检索结果-内蒙古大学图书馆

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Elghazaly, Osama Nasser, Nidal El Ouadrhiri, Ahmed Ali, Asmaa Alfaisal University IoT Research Lab Riyadh Saudi Arabia Rockford University Department of Mathematics Computer Science and Physics RockfordIL United States Wastern University Electrical and Computer Engineering Department London Canada

ISBN: (纸本)9798350351255

Blockchain-based smart contracts, while transformative, pose privacy concerns due to Ethereum's transparency. To address this, we present Safe Smart Contracts (SafeSC), leveraging zk-SNARKs for privacy without compromising Ethereum's transparency. SafeSC's Python tool facilitates contract understanding and verification without accessing the source code. Our paper explores privacy preservation techniques, favoring Zero-Knowledge Proofs (ZKPs). SafeSC employs zk-SNARKs and Groth-16, achieving a delicate balance between transparency and privacy in smart contract development. The tool's design, covering architecture, assumptions, data flow, and zero-knowledge proof workflow, marks a step toward secure smart contract solutions. We advocate for continued exploration and refinement to enhance blockchain technologies. © 2024 IEEE.

关键词： Blockchain ChatGPT Ethereum Smart Contracts

来源：评论

学校读者我要写书评

暂无评论

PERFORMANCE ANALYSIS OF VLC-BASED LI-FI NLOS UNDERWATER CHANNEL USING ASK MODULATION SCHEME OVER WDM UNDER THE INFLUENCE OF AMBIENT LIGHT

PERFORMANCE ANALYSIS OF VLC-BASED LI-FI NLOS UNDERWATER CHAN...

引用

2025 International Conference on Energy, Power, Environment, Control and Computing, ICEPECC 2025

作者： Umer, Rao Behram Mushtaq, Farhan Khan, Faisal Hammad Nouman, Muhammad Hassan, Usman Amanullah Adnan, Muhammad Photonics And Communication Lab Department of Electrical Engineering University of Engineering & Technology Taxila Pakistan Electronics and Communication Systems Lab Department of Telecommunication Engineering University of Engineering & Technology Taxila Pakistan School of Electrical Engineering and Computer Science National University of Sciences and Technology Islamabad Pakistan

ISBN: (纸本)9781837243235

Li-Fi is another term for Visible light communication (VLC) which operates by transmitting data through free space by using either Light Emitting Diodes (LEDs) or Laser Diodes (LDs). The technique finds substantial applications in scientific research as well as military applications when used underwater. VLC technology helps eliminate radio interference alongside providing replacement solutions for traditional underwater communication systems. The research develops and models a visible light wireless communication system through ambient light testing with two 550 nm and 450 nm LD light sources and Pin photodetector over 10 meters using Opti System software. The system uses Non-Return-to-Zero On-Off Keying (NRZ OOK) also known as Amplitude Shift Keying (ASK) modulation through Mach-Zehnder Modulator with WDM technology in NLOS environment. A 10 Gbps data transmission occurs through the clear ocean environment along a 10-meter channel with 0.0405 1/m absorption and 0.0025 1/m scattering. The 550 nm transmitted source emits its maximum Quality factor as 8.35 when BER analyzers operate under ambient light conditions and produce its minimum BER as 4.89e-11 under the same conditions. Examining similar ambient light influences reveals the BER analyzers demonstrate a maximum Quality factor of 8.62 and minimum BER of 18.11e-12 when operating under 450 nm transmitted light. © The Institution of engineering & Technology 2025.

关键词： BIT ERROR RATE LASER DIODE LI-FI QUALITY FACTOR UNDERWATER WIRELESS COMMUNICATION

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach for Service Selection and Ranking in Federated cloud 1

引用

5th International Conference on Information Systems and Management science, ISMS 2022

作者： Saxena, Rajat Dubey, Shatendra Kumar, Upanshu Cloud Computing Lab Department of Computer Science and Engineering Shri Vaishnav Institute of Information Technology Shri Vaishnav Vidyapeeth Vishwavidyalaya Indore India Department of Information Technology NRI Institute of Information Science and Technology Bhopal India

