检索结果-内蒙古大学图书馆

OntoBlock: a novel ontological-based and blockchain enabled spectrum sensing framework for detection of malicious users in cognitive radio internet of things (CR-IoT) networks

引用

International Journal of Information technology (Singapore) 2024年第6期16卷 3913-3921页

作者： Marriwala, Nikhil Kumar Shukla, Vinod Kumar Raju, Ayalapogu Ratna Panda, Sunita S, Suma Purad, Hemavati C. Electronics and Communication Engineering Department University Institute of Engineering and Technology Kurukshetra University Haryana Kurukshetra India Information Technology Head of Academics–School of Engineering Architecture Interior Design Amity University Dubai Dubai International Academic City Dubai United Arab Emirates Department of Computer Science and Engineering Mahatma Gandhi Institute of Technology Hyderabad India Department of Electrical Electronics and Communication Engineering GITAM School of Technology Bengaluru Campus Karnataka Bengaluru India CMR Technical Campus Hyderabad India Department of AIML BITM Karnataka Ballari India

CR-IoT networks can benefit from the idea of blockchain technology to achieve accurate decisions in order to provide very high-accuracy spectrum sensing in the network. It allows for multi-user cooperation as the sensing readings are being exchanged in the spectrum. It leads to security issues in CR-IoT networks. Thus, in order to increase the quality of decision-making in spectrum sensing, the given paper introduces an ontological framework with a blockchain-enabled system to detect malicious users in networks. The proposed framework first captures network packets from available Wi-Fi, followed by the creation of blocks with private, public, and hash keys. The keys are used to encode information about the nodes, such as confidential information and their location, data relative to users, their position where packets are delivered, etc. This is subsequently followed by the generation of network ontology, which includes parsing, computation of similarity, and reduction in clustered packets. Finally, the performance of the suggested mechanism is validated using a set of evaluation measures such as authentication rate, intrusion rate, average network throughput time consumption, and energy efficiency. As seen from the findings, it is evident that the proposed framework performs better than existing recent studies, thereby improving the performance of CR-IoT networks. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Blockchain Cognitive radio Internet of things (IoT) Ontology Spectrum sensing

来源：评论

学校读者我要写书评

暂无评论

Multi-frame Correlated Representation Network for Video Super-Resolution

Multi-frame Correlated Representation Network for Video Supe...

引用

2023 IEEE International Conference on computer, Information, and Telecommunication Systems, CITS 2023

作者： Jin, Shuo Liu, Meiqin Guo, Yu Yao, Chao Obaidat, Mohammad S. Institute of Information Science Beijing Jiaotong University Beijing China School of Computer & Communication Engineering University of Science and Technology Beijing Beijing China King Abdullah Ii School of Information Technology The University of Jordan Amman11942 Jordan School of Computer and Communication Engineering University of Science and Technology Beijing Beijing100083 China The Amity University UP Noida201301 India

ISBN: (纸本)9798350336092

Video super-resolution aims to reconstruct the high-resolution video from its degraded observation. Existing methods primarily utilize explicit alignment strategies, including optical flow and motion compensation, and implicit alignment strategies, including deformable convolution and non-local attention, to model the temporal information. However, these alignment strategies with motion estimation and motion compensation (MEMC) introduce inaccurate inter-frame information to some extent, which largely affects the reconstruction performance. To avoid the error compensation information, we propose to model the temporal information from the perspective of the self-similarity between frames and design a multi-frame correlated representation network (MCRNet) for video super-resolution. To address the issue of temporal information distortion caused by large-scale pixel displacement and object occlusion, MCRNet extracts temporal information through similar regions on multiple frames, which are aggregated with allocated weights for information compensation. Moreover, we design a multi-scale non-local information fusion module for non-local correlation matching of spatio-temporal features in the multi-scale space, which maintains the scale consistency of spatio-temporal features. Experimental results indicate that MCRNet achieves promising gains over other competing methods which employ explicit and implicit alignment strategies on different datasets. © 2023 IEEE.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Systematization in Asr Systems: A Review

