检索结果-内蒙古大学图书馆

Machine Learning for Wireless Network Optimization: Algorithms and Applications for Adaptive Communication

Machine Learning for Wireless Network Optimization: Algorith...

Advances in computer Science, electrical, Electronics, and Communication Technologies (CE2CT), International Conference on

作者： Madhira Srinivas S. Surya Prachi Deepak Thakar Amit Kumar Jain Department of Computer Science & Engineering Data Science Geethanjali College of Engineering & Technology (GCET) Hyderabad India Sri Ramachandra Faculty of Engineering & Technology (SRET) Sri Ramachandra Institute of Higher Education & Research Porur Chennai India Department of Computer Engineering KJ college of Engineering & Management Research Pune India Department of Electrical & Electronics Engineering Poornima University Jaipur Rajasthan India

ISBN: (数字)9798331518578

ISBN: (纸本)9798331518585

This project looks into the possibility of applying machine learning to optimize wireless networks for adaptive communication. Using 5G resource data, it applies preprocessing, exploratory analysis, and visualization to identify key trends: signal strength, latency, and bandwidth utilization. Machine learning algorithms predict resource allocation based on latency-sensitive and bandwidth-demanding applications. The approach emphasizes energy efficiency, scalability, and service quality, and dynamically adjusts communication strategies to meet diverse network demands. The findings indicate the machine learning importance in enhancing elasticity and robustness in a wireless network and its general function.

关键词： Machine learning algorithms Adaptive systems Wireless networks Scalability Machine learning Bandwidth Predictive models Prediction algorithms Resource management Optimization

来源：评论

学校读者我要写书评

暂无评论

Interpolated hybrid DBIM approach for enhanced imaging in ultrasound tomography

引用

Research on Biomedical engineering 2022年第2期38卷 389-400页

作者： Quang-Huy, Tran Nguyen, Khai Tuan Doan, Phuc Thinh Tran, Duc-Tan Faculty of Physics Hanoi Pedagogical University 2 Nguyen Van Linh Street Xuan Hoa Ward Vinh Phuc Province Phuc Yen City Viet Nam Department of Electrical Electronics and Computer Engineering University of Ulsan Daehak-ro Nam-gu Ulsan44610 Korea Republic of NTT Hi-Tech Institute Nguyen Tat Thanh University Ho Chi Minh City700000 Viet Nam Faculty of Mechanical Electrical Electronic and Automotive Engineering Nguyen Tat Thanh University Ho Chi Minh700000 Viet Nam Faculty of Electrical and Electronic Engineering Phenikaa University Hanoi12116 Viet Nam No. 167 Hoang Ngan Trung Hoa Cau Giay Hanoi11313 Viet Nam

Purpose: In ultrasound tomography (UT), Born iterative method (BIM) and distorted-Born iterative method (DBIM) based on Born approximation are considered efficacious. DBIM offers faster convergence compared to BIM;however, it is more susceptible to noise and vice versa. Combined or multi-model imaging is an indispensable trend of modern imaging to detect and accurately assess tissue states. The proposed method exploits the advantages, limiting the disadvantages and increasing the imaging speed of the merging of BIM and DBIM. Methods: The combination of BIM and DBIM is proposed to increase UT reconstruction quality. This promising approach aims to maintain good convergence while still being robust to noise. Furthermore, we suggest using the interpolation technique sandwiched between BIM and DBIM (named hybrid DBIM) to enhance imaging speed and reduce computational complexity. Results: Different numerical simulation scenarios were performed to prove this method’s reliability. The proposed hybrid DBIM method offers significantly better performance with a 47.4% drop in normalized error, a 13% decrease in time consumption, and reduced calculations of 18% compared to the conventional DBIM method. Conclusions: UT is a promising quantitative imaging technique because it offers a more sophisticated imaging method than conventional B-mode due to its inverse scattering information basis rather than B-mode’s ultrasound feedback. Enhanced image recovery quality and accelerated imaging time are obtained by using the hybrid DBIM. Thanks to the usage of empirical data, this work will be further developed prior to its application in reality. © 2021, Sociedade Brasileira de Engenharia Biomedica.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

A compact wideband printed slot antenna with gain enhancement for GPR applications 18

A compact wideband printed slot antenna with gain enhancemen...

