检索结果-内蒙古大学图书馆

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

作者： Hemkiran, S. Sudha Sadasivam, G. Pradeepa, T. Samukthaa, R.S. Ajay Raj, R. Psg Institute of Technology and Applied Research Department of Computer Science and Engineering Coimbatore India Psg College of Technology Department of Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350335095

Alzheimer's disease (AD) is a brain disorder that is associated with memory loss and is typically observed in elderly and aging individuals. This condition is irreversible in nature. Neural networks have shown better performance than traditional machine learning algorithms when it comes to analyzing high-dimensional data from Magnetic Resonance Images (MRI) brain images. This is an approach for processing such data. Detection of Alzheimer's disease is essential because the early treatment can control the progression of the disease in a slower pace. In this work, the proposed model used different models of convolutional neural networks (CNN) techniques to process the MRI images of the brain and classified them into different classes. The proposed model detects AD using neural network feature extraction and classification methods based on the pre-processed datasets. Here, in the proposed model, various algorithms such as Resnet-50, DenseNet-169 and Hyperparameter tuning of Convolutional Neural Network are utilized to find the better performing model in terms of accuracy when compared with other traditional techniques. © 2023 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

The Two Sides of AI in Cybersecurity: Opportunities and Challenges 2

The Two Sides of AI in Cybersecurity: Opportunities and Chal...

引用

2nd International Conference on Intelligent Computing and Next Generation Networks, ICNGN 2023

作者： Alzboon, Mowafaq Salem Bader, Ahmad Fuad Abuashour, Ahmad Alqaraleh, Muhyeeddin Kamel Zaqaibeh, Belal Al-Batah, Mohammad Jadara University Faculty of Science and Information Technology Department of Computer Science Irbid Jordan Arab Open University Department of Information Technology and Computing Kuwait

ISBN: (纸本)9798350329070

The advancement of artificial intelligence (AI) over the past several years has enabled businesses to identify and respond to cyberattacks in real-time. Nevertheless, its implementation is fraught with difficulties and dangers, such as possibly introducing bias and producing unpredictable results. For enterprises to make responsible and productive use of AI, they must take measures to reduce the dangers and difficulties outlined above. When enterprises do so, they can design cybersecurity solutions that are effective but also ethical and trustworthy, protecting against threats while retaining trust and transparency. © 2023 IEEE.

关键词： Risk management

来源：评论

学校读者我要写书评

暂无评论

Mapping the Evolution of English language: Insights from Big Data Analysis 6

Mapping the Evolution of English language: Insights from Big...

引用

6th International Conference on Cybernetics, Cognition and Machine Learning Applications, ICCCMLA 2024

作者： Elamadurthi, Ranjit Kumar Chakraborty, Ayush Sau, Tamal Pukkalla, Satyanarayana Suryanarayana, G. Vardhaman College of Engineering Department of English Hyderabad India Avanthi Institute of Engineering and Technology Department of Computer Science and Engineering Vizianagaram India Vardhaman College of Engineering Department of Information Technology Hyderabad India

ISBN: (纸本)9798331505790

This paper explores the transformative role of big data in studying language evolution, tracing historical linguistic shifts, and revealing contemporary trends. Traditional methods relied on manual analysis, but big data enables realtime, large-scale examinations through tools like NLP and social media analytics. Case studies, including 'Quantitative Analysis of Culture Using Millions of Digitized Books' and analyses of Twitter language, demonstrate how big data uncovers new insights into cultural and linguistic dynamics. Despite challenges like data reliability and ethical concerns, integrating big data with conventional research methods offers a comprehensive approach to understanding language evolution and its broader implications. © 2024 IEEE.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Numerical approximation of nonlinear stochastic Volterra integral equation based on Walsh function

引用

SeMA Journal 2024年第4期81卷 665-678页

作者： Paikaray, Prit Pritam Parida, Nigam Chandra Beuria, Sanghamitra Nikan, Omid Department of Mathematics College of Basic Science and Humanities OUAT Bhubaneswar 751003 India School of Mathematics and Computer Science Iran University of Science and Technology Tehran 16846-13114 Iran

This paper adopts a highly effective numerical approach for approximating non-linear stochastic Volterra integral equations (NLSVIEs) based on the operational matrices of the Walsh function and the collocation method. The method transforms the integral equation into a system of algebraic equations, which allows for the derivation of an approximate solution. Error analysis is performed, confirming the effectiveness of the proposed method, which results in a linear order of convergence. Numerical examples are provided to illustrate the precision and effectiveness of the proposed method. © 2023, The Author(s), under exclusive licence to Sociedad Española de Matemática Aplicada.

关键词： 60H05 65C30 Brownian motion Collocation method Ito^ integral Lipschitz condition Non-linear stochastic Volterra integral equation Walsh approximation

来源：评论

学校读者我要写书评

暂无评论

Reducing power consumption in 2 - tier H-CRAN using switch active/sleep of small cell RRHs

Reducing power consumption in 2 - tier H-CRAN using switch a...

