检索结果-内蒙古大学图书馆

A DECOUPLED,LINEARLY IMPLICIT AND UNCONDITIONALLY ENERGY STABLE SCHEME FOR THE COUPLED CAHN-HILLIARD SYSTEMS

Journal of computational Mathematics 2025年第3期43卷 708-730页

作者： Dan Zhao Dongfang Li Yanbin Tang Jinming Wen School of Mathematics and Statistics Huazhong University of Science and TechnologyWuhan 430074China Hubei Key Laboratory of Engineering Modeling and Scientific Computing Huazhong University of Science and TechnologyWuhan 430074China College of Information Science and Technology Jinan UniversityGuangzhou 510632China

We present a decoupled,linearly implicit numerical scheme with energy stability and mass conservation for solving the coupled Cahn-Hilliard *** time-discretization is done by leap-frog method with the scalar auxiliary variable(SAV)*** only needs to solve three linear equations at each time step,where each unknown variable can be solved *** is shown that the semi-discrete scheme has second-order accuracy in the temporal *** convergence results are proved by a rigorous analysis of the boundedness of the numerical solution and the error estimates at different *** examples are presented to further confirm the validity of the methods.

关键词： Coupled Cahn-Hilliard system Leap-frog method Scalar auxiliary variable Error estimate

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Approach of Black Widow Optimization with Firefly (FF) Algorithm for Efficient Routing in Wireless Sensor Network 2

A Hybrid Approach of Black Widow Optimization with Firefly (...

引用

2nd International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2024

作者： Sindhuja, M. Srm Institute of Science and Technology Department of Computing Technologies School of Computing College of Engineering and Technology Kattankulathur Tamil Nadu Chennai India

ISBN: (纸本)9798350368413

The sensor nodes that make up a Wireless Sensor Network (WSN) can be located anywhere and are linked wirelessly so that they can all keep tabs on the same set of physical characteristics in the area of interest. The nodes in a WSN run on internal batteries, thus when they run out of energy after repeated uses, the network has a shorter lifespan. Clustering and routing methods are frequently utilized in WSN to improve energy efficiency and network lifetime. For WSN's cluster-based routing, this work introduces the innovative black widow optimization with firefly algorithm (FFA). The suggested BWO-FF algorithm comprises BWO based clustering procedure to elect an optimal set of cluster heads (CHs). The BWO algorithm creates a fitness function utilizing input parameters. In addition, route selection for inter-cluster communication requires an FF-based routing method. This routing method aims to enhance network throughput and lifetime by calculating the ideal route from each node to the sink in an effort to ensure uniform energy consumption across the network. MATLAB simulations have been used to analyze the proposed approach from several perspectives. The BWO-FF algorithm's superiority to all other techniques studied is guaranteed by a selection of comparison evaluations. © 2024 IEEE.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Computer Aided Diagnosis Multi-model System using Late Fuison and Ensemble Learning

Computer Aided Diagnosis Multi-model System using Late Fuiso...

引用

2025 International Conference on Pervasive computational Technologies, ICPCT 2025

作者： Priya, M.Kani Aruru, Gunabhiram Vanam, Nikhil Suganiya, M. Salomi, M. Srm Institute of Science and Technology School of Computing Faculty of Engineering and Technology Department of Computational Intelligence Tamil Nadu Chennai India Srm Institute of Science and Technology Department of Computing Technologies Tamil Nadu Chennai India Srm Institute of Science and Technology Department of Computational Intelligence Tamil Nadu Chennai India

ISBN: (纸本)9798331508685

Lung Cancer and brain tumors are the well-known causes of cancer deaths universal. Therefore, appropriate and accurate diagnosis is an important issue that affects better and more reliable treatment and the patient's chance of survival. Present diagnostic strategies are mostly based on a single piece of information. This often leads to missing necessary information, which can lead to Misidentification of condition or delay in timely treatment. This study presents a novel Computer-Aided-Diagnosis system designed to enhance the detection of lung cancer and brain tumors by integrating multimodal data, including medical images (CT and MRI scans) and clinical information. The proposed approach employs late fusion and ensemble learning techniques, utilizing CNN for processing CT images, VGG19 for analyzing MRI scans, and Random Forest classifiers for evaluating clinical data. By separately training these models, the system capitalizes on the distinct characteristics of each data modality, overcoming the limitations of traditional CAD systems that typically rely on a single data source. This comprehensive analysis not only improves diagnostic accuracy but also provides reliable predictions, ultimately facilitating better clinical decision-making for lung cancer and brain tumor detection. © 2025 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