引用

18th International Conference on electrical engineering/Electronics, computer, Telecommunications and Information Technology, ECTI-CON 2021

作者： Sutham, Thanakorn Thaiwirot, Wanwisa Akkaraekthalin, Prayoot Chalermwisutkul, Suramate King Mongkut's University of Technology North Bangkok Faculty of Engineering Department of Electrical and Computer Engineering Bangkok Thailand Bangkok Thailand

ISBN: (纸本)9780738111278

This paper presents a printed wide slot antenna fed by double-shaped feeding strip with a modified slot for gain enhancement. The inverted U-shaped slot of the original slot antenna is modified by adding the wide rectangular slot. In addition, the small rectangular slots are etched on the bottom edge of the radiating slot to improve impedance matching, especially at lower frequencies. The proposed antenna has dimensions of 230 mm × 270 mm, which provides a very wide impedance bandwidth, covering the frequency range from 0.3 to 3.564 GHz. Moreover, a stable and bi-directional radiation pattern is observed within the frequency lower than 1 GHz for subsurface imaging application. The proposed antenna has maximum realized gain about 8.8 dBi at 2.5 GHz, while improving the gain of original antenna about 1 dBi without increasing the antenna size. © 2021 IEEE.

关键词： Slot antennas

来源：评论

学校读者我要写书评

暂无评论

Log-Scale Quantization in Distributed First-Order Methods: Gradient-based Learning from Distributed Data

arXiv

引用

arXiv 2024年

作者： Doostmohammadian, Mohammadreza Qureshi, Muhammad I. Khalesi, Mohammad Hossein Rabiee, Hamid R. Khan, Usman A. Faculty of Mechanical Engineering Semnan University Semnan Iran Electrical and Computer Engineering Department Tufts University Medford United States Computer Engineering Department Sharif University of Technology Tehran Iran ECE/CS Tufts University United States Amazon United States

Decentralized strategies are of interest for learning from large-scale data over networks. This paper studies learning over a network of geographically distributed nodes/agents subject to quantization. Each node possesses a private local cost function, collectively contributing to a global cost function, which the considered methodology aims to minimize. In contrast to many existing papers, the information exchange among nodes is log-quantized to address limited network-bandwidth in practical situations. We consider a first-order computationally efficient distributed optimization algorithm (with no extra inner consensus loop) that leverages node-level gradient correction based on local data and network-level gradient aggregation only over nearby nodes. This method only requires balanced networks with no need for stochastic weight design. It can handle log-scale quantized data exchange over possibly time-varying and switching network setups. We study convergence over both structured networks (for example, training over data-centers) and ad-hoc multi-agent networks (for example, training over dynamic robotic networks). Through experimental validation, we show that (i) structured networks generally result in a smaller optimality gap, and (ii) log-scale quantization leads to a smaller optimality gap compared to uniform quantization. © 2024, CC BY.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Discrepancy and Thematic Bibliometric Analyses of the Remaining Limitations in Artificial Intelligence

Discrepancy and Thematic Bibliometric Analyses of the Remain...

引用

2024 IEEE International Conference on Computing, ICOCO 2024

作者： Mansor, Mahayaudin M. Ibrahim, Nurain Radi, Noor Fadhilah Ahmad Rahim, Nadirah Abdul Yahaya, Syarul Heiry Bakar, Mohd Aftar Abu Zakaria, Roslinazairimah School of Mathematical Sciences College of Computing Informatics and Mathematics Universiti Teknologi MARA Malaysia Institute of Big Data Analytics and Artificial Intelligence Universiti Teknologi MARA Malaysia Department of Electrical and Computer Engineering Kuliyyah of Engineering International Islamic University Malaysia Department of Science Computer and Mathematics Universiti Teknologi MARA Penang Campus Malaysia Department of Mathematical Sciences Faculty of Science & Technology Universiti Kebangsaan Malaysia Centre for Mathematical Sciences Universiti Malaysia Pahang Al-Sultan Abdullah Malaysia

ISBN: (纸本)9798331530303

As artificial intelligence (AI) advances, it is essential to continuously comprehend its limitations to optimise the integration of AI into autonomous systems that empower humans. The first objective of this study is to highlight the key capabilities of both humans and AI, focusing on the differences and identifying limitations of AI from the literature. Through discrepancy analysis, this study uses a Venn diagram to visualise the remaining limitations of AI into five key domains: (i) emotional intelligence, (ii) consciousness and awareness, (iii) creative imagination, (iv) communication, and (v) ethical decision-making. Furthermore, this study employs thematic bibliometric analysis to provide a more detailed examination of each AI limitation as the second objective. This study has identified underdeveloped and emerging research themes with potential for future development, such as emotion recognition, human-computer interaction, digital health, and situational awareness, which may require further research. Additionally, this study commends the ongoing efforts to harness AI’s computational power and algorithmic innovations to enhance AI’s overall performance and applicability. ©2024 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Unified Power Flow controller: Operation, Modelling and Applications

Unified Power Flow Controller: Operation, Modelling and Appl...