引用

International Conference on Artificial Intelligence, Blockchain, Computing and Security, ICABCS 2023

作者： Tiwari, Amit Kumar Mishra, Pavan Kumar Pandey, Sudhakar Department of Computer Science and Engineering United Institute of Technology Prayagraj India Department of Information Technology National Institute of Technology Raipur Raipur India

ISBN: (纸本)9781032669663

The shift to 5G networks was motivated by an exponential increase in data traffic requirements and the number of connected devices that adhere to severe quality of service (QoS) criteria. This evolution boosts total energy consumption while indirectly generates polluting carbon footprints. To deal with 5G traffic needs and power consumption issues, a novel 2 tier Heterogeneous Cloud Radio Access Network (H-CRAN) architecture is being developed. This research examines the energy usage in a two-tier 5G HCRAN employing switch active/sleep and Small Cell Remote Radio Heads (HSC-RRHs). We create HSC-RRH switching algorithms to minimise the number of unused HSC-RRH per Macro Cell RRH (HMC-RRH). The simulation results show that our suggested strategies based on switching active/sleep via HSC-RRH can reduce more than 48% of power, which makes them more effective in terms of power savings than existing schemes. © 2024 The Author(s).

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

LiDAR Image-Based Climate Change Detection with Their Economic Ecosystem Modelling: Artificial Intelligence Application

引用

Remote Sensing in Earth Systems sciences 2025年第1期8卷 173-181页

作者： Sravani, Chekka Ananth, Prithiviraj Sasikala, C. Kumar, N. Sathish Kumari, Ch D. V. P. Thrimurthulu, V. Computer Science and Engineering Marri Laxman Reddy Institute of Technology and Management Telangana Hyderabad 500043 India Department of CSE Sona College of Technology Salem-5 Salem India Department of CSE Srinivasa Ramanujan Institute of Technology (Autonomous) Andhra Pradesh Ananthapuramu India Department of ECE Sri Ramakrishna Engineering College Coimbatore 22 India Department of Computer Science and Engineering Aditya University Andhra Pradesh Surampalem India Department of Computer Science and Engineering MLR Institute of Technology Telangana Dundigal Hyderabad India

Over the past few decades, change detection has been the subject of more research in both close-quarters and distant sensing due to its significance in environment monitoring and database updating. The advancement of sensing technology has made data collecting more accessible and economical, which has increased the amount of data available from different sensing platforms. Studying these atmospheric components has become much easier because of LiDAR technology, which can measure backscattered signals and explore the atmosphere at very high spatial and temporal resolution. This research proposes a novel technique in satellite data security analysis with climate change detection utilizing ML algorithm. Input has been collected as input as satellite data based on security and processed for noise removal as well as normalisation. Processed data has been segmented and classified using SegNet histogram graph cut contour model and transfer AlexNet adversarial Markov model. The experimental analysis has been carried out in terms of data integrity, precision, normalised coefficient, recall and F-1 score. The proposed technique attained data integrity of 98%, F-1 score 95%, PRECISION of 97%, normalised coefficient of 93% and RECALL of 92%. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Adversarial Markov Climate change detection Graph cut contour model LiDAR technology Machine learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Feature Space-Based Mammogram Image Analyse Using Decomposition Method 1

Feature Space-Based Mammogram Image Analyse Using Decomposit...

引用

1st International Conference on Innovations in Communications, Electrical and computer Engineering, ICICEC 2024

作者： Shaik, Nazma Sultana Bhuyan, Hemanta Kumar Department of Computer Science Engineering Andhra Pradesh Guntur India Department of Information Technology Andhra Pradesh Guntur India

ISBN: (纸本)9798350376517

This paper has focused on detecting breast tumors from mammograms using the Fourier decomposition approach with enhancing feature space. Detecting breast tumors from mammograms is a challenging task without regional feature space. Thus, the texture features are considered for analysis of regional features for breast tumors from mammogram images. The Fourier decomposition method-based framework is considered for texture features in mammogram images. These texture features collect imperfections, roughness, and smoothness from the above framework. Further, the linear regression method enhances the feature space compared to old feature space towards effective classification. The impacts on classification performance are examined after producing an enhanced feature space based on linear regression and ensemble it with the original feature space. The suggested framework achieves sensitivity (98.48%), specificity (99.74%), accuracy (99.06%), and area under the curve (0.99). Investigating the tiny image dataset also provides the suggested framework's resilience. © 2024 IEEE.

