检索结果-内蒙古大学图书馆

Polycystic Ovary Syndrome (PCOS) diagnostic methods in machine learning: a systematic literature review

Multimedia Tools and Applications 2025年第16期84卷 16301-16337页

作者： Arora, Shikha Vedpal Chauhan, Naresh J.C. Bose University of Science and Technology YMCA Haryana Faridabad India Department of Computer Applications J.C. Bose University of Science and Technology YMCA Haryana Faridabad India Department of Computer Engineering J.C. Bose University of Science and Technology YMCA Haryana Faridabad India

Polycystic Ovarian Syndrome, also known as PCOS, is a major hormonal imbalance affecting women primarily in their reproductive age. Women with PCOS may have either infrequent or extended menstrual cycles or sometimes excess male hormone i.e. androgen levels. The ovaries may grow with number of slight collections of fluid, called follicles that fail to release eggs every month regularly. It is also seen that PCOS not only affects a woman’s fertility but also indirectly causes various other health issues like type 2 Diabetes, obesity, blood pressure and other metabolic disorders. Recent researches have focussed on the use of different algorithms in Machine Learning to diagnose PCOS using structured or unstructured data. Therefore, in this study, a considerable Literature Review has been carried out to provide a detailed analysis of various algorithms that have been used to detect PCOS with their comparative study. Also some of the work particularly focuses on health issues, the food and dietary patterns and the ways to manage PCOS. Further, these algorithms are critically analysed to understand the framework and limitations that should be considered while putting forward the solutions relevant to the diagnosis of PCOS in an effective way. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Blood pressure

来源：评论

学校读者我要写书评

暂无评论

Hybrid energy efficient deep learning and redactable consortium blockchain-based secure framework for smart parking in smart cities

引用

Multimedia Tools and Applications 2024年第37期83卷 85391-85420页

作者： D, Amu Baskaran, Santhi Department of Computer science and Engineering Puducherry Technological University Puducherry India Department of Information Technology Puducherry Technological University Puducherry India

Management of vehicular parking in the crowded environment is the indispensable requirement for the smart city scenario. The advent and potential development of Information Communication Technologies (ICT) and Internet of things (IoT) helped in proper thinking, operation and planning of parking management in smart city environment. But they suffer from the issue of privacy, security, integrity, energy efficiency, communication bandwidth and centralization. In this paper, Hybrid Deep learning and Redactable consortium blockchain-based Secure Framework (HDLRCBSF) is proposed for achieving the objective of energy-efficient smart parking in smart cities. This HDLRCBSF adopted the merits of Deep Bi-LSTM network for exploring the data associated with parking zones, such that optimal parking zones can be potentially allocated to the drivers with the ideal timing and location. It used the Redactable consortium blockchain network using Road Side Units (RSUs) which helped in attaining data verification and authentication at the security layer. It also implemented Threshold Chameleon Hash (TCH) algorithm for the objective of encrypting and decrypting the data related to the parking zones to establish secure communication. It adopted the significance of Deep Auto Regression Feature Augmented Bi-LSTM Networks in the analysis layer for exploring the cloud data that provides optimal parking lot to the drivers depending on the requirements that include cost, distance, and time. The quantitative and qualitative investigation conducted on the proposed HDLRCBSF confirmed its efficacy in terms of best parking space allocation rate of 21.32%, better than the baseline approaches that offered to the drivers with maximized privacy and security. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Multi-Class Brain Tumour Classification with CNN on MRI Scans

Multi-Class Brain Tumour Classification with CNN on MRI Scan...

引用

2024 IEEE International Conference on Signal Processing, Information, Communication and Systems, SPICSCON 2024

作者： Mridha, Nisarga Rafa, Sofia Noor Shayon, Md. Siamul Islam Sultana, Nusrat Safin Kamal, K.M. Reza, Ahmed Wasif Arefin, Mohammad Shamsul Department of Computer Science and Engineering East West University Dhaka Bangladesh Department of Computer Science and Engineering Chittagong University of Engineering and Technology Chittagong Bangladesh

ISBN: (纸本)9798331510213

The process of classifying brain tumors using MRI data is difficult to do accurately. The challenges and limitations of manual analysis in treatments can be overcome by implementing computer-Aided Diagnosis (CAD) systems for categorizing brain tumors. This study assesses the performance of five well-known Transfer Learning CNN architectures - VGG19, VGG16, GoogleNet, ResNet-50, and DenseNet-121 - using magnetic resonance imaging (MRI) scans. The main goal is to classify brain malignancies into four groups: no tumor, pituitary, meningioma, and glioma. The focus of this research for the classification task was on data preparation, training on preprocessed data, and comparing each model using evaluation metrics such as f1-score, accuracy, recall, and precision. Following pre-processing and training, the evaluation of the five CNN models revealed promising results for the VGG models, with both VGG19 and VGG16 achieving an accuracy score of 97%. This study indicates that among the base variants of Transfer Learning models, VGG19 and VGG16 are well-suited for classifying different types of brain tumors. © 2024 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis of Network Intrusion Detection in Internet of Things and Wireless Networks 2

A Comprehensive Analysis of Network Intrusion Detection in I...

