检索结果-内蒙古大学图书馆

2023 International Conference on New Frontiers in Communication, Automation, Management and Security, ICCAMS 2023

作者： Kaushal, Rajanish Kumar Kumar, B.Anjanee Chauhan, Krupesh A. Munagala, Madhu Singh, Pavitar Parkash Hazela, Bramah Chandigarh University Department of Electrical Engineering Punjab Mohali India Dadi Institute of Engineering and Technology Anakapalle Electronics and Communication Engineering Visakhapatnam India Sardar Vallabhbhai National Institute of Technology Department of Civil Engineering Surat India Koneru Lakshmaiah Education Foundation Department of English Vaddeswaram India Lovely Professional University Department of Management Phagwara India Amity University Amity School of Engineering & Technology Department of Computer Science and Engineering Lucknow India

ISBN: (纸本)9798350317060

The use of automobiles is becoming more important worldwide, especially in densely populated cities. Current transportation infrastructure technologies include wired sensors, inductive loops, and satellite navigation. The installation and upkeep of surveillance equipment (cameras, etc.) are quite costly. In addition, environmental factors affect these instruments' precision. Traditional methods typically aim to optimize traffic light management for a given traffic density and layout. One key draws back all these methods, however, it may be challenging to represent the dynamic behaviour of traffic volumes and configurations, which is always changing. Therefore, in an effort to solve the aforementioned problem, this study proposes methods for adaptive traffic light management via the use of a distributed sensor network. The purpose of this study is to examine approaches to developing a smart system that can integrate and support some of the current technologies of traffic management, therefore decreasing the typical wait time for cars at a junction. The suggested algorithms are flexible enough to adjust to the particulars of traffic at every given crossroads. (GLD) is a traffic simulation tool used to model real-world traffic conditions and provide graphs of average waiting time vs cycle counts. The collected findings validate the efficacy of the suggested strategy for traffic regulation at a real-world road junction. © 2023 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Federated Learning Strategies for Privacy-Preserving Machine Learning Models in Cloud Computing Environments

Federated Learning Strategies for Privacy-Preserving Machine...

引用

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

作者： Tiwari, Shashank Shekhar Dhasmana, Gulshan Al-Jawahry, Hassan M. Rana, Aditya Bhardwaj, Garima Srivastava, Arun Pratap Rec Department Of Information Technology U.P Ambedkar Nagar India Dr. Abdul Kalam Technical University Lucknow India Graphic Era Deemed To Be University Department Of Computer Science & Engineering Dehradun India College Of Technical Engineering The Islamic University Department Of Computers Techniques Engineering Najaf Iraq Amity Business School Amity University Greater Noida India Lloyd Institute Of Engineering & Technology Greater Noida India

ISBN: (纸本)9798350366846

Federated learning presents a promising approach for preparing machine learning models while protecting information protection in cloud computing situations. This investigation examines the adequacy of different unified learning procedures, including Federated Averaging, Secure Multi-Party Computation (SMPC), Differential Security, and Homomorphic Encryption, in keeping up show precision while securing delicate information. Through tests conducted in a reenacted cloud computing environment, exactness, security conservation, and computational overhead were assessed. Results appears that Federated Averaging accomplishes the most noteworthy show exactness (86.5%), followed by SMPC (84.2%), Differential Privacy (83.8%), and Homomorphic Encryption (82.1%). Differential Privacy offers the most elevated level of protection assurance, whereas Unified Averaging shows the least computational overhead. These findings underscore the importance of taking into account such trade-offs between showing performance, security preservation and computational efficiency while choosing unified learning algorithms for privacy sensitive applications. © 2024 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

An approach to summarize multilingual news using deep learning technique

An approach to summarize multilingual news using deep learni...

引用

8th IET Smart Cities Symposium (SCS 2024)

作者： Sumita Gupta Sapna Gambhir Rana Majumdar Department of Computer Science & Engineering Amity School of Engineering & Technology Amity University Noida India Department of Computer Science College of Engineering and Computing George Mason University USA Department of Computer Science Sister Nivedita University India

ISBN: (数字)9781837243105

Every single day the volume of data is growing exponentially high aiding more than half of the overall digital content. As now technologies are getting advanced and computing infrastructure is affordable, the digital content is catastrophically growing. The most critical challenge is to distinguish between the structured and unstructured data available in the form of text, image, audio, or videos etc on the internet where most of the content are unstructured. In this paper, deep learning algorithms are used for training and testing the data. Also, news translation and summarization from Hindi website to English is done for those people who are fond of news on the web and are not interested to go through the entire news instead they are looking for highlights or summary of those news. So, the automatic summarization of news articles is required. Here, an automatic text summarizer using extractive summarization approach is proposed and implemented by considering deep learning for categorization of news content and text rank algorithm for summarization. To evaluate accuracy, F-measure and recall of the produced summary, deep learning algorithms are applied. The result produced 99.4% of accuracy using LSTM over other deep learning like CNN, LSTM, CNN-LSTM, BI-LSTM etc.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Robust Protocol Design to Perform Data Communication over Wireless Sensor Networks with Enhanced Privacy Preserving Principles

A Robust Protocol Design to Perform Data Communication over ...

