检索结果-内蒙古大学图书馆

2024 International Conference on Communication, computer sciences and engineering, IC3SE 2024

作者： Verma, Rashmi Jailia, Manisha Kumar, Munish Kaliraman, Bhawna Banasthali Vidyapith Department Of Computer Science And Engineering Rajasthan Tonk India Koneru Lakshmaiah Education Foundation Department Of Computer Science And Engineering Vaddeswaram India Dpg Institute Of Technology And Management Department Of Computer Science And Engineering Gurugram India

ISBN: (纸本)9798350366846

With the increasing reliance on cloud computing services, ensuring the security of cloud-based infrastructures has become paramount. This paper proposes a novel approach utilizing Convolutional Neural Networks (CNNs) to detect Distributed Denial of Service (DDoS) attacks in a multi-cloud environment. The utilization of CNNs, known for their proficiency in feature extraction from structured and unstructured data, offers an innovative solution to the dynamic and evolving nature of DDoS attacks. The datasets utilized in this study include NSL-KDD. As the global frequency of cyberattacks rises, the digital landscape faces significant threats impacting both individual online presence and corporate entities. This paper employs deep learning techniques to enhance security against DDoS attacks, utilizing the inherent ability of deep learning to extract intricate patterns from vast datasets. This makes it a potent tool for constructing effective detection and mitigation systems for the DDoS threat. The research presents a comprehensive approach for detecting DDoS attacks by leveraging CNNs (Convolutional Neural Networks) and advanced data preprocessing methods, focusing on the widely recognized NSL-KDD dataset. The research findings reveal that the proposed CNN-based approach consistently outperforms, achieving an impressive accuracy score of 97.46%. These results underscore the promising potential of the proposed methodology in significantly improving the accuracy and effectiveness of intrusion detection systems. In a parallel exploration, another research paper introduces an alternative approach by offering a CNN model on the same dataset, achieving an accuracy outcome of 96.61%. While this alternative approach demonstrates commendable performance, the findings highlight the superior accuracy achieved by the proposed CNN methodology in the context of DDoS attack detection. © 2024 IEEE.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

Proficient Exam Monitoring System Using Deep Learning Techniques 1

引用

8th International Conference on Information and Communication Technology for Competitive Strategies, ICTCS 2023

作者： Parkhi, Priya N. Patel, Amna Solanki, Dhruvraj Ganwani, Himesh Anandani, Manav Department of Computer Science and Engineering Shri Ramdeobaba College of Engineering and Management Nagpur Nagpur India

ISBN: (数字)9789819707447

ISBN: (纸本)9789819707430

Recently, online education and remote learning have grown in popularity. With this increase comes the necessity for efficient safeguards to guarantee academic integrity during online exams. This research paper includes a thorough investigation into the design of a deep learning-based automated online exam monitoring system. By monitoring and identifying instances of misconduct or cheating during online exams, the suggested method attempts to create a safe and impartial evaluation environment. The research begins by examining the many difficulties and restrictions related to online tests, such as identity verification, content security, and student behavior monitoring. The literature study examines current techniques and tools for proctoring systems, highlighting their advantages and disadvantages. This research paper has suggested a novel method that uses deep learning algorithms for reliable and accurate monitoring based on this research. Face detection, face recognition, face spoofing detection, head-pose estimation, eye tracking, mouth ratio analysis, facial landmark identification, object detection, audio recording, plagiarism checking, and speech-to-text conversion are the main elements of the automated online exam monitoring system. The system offers a multi-modal strategy to monitor and identify probable instances of cheating or unauthorized behavior during exams by merging various components. We have made an effort to suggest a method that is efficient, improves academic integrity in online exams, and has the potential to be included in a number of e-learning platforms and educational institutions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Sentiment analysis in social internet of things using contextual representations and dilated convolution neural network

