检索结果-内蒙古大学图书馆

SNN-IoMT:A Novel AI-driven Model for Intrusion detection in Internet of Medical Things

computer Modeling in engineering & Sciences 2025年第4期143卷 1157-1184页

作者： Mourad Benmalek Abdessamed Seddiki Kamel-dine Haouam Computer Engineering Department College of EngineeringAl Yamamah UniversityRiyadh11512Saudi Arabia Ecole Nationale Supérieure d’Informatique BP 68MOued-SmarAlgiers16309Algeria

The Internet of MedicalThings(IoMT)connects healthcare devices and sensors to the Internet,driving transformative advancements in healthcare ***,expanding IoMT infrastructures face growing security threats,necessitating robust Intrusiondetection Systems(IdS).Maintaining the confidentiality of patient data is critical in AI-driven healthcare systems,especially when securing interconnected medical *** paper introduces SNN-IoMT(Stacked Neural Network Ensemble for IoMT Security),an AI-driven IdS framework designed to secure dynamic IoMT *** a stacked deep learning architecture combining Multi-layer Perceptron(MlP),Convolutional Neural Networks(CNN),and long Short-Term Memory(lSTM),the model optimizes data management and integration while ensuring system scalability and *** on the WUSTl-EHMS-2020 and IoT-Healthcare-Security datasets,SNN-IoMT surpasses existing IdS frameworks in accuracy,precision,and detecting novel *** addressing the primary challenges in AI-driven healthcare systems,including privacy,reliability,and ethical data management,our approach exemplifies the importance of AI to enhance security and trust in IoMT-enabled healthcare.

关键词： Healthcare Internet of Medical Things artificial intelligence deep learning intrusion detection system

来源：评论

学校读者我要写书评

暂无评论

FAMMNPB: design of an Enhanced Forensic Analysis Model with Multidomain Feature Extraction and Advanced Neural Architecture for Permissioned Blockchains 9

FAMMNPB: Design of an Enhanced Forensic Analysis Model with ...

引用

9th IEEE International Conference for Convergence in Technology, I2CT 2024

作者： Mate, Ashwini Y. Khandare, Kiran S. Hassan, Mohammad Bode, Kiran Nikesh Bode, Nikesh S. Missal, Karishma K. Nagpur India Nagpur India J D College of Engineering And Technology Department of Electronics And Telecommunication Nagpur India J D College of Engineering And Technology Department of Computer Science And Engineering Nagpur India Suryodaya College of Engineering And Technology Department of Computer Science And Engineering Nagpur India J D College of Engineering And Technology Department of Information Technology Nagpur India

ISBN: (纸本)9798350394474

This work introduces a novel approach that leverages multidomain feature extraction coupled with a 1d Convolutional Neural Network (CNN) for robust anomaly detection. To address the challenge of transaction delay predictions, we employ a Bi-directional Gated Recurrent Unit (BiGRU) RNN, for its capability to capture temporal sequences with high precision. For the task of chain splitting, the Teaching-learning-based Optimization (TlbO) technique is used to ensure the efficient creation of sidechains. Further, we integrated deepSHAP, in tandem with 1d CNN and BiGRU, to enhance the performance of our models, fostering better trust in the results. Our proposed methodology yields notable improvements over existing techniques. As we observed enhancements in the precision of anomaly detection by 4.9%, accuracy in detecting anomalous events by 3.5%, Recall by 4.5% and AUC by 3.9%. These advancements fortify the security posture of permissioned blockchains and optimize their operational efficacy, thus marking a significant improvement in blockchain forensics. © 2024 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Onion Crop Cultivation & Prediction of Yields by Machine learning 2

Onion Crop Cultivation & Prediction of Yields by Machine Lea...

