检索结果-内蒙古大学图书馆

Artificial Intelligence and Smart Systems (ICAIS), International Conference on

作者： Vahini Siruvoru S. Aparna Dept. of Computer Science and Engineering GITAM School of Technology GITAM Deemed to be University Hyderabad India Dept. of Computer Science and Engineering (AIIL) B V Raju Inistitute of Technology Narsapur India

Load-balancing is critical in cloud-computing for optimizing workload distribution and making the most use of available resources, which in turn speeds up the system's total response time. There have been several tactics and methodologies proposed to handle load balancing-related issues such as task scheduling, migration, resource use, and others. This study offered numerous solutions to the crucial problem of load-balancing in cloud-computing. The difficulties regarding Load-balancing been examined by contrasting the methods put forth by researchers during the last six years. Many techniques have been proposed, however some issues, such as VM migration and unsolved fault tolerance issues, continue in the cloud setting.

关键词： Resistance Fault tolerance Fault tolerant systems Load management Time factors Task analysis Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Investigating Fault-Tolerance Techniques for Protecting Cyber-Physical Systems 2

Investigating Fault-Tolerance Techniques for Protecting Cybe...

引用

2nd International Conference on Advances in Computation, Communication and Information technology, ICAICCIT 2024

作者： Jaggi, Arjun Takkalapally, Prashamsh Rajaram, Shravan Kumar Hudani, Karim Jiwani, Nasmin Natarajan, Yuvaraj HCLTech San DiegoCA United States Department of Engineering Computing and Mathematical Sciences Lewis University United States Microsoft Inc. CharlotteNC United States Tampa FL United States Dept. of Information Technology University of The Cumberlands WilliamsburgKY United States Department of Computer Science Engineering Sri Shakthi Institute of Engineering and Technology Tamil Nadu Coimbatore India

ISBN: (纸本)9798331541217

Cyber-physical systems (CPSs) gift a unique set of protection demanding situations because they rely on a huge and various set of digital additives. To protect CPSs from cyber-attacks, fault-tolerance techniques, inclusive of redundancy and diversity, can help to mitigate the chance of assault. The purpose of this study is to analyze the capability advantages of several fault-tolerance techniques and provide a comprehensive assessment of their effectiveness in securing CPSs. It is going to examine the impacts of different techniques on system safety, security, availability, and reliability. Furthermore, the paper will present a standard dialogue of the ability trade-offs and costs associated with distinctive fault-tolerance techniques and provide tips for deciding on the maximum appropriate method to satisfy the required level of security. This research will offer treasured perception into the relevant subjects, facilitating the development of at ease CPSs. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Delta-γ Modeling of Wireless System Resilience in Multipath Fading and Interference Environments

Delta-γ Modeling of Wireless System Resilience in Multipath...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Deepak Upadhyay Abhay Upadhyay Kunj Bihari Sharma Mridul Gupta Nookala Venu Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun India Dept. of Computer Science and Engineering Graphic Era deemed to be University Dehradun India Dept. of Electronics and Communication Engineering Graphic Era deemed to be University Dehradun India Centre for Internet of Things Madhav Institute of Technology & Science Deemed University Gwalior India

ISBN: (数字)9798350350067

ISBN: (纸本)9798350350074

In this paper, we pursue the resilience of wireless communication systems in multipath fading and interference environments utilizing Delta- $\gamma$ modelling. Furthermore, fading phenomena such as Rayleigh/Rician/Nakagami channels can be simulated to examine the impact on important performance metrics like SNR, BER and throughput. Different types of interference scenarios, covering co-channel and adjacent channel interferences are also studied to understand impact on system capacity as well as reliability. This article investigates the use of adaptive modulation techniques, multiple-input multiple-output (MIMO) strategies and advanced interference management schemes by extensive *** results illustrate the importance of adaptive strategies in overcoming fading and interference which leads to an increase in system resilience as well as a robust communication link. Metrics for the outage probability and mean time to failure (MTTF) can inform how reliable systems are across operational scenarios. This work reconciles theory with practice to provide a systematic way of controlling the operational parameters in wireless networks under varying conditions. These lessons will be crucial in steering the design of forthcoming wireless systems that must more reliably satisfy a broader set of application requirements.