引用

Sentiment Analysis and Deep Learning (ICSADL), International Conference on

作者： Bandela Sathyavani Rakesh Kumar Yadav John Shiny J Revathi. R Ashish Kumar Bulakh Shilpa Jain Department of EEE School of Engineering SR University Warangal Telangana India Amity School of Engineering and Technology Amity University Patna Bihar Velammal College Of Engineering And Technology Madurai Department of Computer Science-Information Technology PSGR Krishnammal College for Women Coimbatore Department of Computer science and Engineering CDGI Indore Department of Computer Science and Engineering IES College of Technology Bhopal

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

the growth of wireless sensor networks has transformed all automation and industrial systems. Nonetheless, guaranteeing safe and privacy-preserving connectivity in sensor networks continues to be a difficult task. Current authentication and routing techniques frequently jeopardize privacy, entail significant design intricacy, also vulnerable to malware assaults. To mitigate these restrictions, we present an innovative secure protocol, the Asymmetric Cryptography-based Modified Cuckoo Search Optimization Protocol (MCuSO) for wireless sensor networks. Our proposed technique impacts asymmetric credentials with belief supervision for the privacy preservation of WSN data. This method attains an equilibrium in the middle of security and efficiency. Through comprehensive simulations utilizing the MATLAB platform, we illustrate that MCuSO attains an average network throughput of 94% and a network residual energy of 89%, in comparison to leading other algorithms. Moreover, the protocol efficiently reduces malware attacks. These findings underscore MCuSO as a viable outcome of resource limited WSN devices, providing an advantageous equilibrium of information security, data integrity and data efficacy.

关键词： Wireless sensor networks Data privacy Protocols Heuristic algorithms Authentication Throughput Routing Malware Cryptography Optimization

来源：评论

学校读者我要写书评

暂无评论

Two-way Speech to Sign Language Converter application using Python, OpenCV and NLP 6

Two-way Speech to Sign Language Converter application using ...

引用

6th International Conference on Contemporary Computing and Informatics, IC3I 2023

作者： Suman, Shashikant Lohani, Bhanu Prakash Singh, Vijay Gupta, Amar Deep Khan, Akhilesh Kumar Kumar, Anil Amity School of Engineering & Technology Amity University Department of Computer Science Uttar Pradesh Greater Noida India Lloyd Institute of Management and Technology Greater Noida Uttar Pradesh India Lloyd Law College Greater Noida Uttar Pradesh India

ISBN: (纸本)9798350304480

Language is one of the cornerstones of modern society. It has a very important role as it is responsible for conveying and sharing information with others. The people who are challenged with hearing and speaking disabilities are unable to communicate well with others. To aid them in this scenario, we have developed a program which can translate Sign Language to speech and vice versa. The models for the program were created with the help of public ISL datasets containing sign dictionaries. Speech to sign language modules used speech to text and NLP principles to generate signs for the provided sentence. Random Forest classifier was used for sign recognition. © 2023 IEEE.

关键词： CNN communication Machine Learning Natural Language Processing RF Sign language

来源：评论

学校读者我要写书评

暂无评论

Customer Retention Using Machine Learning 10

Customer Retention Using Machine Learning

引用

10th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and computer engineering, UPCON 2023

作者： Das, Lipsa Salman, Rahama Sabeer, Shaista Ansari, Subuhi Kashif Aarif, Mohd Rana, Ajay Amity School of Engineering and Technology Amity University UP Greater Noida India Jazan University Department of Computer Science Saudi Arabia Global Research Network UP Noida India College of Computer Science & Information Technology Jazan University Department of Information Technology and Security Jazan Saudi Arabia College of Computer Science and Information Technology & Security Jazan University Jazan Saudi Arabia

ISBN: (纸本)9798350382471

Maintaining customer retention stands as a pivotal element in ensuring business success, given that the costs associated with acquiring new customers often surpass those linked to retaining existing ones. Recognizing the significance of retaining a loyal customer base, businesses prioritize strategies and initiatives that cultivate lasting relationships with their current clientele, understanding that sustained customer loyalty contributes substantially to long-term viability and profitability.. Machine learning techniques offer a promising approach to predicting customer behavior and developing personalized retention strategies. In this research paper, we explore the use of machine learning for customer retention, specifically focusing on predictive modeling and recommendation systems. We review recent literature on the topic, discussing different machine learning algorithms and techniques that have been applied to customer retention. We also present a case study of a company that has successfully implemented machine learning-based retention strategies, highlighting the benefits and challenges of this approach. Our findings suggest that machine learning can be an effective tool for improving customer retention, but its success depends on several factors, including data quality, model accuracy, and implementation strategy. Our conclusion involves an exploration of the consequences of our research for forthcoming studies and practical applications within business environments.. © 2023 IEEE.