引用

2nd International Conference on Advances in Computation, Communication and Information Technology, ICAICCIT 2024

作者： Chaudhari, dipti dhaygude, Rakhi Mulani, Umar Rane, Priyanka Khalate, Yogesh Borate, Vishal Department of Computer Engineering Pimpri Chinchwad College of Engineering and Research Pune India Department of Computer Engineering SVPM College of Engineering Maharashtra Malegoan India Department of Computer Engineering K J College of Engineering & Management Research Pune India Vasantdada Patil Pratishthan's College of Engineering & Visual Arts Sion Mumbai India Department of Computer Engineering SVPMs College of Engineering Pune Malegaon Bk India Department of Computer Engineering Dr. D. Y. Patil College of Engineering and Innovation Pune Talegaon India

ISBN: (纸本)9798331541217

The rising worldwide populace prompts the Indian government to upgrade food supply the executives for a long time to come. Reasonable farming practices are critical for guaranteeing steady food creation while protecting the climate against unsafe synthetics, accomplished through mechanical progressions in administration. This study presents a complex multi-phantom imaging framework customized for accuracy farming. Including a RGB camera and Pi NoIR camera worked by a Raspberry Pi installed a robot;this framework catches ethereal pictures for investigation. The pictures are communicated to a Java application for handling, including honing and resizing. Ongoing information is utilized to register the Standardized Contrast Vegetation Record (NdVI), working with crop wellbeing appraisal. Utilizing Profound learning (dl) strategies, the framework successfully distinguishes onion crop development stages from the gained dataset. The detail the execution of a dynamic profound brain network model for this reason. The framework exhibits a great presentation precision of 97.63% for a cluster size of 24 and 98.45% for a bunch size of 56. © 2024 IEEE.

关键词： Vegetables

来源：评论

学校读者我要写书评

暂无评论

Real-Time Implementation of Controlled Energization of Coupled Power Transformer Using Multi-Stepped PIR, Part-1

引用

Journal of The Institution of Engineers (India): Series B 2024年第3期105卷 533-540页

作者： Bhatt, K.A. Bhalja, Bhavesh R. Makwana, U.l. Macwan, F.A. Giri, A.K. Chittibabu, B. Department of Electrical Engineering L. D. College of Engineering Gujarat Ahmedabad India Department of Electrical Engineering Indian Institute of Technology Uttarakhand Roorkee India Department of Electrical Engineering Government Engineering College Gujarat Modasa India Department of Electrical Engineering Government Engineering College Gujarat Bharuch India 5Department of Electrical Engineering Indian Institute of Information Technology Design and Manufacturing Tamil Nādu Kancheepuram India

A novel concept to minimize the magnitude of inrush during the energization of unloaded power transformers using point-on-wave technique. Point-on-wave switching device (PoWd) and multi-stepped pre-insertion resistor (PIR) are presented in this article. Further, to diminish the consequences of the mechanical operating time scatter (MOTS) of the circuit breaker (CB), a combination of PoWd with a PIR-equipped CB is proposed. This combination is readily available at extra high-voltage substations in the Asia region. In the proposed work, a multi-stepped PIR is proposed to reduce the energy consumed in PIR. The suggested technique has been assessed by precise modelling of the electrically and magnetically coupled power transformer and PIR. At the same time, for optimum results, mathematical analysis has been carried out to determine the energization target of the power transformer. The comparative analysis of the suggested scheme with the existing technology has been carried out which suggests that the proposed technique minimizes the level of inrush and reduces the energy consumed by 65% and 52% during the application of PoW switching technique for energization of the magnetically and electrically connected unloaded power transformers, respectively. Moreover, the obtained results show that the power quality has been improved by large as the second harmonics and dc components of the inrush current are improved by 73.68% and 87.4%, respectively. © The Institution of Engineers (India) 2024.

关键词： Power transformers

来源：评论

学校读者我要写书评

暂无评论

Analysis of electric field strengths and focality for healthy and neurologically impaired subjects upon multiple tdCS stimulation protocols

引用

Research on Biomedical engineering 2023年第4期39卷 991-1006页

作者： Pancholi, Utkarsh dave, Vijay Biomedical Engineering Department L.D. College of Engineering Gujarat Ahmedabad India Gujarat Technological University Gujarat Ahmedabad India Biomedical Engineering Department Government Engineering College Sector-28 Gujarat Gandhinagar India