关键词： Fading channels Measurement Adaptive systems Wireless networks Interference Reliability theory Probability Throughput Resilience Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

An Experiment on Feature Selection Using Logistic Regression

An Experiment on Feature Selection Using Logistic Regression

引用

Information Communication Technologies Conference (ICTC)

作者： Raisa Islam Subhasish Mazumdar Rakibul Islam Dept of Computer Science & Engineering New Mexico Institute of Mining and Technology Socorro NM USA

ISBN: (数字)9798350373523

ISBN: (纸本)9798350373530

This study investigates feature selection using L1 and L2 regularization methods associated with logistic regression (LR) by leveraging its coefficient-based feature ranking. This research aims to optimize the feature set, enhancing model explainability and performance. The CIC-IDS2018 dataset was selected for the experiment, partially due to its huge volume and the inclusion of problematic classes. The research undertakes a detailed analysis, initially excluding one of the problematic classes and subsequently including both. Feature ranking was performed first with L1 followed by L2 regularization; and thereafter comparing performance of LR with L1 (LR+L1) against LR with L2 (LR+L2) by varying the feature set sizes for each ranking. Through comparative analysis, the outcome reveals no significant discrepancy in accuracy upon finalizing the feature set. Adopting a synthesis approach, the research selects features common to both L1 and L2-derived sets, and this optimized set was tested on more complex models such as Decision Tree and Random Forest. Results indicate a marginal mean accuracy reduction, by 0.8% and 0.6% respectively, while significantly reducing the feature set by 72%, regardless of the incorporation of the problematic class. Additionally, the confusion matrix is reported to facilitate the calculation of standard metrics: accuracy, precision, recall, and F1-score.

关键词： Measurement Logistic regression Accuracy Feature extraction Communications technology Decision trees Standards

来源：评论

学校读者我要写书评

暂无评论

Population Density Estimation using Single Shot Detection Algorithm

Population Density Estimation using Single Shot Detection Al...

引用

Sustainable Computing and Smart Systems (ICSCSS), International Conference on

作者： G.Litisha Miraclin Kumudha Raimond I. Keren Beulah Dept. of Computer Science and Engineering (Bachelor’s of Technology) Karunya Institute of Technology and Sciences (Deemed to be University) Coimbatore India

The proposed system consists of an Artificial Intelligent software that is capable of counting the number of people from the user inputs such as images and video frames more accurately. The system uses the advanced MobileNet Single Shot Detection algorithm to detect the human class in the given frame at the given moment. The count of individuals in the frame is dependent on the threshold set by the end-user. The primary goal of the application is to provide an easy-to-use and efficient tool for analyzing images and videos. The model used for object detection is trained on the mall dataset from Kaggle website and is capable of accurately detecting people in real-time, making it suitable for a wide range of applications. The people in the frame are tracked using centroid tracker algorithm, and the tracked classes are counted. The detection algorithm is built using the popular library keras for its versatile usage. This system uses Keras, a high-level deep learning library, and OpenCV, a computer vision library, to perform real-time people counting. The system utilizes object detection algorithms to detect and track individuals, and then increments a count each time a person crosses a designated line. The system is capable of handling multiple people simultaneously and accurately counting them in real-time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Internet of Things(IoT) security: Approaches and existing solutions

Internet of Things(IoT) security: Approaches and existing so...

引用

TRON Symposium (TRONSHOW)

作者： Vatsala Upadhyay Abhishek Vaish J. Kokila Dept. of Information Technology Indian Institute of Information Technology Allahabad Prayagraj India Dept. of Computer Science and Engineering Indian Institute of Information Technology Trichy Tiruchirappalli India

The world has become dependent on using the Internet of Things(IoT) owing to its unique features - sensing the environment, acting upon the results obtained by sensors, connecting a network of devices for communication, and many more have made human lives simpler. Research done in the area of the Internet of Things(IoT) has revealed that these devices are vulnerable to physical and network attacks that can directly/indirectly result in the malfunctioning in the normal parameters of the devices, as well as cause important data loss or secret information being leaked which can become useful for the hackers to attack the device and tamper with the stored contents in the device. These problems pave the way for designing a robust, security mechanism for the Internet of Things(IoT). This paper shall present an overview of the security aspects of the Internet of Things(IoT) - starting with the attacks that can occur on this network, the survey done in this area, and towards the end, presenting some solutions for making the IoT secure and resilient to vulnerabilities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Secrecy Capacity Optimization in RF/FSO Systems: Impact of Mixed Rayleigh and Log-Normal Fading with Atmospheric Turbulence

Secrecy Capacity Optimization in RF/FSO Systems: Impact of M...

引用

Intelligent Signal Processing and Effective Communication Technologies (INSPECT), IEEE International Conference on

作者： Deepak Upadhyay Kunj Bihari Sharma Mridul Gupta Abhay Upadhyay Nookala Venu Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun India Dept. of Computer Science and Engineering Graphic Era deemed to be University Dehradun India Dept. of Electronics and Communication Engineering Graphic Era deemed to be University Dehradun India Data Science and Quantum Computing ABV Indian Institute of Information Technology and Management Gwalior India

ISBN: (数字)9798350379525

ISBN: (纸本)9798350379532

This paper investigates the secrecy capacity optimization in RF/FSO systems with mixed Rayleigh and log-normal fading, while masking eavesdroppers channel state information () as well as suffering from atmospheric turbulence. We explore the impact of several parameters including beamforming angles, modulation schemes and hybrid RF/FSO link configurations through a combination of simulations as well as analytical models. Secrecy capacity is enhanced for an improved SNR and vice versa under higher turbulence conditions and cooler influents eavesdropped scenarios. Performance of the hybrid RF/FSO systems dominates considerably over single-link solutions, especially at longer distances. All these mechanisms appreciably increase the secrecy capacity, while beamforming and advanced modulation techniques offer most of the improvement. The study also demonstrates the interdependencies of system parameters, providing guidelines for designing secure communication systems under different environmental and operational conditions.