引用

International Symposium on Applied Computational Intelligence and Informatics ( SACI)

作者： Majid Dehghani Mohammad Reza Yousefi Amir Mosavi Arman Fathollahi Department of Electrical Engineering Najafabad Branch Islamic Azad University Najafabad Iran John von Neumann Faculty of Informatics Obuda University Budapest Hungary Department of Electrical and Computer Engineering Aarhus University Aarhus Denmark

This paper focuses on implementing the unified power flow controller (UPFC) in the optimal power flow approach, a critical aspect of power and control system operations. Optimal power flow minimizes operating costs and maintains safety margins for control variables, making it an indispensable tool for energy management. The flexible AC transmission system (FACTS) is a fundamental component of this approach, with the UPFC playing a crucial role. This versatile device provides various types of energy system compensation, enabling the independent control of reactive and active electrical power in transmission lines and bus voltages simultaneously. Previous studies have explored a wide range of engineering applications for UPFC using diverse techniques. This paper reviews these applications, specifically examining how UPFC can increase power system flexibility and controllability. Additionally, this paper explores utilizing artificial intelligence (AI) in the placement of UPFC in power systems. By incorporating AI techniques such as machine learning and optimization algorithms, power system operators can optimize the placement of UPFC to achieve optimal energy management. This approach enhances the efficiency and reliability of energy systems, resulting in significant cost savings and improved power system performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RedactBuster: Entity Type Recognition from Redacted Documents

arXiv

引用

arXiv 2024年

作者： Beltrame, Mirco Conti, Mauro Guglielmin, Pierpaolo Marchiori, Francesco Orazi, Gabriele University of Padua Department of Mathematics Italy Delft University of Technology Faculty of Electrical Engineering Mathematics and Computer Science Netherlands FDM Business Services Italy

The widespread exchange of digital documents in various domains has resulted in abundant private information being shared. This proliferation necessitates redaction techniques to protect sensitive content and user privacy. While numerous redaction methods exist, their effectiveness varies, with some proving more robust than others. As such, the literature proposes several deanonymization techniques, raising awareness of potential privacy threats. However, while none of these methods are successful against the most effective redaction techniques, these attacks only focus on the anonymized tokens and ignore the sentence context. In this paper, we propose RedactBuster, the first deanonymization model using sentence context to perform Named Entity Recognition on reacted text. Our methodology leverages fine-tuned state-of-the-art Transformers and Deep Learning models to determine the anonymized entity types in a document. We test RedactBuster against the most effective redaction technique and evaluate it using the publicly available Text Anonymization Benchmark (TAB). Our results show accuracy values up to 0.985 regardless of the document nature or entity type. In raising awareness of this privacy issue, we propose a countermeasure we call character evasion that helps strengthen the secrecy of sensitive information. Furthermore, we make our model and testbed open-source to aid researchers and practitioners in evaluating the resilience of novel redaction techniques and enhancing document privacy. © 2024, CC BY-NC-ND.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Transient stability analysis of IEEE 9-bus system integrated with DFIG and SCIG based wind turbines 15

Transient stability analysis of IEEE 9-bus system integrated...

引用

15th International engineering and Computing Research Conference, EURECA 2021

作者： Ramlochun, Brish Vaithilingam, Chockalingam Aravind Alsakati, Ahmad Adel Alnasseir, Jamal School of Computer Science and Engineering Faculty of Innovation and Technology Taylor's University Malaysia Electric Power Engineering Department Faculty of Mechanical and Electrical Engineering Damascus University Syria

