检索结果-内蒙古大学图书馆

1st International Conference on Advanced engineering and Technologies, ICONNIC 2023

作者： Pratama, Zudha Setiarso, Ichwan Mahmood, Sarmad Nozad Almohamadi, Mohammed Alani, Sameer Abbas, Fatima Hashim Abdulhammed, Razan Alkhayyat, Ahmed H. Ali, Rabei Raad University of Dian Nuswantoro Informatics Engineering Kediri Indonesia University of Dian Nuswantoro Visual Communication Design Kediri Indonesia Al-Kitab University Computer Technology Engineering Kirkuk Iraq College of Information Technology Imam Ja'afar Al-Sadiq University Al-Muthanna Iraq University of Mashreq Research Center Baghdad Iraq Al-Mustaqbal University College Medical Laboratories Techniques Babil Iraq College of Technical Engineering The Islamic University Najaf Iraq Northern Technical University Department of Computer Engineering Technology Mosul Iraq

ISBN: (纸本)9798350306484

Vehicular Adhoc Networks (VANETs) provide communication among vehicles to build smart cities using Intelligent Transportation System (ITS). In this paper, we proposed Delay Tolerant and Multipath Reliability (DTMR) in VANETs. The simulation of the DTMR method is performed using OMNet++ network simulator with Simulation of Urban Mobility (SUMO). The parameters which are considered for the performance analysis are end-to-end delay, data failure rate, data success rate and throughput. The results show that the DTMR method produces 85ms lower end-to-end delay, 13% lower data failure rate, 93 % higher data success rate and 614 Kbps higher throughput. The proposed DTMR method has better overall performance than the ISFF and VDPR methods. © 2023 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

The Burn Grafting Image Reclamation Redefined with the Peak-Valley Approach

引用

Critical Reviews in Biomedical engineering 2025年第2期53卷 21-35页

作者： Pradeep Kumar, B.P. Naresh, E. Ashwitha, A. Reddy, Kadiri Thirupal Srinidhi, N.N. Department of Computer Science and Design Atria Institute of Technology VTU Karnataka Bangalore India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of CSE Malla Reddy Engineering College for Women Telangana Hyderabad India Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

Burn injuries constitute a significant public health challenge, often necessitating the expertise of medical professionals for diagnosis. However, in scenarios where specialized facilities are unavailable, the utility of automated burn assessment tools becomes evident. Factors such as burn area, depth, and location play a pivotal role in determining burn severity. In this study, we present a classification model for burn diagnosis, leveraging automated machine learning techniques. Our approach includes an image reclamation system that incorporates the peak and valley algorithm, ensuring the removal of noise while consistently delivering high-quality results. By using skewness and kurtosis, we demonstrate substantial improvements in diagnostic accuracy. Our proposed system sources key features from enhanced grafting samples using peak valley transformation, enabling the computation of BQs and a unique bin analysis to enhance image reclamation. Our experimental results highlight efficiency gains, notably growing the matching features of graft samples for 14 matching images. The intended work involves the creation of a burn classification reclamation model. The proposed approach utilizes a support vector machine (SVM). The evaluation of the model will be conducted using an untrained catalogue, with a specific focus on its effectiveness in reclaiming images that necessitate grafts and distinguishing them from those that do not. Our approach holds promise in grafting sample reclamation in emergency settings, thereby expediting more accurate diagnoses and treatments for acute burn injuries. This work has the latent to save lives and improve patient upshots in burn traumas. © 2025 by Begell House, Inc.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Technicalities of O-RAN for 5G and B5G

Technicalities of O-RAN for 5G and B5G

引用

Knowledge engineering and Communication Systems (ICKECS), International Conference on

作者： Amar Choudhary Geetika Srivastava Mahesh Kumar Jha Department of Electronics and Communication Engineeirng Alliance College of Engineering and Design Alliance University Bengaluru Karnataka India Department of Electronics and Communication Engineeirng Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru Karnataka India Department of Electronics and Communication Engineering CMR Institute of Technology Bengaluru Karnataka India

ISBN: (数字)9798350359688

ISBN: (纸本)9798350359695

Telecom sector across the globe is gradually transiting towards 5G & B5G. This is due to its unparallel advantages of it over the existing technologies i.e. 4G or 3G. At the same time, several new challenges related to Spectrum and Bandwidth, Security, Cost etc. are reported regarding this technical transition. Among these, Interoperability of RAN, and Software Driven Network (SDN) are main starving areas for researchers and developers. The idea of this paper is to provide architectural details of O-RAN, suggested by O-RAN alliance. Also, in this paper the reader will come to know about functional BBU split. With all these, our purpose is to enable readers to have a basic knowledge of architectural technicalities of O-RAN in detail.

