检索结果-内蒙古大学图书馆

A Security Enhanced Chaotic-Map-Based Authentication Protocol for Internet of Drones

IEEE Internet of Things Journal 2024年第12期11卷 22301-22309页

作者： Mahmood, Khalid Ghaffar, Zahid Farooq, Muhammad Yahya, Khalid Das, Ashok Kumar Chaudhry, Shehzad Ashraf National Yunlin University Of Science And Technology Graduate School Of Intelligent Data Science Douliu64002 Taiwan National Yunlin University Of Science And Technology Graduate School Of Engineering Science And Technology Douliu64002 Taiwan Abu Dhabi University Department Of Mathematics And Statistics College Of Arts And Sciences Abu Dhabi United Arab Emirates Istanbul Gelisim University Department Of Electrical And Electronics Engineering Istanbul34310 Turkey Sabratah University Department Of Electrical Engineering Faculty Of Engineering Regdalen Libya Center For Security Theory And Algorithmic Research Hyderabad500 032 India Abu Dhabi University Department Of Computer Science And Information Technology College Of Engineering Abu Dhabi United Arab Emirates Nisantasi University Faculty Of Engineering And Architecture Department Of Software Engineering Istanbul34398 Turkey

The Internet of Drones (IoD) extends the capabilities of unmanned aerial vehicles, enabling them to participate in a connected network. In IoD infrastructure, drones communicate not only among themselves but also with users and a control center. This interconnected communication framework holds promise for various applications, from collaborative decision-making to real-time data exchange. However, the expansion of communication in IoD also introduces new challenges, particularly in terms of security, privacy and authentication. Unfortunately, the current authentication protocols are inadequate in offering robust security features against various attacks in the IoD environment. To address these security issues and limitations, we proposed a secure protocol for the IoD environment using chaotic maps and hash functions. In addition, we also employed a physically unclonable function in the development of the proposed protocol. We assess the security of the protocol through both informal and formal security analysis. The formal security analysis is conducted through a widely used random or real (RoR) model. The informal analysis shows the rigorous security features against various attacks, such as masquerading, anonymity violation, and physical cloning attacks. Moreover, we compare the performance of the devised protocol with similar existing protocols across important performance parameters, such as communication overhead, computation overhead, and security features. The devised protocol provides a 67.86% and 17.80% reduction in computation and communication overheads, respectively, as compared to related protocols. The analysis demonstrates the proposed protocol's capacity to support secure communication in the IoD environment and satisfy desirable security attributes. © 2014 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

RoSe: Rotation-Invariant Sequence-Aware Consensus for Robust Correspondence Pruning 24

RoSe: Rotation-Invariant Sequence-Aware Consensus for Robust...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Liu, Yizhang Zhou, Weiwei Li, Yanping Zhao, Shengjie School of Software Engineering Tongji University Shanghai China College of Computer and Data Science Fuzhou University Fuzhou China Department of Computer Science and Technology Tongji University Shanghai China Engineering Research Center of Key Software Technologies for Smart City Perception and Planning Ministry of Education Shanghai China

ISBN: (纸本)9798400706868

Correspondence pruning has recently drawn considerable attention as a crucial step in image matching. Existing methods typically achieve this by constructing neighborhoods for each feature point and imposing neighborhood consistency. However, the nearest-neighbor matching strategy often results in numerous many-to-one correspondences, thereby reducing the reliability of neighborhood information. Furthermore, the smoothness constraint fails in cases of large-scale rotations, leading to misjudgments. To address the above issues, this paper proposes a novel robust correspondence pruning method termed RoSe, which is based on rotation-invariant sequence-aware consensus. We formulate the correspondence pruning problem as a mathematical optimization problem and derive a closed-form solution. Specifically, we devise a rectified local neighborhood construction strategy that effectively enlarges the distribution between inliers and outliers. Meanwhile, to accommodate large-scale rotation, we propose a relative sequence-aware consistency as an alternative to existing smoothness constraints, which can better characterize the topological structure of inliers. Experimental results on image matching and registration tasks demonstrate the effectiveness of our method. Robustness analysis involving diverse feature descriptors and varying rotation degrees further showcases the efficacy of our method. © 2024 ACM.

关键词： correspondence pruning

来源：评论

学校读者我要写书评

暂无评论

The Investigation and Implementation of Automated Pricing and Replenishment Decisions for Vegetable Commodities Relying on Time Series Forecasting and Linear Programming Models 7

The Investigation and Implementation of Automated Pricing an...