Electricity is in high demand with a fast-growing population;hence it is advisable to turn towards green energy. In this research, Wind Turbine (WT) is modelled with two different types of induction generators (IGs), which are the Doubly-Fed Induction Generator (DFIG) and Squirrel-Cage Induction Generator (SCIG) and implemented to IEEE 9-Bus system to assess the transient stability. MATLAB/Simulink R2019a platform was considered to carry the whole examination. DC1A excitation system was applied to Synchronous Generators (SGs) as well as Power System Stabilizer (PSS). The transmission line7-5 was found to suffer from a high peak value of a relative power angle of approximately 130 degrees. As for the settling time, without PSS it was 20.69 s and with PSS it became 6.23 s. A wind farm with a rated capacity of 60 MW was used in the system. WT integrated with DFIG has the lowest peak value of 127 degrees at Bus locations 4 and 5 and for SCIG, Bus 5 with a peak value of 136 degrees. Thus, it can be propelled as the perfect location. Moreover, this is due to the three-phase fault was located at the transmission line7-5 which is far away from Buses 4 and 5. In the end, the WT integrated with DFIG provides a lower peak value of relative power angle compared to SCIG, whereas for settling time, it is the opposite. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Wind turbines

来源：评论

学校读者我要写书评

暂无评论

EMI Performance Analysis in IRS-Aided Multi-User Wireless Communication Systems

EMI Performance Analysis in IRS-Aided Multi-User Wireless Co...

引用

Virtual Conference on Communications (VCC), IEEE

作者： Rhana M. Elshishtawy Shimaa S. Ali Adly S. Tag Eldien Mostafa M. Fouda Mohamed I. Ismail Esraa M. Eid Department of Electrical Engineering Faculty of Engineering at Shoubra Benha University Egypt Department of Electrical and Computer Engineering Idaho State University Pocatello ID USA Center for Advanced Energy Studies (CAES) Idaho Falls ID USA Department of Electronic Engineering & Communication Technology Modern Academy for Engineering Egypt

This paper presents a comprehensive investigation into the effect of Electromagnetic Interference (EMI) on wireless systems employing single and distributed Intelligent Reflecting Surfaces (IRSs) in three distinct conditions by varying the number of antennas, elements, and users. Through extensive numerical simulations, the performance of the wireless systems is rigorously evaluated under different EMI scenarios. Firstly, the influence of varying the number of antennas on the system performance is thoroughly analyzed. The results demonstrate that an increased number of antennas contributes to improved signal reception and reduced interference levels. Moreover, the enhanced beamforming capabilities offered by additional antennas lead to higher signal quality and increased system Achievable Rate (AR). Secondly, the impact of changing the number of elements within the IRS under EMI conditions is investigated in detail. The simulations reveal that an augmented number of elements facilitates efficient EMI mitigation, enabling advanced signal manipulation and more precise signal focusing. As a result, the system exhibits improved performance in terms of signal strength, coverage, and AR. Lastly, the effect of varying the number of users on system performance in the presence of EMI is thoroughly assessed. The findings unveil that an increased number of users under EMI conditions leads to elevated interference levels, degraded signal quality, and diminished system AR. Thus, it is crucial to develop effective EMI mitigation strategies and resource allocation schemes to ensure reliable and efficient communication in IRS-enabled wireless systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Actor-Critic Reinforcement Learning Scheme for Reactive 3D Optimal Motion Planning Based on Fluid Dynamics

An Actor-Critic Reinforcement Learning Scheme for Reactive 3...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Marios Malliaropoulos Panagiotis Rousseas Charalampos P. Bechlioulis Kostas J. Kyriakopoulos School of Mechanical Engineering Control Systems Laboratory National Technical University of Athens Department of Electrical and Computer Engineering University of Patras Center of AI & Robotics (CAIR) New York University Abu Dhabi

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

This work proposes a novel and provably correct method for three-dimensional optimal motion planning in complex environments. Our approach models the 3D motion planning problem by solving streamlines of the potential fluid flow, filling a gap in traditional motion planning techniques by guaranteeing a closed-loop, smooth and natural-looking navigation solution. Special emphasis is given to an inherent challenge of artificial potential field (APF) methods, namely establishing proofs of safety and stability over the entire optimization process. A model-based actor-critic reinforcement learning algorithm is introduced to approximate the optimal solution to the Hamilton-Jacobi-Bellman equation and update the controller parameters in a deterministic manner. Through a series of ROS-Gazebo software-in-the-loop simulations the proposed methodology demonstrates robustness and outperforms widely used methods such as the RRT ∗ , highlighting its contribution to the field of 3D optimal motion planning.

关键词： Solid modeling Three-dimensional displays Navigation Reinforcement learning Mathematical models Stability analysis Robustness Planning Safety Optimization

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：