检索结果-内蒙古大学图书馆

3rd International Conference on Mechanical and Energy Technologies, ICMET 2023

作者： Nagender, Y. Ravichand, M. Kocherlakota, Nirupama Mary, S. Shyni Carmel Bharathi, S. Kavitha Kalaivaani, P.C.D. School of Computer Science and Artificial Intelligence SR University Telangana Warangal India Vijayawada India Department of Linguistics MIT World Peace University Maharashtra Pune India Assistant Professor in Business Analytics Loyola Institute of Business Administration Loyola College Campus Chennai600 034 India Department of Computer Technology Kongu Engineering College Perundurai India Department of CSE Kongu Engineering College Perundurai638060 India

ISBN: (纸本)9789819727155

Recent years have seen tremendous progress in Natural Language Processing (NLP), particularly in word and document illustration. Conventional methods that relied on contextual embeddings have given way to creative alternatives. In NLP, pre-trained language models have shown remarkable effectiveness, resulting in a fundamental shift away from supervised learning and towards pre-training accompanied by fine-tuning. Enhancing pre-trained models has attracted a lot of research attention in the NLP community. The taxonomy of pre-trained models is introduced, along with a thorough assessment of current advancements and representative work in the field of natural language processing. We initially provide a quick overview of pre-trained models, then go on to distinctive architectures and techniques. Next, we present and examine the implications and difficulties associated with pre-trained models and their subsequent uses. We wrap up quickly and discuss potential future research options in this area. These developments provide more accurate and effective ways to organise and extract data from large textual collections. In conclusion, this study addresses the intrinsic drawbacks of contextual embeddings and emphasises the critical role that word and document illustrations play in advancing NLP. These cutting-edge methods offer a viable avenue to improve natural language comprehension and utilisation as NLP continues to develop, with extensive applications in domains including information retrieval, machine translation, and sentiment analysis. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Enhancing Digital Forensics: Machine Learning Techniques for Social Media Investigation

引用

Procedia computer Science 2025年 258卷 2290-2301页

作者： Dhairya Vyas Milind Shah Ankita Kothari Jyoti Golakia Vruti Parikh Research Scholar The Maharaja Sayajirao University of Baroda Vadodara Gujarat India Assistant Professor Department of Computer Engineering Sardar Vallabhbhai Patel Institute of Technology (SVIT) Vasad Gujarat India

Due to the increasing growth of social media platforms, improved methods are needed to extract, examine, and interpret digital evidence. Due to the vastness and ever-changing nature of the data that is collected via social media platforms, traditional forensic procedures usually meet challenges. Specifically created for the purpose of conducting forensic analysis of material obtained from social media platforms, the purpose of this research is to build and analyze machine learning models and algorithms. Gathering information from various platforms, such as Kaggle, is the first step in the process. The succeeding processes involve data cleaning and categorization, which includes activities such as text normalization, entity recognition, and sentiment analysis. These steps come after the first data gathering has been completed. The extraction of relevant information, such as user behaviors, temporal trends, and network connections, is accomplished through the use of feature engineering. A significant portion of the investigation is centered on the application of supervised machine learning techniques for the purpose of detecting users and detecting offensive language. In order to determine whether or not the proposed approach is effective, comprehensive experiments are conducted utilizing datasets derived from social media activities. The findings indicate that there have been considerable improvements in the capabilities of forensic investigations, including enhanced accuracy, scalability, and automation. In this research we have investigated social media’s data and detected offensive language using various machine learning algorithms such as Support Vector Machine (SVM), K-Nearest Neighbours (KNN), Decision Tree, Random Forest, and Extra Tree. The support vector machine (SVM) achieved 86% accuracy where as KNN achieved only 77% accuracy which was far lower than other learning algorithms. However, the Decision Tree, Random Forest, and Extra Tree models achieved 99% a

关键词： Digital Forensics Machine Learning Social Media Investigation Cyber Crime Investigation Data Analysis

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review on Detection of Dacrocytes from Blood Smear Images using ML Algorithms

A Comprehensive Review on Detection of Dacrocytes from Blood...

