检索结果-内蒙古大学图书馆

International Conference on Inventive Computation Technologies (ICICT)

作者： S. Rosaline K. Maheswari B. Dhanasakkaravarthi Vaishali M Sathish Kannan Nandakumar Selvaraju Department of Electronics and Communication Engineering R.M.K. Engineering College Kavaraipettai Thiruvallur Tamil Nadu India Department of Computer Science and Engineering CMR Technical Campus Kandlakoya Hyderabad Telangana India Department of Mechanical Engineering Agni College of Technology Thazhambur. Chennai Tamil Nadu India Department of Computer Science and Business Systems Sri Eshwar College of Engineering Coimbatore Tamil Nadu India Department of VLSI Microelectronics Saveetha School of Engineering Saveetha Institute of Medical and Techinical Sciences Chennai Tamil Nadu India Department of Automobile Engineering Hindustan Institute of Technology and Science Padur Chennai Tamil Nadu India

ISBN: (数字)9798350359299

ISBN: (纸本)9798350359305

A condition known as an anomaly occurs when some brain features behave improperly and cause either minor or significant harm to brain cells. Brain tumors, vascular malformations, and inflammatory lesions are among the most well-known abnormalities. A variety of Machine Learning (ML) and Deep Learning (DL) methods are employed in the analysis and detection of brain irregularities. The use of metaheuristic optimization is one such method. Three optimization processes have been chosen for this investigation. The study examines and documents anomaly detection efficiency. A public dataset comprising brain scan images from disparate institutions is employed in the research to analyze the effectiveness of the detection procedure. The three algorithms used are Sequential Minimal Optimization (SMO), Krill Herd Optimization (KHO), and Particle Swarm Optimization (PSO). The three algorithms are fed the preprocessed images for training and testing. From the simulation result, it is established that the KHO algorithm is the best method for identifying brain abnormalities. The KHO achieved an accuracy of 0.96, whereas the competitive model like PSO scored an accuracy value of 0.93 and SMO attained 0.95. The KHO method is quite accurate in detecting the presence of any kind of abnormality.

关键词： Training Magnetic resonance imaging Simulation Metaheuristics Software algorithms Medical services Software

来源：评论

学校读者我要写书评

暂无评论

Planning Algorithm for Scientific Workflows: A Cost-Aware and Makespan Approach Based on Locust-Inspired Algorithm

SSRN

引用

SSRN 2023年

作者： Ala’anzy, Mohammed Alaa Othman, Mohamed Hanapi, Zurina Mohd Mohamed, Nader Ahmad, Zulfiqar Almaty040900 Kazakhstan Department of Communication Technology and Networks Universiti Putra Malaysia UPM Selangor D.E. Serdang43400 Malaysia Universiti Putra Malaysia UPM Selangor D.E. Serdang43400 Malaysia Department of Computer Science and Information Systems Pennsylvania Western University California PA15419 United States Department of Computer Science and Information Technology Hazara University Mansehra21300 Pakistan

Job scheduling of scientific workflows in cloud computing is an NP-hard optimisation problem. Efficiently scheduling the tasks in a workflow remains a challenging and open research problem that needs to be addressed. Scientific workflows are data-intensive;whereas, high powered computational resources are needed for handling them. Therefore, cloud computing is an impressive paradigm to handle such massive amounts of data effectively on a pay-as-you-use basis. In cloud computing, cost and execution time limitations are increasingly becoming significant concerns. The challenges of rising cost and time are particularly tough for scientific workflows since they need complex data processing through the communication network. In this paper, we propose a novel planning algorithm based on a locust-inspired algorithm for scientific workflow in a cloud environment for heterogeneous systems. This algorithm aims to optimise the scheduling and execution of tasks in such a way that it can be applied to a wide range of systems, with the goal of minimising overall costs and maximising efficiency. The proposed algorithm generates a task list based on the locust-inspired positioning of the tasks whereas the task list will consist the priority and balance tasks. This task list is used to submit tasks to the heterogeneous virtual machines, taking into account the queue list and the earliest finish times in order to optimise the scheduling of the tasks. Moreover, the child-parent tasks and the link latency are also considered in the scheduling of the tasks. In light to this, the makespan and financial costs have improved in accordance with this method, which has successfully demonstrated its effectiveness. The proposed algorithm is assessed using real-world dataset of data-exhaustive workflows and compared to state-of-the-art algorithms. The performance evaluation result demonstrates that our proposed algorithm could effectively reduce the cost and the makespan of the most of the invest

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Yoga Evolution for Advancing Mindfulness and Well-Being Through Cloud-Connected Practices

AI-Driven Yoga Evolution for Advancing Mindfulness and Well-...