引用

7th IEEE Information Technology, Networking, Electronic and Automation Control Conference, ITNEC 2024

作者： Tong, Yi Zhou, Jinxuan Deng, Liang Zhang, Congao Guo, Tao Long, Xueling Wuhan Business University Department of Information Engineering Hubei430056 China Major in Software Engineering China Major in Data Science and Big DataTechnology China Major in Internet of Things Engineering China Major in Financial Management China

ISBN: (纸本)9798350370782

In modern supermarkets, given the limited shelf life and the propensity for rapid declines in the sales of perishable goods, such as vegetables, it becomes imperative to conduct daily restocking based on historical sales and consumer demand to preclude the occurrence of undersold items the following day. Consequently, conducting restocking and pricing strategies based on sales and demand holds significant research importance for supermarkets. This study initially employs a multiple linear regression model to investigate the impact on profit by adjusting total sales (Q), sales price (P), and each component of cost-plus pricing (C, T, L, A), thereby determining the relationship between total sales and cost-plus pricing for each vegetable category, as well as the functional relationship between total sales and cost-plus pricing for each vegetable category. Based on the derived functional relationship, time series prediction and linear programming models are utilized to forecast the market demand for each vegetable category over a one-week period, subsequently formulating the daily restocking plan and pricing strategy for each vegetable category in the subsequent week to maximize supermarket profit while satisfying market demand. Finally, an analysis of saleable vegetable items reveals that 29 vegetable items can be displayed, with a total profit of 846.35 yuan. Upon testing the sales data of 300,000 vegetables, compared to the conventional display method sans the use of this model, the overall profit margin surged by 269.75 yuan, an increment of 47% relative to the initial profit, effectively enhancing the operational efficiency and profitability of the supermarket. © 2024 IEEE.

关键词： Multiple linear regression

来源：评论

学校读者我要写书评

暂无评论

Mental Stress Analysis of Bangladeshi Job Holders during Covid-19 pandemic: A Machine Learning Approach 13

Mental Stress Analysis of Bangladeshi Job Holders during Cov...

引用

13th International Conference on Computing Communication and Networking Technologies, ICCCNT 2022

作者： Islam, Majharul Arman, Md Shohel Abu Bakkar Siddik, Md. Sonia, Selina Akter Rahman Reesha, Atqiah Islam, Fahadul Daffodil International University DIU Data Science Lab Department of Software Engineering Dhaka Bangladesh

ISBN: (数字)9781665452625

ISBN: (纸本)9781665452625

Due to the Covid-19 epidemic, the work market has changed in the twenty-first century. The management of the organization should check to see if jobholders are mentally competent and suitable before they begin and enter the work environment. The job holders do their business in various ways, such as someone working from the office and someone working from home, to maintain physical distance and protect themselves from the epidemic. We are in office zones for twothirds of the day. We were inspired and informed about the psychological strain caused by the coronavirus. The study paper's goal is to assist and enlighten employment business administrators so that employees who work from home and offices may maintain their regular mental wellness. We employed the machine learning methods Logistic Regression, KNearest Neighbors (KNN), Naive Bayes, and Decision Tree. In the Decision Tree, this research paper's accuracy was approximately 73%. © 2022 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

IBATree: A Novel Method for Interpretable Cancer Cell Diagnosis Using Information Bottleneck Attribution

IBATree: A Novel Method for Interpretable Cancer Cell Diagno...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Raza, Muhammad Umair Chen, Jie Nawaz, Adil Saeed, Faisal Leung, Victor C.M. Li, Jianqiang Wang, Zhaoxia Shenzhen University College of Computer Science and Software Engineering China Shenzhen University National Engineering Laboratory for Big Data System Computing Technology China Shenzhen Children's Hospital Department of Gastroenterology China