引用

2nd IEEE International Conference on Data science and Network Security, ICDSNS 2024

作者： Swathi, Ch. Kare, Suresh Babu Jntuh University College of Engineering Science & Technology Department of Computer Science & Engineering Hyderabad India

ISBN: (纸本)9798350373110

Network Intrusion Detection System (NIDS) is most momentous safety techniques in mobile networks. Intrusion detection (ID) is significant approach aimed at identifying attacks then applying it on security procedures to networks. However, ID is limited by using a singular learning algorithm and is constrained by statistical, computational, and representational limitations. In this survey, various platforms for intrusion detection are analyzed to improve the detection of intrusions. This survey primarily discusses the significant expectations, advantages, and limitations analyzed in framework of Internet of Things (IoT) with Wireless Networks for ID systems. The performance of existing approach was considered by numerous performance metrics: precision, detection rate, false alarm rate (FAR), f1-score recall, accuracy, Mathews Correlation Coefficient (MCC), and missing alarm rate (MAR). This study concludes that the network intrusion detection overcomes the drawbacks of decreasing the detection accuracy and increase efficiency. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

A Case for Deploying Dynamic Neural Network on Edge-Cloud Continuum Environment 8

A Case for Deploying Dynamic Neural Network on Edge-Cloud Co...

引用

8th IEEE International Conference on Edge Computing and Communications, EDGE 2024

作者： Pozi, Muhammad Syafiq Mohd Sato, Yukinori Toyohashi University of Technology Department of Computer Science and Engineering Japan

ISBN: (纸本)9798350368499

As Deep Neural Network models become more accurate, the associated AI applications experience higher inference runtimes. This results in increased overall communication latency within the edge-cloud continuum, where the computing tasks are distributed. To address this, we propose a Dynamic Neural Network based framework to improve inference accuracy with optimal latency overhead within the edge-cloud continuum environment. The framework consists of 2 main components: Deep Neural Network offloading mechanism to the computing resources on edge-cloud continuum, and parameter selection for inference-exiting mechanism. Based on evaluations using the ImageNet dataset, our Dynamic Neural Network-based inference framework successfully improves inference accuracy while maintaining optimal latency overhead within the edge-cloud continuum. The framework surpasses the inference accuracy of single model-based approaches, where our cascaded model obtained 74.17% accuracy compared to single model accuracy, which is 73.95%. © 2024 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Small Population Size is Enough in Many Cases with External Archives 1

引用

13th International Conference on Evolutionary Multi-Criterion Optimization, EMO 2025

作者： Nan, Yang Ishibuchi, Hisao Pang, Lie Meng Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China

ISBN: (数字)9789819635382

ISBN: (纸本)9789819635375

In the evolutionary multi-objective optimization (EMO) field, evolutionary algorithms have a population to store a well-converged and well-distributed solution set. In the literature, the population size is usually specified in the range of 100–300 to approximate the entire Pareto front. Recently, a new framework with an external archive has been actively studied where a solution set selected from the archive is used to approximate the Pareto front. In this framework, a small population size can be better than a standard population size since a smaller population size means a larger number of generations under the termination condition specified by the same number of evaluated solutions. In this paper, we numerically examine whether better results are obtained from a smaller population size specification than a standard specification when the algorithm performance is evaluated using a solution set selected from an external archive. In our experiments, we examine the performance of four representative EMO algorithms (NSGA-II, NSGA-III, MOEA/D, and SMS-EMOA) with four specifications of the population size (36, 66, 120, and 210) on two frequently-used artificial test suites (DTLZ and WFG) and three real-world test suites (RWA, DDMOP, and RE). Our experimental results show that better results are obtained from a smaller population size specification in many cases when we cannot evaluate many solutions (i.e., when solution evaluation is expensive). © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Evolutionary multi-objective optimization Performance comparison Small population size

来源：评论

学校读者我要写书评

暂无评论

Blockchain Integration with Internet of Things (IoT)-Based Systems for Data Security: A Review

Blockchain Integration with Internet of Things (IoT)-Based S...

引用

International Conference on Data Analytics and Management, ICDAM 2023

作者： Kaur, Gagandeep Shrivastava, Rajesh Gupta, Umesh Department of Computer Science and Engineering Madhav Institute of Technology and Science Gwalior India School of Computer Science Engineering and Technology Bennett University Greater Noida India

ISBN: (纸本)9789819965434

The blockchain technology offers a secure channel for communicating between entities without the role of any third party. It is a digital ledger of transactions in a computer network that makes it hard for hackers to attack or alter the information. Banking, supply chain, precision agriculture, smart city, cyber-physical systems, industrial IoT, and health care are the various sectors in which blockchain technology has been adopted to enhance security. In recent times, these sectors are being revolutionized by digital transformation using sensor-aided physical devices forming Internet of Things (IoT) systems. Blockchain-based IoT system plays a vital role in replacing the conventional methods of storage and sharing data with a more reliable method. The integration of the two technology results in a secure, reliable, and smart system. This paper exhibits the background and working principle of blockchain technology. Also, it discusses the need of security and security challenges in IoT-based systems. Furthermore, it discusses briefly about smart contracts and motivation behind integrating blockchain technology with IoT-based systems. Finally, it proposes a secure IoT-based land registry architecture. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Simplified Beam Steering and Fast Error Compensation of Optical Phased Arrays by Using a Novel Weighted-Grouping Algorithm