引用

Smart Technologies for Sustainable Development Goals (ICSTSDG), International Conference on

作者： Chitra Sabapathy Ranganathan T. Senthil Kumar E. Sivanantham Aarthy. S.T S. Murugan M. Nalini Mphasis Corporation Chandler Arizona USA School of Information Technology and Engineering VIT University Vellore Tamil Nadu India Department of Electronics and Communication Engineering Rajalakshmi Institute of Technology Chennai Tamil Nadu India Department of Electronics and Communication Engineering SRM Institute of Science and Technology Chennai Tamil Nadu India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India Department of Computer Science and Business Systems S.A. Engineering College (Autonomous) Chennai Tamil Nadu India

ISBN: (数字)9798331516284

ISBN: (纸本)9798331516291

Yoga, a conventional practice focused on mindfulness and overall well-being, is significantly changing with Artificial Intelligence (AI) and cloud computing technology. This research examines the potential synergies between AI and yoga to improve mindfulness practices and foster overall wellness in the era of digital technology. AI algorithms produce personalized yoga routines that adapt to individual requirements, talents, and objectives. The routines are constantly improved using feedback from users and physiological data gathered from wearable devices, promoting a personalized and adaptable approach to practicing yoga. The cloud connection allows effortless access to an extensive collection of yoga materials, such as instructional videos, guided meditations, and community support networks. Using AI-powered data analytics, individuals may get valuable information about their development, assess their current yoga practice, identify problem areas, and obtain personalised recommendations for improvement. The conventional practice of yoga is updated and made more attainable, enabling people to develop mindfulness, cope with stress, and improve their general well-being in a progressively connected society.

关键词： Cloud computing Technological innovation Data analysis Human factors Real-time systems Artificial intelligence Wearable devices Biomedical monitoring Sustainable development Videos

来源：评论

学校读者我要写书评

暂无评论

Integrated Sensing and communications Towards Proactive Beamforming in mmWave V2I via Multi-Modal Feature Fusion (MMFF)

arXiv

引用

arXiv 2023年

作者： Zhang, Haotian Gao, Shijian Cheng, Xiang Yang, Liuqing State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Peking University Beijing100871 China Guangzhou511400 China Guangzhou511400 China Department of Electronic and Computer Engineering the Department of Civil and Environmental Engineering The Hong Kong University of Science and Technology Hong Kong

The future of vehicular communication networks relies on mmWave massive multi-input-multi-output antenna arrays for intensive data transfer and massive vehicle access. However, reliable vehicle-to-infrastructure links require exact alignment between the narrow beams, which traditionally involves excessive signaling overhead. To address this issue, we propose a novel proactive beamforming scheme that integrates multi-modal sensing and communications via Multi-Modal Feature Fusion Network (MMFF-Net), which is composed of multiple neural network components with distinct functions. Unlike existing methods that rely solely on communication processing, our approach obtains comprehensive environmental features to improve beam alignment accuracy. We verify our scheme on the Vision-Wireless (ViWi) dataset, which we enriched with realistic vehicle drifting behavior. Our proposed MMFF-Net achieves more accurate and stable angle prediction, which in turn increases the achievable rates and reduces the communication system outage probability. Even in complex dynamic scenarios with adverse environment conditions, robust prediction results can be guaranteed, demonstrating the feasibility and practicality of the proposed proactive beamforming approach. Copyright © 2023, 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

ASSESSING THE ROBUSTNESS OF CRITICAL BEHAVIOR IN STOCHASTIC CELLULAR AUTOMATA

arXiv

引用

arXiv 2022年

作者： Pontes-Filho, Sidney Lind, Pedro Nichele, Stefano Department of Computer Science Oslo Metropolitan University Oslo Norway Department of Computer Science Norwegian University of Science and Technology Trondheim Norway AI Lab - OsloMet Artificial Intelligence Lab Oslo Norway NordSTAR Nordic Center for Sustainable and Trustworthy AI Research Oslo Norway Department of Holistic Systems Simula Metropolitan Centre for Digital Engineering Oslo Norway Department of Computer Science and Communication Østfold University College Halden Norway

There is evidence that biological systems, such as the brain, work at a critical regime robust to noise, and are therefore able to remain in it under perturbations. In this work, we address the question of robustness of critical systems to noise. In particular, we investigate the robustness of stochastic cellular automata (CAs) at criticality. A stochastic CA is one of the simplest stochastic models showing criticality. The transition state of stochastic CA is defined through a set of probabilities. We systematically perturb the probabilities of an optimal stochastic CA known to produce critical behavior, and we report that such a CA is able to remain in a critical regime up to a certain degree of noise. We present the results using error metrics of the resulting power-law fitting, such as Kolmogorov-Smirnov statistic and Kullback-Leibler divergence. We discuss the implication of our results in regards to future realization of brain-inspired artificial intelligence *** Codes 68T01 © 2022, CC BY.