关键词： customer behavior Customer retention machine learning predictive modelling

来源：评论

学校读者我要写书评

暂无评论

Performance evaluation of neural network for human classification using blob dataset

Recent Advances in Computer Science and Communications

引用

Recent Advances in computer science and Communications 2021年第5期14卷 1592-1602页

作者： Mehta, Monika Bhadauria, Madhulika Department of Computer Science & Engineering University School of Information Communication & Technology Guru Gobind Singh Indraprastha University Dwarka New Delhi India Amity School of Engineering & Technology Amity University Noida India

Background: Human Classification in public places is an emerging area in the applications of Computational Intelligence. Therefore, modeling of an optimal architecture of the neural network is required to classify them. Methods: In this work for this purpose, blob dataset has been used to train the neural network. This dataset consists of 2408 features of a human blob. Results: Further, analysis of this blob dataset has been done on the basis of various characteristic pa-rameters for affirmation of actual training. During training and testing of this dataset, it has been observed that when nodes at hidden layer are below and above 10 then training of neural network is under fitted and overfitted respectively and works effectively when the nodes are 10 at the hidden layer. Conclusion: From the experimental work performed in this study, an optimal neural network has been obtained to classify human using blob dataset. © 2021 Bentham science Publishers.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Path Detection for Self-Driving Carts by using Canny Edge Detection Algorithm 9

Path Detection for Self-Driving Carts by using Canny Edge De...

引用

9th IEEE International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions), ICRITO 2021

作者： Srivastava, Sumir Gupta, Sumita Amity School of Engineering and Technology Amity University Department of Computer Science and Engineering Noida India

ISBN: (纸本)9781665417037

A lane detection system is the most principal component of a self-driving transportation computation system. It deals with various complex scenarios such as lane curvature worn out marking, lane changing, turning U-turns, ending and separating lines. Many modern corporations and enterprises like Tesla have been able to achieve second grade i.e., partial automation at a commercial level. In this research paper, an improved and optimized lane detection method is proposed by using the OpenCV's canny edge detection algorithm. A quick and robust method that can easily detect lanes in a live video feed or a pre-recorded video stream. This proposed framework effectively combines the OpenCV's canny edge algorithm with the Hough transform function so it can be applied in small scale applications specifically for visitor carts in an apartment complex. Testing and analysis of the program shows that the suggested software is very reliable. © 2021 IEEE.

关键词： Hough transforms

来源：评论

学校读者我要写书评

暂无评论

Detection and Recognition of Hand Gestures for Indian Sign Language Recognition System 6

Detection and Recognition of Hand Gestures for Indian Sign L...

引用

6th IEEE International Conference on Signal Processing, Computing and Control, ISPCC 2021

作者： Bansal, Mitashi Gupta, Sumita Amity University Amity School Of Engineering Technology Department Of Computer Science And Engineering Noida India

ISBN: (纸本)9781665425520

People with disabilities (hearing and listening impaired) have a vast social circle all over the world. For deaf and mute people, the sign language paves a way for the better communication which is the method that everyone understands and leads to effective communication among our diverse population. This study provides a comparative analysis for this complex task problems which are out of reach for a simple machine. As a result, there is a urgent need for the solution for such a problem, so the solution is integrating this problem with Machine Learning algorithms like Support Vector Machine, Convolutional Neural Network, K- Nearest neighbors. The results produced from Convolutional Neural Network are more accurate than those which is achieved by other several classifiers. © 2021 IEEE.

关键词： Audition

来源：评论

学校读者我要写书评

暂无评论

Security Analysis and Improvement of Authenticated Key Agreement Protocol for Remote Patient Monitoring IoMT

Security Analysis and Improvement of Authenticated Key Agree...

引用

2024 IEEE International Conference on Communications, Computing, Cybersecurity and Informatics, CCCI 2024

作者： Gautam, Deepika Thakur, Garima Obaidat, Mohammad S. Hsiao, Kuei-Fang Kumar, Pankaj Central University of Himachal Pradesh Srinivasa Ramanujan Department of Mathematics HP Dharamshala176215 India School of Computer and Communication Engineering University of Science and Technology Beijing China School of Computing SRM University Department of Computational Intelligence TN Kattankulathur India School of Engineering The Amity University UP 201301 India

ISBN: (纸本)9798350349832

The Internet of Medical Things (IoMT) is a network of medical devices, hardware infrastructure, and software that accumulates real-Time data through remote monitoring and minimizes doctor-patient interaction, enhancing the quality of remedies. However, the facile availability and accessibility of data over the web have given rise to serious information security and credibility issues in the IoMT. Recently, Chen et al. [1] proposed a provably secure authenticated key agreement protocol for remote patient monitoring in IoMT. However, after revisiting their scheme, we found security flaws such as user impersonation, ephemeral secret leakage attacks, denial-of-service attacks, and session key disclosure attacks. Therefore, this paper presents cryptanalysis as well as an improvement of Chen et al. 's scheme that strives to furnish protocols with robust security in opposition to the mentioned attacks. The security and effectiveness are displayed through informal analysis and evaluation with other existing state-of-The-Art metrics like computational and commu-nication cost. At last, the findings project the superiority of the proposed improved scheme. © 2024 IEEE.

关键词： Authentication Protocol

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：