关键词： Heating systems Analytical models Array signal processing Communication systems Atmospheric modeling System performance Modulation Rayleigh channels Optimization Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Driver Drowsiness Detection System - An Approach By Machine Learning Application

arXiv

引用

arXiv 2023年

作者： Singh, Jagbeer Kanojia, Ritika Singh, Rishika Bansal, Rishita Bansal, Sakshi Computer Science and Engineering Dept Meerut Institute of Engineering and Technology Meerut India

The majority of human deaths and injuries are caused by traffic accidents. A million people worldwide die each year due to traffic accident injuries, consistent with the World Health Organization. Drivers who do not receive enough sleep, rest, or who feel weary may fall asleep behind the wheel, endangering both themselves and other road users. The research on road accidents specified that major road accidents occur due to drowsiness while driving. These days, it is observed that tired driving is the main reason to occur drowsiness. Now, drowsiness becomes the main principle for to increase in the number of road accidents. This becomes a major issue in a world which is very important to resolve as soon as possible. The predominant goal of all devices is to improve the performance to detect drowsiness in real time. Many devices were developed to detect drowsiness, which depend on different artificial intelligence algorithms. So, our research is also related to driver drowsiness detection which can identify the drowsiness of a driver by identifying the face and then followed by eye tracking. The extracted eye image is matched with the dataset by the system. With the help of the dataset, the system detected that if eyes were close for a certain range, it could ring an alarm to alert the driver and if the eyes were open after the alert, then it could continue tracking. If the eyes were open then the score that we set decreased and if the eyes were closed then the score increased. This paper focus to resolve the problem of drowsiness detection with an accuracy of 80% and helps to reduce road accidents. Copyright © 2023, The Authors. All rights reserved.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-based Automated System for Subjective Answer Evaluation

Machine Learning-based Automated System for Subjective Answe...

引用

IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)

作者： Shubham Dodia V Spoorthy. Trupti Chandak Dept. of Computer Science and Engineering National Institute of Technology Karnataka Surathkal Mangalore India Dept. of Information Technology National Institute of Technology Karnataka Surathkal Mangalore India

An examination is a useful tool for assessing students’ knowledge. Evaluation of exams is a difficult and time-consuming process. The automatic examination of answer scripts makes this task easier for teachers, reducing the amount of effort and time required. The existing literature has a number of methods that have been proposed for evaluating responses to objective questions using machine learning. However, more work needs to be done on evaluating answers to descriptive questions. This study suggests a way to evaluate students’ answers to questions of a descriptive kind without using traditional paper or pencil by teachers. Instead, a computer acts as a teacher and grades the students’ submissions. The primary objective is to communicate the outcomes of subjective responses using Bidirectional Encoder Representations from Transformers (BERT), cosine, and Jaccard distance. The proposed model achieved an accuracy of 91%, an error of 9.01, a precision of 83%, and a recall of 79%, respectively. The suggested model has provided the best results in comparison with state-of-the-art systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

UPI Based Financial Fraud Detection Using Deep Learning Approach

UPI Based Financial Fraud Detection Using Deep Learning Appr...

引用

Advances in Computing Research on science engineering and technology (ACROSET), International Conference on

作者： Vaishali Gupta Sahil Sharma Suhani Nimkar Suhani Pathak Dept. of Computer Sc. & Engg. IPS Academy Institute of Engineering & Science Indore India

ISBN: (数字)9798350388800

ISBN: (纸本)9798350388817

This research seeks to tackle the essential issue of fraud detection in view of the increasing challenges presented by the changing landscape of online transactions, particularly inside the Unified Payments Interface (UPI). The research deviates from the usual methods used in this field and adopts a fresh approach by using Recurrent Neural Network (RNN) as an advanced instrument for detecting fraudulent financial transactions. This break with tradition shows that people have now come to terms with the fact that traditional methods have their limits and that CNN and RNN have something special to convey. By applying the algorithm in UPI transaction dataset, we segregate the fraud and legitimate transaction. To evaluate the proposed approach, we applied the test data on confusion matrix and got the True Positive Rate (TPR) is 87.5%, and the False Positive Rate (FPR) is 13.4%.

关键词： Deep learning Recurrent neural networks Scalability Instruments Finance Real-time systems Fraud Reliability Long short term memory Resilience

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：