Purpose: This simulation study aims to computationally model and optimize electric field strengths and focality for temporal/frontotemporal transcranial direct current stimulation (tdCS) in cognitively normal (CN), mild cognitive impairment (MCI) and Alzheimer's disease (Ad). Methods: T1 weighted magnetic resonance imaging data for these subjects/patients were taken from Alzheimer's disease neuroimaging initiative (AdNI) and simulated for image processing, head modeling, and tdCS stimulation for generated E-field and focality using SimNIBS (Ver.3.2.5). left and right hippocampus were the target locations for stimulation in the optimization study. Temporal and frontotemporal lobes were selected to compare bio-polar stimulation and optimized stimulation. Results: With standard deviation and coefficient variance values, we identified optimization algorithms to achieve desired E-field quantity suitable for a larger group of subjects. Conclusion: Optimization technique-4 (Optimization of electric field strength) demonstrated a low variance coefficient (CN, 9;MCI, 17;and Ad, 20), indicating that it is more suitable for obtaining consistent results in larger groups. Focality exhibited significant variation among the different optimization techniques and subject groups, reflecting characteristic differences in the anatomical structure of the head for each individual. © 2023, The Author(s), under exclusive licence to The Brazilian Society of Biomedical engineering.

关键词： Neuroimaging

来源：评论

学校读者我要写书评

暂无评论

Enhancing Internet Security: A Machine learning-Based Browser Extension to Prevent Phishing Attacks

Enhancing Internet Security: A Machine Learning-Based Browse...

引用

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

作者： Prasad, d. Suhasini, S. Parthasarathy, B. Praveen, J. R.M.D. Engineering College Department Of Computer Science & Engineering Tamilnadu Kavaraipettai India

ISBN: (数字)9798350366846

ISBN: (纸本)9798350366846

Phishing attacks continue to pose a significant threat to internet users, targeting individuals across various online platforms. In response to this pervasive issue, we present a novel approach aimed at bolstering internet security through the development of a browser extension. leveraging machine learning algorithms, our extension provides real-time analysis of URls to determine their susceptibility to phishing attacks. By empowering users with the ability to identify potentially harmful websites, our solution aims to mitigate the risks associated with falling victim to phishing scams. Furthermore, our extension offers a proactive feature allowing users to contribute to a vulnerable site list, enhancing collective defence against emerging threats. Through the implementation of our browser extension, we strive to provide a robust layer of protection for users, thereby fostering a safer online environment. © 2024 IEEE.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

deep convolutional spiking neural network fostered automatic detection and classification of breast cancer from mammography images

引用

Research on Biomedical engineering 2023年第4期39卷 833-841页

作者： SenthilPrakash, T. Kannan, G. Prabhakaran, Salini Prajapati, Bhagirath Parshuram Department of Computer Science and Engineering Shree Venkateshwara Hi-Tech Engineering College Tamil Nadu Gobichettipalayam India Department of Electronics and Communication Engineering Amrita College of Engineering and Technology Nagercoil India Department of Computer Science and Engineering Puducherry Technological University Puducherry India Department of Computer Engineering A. D. Patel Institute of Technology Gujarat New Vallabh Vidyanagar India

Purpose: Breast cancer (BC) is a leading cause of death among women. Several existing methods on breast cancer classification were suggested with machine learning, but none of them accurately classify the breast cancer and requires high computational time. To overcome these problems, deep convolutional spiking neural network fostered automatic detection and classification of breast cancer from mammography images (dCSNN-BCdC-MI) is proposed in this manuscript. Methods: Initially, input breast mammography pictures are taken from digital database for Screening Mammography (ddSM) data set. The input breast mammography images are pre-processed and feature extracted. The dCSNN is employed to categorize pictures using retrieved characteristics, such as benign and malignant. Results: The proposed dCSNN-BCdC-MI technique is implemented at PYTHON. The performance of the proposed dCSNN-BCdC-MI technique attains 31.13%, 12.78%, 14.38%, 19.33%, and 19.11% high accuracy and 61.08%, 66.42%, 66.54%, 50.26%, and 53.03% low computation time comparing to the existing techniques, like deep learning fed capsule neural network for breast cancer detection utilizing mammogram images (OMlTS-dlCN-BCdC-MI), extended model for tumor location detection based on deep learning (VGG-CNN-BCdC-MI), deep learning algorithm for automated identification with breast cancer classification depending on transfer-learning strategy (VGG16-BCdC-MI), deep learning method for breast cancer identification on mammography by learning certain cancerous mass representations (CNN-deep AE-BCdC-MI), and automatic identification with mammograms classification dependent on increased extreme learning machine along deep learning (ICS-ElM-BCdC-MI), respectively. Conclusion: The simulation result exemplifies that the proposed method can be capable to determine the optimum global solutions efficiently with the exact existing methods. © 2023, The Author(s), under exclusive licence to The Brazilian Society of Biomedical Enginee