QIRA: A Quantum-Inspired Cluster Head Selection Algorithm for Wireless Sensor Networks 7

QIRA: A Quantum-Inspired Cluster Head Selection Algorithm fo...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Sindhuja, M. Srm Institute of Science And Technology School of Computing College of Engineering And Technology Department of Computing Technologies Tamil Nadu Kattankulathur603203 India

ISBN: (纸本)9798350359299

Cluster Head Selection (CHS) is one of the critical tasks in Wireless Sensor Networks (WSNs) as it directly impacts the network's performance and lifetime. In this manuscript, a Quantum-Inspired Recommendation Algorithm (QIRA) for optimal cluster head selection in WSNs has been proposed. QIRA utilizes the superposition and entanglement properties of quantum mechanics to explore the search space of potential cluster head candidates. The algorithm is designed to consider multiple features such as residual energy, distance to the base station, and node centrality during the process of Cluster Head Selection. The evaluation of the proposed QIRA algorithm, is has been done using wide-ranging simulations and compared with existing cluster head selection processes. The results demonstrate that QIRA is able to achieve significant improvements in terms of network lifetime, energy consumption, and data throughput. © 2024 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Adaptive sail fish optimizer based optimized region selection for robust video steganography

引用

International Journal of Information Technology (Singapore) 2025年第4期17卷 2417-2427页

作者： Babu, J. Suresh Niranjana, G. Ramana, Kadiyala Department of Computing Science & Engineering School of Computing College of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Kattankulathur Chengalpattu India Department of Computing Technologies SRM Institute of Science and Technology Kattankulathur Chengalpattu India Department of Artificial Intelligence and Data Science Chaitanya Bharathi Institute of Technology (Autonomous) Hyderabad India

Securing data transmission in a digital era is a difficult one due to the broad application of the Internet, personal computers, and mobile phones for communication. Traditional video steganography techniques sometimes fail to identify the best pixels for encoding hidden data, resulting in lowerquality and robustness. To solve this issue, this article proposes an innovative steganography technique that improves the security and quality of data hiding. The proposed method takes cover video and secret images as input. The Structural Similarity Index Measurement (SSIM) first collects key frames from the input video. The adaptive sailfish optimizer (ASFO) is then used to find the best regions within these keyframes to insert the secret data in. To improve security, the discrete wavelet transform (DWT) is applied to the specified region, and the LL band is used for the hiding process. The secret image is encrypted by Adaptive elliptical curve cryptography (AECC) and transformed to binary bits, which then get embedded in the chosen band. This method leads to the construction of a stego-video. The extraction procedure is repeated using the same approach, which ensures secure and robust data transmission. Performance metrics, including PSNR, BER, NAE, TAF, and NC are analyzed to compare each method's efficacy. © Bharati Vidyapeeth's Institute of Computer Applications and Management 2025.

关键词： Adaptive elliptical curve cryptography And stego-video Discrete wavelet transform Structural similarity index measurement Video steganography

来源：评论

学校读者我要写书评

暂无评论

Leveraging HPC with GAN-CNN Integration for Enhanced Tuberculosis Detection using Synthetic Image Generation 3

Leveraging HPC with GAN-CNN Integration for Enhanced Tubercu...