引用

Neural Computing and Applications 2024年第20期36卷 12357-12370页

作者： Abid, Fazeel Rasheed, Jawad Hamdi, Mohammed Alshahrani, Hani Al Reshan, Mana Saleh Shaikh, Asadullah Department of Information Systems Dr. Hassan Murad School of Management University of Management and Technology Lahore Pakistan Department of Computer Engineering Istanbul Sabahattin Zaim University Istanbul34303 Turkey Department of Software Engineering Istanbul Nisantasi University Istanbul34394 Turkey Department Computer Science College of Computer Science and Information Systems Najran University Najran61441 Saudi Arabia Department Information Systems College of Computer Science and Information Systems Najran University Najran61441 Saudi Arabia

The methodologies based on neural networks are substantial to accomplish sentiment analysis in the Social Internet of Things (SIoT). With social media sentiment analysis, significant insights can produce efficient and intelligent applications. Neural networks such as recurrent neural networks (RNNs) and convolution neural networks (CNNs) have been considered widely in many text classification tasks. However, RNNs are computationally expensive and require complex training to capture contextual information and long-term dependencies. Similarly, traditional CNNs must stack multiple convolutional layers, requiring massive computations and additional parameters. To address these problems, this work initialized the novel architecture, in which contextual representations (CRs) based on the textual framework are proposed at the initial step. In CRs, state-of-the-art word representation models, such as GloVe (global vectors) and FastText (subword information), collectively produce word representations upon the input sequence using a weight mechanism. Secondly, a unique way is introduced: a three-parallel layered dilated convolutional network with global mean pooling. The experimental results show that the proposed methods when compared with baseline methods, the dilation in CNNs following CRs significantly increases the accuracy from 72.45 to 98.98% and reduces computational resources. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey on Machine Learning Approaches in course Recommendation System

A Comprehensive Survey on Machine Learning Approaches in Cou...

引用

2024 IEEE International Students' Conference on Electrical, Electronics and computer science, SCEECS 2024

作者： Khan, Sanober Abeer Ali, Sadiya Deorankar, Akanksha Dhomble, Radhika Shah, Saurabh A. Prof Ram Meghe College of Engineering and Management Department of Computer Science and Engineering Amravati India

ISBN: (纸本)9798350348460

There is a plethora of online platforms that offer courses, making the course recommendation a difficult assignment in online learning. The student has the important responsibility of selecting the most suitable course from the available options. As a result, our study incorporates a number of machine learning techniques that were employed to propose the course based on a multitude of criteria, including user preferences, historical data, ratings, and more. Many machine learning methods, such as Collaborative, Content-Based, and Hybrid Filtering, make recommendations easier. In order to improve accuracy and provide the best recommendations, successful course recommendation systems frequently use a combination of these approaches. In the end, we want our research to provide a comprehensive review of machine learning recommendation approaches and to build an educational platform that allows students to choose the ideal course for their needs while also making high-quality learning materials available to students all around the world. © 2024 IEEE.

关键词： course Recommendation coursework Relevance study Tailored Learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cheque Security: Forgery Detection Via Signature Recognition Using Optical Character Recognition and Deep Learning

Enhancing Cheque Security: Forgery Detection Via Signature R...

引用

2024 IEEE International Conference on Recent Advances in science and engineering Technology, ICRASET 2024

作者： Vidhya, S.G. Balarengadurai, C. Prasad, Boddu Ravi Vidyavardhaka College of Engineering Vtu Department of Computer Science & Engineering Mysuru India Marri Laxman Reddy Institute of Technology and Management Department of Computer Science & Engineering Hyderabad India