关键词： Knowledge engineering Costs 5G mobile communication Wireless networks Open RAN Bandwidth Software

来源：评论

学校读者我要写书评

暂无评论

IoT-Connected Telehealth Environments with Long Short-Term Memory Networks for Precise Time-Series Patient Behavior Analysis

IoT-Connected Telehealth Environments with Long Short-Term M...

引用

Intelligent Systems for Cybersecurity (ISCS), International Conference on

作者： B. Maruthukannan R. C. Karpagalakshmi D. Lakshmi Rajapriya M D.C. Joy Winnie Wise C. Srinivasan Department of Computer Science and Engineering NPR College of Engineering & Technology Dindugal Tamil nadu India Alliance College of Engineering and Design Alliance University Bengaluru Karnataka India Department of Electronics and Communication Engineering St. Joseph's College of Engineering OMR Chennai Tamil Nadu India Department of Management Studies Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering Rajalakshmi Institute of Technology Chennai Tamil Nadu India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

ISBN: (数字)9798350375237

ISBN: (纸本)9798350375244

Advanced analytics are becoming more important in telehealth environments as the number of connected devices continues to rise, necessitating the collection of massive amounts of time-series patient data. This system uses Long Short-Term Memory (LSTM) networks in telemedicine that are linked to the Internet of Things (IoT), with an emphasis on accurate longitudinal monitoring of patient behavior. An extensive dataset gathered from IoT devices that track several health metrics in real-time is used in the research. LSTM networks are used to detect patterns and relationships in time-series data using a deep learning technique. In turn, this allows the system to analyze patient behavior with more precision and speed. IoT provides seamless connections for real-time data transfer it offers continuous monitoring within the telehealth framework. The LSTM-based model improves our comprehension of patient behavior, which in turn enables us to spot outliers, forecast health trends, and provide individualized healthcare recommendations. Through its demonstration of LSTM networks' usefulness in the context of IoT-connected telehealth settings, the study makes a valuable contribution to the rapidly growing area of digital health. Accurate time-series analysis has the ability to improve patient monitoring, early intervention, and healthcare outcomes, as shown by the results.

关键词： Patient monitoring Accuracy Telemedicine System performance Scalability Time series analysis Medical services

来源：评论

学校读者我要写书评

暂无评论

Lattice-Based Cryptography and NTRU: Quantum-Resistant Encryption Algorithms

Lattice-Based Cryptography and NTRU: Quantum-Resistant Encry...

引用

Emerging Systems and Intelligent Computing (ESIC), International Conference on

作者： F. Nisha J. Lenin S.K. Saravanan V. Robin Rohit P. D. Selvam M. Rajmohan School of Engineering and Technology Computer Science & Engineering CMR University Bengaluru Karnataka India Department of Computer Science & Engineering Alliance College of Engineering and Design Alliance University Bengaluru Karnataka India Department of BigData and Network Security Saveetha School of Engineering SIMATS Chennai Tamil Nadu India Computer Science & Engineering School of Computer Science & Engineering and Information Science Presidency University Bengaluru Karnataka India Department of Electronics and Communication Engineering Vel Tech High Tech Dr.Rangarajan Dr.Sakunthala Engineering College Chennai Tamil Nadu India Department of Electronics and Communication Engineering Hindustan Institute of Technology and Science Chennai Tamil Nadu India

The quantum-resistant qualities of various encryption methods, such as N-th degree Truncated polynomial Ring Units (NTRU) Encrypt, NTRU Sign, Ring-Lizard, and Kyber protocols are becoming more important in light of the ever-evolving nature of digital threats. An-depth analysis of the mathematical derivation of these algorithms, as well as a determination of their computing efficiency and resistance to quantum assaults is discussed in this paper. Techniques of the Ring-Lizard and Kyber algorithms to lattice-based encryption are analyzed. The study gives an overview of quantum-resistant capabilities of these algorithms and their performance measures. Strengths and weaknesses of the NTRU Encrypt, NTRU Sign, Ring-Lizard, and Kyber algorithms are discussed. The results give useful insights for cybersecurity practitioners, academics, and policymakers, aiding them in making educated choices to protect digital infrastructures against quantum attacks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving Pareto Set Learning for Expensive Multi-objective Optimization via Stein Variational Hypernetworks 39

