检索结果-内蒙古大学图书馆

26th International Conference on Distributed computing and Networking, ICDCN 2025

作者： Jha, Prianshu Singh, Gurpreet Kumar, Amit Agrawal, Dewesh Patel, Yashwant Singh Forough, Javad Department of Computer Science and Engineering Thapar Institute of Engineering and Technology Punjab Patiala India Department of Computing Science Umea University Umeå Sweden

ISBN: (纸本)9798400710629

Web servers are the backbone of modern Internet infrastructure, serving as the primary medium for online information distribution. Despite their critical role, web servers are susceptible to cyber-attacks. While current firewall mechanisms provide some level of protection against cyber threats, the evolving nature of these attacks and emerging vulnerabilities continue to pose significant risks. One of the most prevalent yet lethal attacks known today is DDoS (Distributed Denial of Service) attacks. These growing risks emphasize the urgent need for dynamic and robust threat detection and mitigation systems. This paper presents a comparative analysis of ensemble learning models (e.g., Random Forest, XGBoost, and LightGBM) and neural network-based models (e.g., Graph Neural Networks (GNN), Long Short-Term Memory networks (LSTM) with attention layers, and Gated Recurrent Units (GRU)) for DDoS attack detection and classification. Based on this analysis, we propose a real-time DDoS attack detection system integrated with a mitigation mechanism. The proposed system utilizes a two-tiered mitigation strategy assisted by UFW (Uncomplicated Firewall) and Apache server configuration files to block the incoming and outgoing traffic associated with suspicious IP addresses. The system's overall complexity, integrating both detection and response processes, ensures its efficiency in real-time environments while handling large volumes of traffic. Furthermore, the proposed approach achieves 15% improvement in detection accuracy and 20% reduction in false positives compared to traditional techniques, making it an effective and scalable solution for modern web server security. © 2025 Copyright held by the owner/author(s).

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Enhanced Web based Multi-Platform E-voting Solution 5

Enhanced Web based Multi-Platform E-voting Solution

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Nallapareddy, Anusha Swapna, T. Shanmugam, Sundaramurthy Shabu, Jany Refonaa, J. Hyderabad India G Narayanamma Institute of Technology and Science Department of Computer Science and Engineering Hyderabad India Srm Institute of Science and Technology Department of Computing Technologies Chennai India Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331504403

In democratic nations such as India, the act of voting is a basic right that grants individuals the power to choose their leaders. Traditionally, voting has typically taken place at specific locations called polling booths, either in centralized or distributed. Every Indian citizen above 18 years of age has the right to vote and participate in choosing their representatives. Voters go to the polling booths where they can cast their votes under the observation of authorized individuals. However, this traditional voting system has various challenges such as low voter turnout and instances of fraudulent voting. To address these issues, a secure multi-platform E-Voting system is proposed in this research, developed using the Flutter framework and Firebase backend services. The system aims to verify each voter before they can cast their vote, employing multiple levels of verification. The proposed application consists of an administrator (admin) interface and a voter interface. The admin interface allows for the addition of elections, candidates, and constituencies, while the voter interface requires voters to register, log in, and cast their vote. The verification process includes One Time Password (OTP) authentication, face recognition, fingerprint verification, and validation through government-issued identification cards. Two commonly used identification cards in India are the Aadhaar card and the Permanent Account Number (PAN) card, which are unique to each citizen. By utilizing this proposed online voting application, eligible voters can conveniently cast their votes from anywhere in the world, using internet-connected devices like mobile phones or tablets. The primary objectives of the proposed system are to increase voter turnout and reduce instances of fraudulent voting. Furthermore, conducting elections through this application also helps reduce the required workforce. © 2024 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Performance analysis of various classification algorithms for providing competency training to workplace risk prevention

引用

Multimedia Tools and Applications 2025年第15期84卷 15123-15149页

作者： Garg, Shruti Murugan, Prabhu Manimaran, A. Sundar, Ramesh Dakshinamoorthy, Prabakar Rajaram, Gnanajeyaraman Birla Institute of Technology Ranchi Mesra India Department of ECE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai602105 India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai602105 India Department of Networking and Communication School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur India Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology SRM Nagar Kattankulathur India