引用

International Conference on Recent Trends in Advance Computing (ICRTAC)

作者： D. Kavitha B. Padmavathi Shakthi Priya S Sanjana N Sidesh S Department of Computer Science and Engineering Assistant Professor of Easwari Engineering College Chennai India Department of Computer Science and Engineering Student of Easwari Engineering College Chennai India

A nation’s capacity to develop is greatly impacted by the prevalence of anemia, a major public health issue. Despite this, it is a sickness that many developing countries choose to overlook. A million people die each year from iron deficiency, which is the underlying cause of anemia in at least half of those cases. Approximately 75% of these fatalities take place in Southeast Asia and Africa. One of the leading causes of death on a global scale is iron deficiency anemia (IDA). The use of machine learning techniques for the prediction of anemia was the focus of this work. Light Gradient Boosting Machines, Logistic Regression, Gaussian Naive Bayes, Support Vector Machines, and K-Nearest Neighbors were the five machine learning models studied in the study. The voting classifier method is used to merge various models in order to improve the accuracy of predictions. The need of accurate sickness forecasting by medical practitioners is highlighted by the study. Being able to predict when anemia may occur is crucial for effective prevention and treatment of the condition. This study proves that specific machine learning algorithms can improve disease prevention and treatment by predicting the occurrence of anemia. Using advanced algorithms and data processing techniques can help doctors make better predictions and decisions, which in turn improves patient outcomes. According to the results, the vote classifier has a 99.95% accuracy rate.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Collaborative Defense Strategies: AI, ML, and Cybersecurity: A Comprehensive Study 12th

Collaborative Defense Strategies: AI, ML, and Cybersecurity:...

引用

12th International Conference on Frontiers of Intelligent Computing: Theory and Applications, FICTA 2024

作者： Borah, Samarjeet Dhabliya, Dharmesh Dhage, Prashant Shukla, Jyoti Rai, Sumit Kumar Bhattacharya, Saurabh Department of Computer Applications Sikkim Manipal Institute of Technology Sikkim Manipal University Sikkim India Department of Information Technology Vishwakarma Institute of Information Technology Maharashtra Pune India Nagpur Campus Pune India Computer Science and Engineering Arya College of Engineering Jaipur India Department of Mechanical Engineering Dr. D. Y. Patil Institute of Technology Maharashtra Pimpri Pune India Assistant Professor SCSE Galgotias University Uttar Pradesh Greater Noida India

ISBN: (纸本)9789819601462

In the fast-changing field of cybersecurity, the rise of advanced threats requires new and creative defense strategies. This study thoroughly examines collaborative defense strategies, focusing on the utilization of artificial intelligence (AI) and machine learning (ML) techniques. The study aims to evaluate the effectiveness of five prominent machine learning algorithms (random forest, support vector machine (SVM), gradient boosting, isolation forest, and one-class SVM) in the field of cybersecurity. The assessment is carried out utilizing the NSL-KDD dataset, which is a standard in the industry. The study commences by investigating the origins of collaborative defense, analyzing its historical development and fundamental principles. The text explains the importance of AI in collaborative defense, highlighting machine learning algorithms and natural language processing as essential elements. The study explores the uses of artificial intelligence, specifically in identifying, averting, and reacting to threats. A substantial part of the research focuses on evaluating the effectiveness of the five chosen machine learning algorithms. The evaluation includes predictive analysis to forecast cyber threats and proactive defense measures. The study examines how machine learning improves the sharing of threat intelligence by facilitating real-time information exchange between collaborating entities. The challenges and considerations related to incorporating AI and ML into cybersecurity are examined, emphasizing ethical implications, bias, fairness, transparency, and accountability. Case studies and success stories from real-world scenarios showcase examples of successful collaborative defense strategies applied in various industries and sectors. The study evaluates and contrasts the random forest, SVM, gradient boosting, isolation forest, and one-class SVM algorithms based on performance metrics like accuracy, precision, recall, and F1 score, utilizing the NSL-KDD dataset. T

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Design and Development of a Novel Algorithm to Predict Fake Logo using Learning based Digital Image Analysis Methodology

Design and Development of a Novel Algorithm to Predict Fake ...