Improving Pareto Set Learning for Expensive Multi-objective ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Nguyen, Minh-Duc Dinh, Phuong Mai Nguyen, Quang-Huy Hoang, Long P. Le, Dung D. College of Engineering and Computer Science VinUniversity Viet Nam VinUni-Illinois Smart Health Center VinUniversity Viet Nam Department of Computer Science and Engineering The Ohio State University United States Information Systems Technology and Design Singapore University of Technology and Design Singapore

ISBN: (纸本)157735897X

Expensive multi-objective optimization problems (EMOPs) are common in real-world scenarios where evaluating objective functions is costly and involves extensive computations or physical experiments. Current Pareto set learning methods for such problems often rely on surrogate models like Gaussian processes to approximate the objective functions. These surrogate models can become fragmented, resulting in numerous small uncertain regions between explored solutions. When using acquisition functions such as the Lower Confidence Bound (LCB), these uncertain regions can turn into pseudo-local optima, complicating the search for globally optimal solutions. To address these challenges, we propose a novel approach called SVH-PSL, which integrates Stein Variational Gradient Descent (SVGD) with Hypernetworks for efficient Pareto set learning. Our method addresses the issues of fragmented surrogate models and pseudo-local optima by collectively moving particles in a manner that smooths out the solution space. The particles interact with each other through a kernel function, which helps maintain diversity and encourages the exploration of underexplored regions. This kernel-based interaction prevents particles from clustering around pseudo-local optima and promotes convergence towards globally optimal solutions. Our approach aims to establish robust relationships between trade-off reference vectors and their corresponding true Pareto solutions, overcoming the limitations of existing methods. Through extensive experiments across both synthetic and real-world MOO benchmarks, we demonstrate that SVH-PSL significantly improves the quality of the learned Pareto set, offering a promising solution for expensive multi-objective optimization problems. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Grammar Error Correction Using Natural Language Processing

Grammar Error Correction Using Natural Language Processing

引用

Sustainable Communication Networks and Application (ICSCNA), International Conference on

作者： M. Geetha K. Vijaya Subramanian K M Rajesh Kanna P Rajeshkumar G Karthika S Department of Computer Science and Engineering M. Kumarasamy College of Engineering Karur Department of Computer Science and Design Kongu Engineering College Erode Department of Computer Science and Engineering Shadan College of Engineering and Technology Hyderabad Department of Computer Science and Engineering Bannari Amman Institute of Technology Sathyamangalam Department of Artificial Intelligence and Machine Learning Bannari Amman Institue of Technology Sathyamangalam

In the digital era, mos t of the communication is happening through online platforms. English plays a vital role for better understanding. Good grammar helps in framing a better sentence. This demands for the development of an automatic Grammar Error Correction (GEC) tool. Many research works have been initiated to make Grammar Error Correction possible by using various machine learning algorithms. Some of the algorithms are Naive Bayes, BERT, Support Vector Machine, and ULMFIT. Among these algorithms BERT gives a comparatively best accuracy rate. The fundamental goal of this research work is to compare these algorithms with respect to accuracy Here, NLP is used for analyzing the grammatical corrections in the sentence. Further, this study can be extended to overcome the drawbacks faced by the BERT algorithm such as increase in time cons umption for training and cos t.

关键词：

来源：评论

学校读者我要写书评

暂无评论

design and Behavioral Analysis of Students during Examinations using Distributed Machine Learning

Design and Behavioral Analysis of Students during Examinatio...

引用

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering, RMKMATE 2023

作者： Patil, Sangram Sungheetha, Akey Bansode, G.S. Kalaivaani, P.T. Kandaswamy, Vijay Anand Jagannathan, Sharath Kumar Department of Computer Science & Engineering D Y Patil Agricultural and Technical University Talsande Maharashtra Kolhapur India Dept. of CSE Alliance College of Engineering and Design Alliance University Karnataka Bangalore India University Guntur AP Vaddeswaram India Tamilnadu Tiruchengode India Electronics and Communication Engineering R.M.K. Engineering College Chennai India Data Science Institute Frank J. Guarini School of Business Saint Peter's University New Jersery NJ07306 United States

