检索结果-内蒙古大学图书馆

2nd International Conference on emerging Trends in Information Technology and engineering, ic-eTITe 2024

作者： Kousalya, S. Sundararajan, Kanthimathi Vasudevan, I. Jaichitra Sheela, L. Jaba Thyagarajan, Sarunya Panimalar Engineering College M.E. Computer Science and Engineering Tamil Nadu Chennai India Panimalar Engineering College B.E. Computer Science and Engineering Tamil Nadu Chennai India Panimalar Engineering College Dept of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350328202

Software-Defined Networking (SDN) is known for its remarkable versatility and adaptability. SDN applications encompass a wide range of network management and control functionalities, including load balancing, access control, and routing. However, SDN can encounter issues stemming from conflicting traffic patterns that may degrade network performance in relation of efficiency and optimization. These conflicts arise when factors such as priority and action settings are adjusted. Furthermore, IP spoofing, commonly employed for anonymity and amplification, frequently leads to widespread distributed denial-of-service (DDoS) attacks. We've established a sufficient condition based on the duration and frequency of DDoS attacks. Notably, our sophisticated attack method generates legitimate traffic within the SIP network using reflection techniques. 'As a result, it has the ability to bypass security measures such as blacklists, IP blocking, rate limiting based on packet counts or session/transaction volumes, and automated systems designed to detect unnatural message generation. These security mechanisms are commonly employed in advanced security setups, but the system or technique in question can effectively avoid detection or restriction when interacting with digital environments.' © 2024 Ieee.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Continuous monitoring of Web Server Assaults Using machine Learning 2

Continuous Monitoring of Web Server Assaults Using Machine L...

引用

2nd International Conference on emerging Trends in Information Technology and engineering, ic-eTITe 2024

作者： Vishali, m. mirudhula, A. Priya, A. Iswarya, m. Subramanian, Kavitha Panimalar Engineering College M.E Computer Science and Engineering Tamil Nadu Chennai India Panimalar Engineering College Dept of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350328202

Because of the widespread accessibility of the weband its ease of use, every organisation nowadays uses web apps to expand its company. With the growth of Due to growing online usage, attack riskhas grown as well. An effective monitoring tools that can recognise these threats Timely is necessary. Java script, PHP, and HTmL are utilisedfor website development and database use of SQL management in depth. most typical web server assaults include XSS, DOS (Denial of Service), and SQL injection Cascading Style Sheets. IDS with rules work with keywords and patterns but fail to recognise unidentified assaults. In this article, mL based model is used for leveraging web server logsto identify intrusions. It identifies the sort of assault as well as if a given log is normal or malicious. By establishing a private network with the aid of an Apache WAmP server, web server logs are produced and gathered. © 2024 Ieee.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Identification of Therapeutic Plants Using machine Learning 2

Identification of Therapeutic Plants Using Machine Learning

引用

2nd International Conference on emerging Trends in Information Technology and engineering, ic-eTITe 2024

作者： Rohini, S. Keerthana Shree, m.U. Jayalakshmi, R. malathi, m. Jabasheela, L. Panimalar Engineering College M.E Computer Science and Engineering Tamil Nadu Chennai India Panimalar Engineering College B.E Computer Science and Engineering Tamil Nadu Chennai India Panimalar Engineering College Dept of Computer Science and Engineering Tamil Nadu Chennai India Panimalar Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350328202

It takes a lot of work to develop a computerized method for classifying plants for medicinal purposes. There are countless kinds of plants found in India, and each one has its own unique set oftherapeutic advantages. Background information is necessary for manual identification and categorization because it is difficult for people to recall the proper titles of all plant species and their *** is crucial to preserve these medicinal plants since doing so will benefit several industries, including medicine, botanical research, and taxonomic studies, among others. Current technology cannot match thediversity of medicinal herb species that existin India. Utilizing textural traits that are crucial for recognizing and classifying leaves, the recom.e.ded technique makes itsimpler to categorize medicinal plants. The feature extraction, categorization, and picture enhancement stages are the three main components of the suggested method. The qualities that could be matched betweenthe leaf images were gathered using digital image processing methods after cell phones were used to snap the leaf photos. The CNN classifier is then used to create a machine learning classifier. © 2024 Ieee.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Predicting Urban Vartur Lake Health: A multi-context machine Learning Approach to Water Quality Assessment