引用

IEEE Access 2024年 12卷 63701-63712页

作者： Gayatri, N.S.R. Lin, Yi-Hsuan Donati, Silvano Lee, San-Liang National Taiwan University of Science and Technology Department of Electronic and Computer Engineering Taipei10607 Taiwan Taipei10607 Taiwan

Optical phased arrays (OPAs) serve as pivotal components for non-mechanical beam steering and find relevance in various applications. However, they necessitate correction of optical phase errors within the antenna array, arising from fabrication imperfections in waveguides. We introduce a novel weighted group phase compensation (w-GPC) algorithm to simplify phase compensation and beam steering for OPAs but also enhances sidelobe suppression. A key advantage lies in its reduced hardware requirements, enabling phase compensation with only half or a quarter of the original number of electrodes. Simulation-based verification confirms that beam steering remains achievable even with the reduced number of phase shifts. Consequently, this minimizes the necessary electrodes on the OPA chip and significantly streamlines control circuitry. This feature is especially beneficial for large-scale OPAs comprising hundreds or even thousands of phase shifters. The w-GPC's phase compensation significantly outpaces traditional Genetic and PSO algorithms in computation speed. Applying the proposed algorithm with half controlled phases to optimize 64- and 1024-element OPAs yields impressive peak-to-sidelobe level (PSLL) enhancements, reaching up to 15 dB and 22 dB, respectively. Remarkably, PSLL remains over 19 dB even when only one sixteen of the phases are utilized to correct phase errors and steer the beam for a 1024-element OPA. These outcomes affirm that exceptional PSLL values can be achieved by great reduction in the number of control electrodes. © 2013 IEEE.

关键词： Error compensation

来源：评论

学校读者我要写书评

暂无评论

An Enhanced RNN-LSTM Model for Fundus Image Classification to Diagnose Glaucoma

引用

SN computer science 2024年第5期5卷 1-17页

作者： Veena, H.N. Patil, Kavita K. Vanajakshi, P. Ambore, Anilkumar Gowda, Naveen Chandra Department of Computer Science and Engineering SJB Institute of Technology Bengaluru India Department of Information Science and Engineering Global Academy of Technology Bengaluru India Department of Information Science and Engineering Vivekananda Institute of Technology Bengaluru India School of CSE REVA University Bengaluru India School of Computer Science and Engineering REVA University Bengaluru India

In the current medical implications, one of the leading ocular diseases is Glaucoma which majorly damage the Optic Nerve Head (ONH) of the eye retina. The intraocular pressure of the eye leads to glaucoma, which may lead to complete or partial vision loss. Regular screening and early detection is the only solution to avoid further vision loss. Due to the laborious and manual procedure in diagnosis, an automatic system is needed to diagnose glaucoma. This paper presents a novel method using deep learning-based RNNLSTM classification model to develop an automatic approach to predict and classify the images to be as healthy or glaucomatous. The RNN and LSTM with dense, dropout, and batch normalization layers are used for training and testing the proposed prediction model. The RNN model is used for training the model and to overcome the problems that occur during training, the LSTM model is applied to increase the performance of the model. The proposed model achieved an accuracy of 97.4%, specificity of 97.9% and sensitivity of 97%in classifying the images. We have made use of the DRISHTI-GS database for training and testing the proposed model. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Deep learning Glaucoma Long short-term memory (LSTM) Recurrent neural network (RNN)

来源：评论

学校读者我要写书评

暂无评论

An In-Depth Analysis of Network Security: Intrusion Detection and Prevention Systems 3

An In-Depth Analysis of Network Security: Intrusion Detectio...

引用

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Kaur, Amritpal Tyagi, Rajesh Kumar Sinha, Shweta Vats, Prashant Amity School of Engineering and Technology Department of Computer Science and Engineering Haryana India Manipal University Department of Computer Science and Engineering Rajasthan Jaipur India

ISBN: (纸本)9798331518592

The concept of making everything easily and widely accessible has revolutionized the network industry. Even with the rapid advancements in networks and information technology, we still have difficulty guarding against attacks and theft of our resources. Small organizations might not be affected by this, but industry, businesses, and national security are all seriously affected. Every day, organizations encounter more and more dangers in the form of malware, intrusions, etc. Despite the fact that corporations have implemented a variety of defences against these types of assaults, including intrusion detection and prevention systems (IDPS), many security breaches remain undiscovered. To understand the security risks and IDPS, we will first survey common security breaches and then discuss the different opportunities and challenges in this field. In this paper, we survey the overall progress of intrusion detection systems, including existing types, techniques, and architectures found in the literature. © 2024 IEEE.

关键词： Network intrusion

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：