关键词： Stochastic models

来源：评论

学校读者我要写书评

暂无评论

Nodes Number Estimation based on ML for Multi-operator Unlicensed Band Sharing to Extend Indoor Connectivity

Nodes Number Estimation based on ML for Multi-operator Unlic...

引用

IEEE Conference on Wireless communications and Networking

作者： Oluwatobi Baiyekusi Haeyoung Lee Klaus Moessner Department of Computer & Information Sciences University of Strathclyde Glasgow UK School of Physics Engineering and Computer Science University of Hertfordshire Hatfield UK 5GIC & 6GIC Institute for Communication Systems (ICS) University of Surrey Guildford UK Faculty of Electronics and Information Technology University of Technology Chemnitz Germany

Due to ever-increasing data and resource-hungry applications, the need for new spectrum by mobile networks keeps increasing. Unlicensed spectrum is still expected to play a crucial part in meeting the capacity demand for future mobile networks. But if this will be a reality, fair coexistence attained via practical and efficient channel access procedures would be necessary. In designing such channel access schemes, awareness of the number of nodes contending for the channel resource will be required. This paper investigates a node number estimation approach using channel idle time and analysed via machine learning (ML) techniques. When multiple nodes access the same unlicensed channel, varying idle times can be associated with a statistical distribution. In this paper, a statistical distribution of the idle-time slots over the channel is used to characterise and analyse the channel contention based on the number of nodes. Three ML model-based approaches are evaluated and the results confirm the proposed solution’s viability but also reveal the best-performing ML technique of the three, for the task of node number estimations.

关键词： Radio frequency Maximum likelihood estimation Statistical distributions Channel estimation Machine learning Predictive models Data models

来源：评论

学校读者我要写书评

暂无评论

A secure medical image encryption technique based on DNA cryptography with elliptic curves

引用

Scientific Reports 2025年第1期15.0卷 1-18页

作者： Kumaran, V. N. Senthil Manikandan, T. Dhanaraj, Rajesh Kumar Al-Shehari, Taher Alsadhan, Nasser A. Selvarajan, Shitharth Department of Electronics and Communication Engineering SRM Institute of Science and Technology Tiruchirappalli Campus Tiruchirappalli India Department of Computer Science and Business Systems Rajalakshmi Engineering College Thandalam India Symbiosis Institute of Computer Studies and Research (SICSR) Symbiosis International (Deemed University) Pune India Computer Skills Department of Self-Development Skill Common First Year Deanship King Saud University Riyadh 11362 Saudi Arabia Computer Science Department College of Computer and Information Sciences King Saud University Riyadh 12372 Saudi Arabia Department of Computer Science Kebri Dehar University 250 Kebri Dehar Ethiopia Department of Computer Science and Engineering Chennai Institute of Technology Chennai India Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura 140401 India School of Built Environment Engineering and Computing Leeds Beckett University LS6 3HF Leeds United Kingdom

Health services and telemedicine have proven to be an important area for information protection in research, especially with medical services and smart health care applications. In these systems, medical imaging protection are important not only for clinical diagnosis, but also to protect the very sensitive and confidential patient data. With progress in imaging technologies and biomedical processing algorithms, the amount of image data increases rapidly. However, securing this information while transferring through insecure channel is still a constant challenge. Existing encryption techniques often face limitations such as high computational complexity, insufficient security against advanced cryptographic attacks, poor reversal and pixel correlation. To overcome these challenges, the proposed approach provides an innovative hybrid encryption technique that integrates DNA cryptography with Elliptical Curve Cryptography (ECC). The DNA-based coding shows high randomness and equality while the ECC provides strong security and confidentiality. The DNA encoding and secure key generation are employed in the proposed technique to obtain the encrypted medical image. The combination of these techniques addresses the main boundaries of existing disadvantage by increasing both security and calculation efficiency, making it well suited for real time medical applications. The experimental analysis was carried out with various parameters like histogram analysis, correlation coefficient, Chi square, MSE, PSNR, entropy etc. The result analysis states that the proposed methodology outperforms the state-of-the-art existing methods with enhanced performance such as entropy of 7.9981, Correlation coefficient of 0.0019 and PSNR of 53.97. Also, the proposed methodology is tested for runtime analysis, memory analysis and security analysis. © The Author(s) 2025.