In the workplace, risk prevention helps detect the risks and prevent accidents. To achieve this, workers' mental and physical parameters related to their health should be focused on and analyzed. It helps improve the workers' mental health and thus improves organizational performance. There are a lot of mental illnesses due to excess work and a lack of professional knowledge. It affects the performance of the worker. So, the organization needs to conduct competency training programs to improve their professional skills and the mindset to tackle the work pressure. There are several competency training programs given in various organizations to mold the workers, and it considerably reduces workplaces risks. Competency training in the workplace teaches integrity, honesty, managerial skills, and other workers. Developing organizational skills is the primary concern in this competency training. This paper enabled one of the best machine learning algorithms to be chosen to predict the hazards in the workplace and provide a healthy environment to the workers. For that, several classification methods such as Logistic Regression, Decision trees, AdaBoost classifier, Random Forest, Gradient Boosting classifier, and XGBoost classifier are implemented experimented with, and the performance is verified with python software. From the comparison, it has been found that the XGBoost classifier is selected as the best classifier and identified that it is highly suitable for analyzing and predicting workplace risks data. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Occupational risks

来源：评论

学校读者我要写书评

暂无评论

Road Damage Detection Using Real Time Video 8th

Road Damage Detection Using Real Time Video

引用

8th IFIP TC 12 International Conference on computer, Communication and Signal Processing, ICCCSP 2024

作者： Gomathi, G. Niranjana, G. Department of Computer Science and Engineering SRM Institute of Science and Technology Tamil Nadu Kattankulathur India Department of Computing Technologies SRM Institute of Science and Technology Tamil Nadu Kattankulathur India

ISBN: (纸本)9783031736162

This study presents a completely unique deep-learning- powered real-time road damage detection system, paving the way for more secure roads and smarter infrastructure. With the help of convolutional neural networks (CNNs) and an easy to use interface, the system can automatically and clearly identify different types of road damage, such as surface irregularities, detailed fractures, and dangerous potholes. This innovative method surpasses the drawbacks of laborious manual inspections and ushers in a brand new age of advanced road safety and efficient maintenance. A strong CNN model that has been painstakingly trained on an intensive collection of annotated pictures and videos forms the basis of the system. It, as it should be, detects different sorts of damage with an accuracy close to 89%, offering users useful visible information via highlighting particular places on output pictures. However, the creativity doesn’t stop there. The system has a clean-to-use Tkinter graphical consumer interface (GUI) that facilitates engagement. It also has real-time alarm triggers that, without delay, inform the appropriate authorities, ensuring timely restoration and decreasing any safety threats. To make the system work better, it is put through a radical testing process using common evaluation standards along with F1-rating, accuracy, precision, and recall. The findings are clear-cut, which is revolutionary pressure in addition to a useful tool for finding road degradation. Beyond the instantaneous safety advantages, it offers better infrastructure management and optimized useful resource allocation, opening the door to a future in which technology protects our lives and creates more secure, more convenient travel. © IFIP International Federation for Information Processing 2025.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Optimizing Vanet Communications: A Bibliometric Analysis of Energy-Efficient Strategies with Deep Learning

Optimizing Vanet Communications: A Bibliometric Analysis of ...

引用

2024 International Conference on System, Computation, Automation and Networking, ICSCAN 2024

作者： Suganya, R. Prakash, B. Srm Institute of Science and Technology Department of Computer Science and Engineering Tamilnadu Kattankulathur India Srm Institute of Science and Technology Department of Computing Technologies Tamilnadu Kattankulathur India

