检索结果-内蒙古大学图书馆

2nd International Conference on Distributed computing and Optimization Techniques, ICDCOT 2024

作者： Umasankar, L. Anitha, D. Trisheela, S. Al-Jawahry, Hassan M. Borra, Subba Reddy S.A.Engineering College Electrical and Electronics Engineering Tiruvallur Poonamallee India School of Computing Srm Institute of Science and Technology Department of Computational Intelligence Tamilnadu Kattankulathur India Nitte Meenakshi Institute of Technology Dept of Cse Bengaluru India The Islamic University Najaf Iraq Computer Science and Engineering Maisammaguda Hyderabad India

ISBN: (纸本)9798350382952

The recent technology in surveillance for military vehicle parts forms the basis of intelligence warfare through information realized through monitoring and tracking operations in complex situations. Therefore, the process of identifying and classifying vehicles by an aerial vehicle installed with a resource-limited device and an intelligent object detection algorithm significantly assists security agencies. It is possible to make use of this vehicle either manually or autonomously. To overcome these issues, edge device based military vehicle detection from Unmanned Aerial Vehicle (UAV) is proposed. At present, no publicly available dataset exists that includes different military classes. Therefore, the proposed approach use a dataset consisting of 6772 images labeled as Tanks, Military Trucks, Helicopters, Aircraft, Civilian Cars and Civilian Aircraft. This data set is used to train deep learning models such as Quantized SSD Mobilenetv2 and Tiny Yolo v5 that are then compared with resource limited edge devices. The results reveal that Tiny Yolo v5 outperforms other models, showing high efficiency and suitability for edge-based devices due to its lightweight design. © 2024 IEEE.

关键词： Military vehicles

来源：评论

学校读者我要写书评

暂无评论

HPE Transformer: Learning to Optimize Multi-Group Multicast Beamforming Under Nonconvex QoS Constraints

arXiv

引用

arXiv 2024年

作者： Li, Yang Liu, Ya-Feng The Shenzhen Research Institute of Big Data Shenzhen518172 China The State Key Laboratory of Scientific and Engineering Computing Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China

This paper studies the quality-of-service (QoS) constrained multi-group multicast beamforming design problem, where each multicast group is composed of a number of users requiring the same content. Due to the nonconvex QoS constraints, this problem is nonconvex and NP-hard. While existing optimization-based iterative algorithms can obtain a suboptimal solution, their iterative nature results in large computational complexity and delay. To facilitate real-time implementations, this paper proposes a deep learning-based approach, which consists of a beamforming structure assisted problem transformation and a customized neural network architecture named hierarchical permutation equivariance (HPE) transformer. The proposed HPE transformer is proved to be permutation equivariant with respect to the users within each multicast group, and also permutation equivariant with respect to different multicast groups. Simulation results demonstrate that the proposed HPE transformer outperforms state-of-the-art optimization-based and deep learning-based approaches for multi-group multicast beamforming design in terms of the total transmit power, the constraint violation, and the computational time. In addition, the proposed HPE transformer achieves pretty good generalization performance on different numbers of users, different numbers of multicast groups, and different signal-to-interference-plus-noise ratio targets. Copyright © 2024, The Authors. All rights reserved.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

An Efficient Novel Approach for Iris Recognition and Segmentation Based on the Utilization of Deep Learning

An Efficient Novel Approach for Iris Recognition and Segment...