引用

3rd International Conference on Automation, computing and Renewable Systems, ICACRS 2024

作者： Manasa, Pokala Veeramalla, Vaishnavi Vanusha, D. Vathana, D. Robinsha, Delsi S. Department of Computing Technologies School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu Chengalpattu603203 India Department of Computing Technologies School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu Chengalpattu603203 India

ISBN: (纸本)9798331532420

Tuberculosis (TB) remains a significant global health challenge, especially in remote areas with limited medical resources. Early and accurate diagnosis is crucial to control its spread. This project harnesses high-performance computing (HPC) to address two key issues: managing unreliable medical data and improving TB diagnosis. Given the imbalance between healthy and TB-affected samples, Generative Adversarial Networks (GANs) are used to generate synthetic images, enriching the dataset and making it more diverse. This helps train Convolutional Neural Networks (CNNs), which are highly effective in medical image analysis. By leveraging HPC, we accelerate the training of CNNs on large, augmented datasets, significantly reducing processing time while maintaining accuracy. This system improves TB detection by combining GAN-enhanced data and CNN models, enabling faster and more reliable diagnosis. © 2024 IEEE.

关键词： X ray apparatus

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Dynamic Signal Switching: A Promising Solution to Traffic Congestion

Machine Learning-Based Dynamic Signal Switching: A Promising...

引用

2023 International Conference on Innovative computing, Intelligent Communication and Smart Electrical Systems, ICSES 2023

作者： Kanchana, M. Gopirajan, P.V. Mahalakshmi, B. Vijaya Nirmala, B. SRM Institute of Science and Technology School of Computing Department of Computing Technologies Katankulathur Tamil Nadu Chennai603203 India SRM Institute of Science and Technology School of Computing Department of Computational Intelligence Katankulathurx Tamil Nadu Chennai603203 India AMC Engineering College Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350319200

Today's growing urban population means increased revenue for individuals, translating into growing vehicles on the road. Nowadays, people use their private vehicles instead of public transportation, which results in a considerable number of personal vehicles that lead totraffic congestion everywhere. The ever-increasing number of vehicles and complex congestion leads to frequent traffic jams in major cities. In today's scenario, traditional traffic management methods have become redundant as the traffic volume has grown exponentially. The primary goal of this proposed work is to develop an algorithm that uses machine learning to control traffic effectively and ensure efficient traffic flow in the event of unforeseen events like accidents. The existing algorithm focuses on predicting shortterm traffic flow but ignores that traffic congestion may also occur due to accidents and emergencies. Our proposed model will consider all the above factors and use dynamic signal switching among lanes to predict the best and most efficient solution to reducing waiting time for vehicles and congestion on the road. To create an effective traffic flow management model with the least amount of road mayhem, our suggested model needs traffic data as input, which was then trained using various Machine Learning (ML) models. © 2023 IEEE.

关键词： IDD Image processing Machine Learning Neural Network RCNN Traffic Management YOLO

来源：评论

学校读者我要写书评

暂无评论

Precision Forecasting of Stock Prices: Leveraging XGBoost and Technical Indicator for Advanced Predictive Modeling 1

Precision Forecasting of Stock Prices: Leveraging XGBoost an...

引用

1st International Conference on Intelligent Systems and computational Networks, ICISCN 2025

作者： Yuvaraj, S. Chenni Kumaran, J. Vinston Raja, R. Saveetha University Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India Srm Institute of Science and Technology Faculty of Engineering and Technology School of Computing Department of Computational Intelligence Kattankulathur Chennai India

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529246

The investigation aims to evaluate the performance of machine learning techniques, particularly the XGBoost regression method, for stock price prediction with the help of technical indicators. The research targets the adjusted closing price to reduce the autocorrelation problem in time series. The Five Days and Ten Days Exponential Moving Averages (EMA-5 and EMA-10) are involved in refining feature selection. The performance of the model was evaluated using different error metrics, namely, Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Coefficient of Determination (R2). The results indicate that the XGBoost model, combined with EMA-5 and EMA-10, achieves high predictive performance, obtaining an r2 value of 0.98. It implies that incorporating short-term EMAs into advanced machine learning techniques drastically improves stock price forecasting. © 2025 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Learning for UAV Trajectory and Caching With Federated Cloud-Assisted Knowledge Distillation

