检索结果-内蒙古大学图书馆

Enhancing CNN Weights for Improved Routing in UAV Networks for Catastrophe Relief with MSBO Algorithm

Journal of Mobile Multimedia 2024年第5期20卷 1117-1152页

作者： Gupta, Sachin Kumar Ul Din, Suhail Mohi Upreti, Kamal Mahajan, Shubham Date, Saroj S. Department of Electronics and Communication Engineering Central University of Jammu Jammu Samba 181143 India Department of Electronics and Communication Engineering Indian Institute of Technology Chhattisgarh Bhilai 491002 India Department of Computer Science Christ University Delhi NCR 201003 India Amity School of Engineering and Technology (ASET) Amity University Gurugram Haryana Panchgaon 122412 India Department of Artificial Intelligence and Data Science CSMSS Chh Shahu College of Engineering Maharashtra Chh. Sambhajinagar India

UAVs have become key in various applications lately, from catastrophe relief to environmental monitoring. The plan of powerful and reliable directing protocols in UAV networks is seriously hampered by the dynamic and habitually eccentric mobility patterns of UAVs. This study proposes a novel technique to beat these challenges by utilizing the Modified Smell Bees Optimization (MSBO) algorithm to upgrade the weights of CNNs. This study’s principal objective is to further develop UAV network routing decisions by using CNNs’ ability for design recognition and the Modified SBO’s optimization abilities. Our methodology comprises of randomly relegating CNN weights to a populace of bees at start, evaluating their wellness by fitness of directing performance, and iteratively fine-tuning these weights utilizing local and global search procedures got from bee searching. Broad simulations and performance evaluations show that our recommended approach incredibly expands the general dependability of UAV’s, brings down communication latency, and improves directing productivity. Future exploration in UAV network improvement gives off an impression of being going in a promising direction with the integration of CNNs for pattern recognition and the Modified SBO for weight enhancement. In addition to progressing UAV routing conventions, this work sets out new open doors for machine learning applications of bio-inspired optimization algorithms. © 2024 River Publishers.

关键词： catastrophe relief CNN Modified smell bees optimization (MSBO) optimization algorithms routing protocols UAV networks

来源：评论

学校读者我要写书评

暂无评论

Spinal Cord Disease Identification Using Transfer Learning Techniques 10

Spinal Cord Disease Identification Using Transfer Learning T...

引用

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

作者： Mittal, Ruchi Malik, Varun Goyal, S.B. Yadav, Suman Avdhesh Srivastava, Arun Pratap Sankhyan, Akhil Chitkara University Institute of Engineering and Technology Chitkara University Punjab India City University Faculty of Information Technology Malaysia Amity School of Engineering and Technology Amity University Department of Computer Science and Engineering Greater Noida India Lloyd Institute of Engineering & Technology Greater Noida India Lloyd Law College Greater Noida India

ISBN: (纸本)9798350382471

Spinal cord diseases pose a significant challenge in the medical field due to their complex nature and diverse manifestations. Early and accurate diagnosis is crucial for effective treatment and management. With the advent of deep learning techniques, the field of medical image analysis has witnessed remarkable advancements. Transfer learning, a subset of deep learning, has gained prominence for its ability to leverage pre-trained models on new tasks with limited labeled data, making it ideal for medical image classification tasks. In this study, we propose a novel approach for the identification of spinal cord diseases using transfer learning techniques, specifically employing a modified ResNet (Residual Neural Network) architecture. In order to train incredibly deep networks while avoiding the vanishing gradient issue, ResNet makes use of a deep structure and skip connections. This modification aims to extract subtle features that are crucial for accurate disease classification. A huge collection of spinal cord pictures, including both diseased and healthy instances, is used to train the suggested model. The model's capability to generalize and correctly diagnose spinal cord disorders is enhanced by the use of a pre-trained ResNet backbone, which draws on information gathered from a wide variety of datasets. © 2023 IEEE.