引用

2023 International Conference on Evolutionary Algorithms and Soft computing Techniques, EASCT 2023

作者： Pasha, Syed Nawaz Anitha, D. Anbunathan, R. Gobinath, C. Madhura, G.K. Sr University School of Computer Science & Artificial Intelligence Warangal India School of Computing Srm Institute of Science and Technology Department of Computational Intelligence Kattankulathur India Sa Engineering College Department of Mathematics Chennai India Reva University School of Computing and Information Technology Bangalore India Nitte Meenakshi Institute of Technology Department of Ai and Ml Bengaluru India

ISBN: (纸本)9798350313413

Iris recognition stands out as one of the most stable and accurate biometric identification systems such as facial, voice, fingerprint, handwriting, and iris recognition itself. Deep Learning (DL) plays a pivotal role in enhancing security by leveraging Convolutional Neural Networks (CNNs) for iris recognition. The acquisition of iris images and real-time processing have become focal points demanding heightened attention in the realm of DL. Iris recognition is prized for its high level of protection, making it challenging to reconstruct iris data easily from the database. The CASIA-Iris Dataset serves as a benchmark to verify the uniqueness of iris patterns and evaluate the performance of iris recognition. However, due to limitations in iris image access, the application of CNNs in the segmentation approach remains critical for iris localization and pupil boundary identification, ensuring both efficiency and specificity in iris images. The results obtained from this study reveal that the proposed CNN, utilizing DL models, achieves an impressive accuracy of 99.89% on the CASIA-Iris dataset, better performance of other existing models, such as U-Net and VGG-Net, and ensuring accurate classification. © 2023 IEEE.

关键词： Contrast-Limited Adaptive Histogram Equalization Convolution Neural Network Deep Learning Iris Recognition and Support Vector Machine

来源：评论

学校读者我要写书评

暂无评论

A Perusal of Algrebraic and computational Modelling on Matrix Multiplication Time Complexity 13

A Perusal of Algrebraic and Computational Modelling on Matri...

引用

13th International Conference on Advanced Computer Information Technologies, ACIT 2023

作者： Choudhury, Manan Roy Banerjee, Ishan Government College of Engineering and Textile Technology Computer Science and Engineering West Bengal Serampore India Chennai Mathematical Institute Mathematics and Computing Tamil Nadu Chennai India

In learning linear algebra, matrix multiplication is most likely one of the most fundamental and significant operations with a broad application spectrum. We will mostly concentrate on studying several methods for multiplying two n×n matrices. The simplest technique has an 0(n3) complexity, although curiously, methods with lower complexity have been developed. Via the periodic survey, we will learn how the complexity may be made even more difficult. In this article, we compare the calculation times required by several matrix multiplication techniques, including the Naive and Strassen's methods. Additionally, a quick analysis of the Laser Method, Schonhage's Asymptotic Sum Inequality, Approximate Matrix Multiplication, Matrix Multiplication Tensors, and other algorithms is done to determine which approach is the most advantageous in terms of time and computational complexity. © 2023 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

On the convergence of stochastic gradient descent with bandwidth-based step size

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2023年第1期24卷 1990-2038页

作者： Xiaoyu Wang Ya-xiang Yuan Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China and University of Chinese Academy of Sciences Beijing China State Key Laboratory of Scientific/Engineering Computing Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing China

We first propose a general step-size framework for the stochastic gradient descent(SGD) method: bandwidth-based step sizes that are allowed to vary within a banded region. The framework provides efficient and flexible step size selection in optimization, including cyclical and non-monotonic step sizes (e.g., triangular policy and cosine with restart), for which theoretical guarantees are rare. We provide state-of-the-art convergence guarantees for SGD under mild conditions and allow a large constant step size at the beginning of training. Moreover, we investigate the error bounds of SGD under the bandwidth step size where the boundary functions are in the same order and different orders, respectively. Finally, we propose a 1/t up-down policy and design novel non-monotonic step sizes. Numerical experiments demonstrate these bandwidth-based step sizes' efficiency and significant potential in training regularized logistic regression and several large-scale neural network tasks.