引用

Journal of The Institution of engineers (India): Series A 2025年第2期106卷 577-590页

作者： Teggi, Pralhad P. malakreddy, Bharathi Natarajan, Santhi Dhaduti, madhumati S. Harivinod, N. Department of Computer Science BMSIT & M Visvesvaraya Technological University Karnataka Belagavi590018 India Department of Computer Science Shiv Nadar University Tamil Nadu Chennai603110 India Department of Civil Engineering K.L.E. Institute of Technology Karnataka Hubballi580031 India Department of Computer Science St Joseph Engineering College Karnataka Mangaluru575028 India

This study introduces a novel multi-context approach to water quality assessment by examining the factors influencing Chemical Oxygen Demand in Varthur Lake, Bangalore. Integrating traditional regression techniques with advanced machine learning models, this research analyzes eight water quality parameters collected over two years (July 2022–Septem.e. 2024). exploratory Data Analysis is employed to understand parameter distributions, relationships, and trends. Five distinct environmental contexts affecting COD are identified, and various machine learning models are evaluated for COD prediction within each context. Results indicate that Random Forest models yield superior accuracy, with Gradient Boosting offering a viable alternative. This multi-context framework provides a comprehensive understanding of Varthur Lake’s water health and offers a scalable approach for predictive water quality monitoring applicable to other urban water bodies. © The Institution of engineers (India) 2025.

关键词： Lake pollution

来源：评论

学校读者我要写书评

暂无评论

Blockchain: Secured Solution for Signature Transfer in Distributed Intrusion Detection System

引用

computer Systems science & engineering 2022年第1期40卷 37-51页

作者： Shraddha R.Khonde Venugopal Ulagamuthalvi Department of Computer Science and Engineering Sathyabama Institute of Science and TechnologyChennai600119India Department of Computer Engineering M.E.S.College of EngineeringS.P.Pune UniversityPune411001India

exchange of data in networks necessitates provision of security and *** networks compromised by intruders are those where the exchange of data is at high *** main objective of this paper is to present a solution for secure exchange of attack signatures between the nodes of a distributed *** activities are monitored and detected by the Intrusion Detection System(IDS)that operates with nodes connected to a distributed *** IDS operates in two phases,where the first phase consists of detection of anomaly attacks using an ensemble of classifiers such as Random forest,Convolutional neural network,and XGBoost along with genetic algorithm to improve the performance of *** novel attacks detected in this phase are converted into signatures and exchanged further through the network using the blockchain framework in the second *** phase uses the cryptosystem as part of the blockchain to store data and secure it at a higher *** blockchain is implemented using the Hyperledger Fabric v1.0 and v2.0,to create a prototype for secure signature *** exchanges signatures in a much more secured manner using the blockchain architecture when implemented with version 2.0 of Hyperl-edger *** performance of the proposed blockchain system is evaluated on UNSW NB15 *** performance has been evaluated in terms of execution time,average latency,throughput and transaction processing *** evidence of the proposed IDS system demonstrates improved performance with accuracy,detection rate and false alarm rate(FAR)as key parameters *** and detection rate increase by 2%and 3%respectively whereas FAR reduces by 1.7%.

关键词： Blockchain intrusion detection system machine learning algorithms secured communication ensemble approach

来源：评论

学校读者我要写书评

暂无评论

Diagnosing Progressive Face Recognition from Face morphing Using ViT Technique Through DL Approach 1

Diagnosing Progressive Face Recognition from Face Morphing U...