关键词： Medical Image Analysis Modified ResNet Architecture Spinal Cord Diseases Transfer Learning

来源：评论

学校读者我要写书评

暂无评论

Comparing the Efficacy of Machine Learning Models on Potentially Hazardous Objects 2

Comparing the Efficacy of Machine Learning Models on Potenti...

引用

2nd International Conference on Technological Advancements in Computational sciences, ICTACS 2022

作者： Chhibber, Manasi Bhatia, Madhulika Chaudhary, Aniket Stewart, Christopher Amity School of Engineering & Technology Amity University Noida India Ohio State University Computer Science and Engineering Department OH United States

ISBN: (数字)9781665476577

ISBN: (纸本)9781665476577

An asteroid or a comet is termed as a potentially hazardous object (PHO) if its orbit is such that it can closely approach the Earth and is huge enough to cause serious regional damage in the event of an impact. There are currently nearly 1,500 asteroids documented that have the potential to cause serious damage, but these are solely the ones we know about. In an event like this, it becomes a necessity to keep a check on all celestial bodies near earth so that we can take appropriate measures to minimize the damage. This project aims at analyzing data gathered by NASA about various asteroids or PHOs and predicting whether an Earth approaching body is hazardous or not. On finding an appropriate dataset, extensive data pre-processing was done on Machine Learning workspace on Azure. The Azure platform for machine learning algorithm provide a quick and easy way to apply machine learning algorithms as well as for modelling of data. Experimental results obtained by using diverse Machine Learning models were compared. The Two-Class Decision Forest provided the highest accuracy, a ROC-AUC score of 0.99. © 2022 IEEE.

关键词： Asteroids

来源：评论

学校读者我要写书评

暂无评论

FesNas: A Breakthrough Algorithm for Multi-Classification of Wheat Black Rust Intensity Levels 14

FesNas: A Breakthrough Algorithm for Multi-Classification of...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Singh, Amandeep Sehgal, Sweety Mahajan, Manish Kukreja, Vinay Sharma, Rishabh Vats, Satvik Gulzar Group of Institutions Punjab Ludhiana India Lovely Professional University Department of Computer Science and Engineering Punjab Phagwara India Amity University Amity School of Engineering and Technology Punjab Mohali India Chitkara University Chitkara University Institute of Engineering and Technology Punjab India Graphic Era Hill University Computer Science and Engineering Uttarakhand Dehradun India

ISBN: (纸本)9798350335095

Wheat black rust poses a severe danger to wheat production all over the world. The neural architecture search feature selection (FesNas) classification model is used in this study to offer a multi-classification model for the wheat black rot. It was decided to gather and annotate a dataset consisting of 10,000 high-resolution photographs, with each image indicating a different severity degree of the condition. The model accomplished a remarkable level of overall accuracy by reaching 95.98%. The findings reveal that the FesNas algorithm is successful in properly diagnosing wheat black rust over a wide range of severity levels. This research makes an important contribution to precision agriculture and gives insightful information that can be used to develop effective methods for disease prevention and management. The methodology that was suggested has the potential to help farmers improve crop productivity while also reducing the negative effects that wheat black rot has on their crops. © 2023 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Data storage security issues in cloud computing

Data storage security issues in cloud computing

引用

2021 International Conference on Innovative Practices in technology and Management, ICIPTM 2021

作者： Singh, Devang Pratap Kaushik, Prakarsh Jain, Manjari Tiwari, Vidushi Rajpoot, Subhadra Amity School of Engineering and Technology Student of Computer Science and Engineering Greater Noida India Amity School of Engineering and Technology Department of Applied Science Greater Noida India

ISBN: (纸本)9780738132891

Cloud computing gives on request administration on their information or data to its customers. Information storage(storing) is among one of the essential administration given by the cloud computing. Cloud specialist organization has the information of information proprietor on their server and client can get to their information from these servers. As information, proprietors and servers are various personalities, the worldview of information storage raises numerous security challenges. A free component is required to ensure that information is effectively facilitated to the cloud storage server. Right now, we will examine the various methods that are utilized for secure information storage on cloud. © 2021 IEEE.