关键词： stochastic gradient descent bandwidth-based step size non-asymptotic convergence non-monotonic step size machine learning

来源：评论

学校读者我要写书评

暂无评论

Case study of video compression via tensor train and Tucker decompositions

引用

computational mathematics and Modeling 2023年第1期34卷 42-53页

作者： Kurilovich, A.A. Matveev, S.A. Center for Energy Science and Technology Skolkovo Institute of Science and Technology Moscow 121205 Russian Federation Department of Materials Science and Engineering Technion – Israel Institute of Technology Haifa 3200002 Israel Faculty of Computational Mathematics and Cybernetics Lomonosov MSU Moscow 119991 Russian Federation Marchuk Institute of Numerical Mathematics RAS Moscow 119333 Russian Federation

This work represents a study of the capabilities of an approach for lossy video compression based on the tensor train and Tucker tensor formats. The TTSVD and st-HOSVD algorithms are used for video compression, which are represented as multidimensional arrays. The developed approach allows for analytical control of compression errors by determining the target PSNR. Thus, it provides a simple pipeline compared to traditional approaches. The detailed analysis of compression results is conducted (i) using known quality metrics PSNR and SSIM, (ii) by studying typical compression artifacts, and (iii) by identifying low-rank structures in video through the analysis of normalized singular values. For the TTSVD algorithm, additional preprocessing of data with tensorization by modes of the original array is tested, showing an improvement in compression quality. The developed approach does not allow to surpass industrial standards at the current stage of development. Nevertheless, it can be improved and can potentially be included into new approaches based on deep learning. © Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Tensor train Tucker decomposition Video compression

来源：评论

学校读者我要写书评

暂无评论

COMPLEX DYNAMICS OF A HOST-VECTOR DYNAMICS OF DENGUE INFECTION INCORPORATING OPTIMAL CONTROL STRATEGY WITH COST-EFFECTIVENESS: A FRACTIONAL-ORDER DERIVATIVE METHOD

引用

Journal of Mathematical sciences (United States) 2025年 1-30页

作者： Patra, Sathi Jana, Soovoojeet Adak, Sayani Majee, Suvankar Kar, T.K. Department of Mathematics Indian Institute of Engineering Science and Technology Shibpur West Bengal Howrah 711103 India Department of Mathematics Ramsaday College Amta West Bengal Howrah 711401 India Centre for Soft Computing Research Indian Statistical Institute West Bengal Kolkata 700108 India Department of Electrical and Electronics Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Karnataka Bengaluru 560035 India

Dengue is a resurging ailment infecting an estimated 100–140 million individuals annually. To understand the transmission mechanism of dengue, we define a nine-compartmental (six compartments for humans and three compartments for vectors) model incorporating fractional-order derivatives. Three different control measures, namely insecticide control for mosquitoes, treatment, and public awareness campaigns for the human population, are considered for the mathematical model to be proposed. We assess the existence and uniqueness of the solution and calculate the basic reproduction number (R0) using the next-generation matrix approach. It has been established that the proposed system has two equilibria viz: disease-free and endemic equilibrium, depending on R0. The stability of these equilibria has been investigated, considering R0 as the threshold parameter. Also, we have found that at R0=1, the system produces a transcritical bifurcation. Through numerical simulation with feasible parameter values, we demonstrate that employing controls decreases the infection, and all controls lead to a quicker removal of the disease. A cost-effectiveness analysis has been performed utilizing infection averted ratio (IAR) and incremental cost-effectiveness ratio (ICER) methods to determine the most cost-effective policy. Finally, the model has been calibrated using real dengue cases in Cambodia, one of the most dengue-prone countries, resulting in short-term predictions showing that the fractional-order system is more appropriate. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Cost-effectiveness analysis Dengue Fractional-order calculus Short-term prediction of dengue Transcritical bifurcation

来源：评论

学校读者我要写书评

暂无评论

Predictive Modeling of Cardiovascular Disease Using ML Algorithms

Predictive Modeling of Cardiovascular Disease Using ML Algor...

