiveness of the proposed model in securing VANETs from DoS attacks, offering uninterrupted network availability and improved vehicular communication security for intelligent transportation systems. © 2025 IEEE.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

Self–triggered Scheme Design for Takagi–Sugeno Fuzzy Model based on Mismatch Premise Variable With Time–varying Delay

引用

IEEE Transactions on Automation science and engineering 2025年 22卷 15536-15548页

作者： Aslam, Muhammad Shamrooz Bilal, Hazrat Vasilakos, Athanasios V. China University of Mining and Technology Artificial Intelligence Research Institute Xuzhou2211106 China College of Mechatronics and Control Engineering College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China College of Computer Science and Information Technology IAU Department of Networks and Communications P.O. Box 1982 Dammam31441 Saudi Arabia Grimstad Norway

Over the last 20 years, numerous experts in the manufacturing companies have become interested in controlling flexible joint robots. The control design process using a networked framework has played a significant role in the industrial sector. This research addresses the self–triggered control problem for Takagi–Sugeno (T–S) fuzzy systems based on time delay is established in this research. A new self–triggered mechanism determines when the plant state is transmitted. Instead of continuously tracking predefined triggering conditions, the self–triggered system determines the next triggering instant based on the most recently triggered state information. The self–triggered mechanism relying on T–S fuzzy controller is then created using the triggered state, allowing for flexible configuration of its fuzzy rules and membership operations (MOs) that are not dependent on the controlled fuzzy system. Furthermore, it precisely demonstrates the interaction between the triggered condition and the plant state under the constraint of mismatched premise variables. To ensure system stability and performance, delay–dependent requirements are derived using a novel Lyapunov–Krasovskii functional based on fuzzy concepts to develop the fuzzy control design. The presence of the required controller is then shown under LMI–based conditions. Lastly, a simulation of a flexible robotic arm example is provided along with an evaluation of other triggered methods. © 2004-2012 IEEE.

关键词： Industrial plants

来源：评论

学校读者我要写书评

暂无评论

Connectome graph attention network (CGAT): A multimodal approach for enhanced classification of Alzheimer's disease

引用

Results in engineering 2025年 26卷

作者： P, Udayakumar Subhashini, R. School of Computer Science Engineering and Information Systems Vellore Institute of Technology Vellore India

This study proposes a model for Alzheimer's Disease (AD) diagnosis called the Connectome Graph Attention Network (CGAT), designed to improve the classification of AD stages. By integrating multimodal neuroimaging data and clinical diagnosis information, CGAT constructs a connectome graph for each individual, with brain regions as nodes and the connections between them as edges. CGAT enhances classification by employing an attention mechanism that highlights critical brain region connections. A unique feature of the model is its capacity to merge features from diverse imaging modalities effectively, using modality-specific loss weighting to ensure balanced data contribution in the final classification. Developed in PyTorch Geometric (PyG), CGAT was optimized through the NNI AutoML toolkit. The model demonstrated a notable AUROC score of 94.00, outperforming other graph-based models like GCN, GraphSAGE, GGNN, and ChebNet, especially in differentiating EMCI from LMCI. Visualizations using t-SNE revealed CGAT's ability to distinctly separate cognitive states, emphasizing important connections among brain regions. Overall, CGAT efficiently combines multimodal neuroimaging data for improved, multi-class AD stage classification. © 2025 The Author(s)

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Trauma-Informed Insights from Co-Design of Self-Disclosure Robots with Domestic Abuse Survivors 20

Trauma-Informed Insights from Co-Design of Self-Disclosure R...

引用

20th Annual ACM/IEEE International Conference on Human-Robot Interaction, HRI 2025

作者： Morris, Nyomi Carrine Williams, Tom Jelen, Ben Colorado School of Mines MIRRORLab GoldenCO United States Rose-Hulman Institute of Technology Department of Computer Science and Software Engineering Terre HauteIN United States

ISBN: (纸本)9798350378931

Survivors of domestic abuse face significant challenges securing recovery resources, such as housing, mental health care, and social connections. Accessing these resources requires survivors to disclose their status as survivors of domestic abuse;a process that can be traumatic and emotionally burdensome. In this work, we consider how social robots might help domestic abuse survivors to address challenges surrounding self-disclosure. To do so, we conducted a three-session co-design workshop involving 8 participants from a domestic abuse shelter. Our results provide three key contributions: (1) new insights into the benefits and barriers to self-disclosure;(2) new insights into the ways that social robots can help survivors to better achieve those benefits and overcome those barriers before, during, and after disclosure, including key design recommendations associated with each of these phases;and (3) observations into how a trauma-informed computing perspective may enable more effective design work in Human-Robot Interaction. © 2025 IEEE.

关键词： Social robots

来源：评论

学校读者我要写书评

暂无评论

Smart Grid Security Framework for Data Transmissions with Adaptive Practices Using Machine Learning Algorithm

引用

computers, Materials & Continua 2025年第3期82卷 4339-4369页

作者： Shitharth Selvarajan Hariprasath Manoharan Taher Al-Shehari Hussain Alsalman Taha Alfakih School of Built Environment Engineering and ComputingLeeds Beckett UniversityLeedsLS13HEUK Department of Computer Science and Engineering Chennai Institute of TechnologyChennai602109India Centre for Research Impact & Outcome Chitkara UniversityChandigarh140401India Department of Electronics and Communication Engineering Panimalar Engineering CollegeChennai600123India Department of Self-Development Skill Common First Year DeanshipKing Saud UniversityRiyadh11362Saudi Arabia Department of Computer Science College of Computer and Information SciencesKing Saud UniversityRiyadh11543Saudi Arabia Department of Information Systems College of Computer and Information SciencesKing Saud UniversityRiyadh11543Saudi Arabia

This research presents an analysis of smart grid units to enhance connected units’security during data *** major advantage of the proposed method is that the system model encompasses multiple aspects such as network flow monitoring,data expansion,control association,throughput,and *** addition,all the above-mentioned aspects are carried out with neural networks and adaptive optimizations to enhance the operation of smart grid ***,the quantitative analysis of the optimization algorithm is discussed concerning two case studies,thereby achieving early convergence at reduced *** suggested method ensures that each communication unit has its own distinct channels,maximizing the possibility of accurate *** results in the provision of only the original data values,hence enhancing *** power and line values are individually observed to establish control in smart grid-connected channels,even in the presence of adaptive settings.A comparison analysis is conducted to showcase the results,using simulation studies involving four scenarios and two case *** proposed method exhibits reduced complexity,resulting in a throughput gain of over 90%.

关键词： Machine learning power systems security smart grid

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：