关键词： Cloud storage

来源：评论

学校读者我要写书评

暂无评论

Utilizing Sentiment Analysis for Assessing Suicidal Risk in Personal Journal Entries 3

Utilizing Sentiment Analysis for Assessing Suicidal Risk in ...

引用

3rd International Conference on Innovative Sustainable Computational Technologies, CISCT 2023

作者： Indoria, Devadutta Singh, Jagendra Rubi Singh, Yajush Pratap Kumar, Bura Vijay Singh, Prabhishek Vikram Dev University Department of Commerce Jeypore India School of Computer Science Engineering & Technology Bennett University Greater Noida India Swami Vivekanand Subharti University Department of Education Meerut India Amity School of Engineering and Technology Amity University Noida India School of Computer Science and Artificial Intelligence SR University Warangal India

ISBN: (纸本)9798350303360

Mental health is a rising alarming issue and its condition among teenagers and adults is influenced by various factors including financial situation sociocultural context resource availability and personal experiences according to the national institute of mental health factual evidence suggests that mental health concerns are largely common among teenagers One out of five teenagers in the united states experiences mental health disorder which includes anxiety and depression ranking up being the most common conditions similarly various studies have found that many white-collar such as healthcare workers first responders and educators have a higher risk of having mental health problems because of their high-stress work environment and exposure to traumatic events. © 2023 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Behavioral Biometrics Authentication Systems: Leveraging Machine Learning for Enhanced Cybersecurity

Behavioral Biometrics Authentication Systems: Leveraging Mac...

引用

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

作者： Madavarapu, Jhansi Bharathi Mittal, Mudit Salagrama, Shailaja Adnan, Myasar Mundher Rana, Aryan Yadav, Kanchan University Of Cumberlands Department Of Information Technology 6178 College Station Drive WilliamsburgKY40769 United States Department Of Computer Science & Engineering Graphic Era Deemed To Be University Dehradun India College Of Technical Engineering The Islamic University Department Of Computers Techniques Engineering Najaf Iraq Amity School Of Engineering & Technology Amity University India Gla University Department Of Electrical Engineering Mathura India

ISBN: (纸本)9798350366846

This study focuses on behavioral biometrics and machine learning procedure that is employed vigorous in the verification frameworks to improve cybersecurity. Elaborating interesting designs in client behaviour, such as keystroke flow and mouse developments along with advanced machine learning algorithms we propose to generate verification components capable of accurately identifying a person's identity while adapting themselves all the fast live changes associated either. The experiments carried out on real-life datasets demonstrate LSTM models pervasive implementation in contrast to traditional machine learning algorithms (SVM, KNN and Random Forest). Thus, LSTM achieved an accuracy of 95.6%, outperforming SVM (88.7%), KNN (84.5%) and Random Forest (923). Additionally, LSTM proved great flexibility and competitive performance despite longer training times. The abovementioned results have demonstrated that LSTM is effective in learning the complicated real world conditions in sequential data and could be used for improvement of behavioral biometric recognition systems. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Software Reliability Evaluation using a Hybrid Soft Computing Approach for Battery Management System

Software Reliability Evaluation using a Hybrid Soft Computin...

引用

Sustainable Energy and Future Electric Transportation (SEFET), International Conference on

作者： Shrddha Sagar Avadhesh Kumar Garima Shukla Sofia Singh Dipak Raskar School of Computer Science and Engineering Galgotias University Uttar Pradesh India Department of Computer Science and Engineering Amity School of Engineering and Technology Amity University Mumbai Maharashtra Department of Artificial Intelligence Amity School of Engineering and Technology Amity University Uttar Pradesh Noida

ISBN: (数字)9798350383997

ISBN: (纸本)9798350384000

Predicting faults in a software system can be performed using software reliability models. Reliability is a real- world aspect that is related to several real-life issues which depends on several factors. Different algorithms and methodologies are present to predict software reliability, still the exploration of hybrid soft computing approaches is required to predict software reliability inefficient way. The reason is soft computing algorithms are able to deal with uncertainties and real time issues. The objective of this study is to propose a reliability assessment model using hybrid approach of GeneticAlgorithm and Self-Organizing Map (SOM) for Component Based Software System (CBSS). The reason for selecting CBSS is the reusability aspects of components, which makes software development process cheaper and faster. This paper is an attempt to identify most reliable components based on three reliability factors (cohesion, coupling, and component dependency) from a software project that can be reused for developing other applications efficiently. Simulation of Battery Management System software package components is completed by the use of MATLAB which were having 37 components out of which 6 most reliable components are selected using proposed method.