ISBN: (数字)9798331510022

ISBN: (纸本)9798331510022

Vehicular Ad Hoc Networks (VANETs) are important for intelligent transportation systems, permitting vehicles to communicate with one another and nearby infrastructure in order to enhance road safety, traffic management and infotainment services. But the VANET communication is a high energy consumption technology, which may become a big challenge of large-scale power efficiency being in some real scenarios where huge number vehicles are needed to implement such V2I or V2V services sustaining. This paper conducts a analysis of different transmission stratagems for energy-efficient communication strategies among vehicles in VANETs, along with the focus to incorporate deep learning accelerators into an optimized architecture framework for enhancing communication processes. The paper presents an overview of VANET architecture and communication protocols, and then reviews the techniques to save energy in a VANET including efficient mechanisms for Transmission Power Control (TPC), some energy-aware routing protocols, as well as data aggregation realizations. Next, the paper introduces deep learning models that can adaptively optimize VANET transmission by forecasting network states and updating strategies on-the-fly. This analysis emphasizes hybrid solutions where deep learning is combined with traditional communication strategies to improve the energy efficiency apparent on a system level. Finally addresses the current challenges in the field and the need for advanced AI-driven techniques. This bibliometric analysis provides a comprehensive overview of energy-efficient communication strategies in VANETs, offering insights into how deep learning can contribute to the development of more sustainable vehicular networks. © 2024 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

Advances in Machine Learning for Stroke Prediction: A Comprehensive Review 8

Advances in Machine Learning for Stroke Prediction: A Compre...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Arshad, F. Mohammed Sharmila, K. School of Computing Sciences Vels Institute of Science Department of Computer Science Chennai Tamil Nadu Pallavaram600117 India

ISBN: (纸本)9798350376425

The comparative study in this review paper covered several phases of predictive modelling and examining the efficacy of different models for stroke prediction. Thorough exploratory data analysis (EDA) and strict data pretreatment were part of the initial look into, which made sure the model building process had a strong foundation. A thorough examination of the prediction performance of a various machine learning algorithms was made possible by the analysis, which included everything from traditional classifiers to state-of-the-art ensemble techniques. Lazy Predictor was used for benchmarking and initial model selection, which made it simple to identify the best-performing algorithms. These models' predictive accuracy was further improved by subsequent fine-tuning, which improved their appropriateness for stroke prediction tasks. In addition, the investigation of ensemble learning strategies cleared the way for the creation of hybrid models, which combine the advantages of distinct classifiers to produce better prediction results. The comparison analysis yielded useful insights that influence the selection of classification models for stroke prediction by healthcare researchers and practitioners. Stakeholders can embrace and apply ML approaches for stroke prediction with more knowledge if the study's findings are summarized. This will lead to improved medical outcomes and therapy. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Comparative Methods of Implementation for Different Question Answering Systems 5

Comparative Methods of Implementation for Different Question...

引用

5th International Conference on Intelligent Communication Technologies and Virtual Mobile Networks, ICICV 2024

作者： Naveen, C. Amutha, B. Srm Institute of Science and Technology Department of Computer Science and Engineering Kattankulathur Chennai India Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur Chennai India

ISBN: (纸本)9798350385649

This research introduces an innovative Question Answering (QA) system tailored explicitly for government department inquiries regarding individuals. Harnessing the prowess of cutting-edge language models such as BERT and T5 (Text-to-Text Transfer Transformer), the system excels in understanding complex queries within diverse governmental domains. Moreover, it incorporates a specialized Knowledge Graph meticulously curated with interconnected information about people across various departments. By integrating BERT and T5 for versatile query comprehension and answer generation alongside a comprehensive People-centric Knowledge Graph, this system aims to revolutionize information retrieval within government entities. The seamless fusion of these technologies promises accurate, contextually rich responses, optimizing operational efficiency across government departments and fostering streamlined access to crucial information. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Evaluating Large Language Models for Pronoun Resolution in Punjabi: A Comparative Study of ChatGPT and Gemini 1

Evaluating Large Language Models for Pronoun Resolution in P...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Prajapati, Priyanka Goyal, Vishal Kaur, Kawaljit Punjabi University Department of Computer Science Patiala India University Institute of Computing Chandigarh University Mohali India

ISBN: (纸本)9798331529246

In artificial intelligence, Large Language Models (LLMs) are becoming essential, especially in Natural Language Processing (NLP). These models enable researchers to develop more complex and effective solutions for various NLP tasks, including text summarization, sentiment analysis, question-answering systems, and many more. Reference resolution (pronoun resolution), is essential for the functionality of systems such as question-answering platforms and machine translation tools. While LLMs have demonstrated remarkable performance in reference resolution for languages with abundant resources, such as English, their effectiveness in languages with limited resources remains unknown. This paper evaluates LLMs, specifically ChatGPT and Gemini, emphasizing their ability to resolve references in Punjabi, a resource-poor language. In addition to assessing the current capabilities of these models, our research aims to identify their shortcomings and areas for improvement. The experiment indicates that ChatGPT demonstrates superior performance compared to Gemini, but additional refinement and enhancement are needed to produce more consistent and reliable outcomes. © 2025 IEEE.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Diabetic Foot Ulcer Classification Using Deep Learning Approach 8th

Diabetic Foot Ulcer Classification Using Deep Learning Appro...