ISBN: (数字)9783031311536

ISBN: (纸本)9783031311529

In Federated cloud environment, cloud service ranking and selection is a very tedious work because of complexion involved Service Level Agreement (SLA) and Service specifications. Quality of Service (QoS) expected from cloud users may be conflicting based on their applications. cloud Brokers needs to be deal with cloud users and Federated cloud like a heterogeneous interface. A cloud Brokers also fulfils many suitable services from available resources. cloud Broker also choose the federated cloud services based on their rank for available service. Noncommercial and conflicting demands of users evolves cloud Service Selection a very competitive multi-criteria based service ranking and selection problem. cloud User requests from different federated clouds based on some preference order of QoS parameters. This preference order converts into individual QoS parameters by assigning suitable weight. The weighted demands are estimated the available QoS values for each cloud service. In the next step, modified VIKOR method is applied for finding the rank of the services. This rank of service is based on preference of QoS parameters. The service with highest rank is selected and provided to the user. We used cloudSim for the testing of this method. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Enhancing Energy Efficiency in IoT Networks Through Fuzzy Clustering and Optimization

引用

Mobile Networks and Applications 2024年第5期29卷 1594-1617页

作者： Javadpour, Amir Sangaiah, Arun Kumar Zaviyeh, Hadi Ja’fari, Forough Department of Computer Science and Technology Harbin Institute of Technology Shenzhen China ADiT-Lab Electrotechnics and Telecommunications Department Instituto Politécnico de Viana do Castelo Porto4900-347 Portugal International Graduate School Artificial Intelligence National Yunlin University of Science and Technology Douliu Taiwan Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon School of Economics and Statistics Guangzhou University Guangzhou510006 China Department of Computer Engineering Sharif University of Technology Tehran Iran

Wireless Sensor and Internet of Things (WSIoT) networks are characterized by nodes scattered throughout the environment, posing a significant challenge when it comes to battery replacement. The task of developing an algorithm that effectively reduces energy consumption in IoT networks through the utilization of artificial intelligence and fuzzy logic is a formidable one. Heuristic algorithms emerge as valuable tools in this context, capable of swiftly addressing non-deterministic polynomial problems or approximating optimal solutions with remarkable accuracy. Conversely, mathematical optimization approaches often falter due to their sluggishness or inefficiency, rendering them less suited for the dynamic demands of IoT networks. This study embarks on a novel approach, leveraging the synergy of fuzzy clustering to intricately connect sensors to the network and particle optimization to approximate the initial values of head clusters within the realm of WSIoT. A comprehensive evaluation of our proposed strategy is meticulously conducted through extensive simulations utilizing the NS2 simulator. In this evaluation, we distinguish our algorithm from existing methods, including IoTbWSN and REcsIoT. The results of this comparative analysis are illuminating. In contrast to other methodologies, our proposed approach demonstrates a notable 9.57% improvement in network throughput and a substantial 8.47% reduction in energy consumption. This signifies a remarkable leap forward in the quest to address the challenges posed by energy consumption and battery replacement within the complex landscape of IoT networks. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2023.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Medical Diagnostics with Transparent AI-Driven Decision Support Systems 4

Revolutionizing Medical Diagnostics with Transparent AI-Driv...

引用

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Annamalai, M. Mittal, Tanusha Sunkara, Krishna Chaitanya Pandey, Himani Jadhav, Girish Nemane, Vivek Vinsys It Services India Limited Pune India Graphic Era Deemed to be University Department of Computer Science & Engineering Dehradun India Oracle Cloud Engineering Data Center NC United States Baroda University Department of Environmental Science Vadodara India Parul institute of Engineering and Technology Parul University Faculty of Engineering and Technology Department of Electrical Engineering Post Limda India Faculty of Law Pune India

ISBN: (纸本)9798350352931

This study introduces an innovative AI-Driven Decision Support System (DSS) for revolutionizing healthcare diagnostics, emphasizing the use of Explainable AI (XAI) to enhance transparency and trust in medical decision-making. The proposed system integrates machine learning and deep learning algorithms to analyze and interpret complex medical data, providing clinicians with clear, understandable insights that support diagnostic accuracy and patient outcomes. The system was evaluated on a dataset of 25,000 patient records across multiple diagnostic domains, including cardiology, oncology, and radiology. Key performance metrics showed a significant improvement in diagnostic precision and explain ability. The model achieved an accuracy of 94.8% in diagnosing cardiac conditions, with an explanation accuracy of 92.1%, measured by how well the XAI techniques correlated with expert evaluations. For oncology cases, the system demonstrated an 87.5% reduction in false positives, while maintaining an overall accuracy of 93.2%. In terms of clinician trust, surveys indicated a 35% increase in confidence when using the XAI-based system compared to traditional black-box models. Additionally, the time to generate diagnostic explanations was reduced by 40%, improving clinical workflow and decision-making efficiency. These results underscore the transformative potential of integrating XAI into healthcare decision support systems, providing not only accurate predictions but also interpretable insights that enhance trust and usability in medical diagnostics. © 2024 IEEE.