ISBN: (纸本)9798350388602

Trustworthy verification of bank checks is crucial for modern financial transaction security and the prevention of fraudulent activities. A novel approach to the authentication and categorization of bank check signatures is introduced in this study. It employs a comprehensive architecture that integrates CNN, line sweep algorithms, and optical character recognition (OCR). The proposed method aims to improve the accuracy and efficacy of signature verification processes by harnessing the potential of state-of-the-art technology. First, the system uses optical character recognition to extract text from images of checks;this allows it to recognize crucial components including account data and text-based attributes. The line sweep method to spatial connections within images of checks also helps to emphasize key features like account numbers and signatures. The technique relies heavily on Convolutional Neural Networks. The system is able to differentiate between authentic and false samples based on their distinct patterns and characteristics by training convolutional neural networks (CNNs) using a big collection of signatures. With this wealth of information at its disposal, the system can confidently assess the signatures' authenticity, resulting in a more robust and accurate verification procedure. Next, they came up with an innovative way to identify signatures and validate bank checks using convolutional neural networks (CNNs), optical character recognition (OCR), and line sweep analysis. With the automation and improvement of verification procedures, monetary transactions will be more trustworthy, less prone to errors, and more secure. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Personal learning material recommendation system for MOOCs based on the LSTM neural network

引用

Educational Technology and Society 2024年第2期27卷 25-42页

作者： Tzeng, Jian-Wei Huang, Nen-Fu Chen, Yi-Hsien Huang, Ting-Wei Su, Yu-Sheng Department of Information Management National Taichung University of Science and Technology Taiwan Department of Computer Science National Tsing Hua University Taiwan Department of Computer Science and Information Engineering National Chung Cheng University Taiwan Department of Computer Science and Engineering National Taiwan Ocean University Taiwan

Massive open online courses (MOOCs;online courses delivered over the Internet) enable distance learning without time and place constraints. MOOCs are popular;however, active participation level among students who take MOOCs is generally lower than that among students who take in-person courses. Students who take MOOCs often lack guidance, and the courses often fail to provide personalized learning materials. Artificial intelligence (AI) has been applied to manage increasing amounts of learning data in learners’ online activity records. Driven by the trend in big data, AI technology has drawn increasing attention in various fields. AI-based recommendation systems (RSs) are powerful tools for improving resource acquisition through supply customization, and they can provide personalized learning materials as study guides. In this study, a personalized learning path for MOOCs based on long short-term memory (LSTM) was proposed to meet students’ personal needs for learning. According to students’ video-watching behaviors, we proposed an MOOC material RS that identifies students with similar learning behaviors through clustering and then uses the clustering results and the learning paths of each group of students to construct an LSTM model to recommend learning paths. The system’s learning path recommendations can effectively improve the online participation of learners, and students who received recommendations progressed from the slow-progress group to the medium-progress or fast-progress group. In addition, the learning attitude questionnaire results indicated that the proposed system not only motivated learners to continue learning and achieve high learning capacity but also supported their study planning according to their individual learning needs. © (2023), (International Forum of Educational Technology and Society). All Rights Reserved.

关键词： AI-based recommender system Individual learning Knowledge map LSTM MOOCs

来源：评论

学校读者我要写书评

暂无评论

A smart green mashrabiyya-shutter design for residential applications in Egypt

引用

HBRC Journal 2023年第1期19卷 229-252页

作者： Abdel Gelil Mohamed, Nermine Hamid Abd El-Rahman, Eslam Sadek, Mohamed Giza Egypt Mechatronics and Robotics Department Cairo Higher Institute for Engineering Computer Science and Management Cairo Egypt

The revival of traditional latticework mashrabiyya is continually urged in the Middle East and North Africa to address conflicting needs since it optimally balances environmental, social, and aesthetic functions. However, its material and craftsmanship costs and inflexibility are significant barriers. This study aims to provide a preliminary design for a green, smart mashrabiyya-like shutter responsive to climatic conditions and privacy needs in Egypt, manufactured with palm midribs, a waste material available in the MENA region due to annual trimming. The simple, yet responsive and traditional design outlined in this study has a considerable potential for residential applications not only in Egypt, but also in similar socio-environmental contexts. The design generation is based on three steps: 1) constructing a static model that maintains the basic socio-environmental needs, manufactured with palm midrib patterns, 2) modeling dynamic functions, using Grasshopper/Ladybug, through standardizing slats and deciding upon visibility and adjustable parts, and 3) integrating smart controls based on comfort indexes and indoor climatic readings. Using a simple circuit fitted with sensors, actuators, and a microcontroller, the design of a latticework shutter responsive to climate and privacy was generated. The concept depends on computing indoor weather data and comparing them to thermal, daylight, and wind comfort indexes. Consequently, automated decisions could be made to regulate the shutter parts in two ways: 1) its opening angle and 2) openness between the slats. Ultimately, the operating concept of the smart shutter in a room and automated flowcharts that make decisions in daytime and nighttime modes were proposed. © 2023 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： Visibility

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Algorithm for VM Scheduling for Prioritized Cloudlets 3

A Dynamic Algorithm for VM Scheduling for Prioritized Cloudl...