引用

Mobile Computing and Sustainable Informatics (ICMCSI), International Conference on

作者： N. Nagajothi Shabana Memon G. Mohan Parashuram Shankar Vadar Anita Soni S. Prince Sahaya AP/ Mathematics Nandha Engineering College (Autonomous) Erode- 52 Assistant Professor Bharati Vidyapeeth (Deemed to be University) Institute of Management Kolhapur Associate Professor Department of Mathematics K.S.Rangasamy College of Technology Tiruchengode TamilNadu Assistant Professor Yashwantrao Chavan School of Rural Development Shivaji University Kolhapur Maharashtra India Department of Computer Science and Engineering IES University Bhopal Assistant Professor (Sl.G) Department of Computer Science Engineering Sri Ramkrishna Engineering College Coimbatore

In the realm of fake logo detection, the continuous surge in digital content manipulation necessitates advanced and efficient methodologies for safeguarding brand integrity. This study explores the application of diverse machine learning models, ranging from traditional algorithms like K-Nearest Neighbors (KNN) and Support Vector Machines (SVM) to sophisticated deep learning (DL) architectures such as VGG19, Inception, and Convolutional Neural Networks (CNN). The proposed methodology combines feature extraction using VGG19 with classification using an Inception model, presenting a novel approach to enhance detection accuracy. Evaluation metrics, including accuracy, precision, specificity, and sensitivity, which enhance the performance of each model. Computational efficiency is also analyzed, providing a comprehensive understanding of the trade-offs between accuracy and processing speed. The proposed methodology emerges as a promising solution, achieving a remarkable accuracy of 97% while maintaining efficiency. This study contributes to the evolving landscape of fake logo detection, offering valuable insights for practical implementation in scenarios demanding precision, speed, and reliability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generative AI in Agri: Sustainability in Smart Precision Farming Yield Prediction Mapping System Based on GIS Using Deep Learning and GPS 4

Generative AI in Agri: Sustainability in Smart Precision Far...

引用

4th International Conference on Evolutionary Computing and Mobile Sustainable Networks, ICECMSN 2024

作者： Senthil, G.A. Suganthi, S.U. Prinslin, L. Selvi, R. Prabha, R. Department of Information Technology Agni College of Technology Chennai India Department of Artificial Intelligence and Data Science Sri Sai Ram Institute of Technology Chennai India Department of Computer Science and Engineering Agni College of Technology Chennai India Assistant Professor Department of Computing Technologies SRM Institute of Science and Technology kattankulathur Chennai India Department of Electronics and Communication Engineering Sri Sai Ram Institute of Technology Chennai India

Agriculture faces many challenges of precision farming, such as the need for sustainable practices, improving yields, ensuring high yields. In resolution to these challenges, the present research provides an AI-based system that enables the use of deep learning, Global Positioning System (GPS), and Geographic Information System (GIS) technologies to create a highly intelligent smart agricultural precision farming system. Its goal is to monitoring crop health and reduce disease risk, which will lead to improved resource utilization and environmentally sustainability techniques. The proposed framework addresses the urgent need for consistency in agricultural practices, especially as global agriculture deals with pressures from climate change, resource shortages, and increasing demand for food. Traditional agricultural methods for predicting and optimizing crop yields due to increasing factors affecting crop performance Not enough generative AI, especially the use of deep learning models, supports agricultural research in many cases, allowing patterns to be identified and future results to be predicted accurately. The integration of GPS and GIS allows for more accurate mapping, real-time analysis, and effective decision-making. Weather forecasting variability, resource constraints, and demand for more food are isolated from environmental influences using deep learning models, especially Artificial Neural Networks (ANN). By using large data sets, including historical crop yield performance, soil properties, and weather conditions, the system provides highly accurate crop forecasts. Generative Adversarial Networks (GANs) and You Only Look Once (YOLO) hybrid model is playing a key role in generating crop yield and growth potential under different conditions, adjusting model accuracy over time, and this combination of ANN, GANs and YOLO optimization algorithms ensures that the system continuously enhances its predictive accuracy and overall effectiveness. The proposed gene

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

“Machine Learning-Based Food Edibility Prediction Using Neural Networks”

“Machine Learning-Based Food Edibility Prediction Using Neu...

