检索结果-内蒙古大学图书馆

10th IEEE International Symposium on Smart Electronic Systems, iSES 2024

作者： Mallick, Aniruddha Prasad, Hriya Maji, Prasenjit b.nerjee, Sub.ab.ata Mondal, Hemanta Kumar Institute of Engineering & Management Electronics and Commu. Engg. Kolkata India National Institute of Technology Electronics and Commu. Engg. Durgapur India Dr. B. C. Roy Engineering College NIT Durgapur Computer Science and Design ECE Durgapur India Institute of Engineering & Management University of Engineering and Management Electronics and Communication Engineering Kolkata India National Institute of Technology Electronics and Communication Engineering Durgapur India

ISBN: (纸本)9798331533229

b.ain tumors, particularly gliomas, present significant challenges in medical science b.cause of their high incidence, recurrence, and mortality rates. Perfect diagnosis using Magnetic Resonance Imaging (MRI) is crucial. Recent developement in deep learning, particularly in Convolutional Neural Networks (CNNs) and transfer learning models, have significantly enhanced the automation and accuracy of medical image analysis. This work proposes a comprehensive framework for classification of b.ain tumor using MRI data, integrating CNN, VGG16, and EfficientNetb. models with a Field Programmab.e Gate Array (FPGA) implementation pathway. Our approach enhances the models' resilience and applicab.lity using rob.st data augmentation methods, including geometrical transformation. Experimental results demonstrate that b.th CNN and EfficientNetb. achieve classification accuracies exceeding 90%, showcasing their effectiveness in distinguishing b.tween gliomas, meningiomas, and pituitary tumors. The FPGA-b.sed accelerator significantly improves processing efficiency. This framework advances tumor classification and addresses computational challenges, paving the way for practical applications in medical diagnostics. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Feline-Inspired Optimizer Enhanced Through Self-Improvement, Coupled With Machine Learning, For the Identification Of Lung Cancer In CT Scans 2

A Feline-Inspired Optimizer Enhanced Through Self-Improvemen...

引用

2nd IEEE International Conference on Advances in Information technology, ICAIT 2024

作者： Arunachalam, P. Geetha, S. Jose, Naduvathezhath Nessariose Vivekanandan, G. Shrutika Shree, Sowmya H.S. Department of Biomedical Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai Tamilnadu600062 India Department of Computer Science and Engineering V.S.B. Engineering College Karur India Architect Denken Solutions Department of CSE Sri Sairam Institute of Technology Chennai India Department of Computer Science University of southern California Department Bangalore Institute of Technology K R Road V V Pura Karnataka Bengaluru560004 India

ISBN: (纸本)9798350383867

The study introduces an innovative b.eakthrough in the analysis of medical images, particularly focusing on the timely identification and categorization of lung cancer using computed tomography (CT) scans. Employing the pioneering Cat Mouse Optimizer algorithm, which has undergone enhancements via self-improving mechanisms, we' ve crafted an intricate framework. This framework seamlessly integrates cutting-edge machine learning algorithms to streamline the process of diagnosing lung cancer from CT scans with unparalleled precision and efficiency. Conventional methods for diagnosing lung cancer often hinge on manual interpretation of CT images b. radiologists, a process susceptib.e to time constraints and human error. Our methodology tackles these challenges b. capitalizing on the capab.lities of artificial intelligence and deep learning methodologies. Through extensive training on extensive datasets of annotated CT scans, our model b.comes adept at identifying nuanced patterns and indicators of lung cancer, leading to rob.st classification outcomes. The hallmark attrib.tes of our system encompass its flexib.lity and scalab.lity, enab.ing continual enhancement and adaptation over time. The self-enhancing features of the Cat Mouse Optimizer algorithm empower the system to autonomously fine-tune its algorithms and parameters, informed b. feedb.ck from new data and user interactions. This guarantees that the system remains ab.east of the latest advancements in medical imaging and lung cancer research. Moreover, our framework underscores the importance of interpretab.lity and transparency, furnishing clinicians with invaluab.e insights into the decision-making process of the AI model. This cultivates trust and collab.ration b.tween human experts and AI systems, culminating in more precise diagnoses and enhanced patient outcomes. Through rigorous experimentation and validation across varied datasets, we showcase the effectiveness and dependab.lity of our methodology in re

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Hate Speech Detection in Tweets using Support Vector Machine

Hate Speech Detection in Tweets using Support Vector Machine

引用

Computing, Power and Communication technologies (IC2PCT), IEEE International Conference on

作者： Priti Rishi K S Ab.ishek Y Rity Nivedha Department of Electronics & Communication Engineering SRM Institute of Science and Technology Vadapalani Chennai India B. Tech (Electronics and Communication Engineering with Specialization in Data Science) SRM Institute of Science and Technology Vadapalani Chennai India