引用

2023 International Conference on Data science, Agents and Artificial Intelligence, ICDSAAI 2023

作者： Vijayalakshmi, M. Cherukuvada, Srikanth Chinnappa, A. Kavitha, G. Soujanya, A. Nareshkumar, R. Care College of Engineering Artificial Intelligence and Data Science Trichy India Srm Institute of Science and Technology School of Computing Department of Networking and Communications Chennai Kattankulathur India Srm Institute of Science and Technology School of Computing Department of Computer Science and Engineering Chennai Kattankulathur India Department of Mathematics Namakkal India Ibrahimpatnam India

ISBN: (纸本)9798350348910

One of the most significant contributors to morbidity in the global population is the ability to forecast a heart attack. Clinical data analysis is considered one of the most significant aspects for making a forecast, and that aspect is cardiovascular illness, a highly important disease. This can be a very useful tool. Using ML to its full potential, this investigation aims to achieve improved accuracy in diagnosing cardiac disease. In this research, we provide a machine knowledge heart attack diagnosis (MLHAP) technique that involves the study of different risk indicators, and prediction for heart attacks is carried out via ML methodologies, including Support Vector Machines, Logistic Regression, Naive Bayes, Knn, and XGBoost. In this method, the ML-HAP method predicts heart attacks. This approach aims to reduce the mortality rate from heart attacks. The forecast has been optimized as much as possible based on many parameters, which has been the primary focus. KNN, with its parameters optimized, made the most accurate prediction of any of the algorithms. The accuracy obtained using KNN Optimization is 85.24, while the accuracy obtained using Logistic Regression is 78.68. The prediction made by machine learning models for recognizing the signs of a heart attack is extremely effective, particularly when using boosting algorithms. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Incorporating 5G NR Sidelink with MQTT to Maximize Energy Efficiency in IoT-Enabled Microgrids 1

Incorporating 5G NR Sidelink with MQTT to Maximize Energy Ef...

引用

1st IEEE International Conference on Smart Power Control and Renewable Energy, ICSPCRE 2024

作者： Neelamegam, G. Ashforn, Hermina J.M. Raja, Mohamed S. Priyadharshini, J. Akshya, J. Choudhry, Mani Deepak Sundarrajan, M. Vsb College of Engineering and Technology Department of Computer Science and Engineering Coimbatore India Bannari Amman Institute of Technology Department of Artificial Intelligence and Data Science Erode India Kalaignarkarunanidhi Institute of Technology Department of Computer Science and Engineering Coimbatore India K. Ramakrishnan College of Engineering Department of Information Technology Trichy 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 Srm Institute of Science and Technology Department of Networking and Communications Chennai India

ISBN: (纸本)9798350377002

IoT for smart microgrids is an innovative disruption at the cutting edge of energy management, relying on interconnectedness provided by smart sensors and devices to enhance power generation and distribution precision in metropolitan areas. The problems of the real-time operational capabilities required for efficient energy resource management thus progress, inhibit rapid control and management. The main goal of this research proposal consists of to use of the advanced technology of 5G NR Sidelink combined with MQTT to conduct a revolutionary communication system of Microgrid running through the IoT devices. The 5G NR (New Radio) Sidelink enables direct D2D communication, which leads to a dramatic lowering of the latency in the absence of traditional network infrastructures for communication, while the MQTT protocol improves the communication efficiency among networks of numerous IoT devices. The introduction of this system was followed by a 15% decrease in energy transmission losses and by 20% improvement in response times in comparison to conventional models specified in the quantitative evaluation thus increasing operational efficiency by far. These efficiencies not only reduce operating expenses and power consumption but also increase the solution's scalability, pointing out the possibility of building the solution for bigger urban microgrid implementations. In consideration of that, the suggested mechanism with 5G NR Sidelink along with MQTT overcomes elaborate barriers of IoT-based microgrids and establishes a new potency in advanced energy management in smart cities which could make the distribution network in the urban areas on the edge of the verge of a change. © 2024 IEEE.

关键词： Microgrids

来源：评论

学校读者我要写书评

暂无评论

UAV -Based Object Tracking Using Siamese Networks and Kalman Filtering

UAV -Based Object Tracking Using Siamese Networks and Kalman...

引用

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

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：