关键词： Oncology

来源：评论

学校读者我要写书评

暂无评论

Optimizing Antenna Design for 6G Applications Using Machine Learning Techniques

Optimizing Antenna Design for 6G Applications Using Machine ...

引用

2024 International Conference on Artificial Intelligence and Emerging Technology, Global AI Summit 2024

作者： Sharma, Praveen Kumar Yadav, Vivek Prakash Mukesh, Aashiwal Nirmal Jawale, Sourabh Kumar, Ankit Research Center for Electrical and Information Technology Seoul National University of Science and Technology Seoul01811 Korea Republic of FEAL: Flexible Electronics and Antenna Lab Department of Electronics and Communication Engineering Pilani India FEAL: Flexible Electronics and Antenna Lab Department of Electronics and Communication Engineering Mumbai India Medicaps University Department of Computer Science and Engineering Indore India Seoul National University of Science and Technology Department of Computer Science and Engineering Seoul01811 Korea Republic of

ISBN: (纸本)9798350379716

The emergence of 6G networks requires innovative antenna designs that operate at extremely high frequencies. The proposed paper explores the application of advanced machine learning techniques to optimize the design of antennas for 6G applications at 15 GHz. Traditional design methods are often time-consuming and depend on expert knowledge, whereas machine learning can automate and expedite this process. We developed a dataset incorporating critical antenna design parameters such as geometric dimensions and applied algorithms to predict key performance metrics like return loss, gain, and bandwidth. Our results demonstrate that neural networks, in particular, offer superior predictive accuracy, significantly reducing design iteration times. This integration of machine learning into antenna design not only improves performance but also facilitates the development of adaptive antenna systems, meeting the stringent demands of 6G networks. This research highlights the potential of machine learning to revolutionize antenna design, enabling rapid and efficient development of next-generation communication systems. © 2024 IEEE.

关键词： Smart antennas

来源：评论

学校读者我要写书评

暂无评论

Online Learning Behavior Analysis and Prediction Based on Spiking Neural Networks

引用

Journal of Social Computing 2024年第2期5卷 180-193页

作者： Yanjing Li Xiaowei Wang Fukun Chen Bingxu Zhao Qiang Fu the Institute of Education Science Research Heilongjiang UniversityHarbin 150080China the School of Cyberspace Security Shandong University of Political Science and LawJinan 250014China the School of Computer Science and Technology Harbin Engineering UniversityHarbin 150001China the Faculty of Electrical and Computer Engineering University of VictoriaVictoriaV8P 5C2Canada. the Guangxi Key Lab of Brain-Inspired Computing and Intelligent Chips School of Electronic and Information EngineeringGuangxi Normal UniversityGuilin 541004China

The vast amount of data generated by large-scale open online course platforms provide a solid foundation for the analysis of learning behavior in the field of *** study utilizes the historical and final learning behavior data of over 300000 learners from 17 courses offered on the edX platform by Harvard University and the Massachusetts Institute of Technology during the 2012-2013 academic *** have developed a spike neural network to predict learning outcomes,and analyzed the correlation between learning behavior and outcomes,aiming to identify key learning behaviors that significantly impact these *** goal is to monitor learning progress,provide targeted references for evaluating and improving learning effectiveness,and implement intervention measures *** results demonstrate that the prediction model based on online learning behavior using spiking neural network achieves an impressive accuracy of 99.80%.The learning behaviors that predominantly affect learning effectiveness are found to be students’academic performance and level of participation.

关键词： online learning learning outcomes prediction learning behavior analysis spiking neural network

来源：评论

学校读者我要写书评

暂无评论

Enhancing Diversity in Multi-Objective Feature Selection 13

Enhancing Diversity in Multi-Objective Feature Selection

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Miyandoab, Sevil Zanjani Rahnamayan, Shahryar Bidgoli, Azam Asilian Ebrahimi, Sevda Makrehchi, Masoud Lab Department of Electrical Computer and Software Engineering Ontario Tech University OshawaON Canada Brock University Department of Engineering St. CatharinesON Canada Wilfrid Laurier University Faculty of Science WaterlooON Canada