引用

3rd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2024

作者： Datta, Lipika Purkait, Taniya College Of Engineering And Management Kolaght Computer Science And Engineering Department Kolaghat India College Of Engineering And Management Kolaght Information Technology Department Kolaghat India

ISBN: (纸本)9798350318609

Users submit their requests to cloud service providers, and cloud computing delivers services over networks. With the influx of a large number of requests to the cloud, effective scheduling of cloudlets is imperative for optimal performance. This paper focuses on assigning priorities to cloudlets and scheduling them accordingly. Dynamic updating of priorities is implemented to prevent starvation. Cloudlets are allocated to VMs considering the current load of the VMs, further reducing execution time. The CloudSim simulation environment is used for assigning priorities to cloudlets, scheduling the cloudlets, and selecting the least loaded virtual machine for execution of the cloudlets. By prioritizing tasks and considering VM load, this approach aims to optimize system performance and ensure efficient resource utilization in cloud computing environments. It was found that the proposed method performs better in terms of total Turnaround Time and number of context switches than the existing algorithms. © 2024 IEEE.

关键词： Virtual machine

来源：评论

学校读者我要写书评

暂无评论

R–attributes based rough graph concepts lattice

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第10期14卷 14309-14319页

作者： Singh, Prem Kumar Department of Computer Science and Engineering Gandhi Institute of Technology and Management–Visakhapatnam Andhra Pradesh Visakhapatnam530045 India

The characterization of some important attributes in a given context is considered as one of the prominent issues for the decision making process. Same time another problem arises approximation of uncertainty and its graphical structure visualization. To resolve this issue, algebra of rough sets and its extensive properties is utilized in this paper. Extensively, current paper focuses on introducing R–Rough graph visualization of given context and its characterization in positive, negative and boundary regions based on user defined subset of granulation. The knowledge discovered from both of the proposed methods are also compared to validate the result. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Formal concept analysis

来源：评论

学校读者我要写书评

暂无评论

Categorisation by Leveraging CNNs and Remote Sensing Satellite Imagery for Crop Analysis in Arid Environments

引用

Remote Sensing in Earth Systems sciences 2024年第2期7卷 66-79页

作者： Malhan, Anu Chavan, Yogita Rahulsing Swamikan, Brinthakumari Gupta, Megha Varun Bobade, Sunil Department of Artificial Intelligence and Data Science New Horizon Institute of Technology and Management Department of Computer Engineering New Horizon Institute of Technology and Management

The classification of walnuts in the dry areas of Ganquan Township, Awati County, Xinjiang, is investigated in this research using traditional approaches, remote sensing photos taken by satellite, and convolutional neural networks (CNNs). Thorough field sampling and the collecting of Landsat-8 Level-2 data were necessary for correct analysis due to the different environmental features of the research region, which presented major hurdles. Despite some early difficulties, CNN design revisions led to significant gains in classification accuracy. These modifications included AlexNet, VGG, GoogleNet, ResNet, and EfficientNetV2. When compared to more traditional approaches, ResNet and EfficientNetV2 stood up as the most successful models. Nevertheless, challenges including computational complexity and low-resolution imaging highlight the necessity for more research to improve detection efficiency without sacrificing accuracy. The study emphasises the need to keep looking for new ways to analyse and monitor crops, and it suggests that combining remote sensing with advanced machine learning methods could help improve precision agriculture management and increase crop yields in dry areas. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Categorisation of crop Machine learning Precision agriculture Remote sensing Walnut

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：