SSRN

引用

SSRN 2024年

作者： Joshi, Jahanvi Sharma, Dolly Dept. of Computer Science and Engineering Amity School of Engineering and Technology Amity University Uttar Pradesh Uttar Pradesh Noida201301 India

Speech analysis and its recognition play an important role in the advancement of race driven by the primary form of communication, i.e. speech. Automatic speech recognition works on the principle of taking either spoken utterances or text as input, followed by optimum interpretation of each word and analyzed speech as output. The objective of this review paper is to study the already existing technologies of ASR systems and to map out its advantages and disadvantages with needs of today. Optimal ways of finding successful and future oriented models have been discussed in this paper. They are minimum to no training data requirements, minimum operational time, use of complex algorithm to minimize error, low word error rate, multi-speaker applicable, noise and silence detection authenticated, and acceptances to unseen or new data. This paper compares famous ASR models and brings in light the huge success possible in the field of multi-model ASR system(s) technique. © 2024, The Authors. All rights reserved.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

X-Pand: explainable random forest with feature selection for COVID-19 like pandemics in smart cities

X-Pand: explainable random forest with feature selection for...

引用

8th IET Smart Cities Symposium (SCS 2024)

作者： Pronaya Bhattacharya Ashwin Verma Ashwani Kumar Tamoghna Mukherjee Bharat Bhushan Pushan Kumar Dutta Amity School of Engineering and Technology Amity University Kolkata West Bengal India Department of Computer Science and Engineering Institute of Technology Nirma University Ahmedabad Gujarat India School of Computer Science Engineering and Technology Bennett University Greater Noida Uttar Pradesh India Department of Computer Science and Engineering School of Engineering and Technology Sharda University Greater Noida India

ISBN: (数字)9781837243105

The criticality of COVID-19 has burdened our healthcare resources. Thus, there is a growing need to advance our healthcare frameworks. Recently, with the rise of Explainable Artificial Intelligence (XAI) models in healthcare that leverage interpretability and solve the black-box nature of AI, healthcare frameworks and designs in smart cities have improved many folds. To address the crisis in light of future COVID-19-like pandemics in smart cities, we propose a case-study, X-Pand, that utilizes an XAI framework over Random Forest (RF) algorithm for feature selection in COVID-19 detection. Unlike recent schemes that are mostly non-interpretable, X-Pandemphasizes transparency and interpretability, crucial for gaining actionable insights and trust in automated health diagnostics. We present a feature ranking mechanism, which integrates Shapley Additive Explanations (SHAP) for enhanced decision tree interpretability, optimizing feature selection and improving diagnostic accuracy. We evaluate X-Pandon a comprehensive COVID-19 clinical spectrum dataset, demonstrating superior performance in terms of accuracy, sensitivity, and specificity compared to traditional models like XGBoost, Support Vector Machine (SVM), and Multi-Layer Perceptron (MLP). Our findings reveal that X-Pandnot only achieves higher prediction accuracy but also offers clearer justifications for its decisions, thus enabling more informed and confident clinical decisions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Internet of Medical Things: A CT Image Denoising in Tetrolet Domain 5

Internet of Medical Things: A CT Image Denoising in Tetrolet...

引用

5th International Conference on Information Systems and computer Networks, ISCON 2021

作者： Diwakar, Manoj Pandey, Richa Sharma, Ritik Saun, Sapna Singh, Prabhishek Pandey, Neeraj Kumar Graphic Era Deemed to Be University Department of Computer Science Engineering Uttarakhand Dehradun India Graphic Era Hill University Campus-Haldwani Department of Computer Science Engineering Uttarakhand India Amity University Uttar Pradesh Amity School of Engineering Technology Department of Computer Science Engineering Noida India DIT University School of Computing Dehradun India