引用

International Conference on Computation System and Information Technology for Sustainable Solutions (CSITSS)

作者： Narendra Kumar S Ravi KM Arahanth M G Satheesh Pragathi Basavaraj Department of Biotechnology R V College of Engineering BE students Department of Computer Science and Engineering R V College of Engineering Scientific officer cum Assistant Professor R V College of Engineering

ISBN: (数字)9798331505462

ISBN: (纸本)9798331505479

Safety and the edibility of products is a must in the food industry. This research paper introduces a machine learning method for predicting whether food products can be eaten or not. A neural network model was created using various characteristics of the dataset including shelf life, manufacture date, optimum storage temperature and product type (solid, liquid or gas) to predict the edibility of a given item. The performance of the model was measured using accuracy, Mean Squared Error (MSE), and R-squared (R2). These findings demonstrate that neural networks are effective in classification tasks as they offer dependable means of forecasting if food is unsafe to eat.[1] Traditional methods have received a significant boost by this approach since it allows faster scalable automated predictions that could be integrated into larger food safety systems

关键词： Temperature measurement Solid modeling Accuracy Temperature Computational modeling Scalability Neural networks Predictive models Solids Food safety

来源：评论

学校读者我要写书评

暂无评论

Dynamic Defense Model against Eclipse Attacks in Proof-of-Work Blockchain Systems

引用

Procedia computer Science 2024年 235卷 1202-1212页

作者： Surendra Reddy Vinta Sunil A. Patel Aws Zuhair Sameen Mukesh Soni Dr Ihtiram Raza Khan Hayder Mahmood Salman Associate Professor School of Computer Science and Engineering VIT-AP University Amaravati Andhra Pradesh India Assistant Professor L. D. College of Engineering Ahmedabad College of Medical Techniques Al-Farahidi University Baghdad Iraq Assistant Professor Department of CSE University Centre for Research & Development Chandigarh University Mohali Punjab 140413 India Academician Jamia hamdard Delhi Computer Science Department Al-Turath Universiy College Baghdad Iraq

An emerging threat within blockchain systems is the malicious tactic known as eclipse attacks, wherein attackers aim to deceive and gain control over targeted nodes. Despite the increasing popularity of blockchain technology, effective defence mechanisms against eclipse attacks have been lacking. A novel and dynamic defence model designed explicitly for Proof-of-Work (PoW) consensus blockchain systems is proposed to address this critical issue. The model relies on a node-to-node evaluation mechanism to ensure robust protection. By leveraging mutual evaluations conducted between clients and incorporating the renowned Kademlia algorithm, a ranking value is assigned to each node within the defence model. These rankings empower nodes to prudently select trustworthy peers as neighbours based on a threshold comparison, effectively mitigating the risk posed by malicious nodes. Notably, the proposed approach significantly enhances the security of blockchain systems without necessitating modifications to existing protocols or network structures. The effectiveness of the proposed defence model in countering eclipse attacks is extensively validated through a series of experiments. Furthermore, the approach surpasses previous defence strategies, offering a higher probability of successful defence while maintaining minimal overhead. With its straightforward implementation and operational efficiency, the dynamic defence model is an ideal solution for real-world deployment scenarios. This research presents a compelling and robust defence model against eclipse attacks in PoW blockchain systems, addressing the existing gap in defence mechanisms. Furthermore, this advancement paves the way for the wider adoption of blockchain applications across various domains by providing enhanced security, reliability, and trustworthiness.