关键词： Image texture

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection in Surveillance Camera 13

Anomaly Detection in Surveillance Camera

引用

13th International Conference on System Modeling and Advancement in Research Trends, SMART 2024

作者： Gopalakrishnan, K. Kavitha, K. Manisha, S. Kanish, S.G. Dharshini, D. Dharshan, C.L. Information Technology Velalar College of Engineering and Technology Tamil Nadu Erode India Computer Science Engineering Kongu Engineering College Tamil Nadu India Velalar College of Engineering and Technology Department of Information Technology Tamil Nadu Erode India

ISBN: (纸本)9798350380583

In high security locations, anomaly detection in surveillance systems is essential for maintaining public safety. This work proposes an object detection approach utilizing model renowned for its real-time performance for anomaly detection. The system perceives objects and trails actions by using YOLOv5 where it notes down the odd behaviors as perhaps in security video where it abnormal. A dataset which contains of several surveillance synopsis is used to train and evaluate the model. YOLOv5 has such an object detection capability with a custom made revelation framework which grants the system to differentiate between abnormal and legal activities in real-time. An emphasis on prudent processing speed is done to provide scalability in practical applications and the high authenticity abnormality detection is determined by experimental findings. © 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

A Machine Learning Approach to Identifying Employees at Risk of Workplace Injury 2

A Machine Learning Approach to Identifying Employees at Risk...

引用

2nd IEEE International Conference on Interdisciplinary Approaches in technology and Management for Social Innovation, IATMSI 2024

作者： Pramanik, Bablu Modak, Santanu Brainware University Dept. of Computer Science & Engineering India Bengal College of Engineering and Technology Dept. of Information Technology India

ISBN: (纸本)9798350360523

Workplace injuries are a critical concern, with millions occurring annually, leading to substantial human and economic costs. This study focuses on a qualitative analysis based on statistics from 2013 to 2017, with a specific emphasis on fatal and non-fatal workplace accidents within the European Union (EU) and Romania. The primary objective is to assess Romania's workplace safety status in the context of the EU and to propose strategic measures for improvement. To achieve this goal, four key indicators and statistical datasets are utilized, sourced from the National Institute of Statistics (NIS) of Romania, the Eurostat database of the European Commission, and the Romanian Labor Inspection. These indicators include the rate of incidence frequency index for occupational accidents, the average duration index, the frequency index for fatal accidents, and the severity index, enabling a comprehensive evaluation of accident frequency and severity. The rate of incidence, measuring injuries per 100,000 workers, is a pivotal indicator. Additionally, the study calculates the frequency index of non-fatal accidents (injuries per 1,000 employees) and the fatal accident frequency index (injuries per 1,000 workers). Statistical findings are rigorously validated through ANOVA analysis and T-tests. Following data evaluation, the study offers strategic recommendations informed by national and European strategies, including the National Occupational Safety and Health (OSH) Strategy for 2017-2020 and the "EU Strategic Framework on Health and Safety at Work"spanning 2014 to 2020. These recommendations aim to guide efforts for workplace accident control and prevention in Romania and the broader European *** summary, this study's core objective is to comprehensively analyze workplace accidents in Romania and the EU, employing various indicators and statistical data. Its primary aim is to assess the current status and propose evidence-based strategies for improvement, aligning with

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Blockchain and Machine Learning Integration for Secure Data Exchange in Modern Digital Ecosystems

Blockchain and Machine Learning Integration for Secure Data ...

引用

2024 International Conference on Recent Innovation in Smart and Sustainable technology, ICRISST 2024

作者： Chandhok, Gunita Arun Vijayakumar, N. Pundir, Sumit Patjoshi, Pramod Kumar Swaroop, Rupayali Chaya Kumari, H.A. Saveetha College of Liberal Arts and Sciences Department of Commerce Tamil Nadu Chennai India Karpagam College of Engineering Department of Computer Science and Technology Tamil Nadu Coimbatore India Graphic Era University Department of Computer Science and Engineering Uttarakhand India Centurion University of Technology and Management School of Management Odisha Khurda India Jecrc University Department of Computer Science Engineering Rajasthan Jaipur India Vidyavardhaka College of Engineering Department of Computer Science and Engineering Karnataka Mysuru India

ISBN: (纸本)9798350309140

In response to the growing demand for safe data exchange in modern digital ecosystems, the study analyzes the combination of blockchain with machine learning, proposing a unique framework to solve the limitations of existing systems. Existing systems have drawbacks such as compromised data integrity, vulnerability to illegal access, and a lack of fundamental trust mechanisms. The proposed system combines the reliability of blockchain with the analytical capabilities of machine learning, strengthening data security and privacy. Using blockchain's decentralized ledger provides transparency and integrity, while machine learning algorithms contribute predictive analytics and anomaly identification. Through extensive testing and analysis, the proposed system indicates significant improvements in avoiding unwanted access and maintaining data accuracy. The results highlight the revolutionary potential of the integration across multiple industries, minimizing the constraints of outdated technologies and building a stronger and trustworthy environment for data exchange. The study offers critical insights to the growing environment of secure data exchange, paving the way for companies to embrace a future where privacy and dependability are essential. © 2024 IEEE.

关键词： Adversarial machine learning

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：