ISBN: (纸本)9798350386226

Deep Neural Networks (DNNs) have demonstrated remarkable performance in classification and regression tasks on RGB-based pathological inputs. The network's prediction mechanism must be interpretable to establish trust in the clinical routine. One principal approach to interpretation is feature attribution. Feature attribution methods identify the importance of input features for the output prediction. Building on the Information Bottleneck Attribution (IBA) method, we recognize the RGB's input regions with high mutual information with the network's output for each prediction. IBA identifies input regions that have sufficient predictive information. In this paper, we introduce "IBATree", a novel approach that combines IBA with decision trees to enhance both the interpretability and accuracy of DNNs in cancer cell classification. Our method leverages the information bottleneck framework to inject noise into feature maps and then isolates the most informative features for model predictions while maintaining high classification performance. We evaluated our proposed approach on three datasets - CNMC, ISBI2016, and BreaKHis - demonstrating competitive accuracy and producing clear interpretations. This makes IBATree particularly suitable for clinical applications, where understanding the rationale behind predictions is crucial. Our results show that IBATree provides reliable predictions and valuable insights into feature importance, paving the way for its application in various biomedical domains. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

引用

13th International Conference on Computing Communication and Networking Technologies, ICCCNT 2022

作者： Islam, Farha Arman, Md Shohel Jahan, Nusrat Sammak, Musabbir Hasan Tasnim, Nusrat Mahmud, Imran Daffodil International University DIU Data Science Lab Department of Software Engineering Dhaka Bangladesh

ISBN: (数字)9781665452625

ISBN: (纸本)9781665452625

A recommendation system (RS) is a crucial application in the modern world, however it's still unclear if recommendations can be effective and accurate. Collaborative filtering has been used for many years to improve and increase the accuracy of recommendations. Although numerous strategies have been employed, such as content-based filtering and deep learning, collaborative filtering models can identify new interests between users and items without the need for specialized knowledge. The new user problem known as cold start using user ratings can be solved by collaborative filtering, which uses item ratings to predict user preference and is effective to predict better than traditional algorithms and popularity-based approach. A product is referred to as popular by the most user ratings in one specific product. The Daraz ecommerce website, which includes four characteristics, is where we got the data for our study. For this analysis, we used Modelbased Collaborative Filtering and Popularity-based approach to solve issues like cold start and data sparsity where we use Matrix factorization and K-means clustering including Truncated SVD and TF-IDF Vectorizer as algorithm to find user and item relation for better and more effective product recommendation. This study will assist to explore how recommendation systems are employed, their many approaches, and the specific algorithms and methodologies we used in our methodology, all of which may aid in providing a thorough understanding of recommendation systems. © 2022 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

A data Mining Approach to Finding Face Mask from Bangladeshi News Channel 13

A Data Mining Approach to Finding Face Mask from Bangladeshi...

引用

13th International Conference on Computing Communication and Networking Technologies, ICCCNT 2022

作者： Arman, Md Shohel Alam, Md. Rittique Jahan, Hasnur Islam, Lameya Sammak, Musabbir Hasan Biplob, Khalid Been Md. Badruzzaman Daffodil International University DIU Data Science Lab Department of Software Engineering Dhaka Bangladesh

ISBN: (数字)9781665452625

ISBN: (纸本)9781665452625

Face Mask Detection is currently a hot topic that has piqued the interest of researchers all over the world. Today, the entire world is dealing with the COVID-19 pandemic. To control the spread of the Coronavirus the most important task people need to do is use a mask. There is still a lot of research and study being done on COVID-19. Several studies have also shown that wearing a face mask significantly reduces the problem of viral transmission. In addition, a person wearing a face mask perceives a sense of protection. When we are at home, we take care of everything, but when we are in public places such as offices, malls, and colleges, it becomes more difficult to keep people safe. Machine Learning and data Mining are a collection of technologies that provide effective solutions to complex problems in a variety of fields. We attempted to develop a face mask recognition system using machine learning in order to prevent the spread of the Coronavirus. This is a good system for detecting a face mask in news channel images and videos. It can recognize both Mask and No Mask faces. With the advancement of this system, it will be possible to detect whether or not a person is wearing a face mask. If the person is not wearing a face mask, it will display a message such as "No Mask,"otherwise it will display "Mask Detected." © 2022 IEEE.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Vision Based Lane Assistance System 4

Vision Based Lane Assistance System

引用

4th IEEE International Conference on Emerging Techniques in Computational Intelligence, ICETCI 2024

作者： Senthilkumar, Monishaa Logaprakash, M. Aithal, Himajit Shanmgam, Saravanakumar C. Sri Ramakrishna Engineering college Department of Artificial intelligence and data science Coimbatore India Bosch Global Software Technologies Pvt Ltd. Bengaluru India Bosch Global Software Technologies Pvt Ltd. Coimbatore India