关键词： Mammography

来源：评论

学校读者我要写书评

暂无评论

A Novel Method for Human MRI Based Pancreatic Cancer Prediction Using Integration of Harris Hawks Varients & VGG16: A deep learning Approach

引用

Informatica (Slovenia) 2023年第1期47卷 115-130页

作者： Chegireddy, Rama Prakasha Reddy SriNagesh, A. Department of Computer Science and Engineering D.r. Y.S.R ANU College of Engineering and Technology Acharya Nagarjuna University Andhra Pradesh Guntur India Department of Computer Science and Engineering RVR&JC College of Engineering Andhra Pradesh Guntur India

Among all cancers, pancreatic cancer has a very poor prognosis. Early diagnosis, as well as successful treatment, are difficult to achieve. As the death rate is increasing at a rapid rate (47,050 out of 57650 cases), it is of utmost importance for medical experts to diagnose PC at earlier stages. The application of deep learning (dl) techniques in the medical field has revolutionized so much in this era of technological advancement. An analysis of clinical proteomic tumor data provided by the Clinical Proteome Tumor Analysis Consortium Pancreatic ductal Adenocarcinoma (CPTAC-PdA) at the National Cancer Institute was used to demonstrate an innovative deep learning approach in this study. This includes a) collection of data b) preprocessed using ClAHE and BAdF techniques for noise removal and image enhancement, c) segmentation using UNet++ for segmenting regions of interest of cancer. Followed by, d) feature extraction using HHO based on CNN and e) feature selection using HHO based on BOVW for extracting and selecting features from the images. Finally, these are subject to the f) classification stage for better analysis using the VGG16 network. Experimental results are carried out using various state-of-art models over various measures in which the proposed model outperforms with better accuracy:0.96, sensitivity:0.97, specificity:0.98, and detection rate:0.95. © 2023 Slovene Society Informatika. All rights reserved.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Text classification using similarity measure and fuzzy function concept analysis

Text classification using similarity measure and fuzzy funct...

引用

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

作者： Selvi, S. Thilagavathy, A. Shobarani, P. Julian, Anitha lakshmi Haritha, M. Therasa, P.R. Department of Computer Science and Engineering R.M.K. Engineering College Tamil Nadu Chennai India Department of Computer Science and Engineering R.M.D. Engineering College Tamil Nadu Chennai India Department of Computer Science and Engineering Saveetha Engineering College Tamil Nadu Chennai India

ISBN: (纸本)9781032669663

Text Classification during the retrieval of web documents is one of the most challenging tasks in the field of Query Processing. The query processor retrieves a large amount of documents in very less time that contain the query terms. Understanding and categorizing these texts is difficult in the field of Web content mining. This paper aims in categorizing the query terms and retrieving only relevant documents by performing an analysis of term pairs using Fuzzy Function Concept lattice. In our contribution, terms are grouped using Fuzzy Function Concept analysis (FFCA). Our proposed method uses the conceptual relation for term classification, thereby reducing the time of retrieving relevant documents. Hence a user can avoid wasting his resource in retrieving irrelevant information during his Search process. © 2024, CRC Press/Balkema. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A cluster and label approach for classifying imbalanced data streams in the presence of scarcely labelled data

引用

International Journal of Business Intelligence and data Mining 2022年第4期21卷 443-464页

作者： Bhowmick, Kiran Narvekar, Meera Department of Computer Engineering D J Sanghvi College of Engineering Mumbai400056 India

Classifying imbalanced data streams is often a challenging task primarily due to the continuous flow of infinite data and due to the unavailability of class labels. The problem is two-fold when the stream is imbalanced in nature. due to the characteristics of data streams, it is impossible to store and process the data and deal with imbalance. There is a need to provide a solution that can consider the unavailability of class labels and classify the imbalanced data streams. This paper proposes a semi-supervised learning (SSl)-based model to classify scarcely labelled imbalanced data streams. A modified cluster and label SSl approach that uses expectation maximisation for clustering and similarity-based label propagation for labelling the unlabelled clusters is proposed. The model also employs a novel imbalance sensitive cluster merge technique to deal with the imbalance data. The results prove that the model outperforms standard stream classification algorithms. Copyright © 2022 Inderscience Enterprises ltd.

关键词： Classification (of information)

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：