引用

1st Ieee International Conference on Networking and Communications, ICNWC 2023

作者： mohamed Faizal, m.K. Geetha, S. Barveen, A. M.I.E.T. Engineering College Department of Computer Science and Engineering Tamilnadu Trichy India

ISBN: (纸本)9798350336009

The face-morphing attack, which occurs in private, public, and governmental institutions, is one of the most well-known in today's world. Face recognition systems tend to be vulnerable if the face images are manipulated with duplicate images. manipulated images are combined with the original image so that the images look like legitimate ones. Several face recognition studies are being conducted to determine whether the face images are manipulated. Using the DL algorithm, the face image is trained to attain the original and morphed face images by recognizing the face images. DL algorithms determine the images by classifying whether they are morphs or not recognizable to humans. In this paper, the foremost emphasis is on diagnosing the face recognition from those face-morphed images using the different DL techniques. Different DL techniques are effectively compared, where the ViT transformer attains improved accuracy when compared to Resnet, RNN, and CNN, respectively. This paper provides an overview of the various deep learning algorithms for detecting those face recognition images that focus on challenges and issues in the facial datasets from Face Recognition Kaggle dataset with training and testing image dataset. It determines the higher contrast in image efficiency and the evaluation of the face recognized images with an improved image. © 2023 Ieee.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Production enhancement and Process Analysis for Pharmaceutical Industries

Production Enhancement and Process Analysis for Pharmaceutic...

引用

electronics and Sustainable Communication Systems (ICeSC), 2020 International Conference on

作者： T. murali A. Anu Priya M.E. Computer Science and Engineering KIT-KalaignarKarunanidhi Institute of Technology (Autonomous) Coimbatore TN India

“Production enhancement and Process Analysis for pharmaceutical industries” is a Pharma analytics process, which harnesses the power of data analytics to improve operations in the pharmaceutical industry. To provide recom.e.dations to increase the production flow rate in the continuous process. Run-time recom.e.dations and insights based on multivariate parameters to help operators achieve optimal outcomes. The process of working with different teams concerning their shifts working day and night is monitored. The fluctuations in the system help to investigate how each parameter is working in the plant individually and the best range of parameters to guarantee optimized production consistently are identified. In the existing system, the analysis was made unit-wise and batch-wise. Since it was not a continuous process, analysis was done batch by batch without any difficulties. Continuous manufacturing is favored because the results of one production run do not have an impact on the outcomes of subsequent runs, unlike batch manufacturing. Whereas in the proposed system, it was a continuous process which doesn’t contain any batches to overcome this challenge cycle time and lag time approach was used.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detection and Categorization of Conflict Flows Within SDN environments using machine Learning Approach

Detection and Categorization of Conflict Flows Within SDN En...

引用

emerging Trends in Information Technology and engineering (ic-eTITe), Conference on

作者： Kousalya S Kanthimathi Sundararajan I. Jaichitra Vasudevan L. Jaba Sheela Sarunya Thyagarajan M.E. Computer Science and Engineering Panimalar Engineering College Chennai Tamil Nadu India B.E. Computer Science and Engineering Panimalar Engineering College Chennai Tamil Nadu India Dept of Computer Science and Engineering Panimalar Engineering college Chennai Tamil Nadu India

Software-Defined Networking (SDN) is known for its remarkable versatility and adaptability. SDN applications encompass a wide range of network management and control functionalities, including load balancing, access control, and routing. However, SDN can encounter issues stemming from conflicting traffic patterns that may degrade network performance in relation of efficiency and optimization. These conflicts arise when factors such as priority and action settings are adjusted. Furthermore, IP spoofing, commonly employed for anonymity and amplification, frequently leads to widespread distributed denial-of-service (DDoS) attacks. We've established a sufficient condition based on the duration and frequency of DDoS attacks. Notably, our sophisticated attack method generates legitimate traffic within the SIP network using reflection techniques. “As a result, it has the ability to bypass security measures such as blacklists, IP blocking, rate limiting based on packet counts or session/transaction volumes, and automated systems designed to detect unnatural message generation. These security mechanisms are commonly employed in advanced security setups, but the system or technique in question can effectively avoid detection or restriction when interacting with digital environments.”