引用

IEEE Transactions on Network and Service Management 2025年第3期22卷 2516-2533页

作者： Tietaa Maale, Gerald Arden Elorm Kuadey, Noble Arafat, Yeasin Thomas, Kwantwi Sun, Guolin Liu, Guisong Research Institute of Intelligent Computing University of Electronic Science and Technology of China School of Computer Science and Engineering National Key Laboratory of Intelligent Collaborative Computing Chengdu611731 China McCoy University College of Education Department of Mathematics and ICT Nadowli Ghana Research Institute of Intelligent Computing at the University of Electronic Science and Technology of China School of Computer Science and Engineering National Key Laboratory of Intelligent Collaborative Computing Chengdu611731 China Ho Technical University Department of Computer Science Ho Ghana University of Mines and Technology Department of Computer Science and Engineering Tarkwa Ghana Southwestern University of Finance and Economics Complex Laboratory of New Finance and Economics School of Computing and Artificial Intelligence Chengdu610074 China Ministry of Education Engineering Research Center of Intelligent Finance Chengdu610030 China

The proliferation of Internet of Things (IoT) technologies and ubiquitous connectivity has led to uncrewed aerial vehicles (UAVs) playing key role as edge servers, revolutionizing the wireless communications landscape by facilitating computing and caching resources closer to ground users (GUs). This advancement significantly alleviates core network loads, reduces latency, and guarantees content availability even in congested or remote areas. However, jointly optimizing UAV caching strategies and trajectories gives rise to a multi-task optimization (MTO) problem. This paper introduces a novel multi-task geo-temporal caching (MT-GTC) framework that addresses the interplay between UAV caching mechanisms and trajectory optimization in a cohesive manner. Leveraging a proposed multi-task learning (MTL) model for joint optimization of UAV caching and trajectory design, we develop a federated learning cloud-assisted knowledge distillation (FL-CAKD) scheme to preserve data privacy and adapt to data heterogeneity. FL-CAKD transfers knowledge from a cloud model orchestrator (CMO), which houses a large and sophisticated teacher model, to a lightweight on-device MTL student models using soft target distributions instead of large model parameters, significantly reducing communication costs. MT-GTC optimizes caching and trajectories to maximize cache hits and minimize latency. Evaluations on real-world mobility datasets demonstrate up to 95% cache hit rates and 21% lower delays compared to baselines. © 2004-2012 IEEE.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

ENCODING UNITIG-LEVEL ASSEMBLY GRAPHS WITH HETEROPHILOUS CONSTRAINTS FOR METAGENOMIC CONTIGS BINNING 12

ENCODING UNITIG-LEVEL ASSEMBLY GRAPHS WITH HETEROPHILOUS CON...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Xue, Hansheng Mallawaarachchi, Vijini Xie, Lexing Rajan, Vaibhav School of Computing Australian National University Canberra Australia School of Computing National University of Singapore Singapore College of Science and Engineering Flinders University Adelaide Australia

Metagenomics studies genomic material derived from mixed microbial communities in diverse environments, holding considerable significance for both human health and environmental sustainability. Metagenomic binning refers to the clustering of genomic subsequences obtained from high-throughput DNA sequencing into distinct bins, each representing a constituent organism within the community. Mainstream binning methods primarily rely on sequence features such as composition and abundance, making them unable to effectively handle sequences shorter than 1,000 bp and inherent noise within sequences. Several binning tools have emerged, aiming to enhance binning outcomes by using the assembly graph generated by assemblers, which encodes valuable overlapping information among genomic sequences. However, existing assembly graph-based binners mainly focus on simplified contig-level assembly graphs that are recreated from assembler's original graphs, unitig-level assembly graphs. The simplification reduces the resolution of the connectivity information in original graphs. In this paper, we design a novel binning tool named UNITIGBIN, which leverages representation learning on unitig-level assembly graphs while adhering to heterophilous constraints imposed by single-copy marker genes, ensuring that constrained contigs cannot be grouped together. Extensive experiments conducted on synthetic and real datasets demonstrate that UNITIGBIN significantly surpasses state-of-the-art binning tools. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Graphic methods

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：