关键词： Blockchain Eclipse Attacks Dynamic Defence Model Proof-Of-Work (Pow) Consensus Network Structures Targeted Nodes

来源：评论

学校读者我要写书评

暂无评论

Challenges and Innovations in Multimedia and Real-Time Networking: A Review of Modeling Approaches

引用

Procedia computer Science 2025年 252卷 53-62页

作者： Milind Shah Kajal Parmar Priyanka Padhiyar Naina Parmar Monali Parikh Dhruvansh Patni Assistant Professor Department of Computer Engineering Sardar Vallabhbhai Patel Institute of Technology (S.V.I.T) Vasad Gujarat India Department of Computer Engineering Devang Patel Institute of Advance Technology & Research (DEPSTAR) Faculty of Technology & Engineering (FTE) Charotar University of Science & Technology (CHARUSAT) Changa 388421 India Assistant Professor Department of Information Technology Krishna School of Emerging Technology & Applied Research - Drs. Kiran & Pallavi Patel Global University (KPGU) Vadodara Gujarat India

Over the past decade, the rise of broadband and mobile Internet access has led to the widespread adoption of real-time networking and multimedia applications. These platforms have become essential for connecting individuals and supporting businesses, particularly with the growing trend of remote work. The demand for video streaming services has surged significantly and is expected to continue rising. However, this increased traffic has strained network performance, leading to congestion and diminishing the quality of service, especially during peak evening hours and the COVID-19 pandemic. Besides upgrading network infrastructure, it is crucial to develop intelligent streaming systems that adapt to network conditions and user expectations to enhance customer satisfaction. This review paper explores into the basics and introduction of Multimedia and Real-Time Networking. It also explores the advancements in Adaptive and Intelligent Networking for real-time multimedia communication. The paper formulates research questions based on the discussed topics, such as the distinctions between real-time networking and traditional networking, the ways multimedia applications adjust to fluctuating network conditions, and the challenges and limitations associated with these technologies.

关键词： Real Time Networking Multimedia Challenges Innovations Intelligent Networking

来源：评论

学校读者我要写书评

暂无评论

Standardization of Pediatric Cardiovascular Anomaly Anatomy Reconstructions

Standardization of Pediatric Cardiovascular Anomaly Anatomy ...

引用

Medical Technologies National Conference (TIPTEKNO)

作者： Mohamad Humam Alzaeim Kevser Banu Köse Şenol Pişkin Wael Shamsi Basha Fatma Zeynep Gungoren Ömer Faruk Şahin Js Femilda Josephin Master’s Student in Biomedical Engineering & Bioinformatics Istanbul Medipol University Istanbul Turkey Assistant Professor in Biomedical Engineering department Istanbul Medipol University Istanbul Turkey Assistant Professor in Mechanical Engineering department İstinye University Istanbul Turkey Department of Radiology The Anadolu Medical Center Istanbul Turkey Bachelor of Science in Molecula Biotechnology İstinye University Istanbul Turkey Assistant Professor in Computer Engineering Department İstinye University Istanbul Turkey

ISBN: (数字)9798331529819

ISBN: (纸本)9798331529826

In the realm of congenital cardiovascular diseases, the understanding, modeling, and visualization of such diseases as they develop during the neonatal growth period continues to be a challenge despite the current technological advancements. Moreover, such diseases as vascular abnormalities pose further risks due to their implications for a proper standardized method for three-dimensional visualization for planning and growth monitoring. This study uses imaging and computational techniques to create multiple models that relate the diseases as they progress from the initial phase toward the late growth stage for newborns’ cardiovascular systems. Three-dimensional modeling of patients would be created from patient-specific scans coupled with image processing algorithms. This study also aims to use the working principles of already existing tools for diagnosing aortic & brain aneurysms and pulmonary hypertension for cardiovascular development. To comprehensively understand such diseases and how their physical morphology may be standardized.

关键词： Visualization Solid modeling Pediatrics Computational modeling Morphology Standardization Brain modeling Planning Monitoring Medical diagnostic imaging

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：