引用

8th IFIP TC 12 International Conference on computer, Communication and Signal Processing, ICCCSP 2024

作者： Sivakamasundari, P. Niranjana, G. Department of Computer Science and Engineering SRM Institute of Science and Technology Tamil Nadu Kattankulathur India Department of Computing Technologies SRM Institute of Science and Technology Tamil Nadu Kattankulathur India

ISBN: (纸本)9783031736162

Podiatrist diagnosis and lesion localization are used as current testing approaches for Diabetic Foot ulcers (DFU). Current systems for automation concentrate on either categorization or division. One of the most common metabolic conditions, Diabetes (also called diabetes mellitus), is brought on by the pancreas incapacity to generate sufficient anti hyper-glycemic hormone to control glycemia levels. It may cause "Diabetic Peripheral Neuropathy," a collection of nerve diseases that can develop if the blood glucose level is left uncontrolled and unmanaged. Blood glucose levels may be efficiently maintained by recognising diabetes initially through constant surveillance and screenings. Using image processing methods such as data stretching with Deep Learning, image reduction and improvement, image division, and feature extraction, this paper offers a thorough approach for analysing thermal scans of the diabetic foot. By using these techniques, doctors may assess and track a patient's condition with fewer examinations. In this work, EfficientNetB3 architecture is compared with other Deep Learning models for accuracy in DFU identification. To create a powerful deep learning model, we gathered an extensive collection of 1,775 DFU photos. The basis of belief for this data gathering was created by two medical experts using annotator software to define the DFU region of interest. It took 48 ms to figure out a single image and 57.2 MB to validate the model. EfficientnetB3 got an average mean accuracy of 93%. This work demonstrates the effectiveness of Deep Learning for DFU localization in real-time, which could have improved with the use of a larger data set. © IFIP International Federation for Information Processing 2025.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

A novel brain tumor segmentation and classification model using deep neural network over MRI-flair images

引用

Multimedia Tools and Applications 2024年第17期84卷 1-32页

作者： Rajendirane, Rajmohan Ananth Kumar, T. Sandhya, S.G. Hu, Yu-Chen Department of Computing Technologies SRM Institute of Science and Technology Kattankulathur Campus Tamil Nadu Kattankulathur India Department of Computer Science and Engineering IFET College of Engineering Tamil Nadu Villupuram India Department of Computer Science and Engineering Annamalai University Chidambaram India Department of Computer Science Tunghai University No. 1727 Sec. 4 Boulevard Xitun District Taichung City407224 Taiwan

Brain tumors pose a significant health concern globally, with their detection and diagnosis being crucial for timely intervention and treatment planning. These abnormal growths can develop within the brain or originate from other parts of the body, spreading to the brain. They can be benign or malignant, and their impact on cognitive and physical function can vary widely depending on their location, size, and type. Detecting brain tumors involves a combination of imaging techniques and clinical assessment. Magnetic Resonance Imaging (MRI) is one of the primary imaging modalities used for this purpose due to its ability to provide detailed images of the brain's anatomy and pathology. Advanced image processing techniques and machine learning algorithms play an increasingly important role in enhancing the accuracy and efficiency of brain tumor detection. This study presents a comprehensive approach for enhancing brain tumor detection in MRI images using a combination of advanced techniques. Firstly, an improved K-means clustering algorithm is introduced to segment tumor regions effectively. Following this, Median Filtering is applied to refine image quality and reduce noise interference. Subsequently, a deep neural network architecture is employed for precise tumor classification utilizing the BRATS dataset. The proposed methodology aims to improve the accuracy and efficiency of brain tumor detection, offering potential advancements in medical image analysis and diagnosis. Experimental results demonstrate promising outcomes, indicating the effectiveness of the proposed approach in accurately identifying tumor regions in MRI scans. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Magnetic resonance 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：