ISBN: (纸本)9781665403412

The Internet of Medical Things (IoMT) is a huge community of linked medical equipment and technologies that communicate with a large number of Servers over the internet to provide a variety of services such as medical image denoising. Projection-based reconstructed images in computed tomography (CT) are noisy due to thermal noise and electrical noise, both of which are approximately AWGN in magnitude. Because of the variety of clinical features and textures included in CT reconstructed images, denoising is a difficult process. It is possible to estimate the true noise of a single image, and then to minimize both the real noise and the additional noise by reconstructing CT images. A unique modified approach is proposed in this work, in which the noise will be calculated actual as well as added, followed by a proposed method for denoising, which is based on thresholding in tetrolet domain. Different denoising schemes are used in the experiments, and the results are compared to one another. Experimentation has revealed that both in terms of PSNR and visual quality, the suggested technique yields promising results that are favorable to both. © 2021 IEEE.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

Exploring Machine Learning to Predict Brain Tumour Disease 7

Exploring Machine Learning to Predict Brain Tumour Disease

引用

7th International Conference on Contemporary Computing and Informatics, IC3I 2024

作者： Sharma, Sukrati Sunaina Shivahare, Basu Dev Singh, Kirti Singh, Prabhishek Bibhu, Vimal Just Dial Karnataka Bangalore India Amity University Department of Mathematics Uttar Pradesh Greater Noida India Galgotias University School of computer science & Engineering Uttar Pradesh Greater Noida India Bennett University School of computing science & Engineering Uttar Pradesh Greater Noida India Noida International University School of Engineering & Technology Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350350067

The demand of AI is increasing day by day in the medical field. Machine Learning (ML) is subset of AI. ML has become popular tool and widely used to detect several medical diseases at higher accuracy. Promising accuracy of ML algorithms depend on training of digital images like CT, MRI, X-rays etc. In this paper, CNN model is proposed to classify brain tumour into malignant and non-malignant class and comparative study using diverse ML algorithm is conducted and their accuracy is compared. This paper explores role of ML in clinical diagnosis, accurate prediction and clinical analysis regarding brain tumour disease based on various brain tumour dataset like figshare, brats, Kaggle. Proposed CNN model has achieved 98% promising accuracy. © 2024 IEEE.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence in System and Software engineering for Auto Code Generation

Artificial Intelligence in System and Software Engineering f...

引用

2024 International Conference on Electrical, Electronics and Computing Technologies, ICEECT 2024

作者： Ghai, Anupriya Sharma Rawat, Vandna Gupta, Vishan Kumar Ghai, Kapil Graphic Era Hill University School of Computing Dehradun India Graphic Era Deemed to be University Science Engineering Department of Computer Dehradun India Amity University. Punjab School of Engineering and Technology Mohali India Graphic Era Hill University Department of Chemistry Dehradun India

ISBN: (纸本)9798350378092

Artificial Intelligence has profoundly impacted system and software engineering by facilitating the automation of complicated tasks, reducing errors, and accelerating the development process. AI-driven tools help enhance efficiency, improve code quality, and promote the generation of more adaptive and innovative software solutions. The present research uses AI-generated tools to explore how AI transforms code synthesis. The study will include a comparative analysis of the performance of manual coding and other automated methods to explore how AI can accelerate code synthesis and make modern web development more competent or effective. It is suggested in the research that with algorithmic and contextual consideration, the quality of code developed by the AI would be higher in most cases than by people due to lower error rates and shorter synthesis. Overall, the central conclusion of the research is that AI plays a crucial role in transforming systems and software engineering. The paper also includes information on ethical dilemmas, robust validation mechanisms, conservative modes, and current research. © 2024 IEEE.

关键词： Software quality

来源：评论

学校读者我要写书评

暂无评论

A Review on Advancing Cybersecurity Frameworks by Integrating Machine Intelligence with Federated Learning

A Review on Advancing Cybersecurity Frameworks by Integratin...