关键词： Self-organizing feature maps Couplings Computational modeling Software algorithms Battery management systems Software systems Prediction algorithms Software reliability MATLAB Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Deceptive Plastic: Unveiling the World of Financial Fraud 6

Deceptive Plastic: Unveiling the World of Financial Fraud

引用

6th International Conference on Futuristic Trends in Networks and Computing Technologies, FTNCT 2024

作者： Singh, Shikha Hazela, Bramah Asthana, Pallavi Barnwal, Shagun Srivastava, Garima Department of Computer Science and Engineering Amity School of Engineering and Technology Amity University Uttar Pradesh Lucknow India Department of Electronic and Communication Engineering Amity School of Engineering and Technology Amity University Uttar Pradesh Lucknow India

As human society is developing, so is electronic commerce and with that the use of credit card are increasing. And along with this growth, as people prefer to shop using credit cards in both mode of payments, the possibility of fraud and fraud of credit card is also on rise. The criminals may steal the card physically, but more frequently, they use digital ways to obtain the credit card details along with the personal information linked to it in order to engage in illicit actions. There is a lot of overlap between credit card fraud and identity theft. Indeed, credit card theft is one of the most common forms of identity theft. In these cases, the personal information of victims is stolen to somehow get access to cards by registering a new account without the owner's knowledge and certainly it is a form of cyberattack as well as data breach and is offensive crime. This behavior is both identity fraud and credit card fraud. In this study, we employ a CAT Boost, ADA Boost, LIGHT GRADIENT BOOSTING and CONVOLUTIONAL NEURAL NETWORK model to simulate the process of credit card transaction processing and display how it can be applied to the spot of such frauds. The dataset inspection method, factor determination, and techniques used for detection have a significant influence on the demonstration of fraud detection in credit card transactions. The accuracy for models can be determined by finding precision, recall, f1score, accuracy values but to compare the models, we will take ROC AUC Score into account. So, the ROC AUC Score of CAT BOOST, ADA BOOST, LIGHT GRADIENT BOOSTING and CONVOLUTIONAL NEURAL NETWORK model are 92.44, 79.74, 93.34, 95.25 respectively. And CONVOLUTIONAL NEURAL NETWORK is best among four with 95.25 ROC Score. © 2025 The Author(s). Published by Elsevier B.V.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Hardware Acceleration Using SIMD Based Vector Processor Array to Enhance Performance of Deblurring Methods for CT and MRI Images Having Motion Blur Artifacts

Hardware Acceleration Using SIMD Based Vector Processor Arra...

引用

2023 International Conference on Smart Systems for Applications in Electrical sciences, ICSSES 2023

作者： Sharma, Poonam Dubey, Ashwani Kumar Goyal, Ayush Amity School of Engineering and Technology Amity University Uttar Pradesh Dept. of Electronics and Communication Engineering U.P. Noida India Texas A&m University Dept. of Electrical Engineering and Computer Science Kingsville United States

ISBN: (纸本)9798350347296

A typical medical imaging that gives deep cross-sectional details of human body like MRI and CT, usually scans the subject area in form of many scans called slices. These slices are generally in the order of 100s or 1000s per unit of time. However, these slices have many artifacts including blurring of fine details due to motion between the scan device and the subject that may happen because of several reasons like nonstationary subject or jerk in the motion of capturing device or inappropriate aperture control. There is never-ending demand to always accelerate the medical image processing for faster and real time diagnosis especially for critical life saving situations. The core processor architecture to exploit such accelerations are the core to meet these requirements. © 2023 IEEE.

关键词： Field programmable gate arrays (FPGA)

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：