ISBN: (纸本)9798350308365

Feature selection plays a pivotal role in the data preprocessing and model-building pipeline, significantly en-hancing model performance, interpretability, and resource efficiency across diverse domains. In population-based optimization methods, the generation of diverse individuals holds utmost importance for adequately exploring the problem landscape, particularly in highly multi-modal multi-objective optimization problems. Our study reveals that, in line with findings from sev-eral prior research papers, commonly employed crossover and mutation operations lack the capability to generate high-quality diverse individuals and tend to become confined to limited areas around various local optima. This paper introduces an augmen-tation to the diversity of the population in the well-established multi-objective scheme of the genetic algorithm, NSGA-II. This enhancement is achieved through two key components: the genuine initialization method and the substitution of the worst individuals with new randomly generated individuals as a re-initialization approach in each generation. The proposed multi-objective feature selection method undergoes testing on twelve real-world classification problems, with the number of features ranging from 2,400 to nearly 50,000. The results demonstrate that replacing the last front of the population with an equivalent number of new random individuals generated using the genuine initialization method and featuring a limited number of features substantially improves the population's quality and, consequently, enhances the performance of the multi-objective algorithm. © 2024 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Ensemble Knowledge Distillation of Self-Supervised Speech Models

Ensemble Knowledge Distillation of Self-Supervised Speech Mo...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Kuan -Po Huang Tzu-Hsun Feng Yu-Kuan Fu Tsu-Yuan Hsu Po-Chieh Yen Wei-Cheng Tseng Kai-Wei Chang Hung-Yi Lee College of Electrical Engineering and Computer Science National Taiwan University ASUS Intelligent Cloud Services

Distilled self-supervised models have shown competitive performance and efficiency in recent years. However, there is a lack of experience in jointly distilling multiple self-supervised speech models. In our work, we performed Ensemble Knowledge Distillation (EKD) on various self-supervised speech models such as HuBERT, RobustHuBERT, and WavLM. We tried two different aggregation techniques, layerwise-average and layerwise-concatenation, to the representations of different teacher models and found that the former was more effective. On top of that, we proposed a multiple prediction head method for student models to predict different layer outputs of multiple teacher models simultaneously. The experimental results show that our method improves the performance of the distilled models on four downstream speech processing tasks, Phoneme Recognition, Speaker Identification, Emotion Recognition, and Automatic Speech Recognition in the hidden-set track of the SUPERB benchmark.

关键词： Emotion recognition Predictive models Signal processing Benchmark testing Robustness Noise robustness Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Design oligoporous-core based multimode fiber for mode division multiplexing applications

引用

Optical and Quantum Electronics 2025年第5期57卷 1-24页

作者： Mitu, Sumaiya Akhtar Abdulrazak, Lway Faisal Ibrahim, Sobhy M. Tahhan, Shaymaa R. Hossain, Md Bellal Ahmed, Kawsar Bui, Francis M. Chen, Li Department of Computer Science and Engineering University of Asia Pacific 74/A Green Rd Dhaka1205 Bangladesh Department of Information and Communication Technology Group of Bio-photomatiχ Mawlana Bhashani Science and Technology University Tangail Santosh1902 Bangladesh Department of Computer Science Cihan University Sulaimaniya Kurdistan Region Sulaimaniya46001 Iraq Department of Biochemistry College of Science King Saud University P.O. Box: 2455 Riyadh11451 Saudi Arabia Department of Laser and Optoelectronics Engineering College of Engineering Al-Nahrain University Jadriya Baghdad64074 Iraq School of Electrical and Information Engineering The University of Sydney SydneyNSW Australia Department of Electrical and Computer Engineering University of Saskatchewan 57 Campus Drive SaskatoonSKS7N 5A9 Canada Health Informatics Research Lab Department of Computer Science and Engineering Daffodil International University Daffodil Smart City Birulia Dhaka1216 Bangladesh

A polarization-maintaining oligoporous-core-based multi-mode fiber is proposed. By tuning the air hole, as well as the core number, shape, size, and position up to 28 distinct linearly polarized (LP) modes are obtained. The Finite Element Method (FEM) is used to perform the numerical investigations. In addition, various materials combinations are used as a doping with silica which is highly helpful to increase or decrease the refractive index of the core material. The multimode fiber is identified by the normalized frequency or V parameter. Besides, the high birefringence value, low loss value, minimum crosstalk with high sensitivity response of 1.46×10-2, 2×10-11dB/m, 41.80 dB and 88,280.46 nm/RIU, respectively, are achieved from the numerical investigations over the wavelength range from 1.55 µm to1.65 µm for the different LP modes. Moreover, good responses also obtain for the numerical aperture, V number, coupling length and other parameters. In the end, every value reveals both an easy-to-fabricate structure design as well as adequate performance analysis. The suggested fiber structure can support many modes and might be applicable in the field of optical communications and spatial multiplexing based on the user demand. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Fiber to the x

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：