引用

IoT Based Control Networks and Intelligent Systems (ICICNIS), International Conference on

作者： Vijayta Patil Jhankar Moolchandani Ashutosh Kumar Dubey Department of Computer Science & Engineering Amity School of Engineering and Technology Amity University Gwalior Madhaya Pradesh India Chitkara University School of Engineering and Technology Chitkara University Himachal Pradesh India

ISBN: (数字)9798331518097

ISBN: (纸本)9798331518103

In today's world, the growth of connected networks has also created a significant risk due to increasing risks of cyber-attacks. In this paper, various hybrid cybersecurity frameworks have been reviewed and analyzed that utilize machine learning approaches in combination with federated learning. These frameworks are assessed in terms of their security against complex cyber threats. In particular, machine learning focuses on improving threats detection by searching for patterns and other oddities in complex datasets, while the federated learning decentralizes the topology of the model training. This decentralization helps to enhance strict data compliance requirements and reduce data exposure risks. When synergized in the dual approach, the security system is strengthened as well as the enforcement of data privacy and other compliance where available. Empirical results have proved that this methodological approach provides better outcomes especially aimed at detection among other benchmarks. The improvement due to the hybridization indicates a scalable and robust solution that can adapt the evolving cyber threats landscape. The hybrid combination may establish new cybersecurity standards and open the door to more secure digital interactions across various sectors.

关键词： Training Data privacy Federated learning Reviews Threat assessment Topology Sensors Safety Reliability Standards

来源：评论

学校读者我要写书评

暂无评论

Human Pose Estimation using Deep Learning Techniques 22

Human Pose Estimation using Deep Learning Techniques

引用

Proceedings of the 4th International Conference on Information Management & Machine Intelligence

作者： Anant Grover Deepak Arora Anuj Grover Department of Computer Science and Engineering Amity School of Engineering and Technology Amity University Uttar Pradesh Lucknow Campus. India Department of Computer Science and Engineering Amity School of Engineering and Technology Amity University Uttar Pradesh Lucknow Campus India

ISBN: (纸本)9781450399937

Human Pose Estimation is a method of detecting and classifying all the key human body joints. A 2D Human Pose Estimation method predicts the two-dimensional coordinates from an input image. Classical methods used deformable parts models for detecting body joints. This paper discusses the state-of-the-art Deep Learning based approaches for estimating human poses. It can be implemented by either using the top-down or bottom-up technique for pose estimation. Here, the authors have studied the Convolutional Pose Machines, Hourglass Network and MoveNet architectures for Pose Estimation. These architectures are compared against each other in terms of their efficiency by measuring the time taken by each of them and their accuracy by evaluating them using the Percentage of Detected Joints metric on the MPII dataset. The architectures were implemented by using TensorFlow and Open-Source libraries built using PyTorch. The inference results for each joint were compared individually for all the body joints. The Hourglass Network showed the best accuracy but is really slow. The MoveNet architecture is the second best according to accuracy but is very fast and can be used in real-time systems.

关键词： Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing the Capacity of Extreme Learning Machines for Biomedical Informatics Applications 1

Optimizing the Capacity of Extreme Learning Machines for Bio...

引用

1st IEEE International Conference on Emerging Research in Computational science, ICERCS 2023

作者： Logeshwaran, J. Bhardwaj, Rajat Salagrama, Shailaja Das, Abhijit Sri Eshwar College of Engineering Department of Electronics and Communication Engineering Tamil Nadu Coimbatore India University of the Cumberland's Department of Information Technology Kentucky Williamsburg United States Amity University Aset Department of Computer Science and Engineering Karnataka Bengaluru India Rv University School of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350359756

the paper discusses a way of growing the capability of severe deep learning machines (ELM) for biomedical informatics programs. This technique involves varying the dimensions of the training set, the variety of neurons in the hidden layer, the kind of activation function used, the range of different sorts of neurons used and the regularization techniques *** that it will maximize the ability of ELM fashions for biomedical informatics applications, the authors advocate using a stepwise seek technique to determine the fine combination of parameters. This technique entails first defining a baseline or initial configuration of ELM parameters and then iteratively enhancing that configuration via deep learning from the empirical effects of each optimization step. distinctive regularization strategies are carried out at every optimization step which could involve pruning hidden neurons as a way to reduce the complexity of the model. The authors verified their technique on publicly to be had datasets consisting of the Michigan Imputation of missing Values (MIMV) dataset and on a dataset of clinical records from the branch of Anesthesiology, branch of health and Human services. © 2023 IEEE.

关键词： Neurons

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：