ISBN: (纸本)9798350387063

Autonomous navigation systems for robots are becoming increasingly essential in various domains, including transportation, surveillance, and logistics. Addressing the challenge of lane keeping is fundamental for safe and efficient navigation, mirroring the capabilities of human drivers. In this work, we present a camera-sensor based deep learning lane keeping system to autonomously move robots while guaranteeing they stay in defined lanes. The need for such a system arises from the rising demand for autonomous robotic solutions in real-world scenarios, where precise lane adherence is critical for safety and effectiveness. By leveraging convolutional neural networks (CNNs), our system accurately detects lane boundaries in real-time, ensuring robustness across diverse environmental conditions. A closed-loop control mechanism translates the CNN output into steering commands, facilitating smooth and precise navigation. Through extensive simulations and real-world experiments, we demonstrate the effectiveness and reliability of our approach, contributing to the advancement of autonomous robotic systems and enhancing their capability for safe and reliable navigation in various applications. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Classifying Cardiovascular Disease Using Gradient Boosting Method Risk Factor Analysis using Shapely Additive exPlanations 13

Classifying Cardiovascular Disease Using Gradient Boosting M...

引用

13th International Conference on Computing Communication and Networking Technologies, ICCCNT 2022

作者： Sammak, Musabbir Hasan Arman, Md Shohel Jahan, Hasnur Mahmud, Imran Alam, Md. Rittique Biplob, Khalid Been Md. Badruzzaman Daffodil International University DIU Data Science Lab Department of Software Engineering Dhaka Bangladesh

ISBN: (数字)9781665452625

ISBN: (纸本)9781665452625

One of the worst diseases in the world is heart disease or cardiovascular disease. Heart disease is on the rise globally, and doctors are becoming quite concerned about it. Therefore, it's crucial to accurately identify heart disease kinds when you require them. The complete understanding of cardiac disease has become one of the most popular scientific topics. In order to determine the best feature for accurately identifying heart disease, we worked with the "statlog"dataset. There, we trained our model using the LightGMB Python module. It is the Boosting Machine framework. We utilized the auROC score together with a 5-fold cross-validation for performance measurements. Figure 3 displays the results on the test data, which were 0.85 auROC with a 95% confidence interval of 0.70-0.99. However, it obtained 0.81 auPRC with a 95% confidence interval of 0.59 to 0.99. It obtained recall scores of 91.83% and precision scores of 77.52%. Shapely Additive exPlanations or shape value is utilized to discover the best features in this case. We categorize our heart disease datasets by identifying the most effective characteristics. As a consequence, it will assist medical professionals in identifying cardiac disease through practical application and help save countless lives © 2022 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Digital Evidence and Forensic Tools in Cyber Law: A Comprehensive Analysis 25

Digital Evidence and Forensic Tools in Cyber Law: A Comprehe...

引用

25th International Arab Conference on Information Technology, ACIT 2024

作者： Al-Sherideh, Ala'A Saeb Al-Zou'bi, Samah Suleiman Alshraiedeh, Fuad Elsoud, Esraa Abu Afaneh, Suha Al-Mousa, Mohammad Rasmi Alazaidah, Raed Khouj, Mohammed Samara, Ghassan Zarqa University Department of Cybersecurity Zarqa Jordan Zarqa University Department of Software Engineering Zarqa Jordan Zarqa University Department of Computer Science Zarqa Jordan Zarqa University Department of Data Science and Ai Zarqa Jordan University of Business and Technology Department of Electrical Engineering Jeddah21432 Saudi Arabia

ISBN: (纸本)9798331540012

The exponential rise in hacking, phishing, information theft, and electronic crime has become an actual concern with the increased use of digital devices and technology. By 2023 the number of IoT devices expectation will be 32.1 billion devices, leading to a significant increase in cybercrimes. These illegal behaviors are specifically connected to computers and communication technology. Consequently, there has been an urgent need for the development of cyber law which is a legal system closely related to digital evidence. This paper aim to provides delve into the significance and multifaceted applications of digital evidence within the context of cyber law, shedding light on the complexities and nuances inherent in its acceptance and reliability. The paper explores the importance and numerous uses of digital evidence in the context of cyber law, highlighting the challenges associated with its legitimacy and acceptance. Additionally, it focuses on the challenges that prevent digital evidence from being seamlessly incorporated into court processes and offers solutions and strategic advice to overcome these challenges. © 2024 IEEE.

关键词： Phishing

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：