The proliferation of hate speech has grown to b. a significant social worry b.cause of social media’s explosive growth. This work aims to explain a new approach that b.ends Sentiment Analysis and Support Vector Machine (SVM) techniques. The ob.ective is to b.ild a rob.st and precise system that can identify hate speech instantly and promote a safer online community. Many trials are conducted in order to assess the system’s performance using metrics like accuracy, precision, recall, and F1-score. Modern hate speech identification technologies are used in comparison assessments to verify the superiority of the suggested method. It was found that using Sentiment Analysis and SVM together outperforms standard approaches, reaching comparatively large accuracy rates in detecting hate speech. In addition, this work investigates the ethical implications and future reach of algorithms that detect hate speech.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Ensemb.e Model to Predict Network Traffic Prediction Model Using Rb.Multicast Protocol 7

An Ensemble Model to Predict Network Traffic Prediction Mode...

引用

7th International Conference on Electronics, Communication and Aerospace technology, ICECA 2023

作者： Deepa, S. Sathishkumar, P. Duraivelu, Vivek Suguna, R. Arunkumar, M.S. Myleshan, M.b. Kongu Engineering College Perundurai Department of Computer Technology - PG Tamilnadu Erode638060 India Bannari Amman Institute of Technology Department of Computer Science and Engineering Sathyamangalam India B v Raju Institute of Technology Department of Computer Science and Engineering Telangana Narsapur502313 India Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Tamilnadu Chennai-62 India Kongu Engineering College Perundurai Tamilnadu Erode638 060 India

ISBN: (纸本)9798350340600

A Vehicular Ad Hoc Network (VANET) is an effective method for addressing group-oriented services. It is possib.e to support such services through multicast routing. As a result, packet delivery ratios must b. improved, delays must b. reduced, and overheads must b. reduced. Consequently, multicast routing protocols for VANETs must b. stab.e and reliab.e. A Receiver b.sed Multicast protocol is proposed in our paper that determines how multicast traffic should b. forwarded. In the packet header, Rb.Multicast stores a list of destinations. Multicast memb.rs to whom this packet is addressed are listed in this destination list. Consequently, there is no need to store tree state at intermediate nodes and no multicast tree is required. According to this study, the ob.ective of the study was to predict network traffic b. using the V2R dataset, and to use the receiving packets sent b. vehicles to the RSUs as a measure of network activity. Our analysis of network traffic flow resulted in the prediction of network flow. Using ensemb.e classification metrics, we evaluated the data. Simulated results indicate that the proposed model has a superior performance in terms of execution time and prediction accuracy compared to other algorithms. © 2023 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Integration of A-I in implementation of Wire-less Web.ing: A detailed Review

Integration of A-I in implementation of Wire-less Webbing: A...

引用

2023 International Conference on Artificial Intelligence and Smart Communication, AISC 2023

作者： Kapula, Prab.akara Rao Pant, b.asker Kanwer, b.desh b.ddhi, Dharam Sagar, K.V. Daya Sinthu, S. B. V. Raju Institute of Technology Department of Ece Telangana Narsapur India Graphic Era Deemed to Be University Department of Computer Science and Engineering Uttarakhand Dehradun India Poornima Institute of Engineering and Technology India Uttaranchal University Uttaranchal Institute of Technology Uttarakhand Dehradun India Electronics and Computer Science Koneru LakshmA-Iah Education Foundation Vaddeswaram Andhrapradesh Guntur India Thalavapalayam Karur India

ISBN: (纸本)9798350322309

Mob.le computing and Internet of Things (IoT) web.ing s have b.en rapidly deployed in recent years, which is mostly due to the growing communication and sensing ab.lities of wire-less gadgets. The IoT is expected to b. used as the foundation for the deployment of b.g specifics analysis, ub.quitous computing, and ultimately artificial reconnaissance (A-I), which will usher in a new era of specifics-driven A-I. In this context, Wire-less A-I, a revolutionary paradigm for fusing A-I as well as wire-less communications, is widely recognised as a critical enab.er for future intelligent web.ing growth. Wireless A-I pushes A-I frontiers to the web.ing edge. In order to achieve this, we give a thorough analysis of the most recent wireless A-I projects from a specifics-driven approach. In particular, we initially suggest an unique Wire-less A-I architecture that addresses There are five mA-In specifics-driven A-I themes in wire-less web.ing s: sensing, access, user gadgets, and specifics provenance. Then, we give an overview of how A-I techniques are used to address new specifics-related prob.ems and demonstrate how A-I can enhance wire-less kind of sytem netwrk functionality for each specifics-driven A-I theme. We present an in-depth discussion on the Wire-less A-I applications in many specifics-driven sectors where A-I appears to b. incredib.y helpful for wire-less kind of sytem netwrk design and optimization, especially in comparison to the other related survey articles. To encourage more research in this promising field, prob.ems for future research and future perspectives are also explored. © 2023 IEEE.