关键词： Applied AI Biomedical image encryption DNA encoding Elliptic curve cryptography Secure key generation Security

来源：评论

学校读者我要写书评

暂无评论

Lightweight Task-Oriented Semantic communication Empowered by Large-Scale AI Models

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Liu, Chuanhong Guo, Caili Yang, Yang Chen, Mingzhe Quek, Tony Q. S. Beijing University of Posts and Telecommunications Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing100876 China Beijing University of Posts and Telecommunications Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing100876 China University of Miami Department of Electrical and Computer Engineering Institute for Data Science and Computing Coral GablesFL United States Singapore University of Technology and Design Dept. of Information Systems Technology and Design 487372 Singapore

Recent studies have focused on leveraging large-scale artificial intelligence (LAI) models to improve semantic representation and compression capabilities. However, the substantial computational demands of LAI models pose significant challenges for real-time communication scenarios. To address this, this paper proposes utilizing knowledge distillation (KD) techniques to extract and condense knowledge from LAI models, effectively reducing model complexity and computation latency. Nevertheless, the inherent complexity of LAI models leads to prolonged inference times during distillation, while their lack of channel awareness compromises the distillation performance. These limitations make standard KD methods unsuitable for task-oriented semantic communication scenarios. To address these issues, we propose a fast distillation method featuring a pre-stored compression mechanism that eliminates the need for repetitive inference, significantly improving efficiency. Furthermore, a channel adaptive module is incorporated to dynamically adjust the transmitted semantic information based on varying channel conditions, enhancing communication reliability and adaptability. In addition, an information bottleneck-based loss function is derived to guide the fast distillation process. Simulation results verify that the proposed scheme outperform baselines in term of task accuracy, model size, computation latency, and training data requirements. © 1967-2012 IEEE.

关键词： NP-hard

来源：评论

学校读者我要写书评

暂无评论

Performance evaluation of IP over cost-optimized optical multilayer networks with SRLGs 9

Performance evaluation of IP over cost-optimized optical mul...

引用

9. ITG-Fachtagung Photonische Netze - 9th ITG Conference on Photonic Networks

作者： Duelli, Michael Hartmann, Matthias Menth, Michael Hülsermann, Ralf Düser, Michael University of Wuerzburg Institute of Computer Science Department of Distributed Systems Am Hubland Würzburg97074 Germany T-Systems Enterprise Services GmbH Goslarer Ufer 35 Berlin10589 Germany

ISBN: (纸本)9783800730971

The design of optical transport and IP networks is investigated with respect to the effect on overall network performance when the two aspects are combined in the same network architecture. The focus is on the identification of advantages in the joint design of IP and transport networks, as well as on the shortcomings and network bottlenecks which may result from sub-optimal design. The impact of different IP routing strategies (shortest path, equal-cost multipath) on the network utilization is quantified, and potential sources for overload in the IP domain are determined. Simulations were carried out to systematically assess technical metrics like link utilization and economic parameters such as cost for a 50-node transport network with line rates up to 40 Gbit/s. The impact of fiber cuts was taken into account, leading to multiple logical IP links to fail simultaneously, i.e. shared risk link groups (SRLGs), and triggering massive IP rerouting. Applying the results allows to identify bottlenecks in the design, and to devise mechanisms which allow cost-optimal network design of future IP and optical transport networks. © 2020 ITG-Fachtagung.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Channel Estimation for 29GHz mm Wave MIMO systems in Tropical Region

Channel Estimation for 29GHz mm Wave MIMO Systems in Tropica...

引用

IEEE International Symposium on Telecommunication Technologies (ISTT)

作者： Li Lu Aduwati Sali School of Microelectronics and Data Science Anhui University of Technology Maanshan China Department of Computer and Communication Systems Engineering Wireless and Photonics Networks Research Centre of Excellence (WiPNET) Faculty of Engineering Universiti Putra Malaysia Serdang Selangor Malaysia Institute for Mathematical Research (INSPEM) Universiti Putra Malaysia Serdang Selangor Malaysia

ISBN: (数字)9798350392074

ISBN: (纸本)9798350392081

This paper focuses on the 29GHz mmWave MIMO communication system in tropical environments, considering the impact of rain attenuation and providing a detailed analysis of channel estimation and system performance. Experimental results indicate that as the signal-to-noise ratio (SNR) increases, the mean square error (MSE) of channel estimation decreases. Under the same SNR conditions, MIMO systems with different antenna configurations exhibit distinct channel estimation error characteristics. Notably, in the 128x128 antenna configuration, the channel estimation error is most pronounced. Furthermore, increasing the number of training signals significantly reduces channel estimation errors, especially in the 128x128 antenna configuration. This study offers a performance evaluation of the 29GHz mmWave MIMO communication system in tropical regions, providing valuable insights for further research and optimization in this field.

关键词： Training Rain System performance Channel estimation Mean square error methods Attenuation Millimeter wave communication Antennas MIMO communication Signal to noise ratio

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：