ISBN: (纸本)9798350305708

This research focuses on the design and behavioral analysis of students during examinations through the utilization of Distributed Machine Learning (DML). With the increasing integration of technology in education, the ability to monitor and understand student behavior during exams has become crucial for educators and institutions. DML offers a powerful approach to process and analyze data collected from various sources, such as online exams, wearable devices, and eye-tracking sensors. This study proposes a framework that employs DML techniques to gather, process, and interpret student behavioral data in real-time. The collected data encompasses factors like gaze patterns, typing speed, hesitation intervals, and physiological responses. By employing machine learning algorithms distributed across multiple nodes, the system aims to provide insights into student engagement, cognitive load, and potential instances of academic misconduct. The analysis of behavioral patterns during examinations can aid educators in adapting teaching methodologies, providing timely interventions, and enhancing the overall learning experience. The proposed approach highlights the potential of DML in the field of education and contributes to the broader discourse on leveraging technology for pedagogical improvement. © 2023 IEEE.

关键词： Cognitive Load Distributed Machine Learning Educational technology Examination Monitoring Online Learning Student Behavior Analysis

来源：评论

学校读者我要写书评

暂无评论

Real-Time Clustering and Classification of Physiological Big Data for Healthcare Monitoring 49

Real-Time Clustering and Classification of Physiological Big...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Tambe, Sagar B. Gajre, Suhas S. Patil, Dipti D. MIT Art Design & Technology University Department of Computer Engg. Pune412201 India Shri Guru Gobind Singhji Institute Engineering &tech. Department of Electronics & Telecom. Nanded431601 India Cummins College of Engineering Department of Information Tech. Women Pune411052 India

ISBN: (纸本)9798350331820

In recent years, there has been a significant increase in interest in medical health applications using Wireless Body Sensor Networks (WBSN). Monitoring people health conditions is crucial activity of today's healthcare system. As the future state of health is a consequence of past state, we induce data mining approaches on the window of past signals to predict worst health condition coming in the future. We propose the combinatorial real-time clustering and classification module, in which the future health risk would be predicted in real time. Also to enable continuous monitoring of the patient in real time, we are introducing mobile healthcare system by which the patient analysis and future predictions are carried out and informed to the patient by physician. The proposed Online Distribution Resource Aware (ODRA) algorithm has demonstrated superior accuracy and a decreased rate of False Positives (FPR) in predicting the risk status of 64 patients with varying illnesses using their Heart Rate (HR), Oxygen saturation (SpO2), and Blood Pressure signals. This performance is in comparison to the Resource Aware High-Quality Clustering (RAH) algorithm. This indicates that ODRA can be a promising algorithm for healthcare professionals to better assess the risk status of their patients and provide more accurate diagnoses and treatment plans. © 2023 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Emotion Analysis of English-Translated Tamil Literature

Emotion Analysis of English-Translated Tamil Literature

引用

International Conference on Computing and Networking technology (ICCNT)

作者： K Swathi G K Kamalam N Suganya Baby A Aadhishri D K Kawethaa Shree Department of Computer Science and Design Kongu Engineering College Tamil Nadu India Department of Information Technology Kongu Engineering College Tamil Nadu India Department of Mathematics Kongu Engineering College Tamil Nadu India Department of Computer Science and Engineering Kongu Engineering College Tamil Nadu India Department of Management Studies SSM College of Engineering Tamil Nadu India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Focus of this study is to investigate the nuanced world of emotions in English-translated Tamil literature through the lens of sentiment analysis. The dataset consists of poems expressing a range of emotions including joy, sadness, love, anger, pride, courage, and fear. To effectively analyze and classify these emotions, we utilized cutting-edge transformer-based models, like BERT, DistilBERT, and RoBERTa, to conduct our analysis. The outcomes of our study showcase the exceptional capabilities of these models in effectively analyzing emotions within poetic expressions. RoBERTa, in particular, emerged as a standout choice, consistently achieving high accuracy, precision, recall, and $F 1$ scores across all emotion categories. Its extensive pre-training and dynamic masking techniques allowed itto excel in capturing the intricate emotional nuancesembedded in the translated poems. DistilBERT demonstrated commendable efficiency without compromising accuracy, making it a practical option for real-time sentiment analysis. BERT, although a strong performer, showcased marginally reduced efficiency compared to RoBERTa and DistilBERT.

关键词： Analytical models Sentiment analysis Accuracy Computational modeling Transformers Real-time systems Computational efficiency Lenses

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：