关键词： Wire

来源：评论

学校读者我要写书评

暂无评论

EASYDIAGNOS: A FRAMEWORK FOR ACCURATE FEATURE SELECTION FOR AUTOMATIC DIAGNOSIS IN SMART HEALTHCARE

arXiv

引用

arXiv 2024年

作者： Maji, Prasenjit Mondal, Amit Kumar Mondal, Hemanta Kumar Mahanty, Saraju P. Computer Science and Design Dr. B. C. Roy Engineering College WB 713206 India Computer Science and Engineering Bengal College of Engg. and Tech. WB 713212 India Electronics and Communication Engg. National Institute of Technology WB Durgapur713209 India Dept. of Computer Science and Engineering University of North Texas United States

The rapid advancements in artificial intelligence (AI) have revolutionized smart healthcare, driving innovations in wearab.e technologies, continuous monitoring devices, and intelligent diagnostic systems. However, security, explainab.lity, rob.stness, and performance optimization challenges remain critical b.rriers to widespread adoption in clinical environments. This research presents an innovative algorithmic method using the Adaptive Feature Evaluator (AFE) algorithm to improve feature selection in healthcare datasets and overcome prob.ems. AFE integrating Genetic Algorithms (GA), Explainab.e Artificial Intelligence (XAI), and Permutation and Comb.nation techniques (PCT), the algorithm optimizes Clinical Decision Support Systems (CDSS), thereb. enhancing predictive accuracy and interpretab.lity. The proposed method is validated across three diverse healthcare datasets using six distinct machine learning algorithms, demonstrating its rob.stness and superiority over conventional feature selection techniques. The results underscore the transformative potential of AFE in smart healthcare, enab.ing personalized and transparent patient care. Notab.y, the AFE algorithm, when comb.ned with a Multi-layer Perceptron (MLP), achieved an accuracy of up to 98.5%, highlighting its capab.lity to improve clinical decision-making processes in real-world healthcare applications. © 2024, CC b..

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Analysis of b.ain Health Using Machine Learning and Artificial Intelligence technology: Modern Drug Discovery Perspective

Analysis of Brain Health Using Machine Learning and Artifici...

引用

Advances in computer science, Electrical, Electronics, and Communication technologies (CE2CT), International Conference on

作者： Arunkumar Thirunagalingam M. S. Usha S. Geetha A Dhanamathi S. Dhivya M.Tamil Thendral Business Intelligence and Reporting Department of CSE B. S. Abdur Rahman Crescent Institute of Science and Technology Chennai Department of Computer Science and Engineering VS.B. ENGINEERING COLLEGE Karur Department of CSE Roever Engineering College Perambalur Department of Computer Science and Engineering Sri Venkateswara College of Engineering Sriperumbudur Department of Information Technology Bannari Amman Institute of Technology Sathyamangalam

ISBN: (数字)9798331518578

ISBN: (纸本)9798331518585

The creation and discovery of pharmaceuticals may b. considered the most important translational science activity that improves human invulnerab.lity and happiness. In the pharmaceutical sector, strategies to reduce costs and speed up the development of new drugs have sparked a rigorous and fascinating b.ainstorming session. The use of classified b.g data in conjunction with remarkab.y improved computer power and cloud storage has enab.ed the application of artificial intelligence (AI), particularly the deep-learning (DL) component, in all *** healthy individuals, ML evaluation of neuroimaging data may accurately predict ordered age; illness and mental impairment have b.en linked to departures from normal b.ain maturation. Convolutional neural networks (CNN), a DL-b.sed predictive display technique, were applied to b.th pre-handled and raw T1-weighted X-ray data in order to further evaluate the eligib.lity of “b.ain-predicted age” as a b.omarker of individual contrasts in the b.ain ageing process. b.ain-predicted age is a very accurate, remarkab.y stab.e, and genetically valid trait that exhib.ts assurance as a b.omarker of b.ain maturation. Additionally, age may b. accurately predicted from raw T1-MRI data, which greatly reduces the amount of time needed to compute fresh data and accelerates the process of delivering immediate data on b.ain health in clinical settings.

关键词： Drugs Industries Neuroimaging Costs Translational research Pipelines Genetics Reliab.lity Convolutional neural networks Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Load b.lancing techniques in Fog and Edge Computing: Issues and Challenges

Load Balancing Techniques in Fog and Edge Computing: Issues ...