关键词：

来源：评论

学校读者我要写书评

暂无评论

enhanced Route Optimization for Wireless Networks Using meta-Heuristic engineering

引用

computer Systems science & engineering 2022年第10期43卷 17-26页

作者： S.Navaneetha Krishnan P.Sundara Vadivel D.Yuvaraj T.Satyanarayana murthy Sree Jagadeesh malla S.Nachiyappan S.Shanmuga Priya Department of Electronics and Communication Engineering SACS MAVMM Engineering CollegeMaduraiIndia Department of Computer Science and Engineering SACS MAVMM Engineering CollegeMaduraiIndia Department of Computer Science Cihan University-DuhokKurdistan RegionIraq Department of Computer Science and Engineering Bapatla Engineering College BapatlaAndhra PradeshIndia Department of Computer Application National Institute of TechnologyThiruchirapalliIndia School of Computer Science and Engineering Vellore Institute of TechnologyChennaiIndia Department of Computer Science and Engineering M.I.E.T Engineering CollegeTrichyIndia

Wireless Sensor Networks(WSN)are commonly used to observe and monitor precise *** consist of a large num.e. of inexpensive sensor nodes that have been separated and distributed in different *** base station received the amount of data collected by the numerous *** current developments designate that the attentFgion in applications of WSNs has been increased and extended to a very large *** Trust-Based Adaptive Acknowledgement(TRAACK)Intrusion-Detection System for Wireless Sensor Networks(WSN)is described based on the num.e. of active positive deliveries and The Kalman filter used in modified Particle Swarm Optimization(mPSO)has been proposed to predict knot *** were run for non-malicious networks(0%malicious)and different percentages of malicious nodes were *** findings suggest that the proposed method TRAACK modified Particle Swarm Optimization(mPSO)packet delivery rate outperforms TRAACKPSO by 3.3%with 0%malicious ***,the packet delivery rate of TRAACKmPSO is 30%malicious,3.5%better than TRAACKPSO in WSN.

关键词： Trust-based adaptive acknowledgment(TRAACK) modified particle swarm optimization(mPSO) intrusion detection system(IDS) kalman filter

来源：评论

学校读者我要写书评

暂无评论

meme expressive Classification in multimodal State with Feature extraction in Deep Learning 2

Meme Expressive Classification in Multimodal State with Feat...

引用

2nd International Conference on electrical, electronics, Information and Communication Technologies, ICeeICT 2023

作者： Barveen, A. Geetha, S. Faizal, m.K.mohamed M.I.E.T. Engineering College Department of Computer Science and Engineering Trichy India University College of Engineering Department of Computer Applications Tamilnadu Trichy India

ISBN: (纸本)9798350397635

memes are a socially interactive way to communicate online. memes are used by users to communicate with one another on social networking sites and other forums. memes essentially focus on speech recognition and image macros. While a meme is being created, it focuses on the semiotic type of resources that the internet community interprets with other resources, which facilitates the interaction among the internet and meme creators. memes recreate based on various approaches, which fall under various acts such as existing speech acts. Based on the expressive face with captioned short texts, even the short text is exaggerated. every year, meme mimicking applications are created that allow users to use the imitated meme expressions. memes represent the shared texts of the younger generations on various social platforms. The classifications of sentiment based on the various memetic expressions are the most efficient way to analyse those feelings and emotions. HOG feature extraction allows the images to be segmented into blocks of smaller size by using a single feature vector for dimension, which characterizes the local object appearances to characterize the meme classification. The existence of specific characteristics, including such edges, angles, or patterns, is then analyzed by combining HOG features using multi-feature analysis on patches. Based upon the classification methodology, it classifies the sentiments, which tend to improve the learning process in an efficient manner. By combining a deep learning approach with a recurrent neural network, the extended LSTm-RNN can identify subtle nuances in memes, allowing for more accurate and detailed meme classification. This proposed method effectively evaluates several classification techniques, including CNN and extended LSTm-RNN for meme image characterization. Through training and validation, extended LSTm-RNN achieved 0.98% accuracy with better performance than CNN. © 2023 Ieee.

关键词： Feature extraction

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：