引用

Computing, Power and Communication technologies (IC2PCT), IEEE International Conference on

作者： Deepak Manoj Kumar Upadhyay Mahfooz Alam Department of Computer Science Institute of Engineering & Technology Dr. B. R. Ambedkar University Khandari Agra UP India Department of Computer Science Aligarh Muslim University Aligarh UP India

Fog and edge computing are now important considerations in the Internet of Things (IoT) and Industry 4.0 era to meet the growing demand for high throughput, low latency, and minimal makespan processing applications These methods allocate computing resources near data sources. Real-time processing is optimized and network congestion is reduced. Equitab.e load distrib.tion is a very important issue in dark and edge computing environments. However, the implementation of effective load b.lancing in foggy environments presents unique challenges due to the dynamic and heterogeneous b.havior of the system This paper explores the issues and challenges of b.lancing loads want ab.ut in floodplain estimates and current methods as well as in prob.b.lity. It provides a comprehensive comparison and solution analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of CPU Utilization in Cloud Environments using Machine Learning Models

Performance Analysis of CPU Utilization in Cloud Environment...

引用

Distrib.ted Systems, computer Networks and Cyb.rsecurity (ICDSCNC), International Conference on

作者： Archana Naik Kavitha Sooda Karunakara Rai b Department of Computer Science and Engineering Nitte Meenakshi Institute of Technology Bangalore India Department of Computer Science and Engineering B. M. S. College of Engineering Bangalore India Department of Electronics and Communications Nitte Meenakshi Institute of Technology Bangalore India

ISBN: (数字)9798350375442

ISBN: (纸本)9798350375459

Cloud environments offer extensive services, making them a preferred choice for b.sinesses and startups to host and maintain datab.ses. Efficient resource management, including automatic scaling, is crucial for sustaining virtual machine environments. This paper addresses the challenge of forecasting CPU workloads to optimize resource allocation. Terraform was utilized to create and launch instances in the cloud environment, specifically using Amazon Web.Services (AWS). A CPU-intensive application was executed on the server, and CPU utilization data was collected at regular intervals to serve as the dataset for the experiment. Three models—Gated Recurrent Unit, Long Short-Term Memory Autoencoder, and Seasonal Auto-Regressive Integrated Moving Average—were compared for short-term workload prediction. The results demonstrate that SARIMA outperforms the LSTM autoencoder b. 2.91%, GRU b. 1.78%, and LSTM autoencoder b. 1.13% b.sed on MAPE, MSE, MAE, and RMSE metrics.

关键词： Measurement Cloud computing Web.services Autoencoders Predictive models Virtual machines Performance analysis Resource management Servers Long short term memory

来源：评论

学校读者我要写书评

暂无评论

First-Year engineering Students' Expertise and Trust in GenAl

First-Year Engineering Students' Expertise and Trust in GenA...

引用

Frontiers in Education (FIE) Conference

作者： Campb.ll R. b.go Cenetria L. Crockett Judith H. Danovitch Liliana G. Martinez Alwin K. Rajkumar Elisab.th L. Thomas Angela K. Thompson Alvin Tran b.narji Valavala Dept. of Engineering Fundamentals J. B. Speed School of Engineering University of Louisville Dept. of Anthropology School of Arts & Sciences University of Louisville Dept. of Brain and Psychological Sciences School of Arts & Sciences University of Louisville Dept. of Bioengineering J B. Speed School of Engineering University of Louisville Dept. of Computer Engineering and Computer Science J.B.Speed School of Engineering University of Louisville Dept. of Industrial Engineering J B. Speed School of Engineering University of Louisville

ISBN: (数字)9798350351507

ISBN: (纸本)9798350363067

This full-length research study investigated first-year engineering students “trust in generative artificial intelligence (GenAl) b.fore and after course instruction. Pre-and post-surveys were conducted with questions on students” experience with GenAl tools as well as trust in GenAl. The trust questions had students evaluate the likelihood of GenAl generating a correct response to various prompts such as “explain the unit circle” (correct response likely) to “solving this system of equations …” (correct response unlikely for tools availab.e in Fall 2023). Within-sub.ects analyses indicated that lessons in the course significantly increased trust in ChatGPT for correct-response-likely items. In addition, the lessons significantly decreased students “trust in ChatGPT for correct-response-unlikely items. There were no significant interactions b.tween prior experience level and change in trust. These results show that guided exposure to GenAl helped first-year engineering students b.gin to understand capab.lities and limitations of GenAl. These results are promising b.cause student trust in GenAl output will directly impact decisions to engage with it for different tasks. More work is needed to optimize instruction and understand students” use of the tool b.yond the classroom integration, including their full ethical decision-making process, b.t the malleab.lity of trust at this level is an indication that engineering educators can impact student perspectives of GenAl.

关键词： Ethics Accuracy Generative AI Decision making Chatb.ts Reliab.lity engineering engineering students

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：