检索结果-内蒙古大学图书馆

2024 International Conference on Brain computer Interface and Healthcare Technologies, iCon-BCIHT 2024

作者： Tojo, Laya Devi, Manju Sujith, Annie The Oxford College of Engineering Department of Electronics & Communication Communication Bengaluru India Jyothy institute of Technology Department of Computer Science & Engineering Bengaluru India

ISBN: (纸本)9798331540067

In this paper we propose a Multi-resolution Dual Convolutional Neural Network (MR-DCNN) which is used to denoise the images. By incorporating sparse mechanism in dual networks, implementing a 2-tier architecture and by downscaling the width and height of CNN layers, we could reduce the computational complexity and achieve better performance and speed. The observed values prove that the novel MR-DCNN method can upgrade the visual quality without even compromising on PSNR, SSIM and MSE values. The suggested MR DCNN method outperforms numerous modern image enhancing techniques, based on objective and subjective results. Later, we propose the MR-DCNN method to boost the visual quality of low contrast retinal images. The MR-DCNN incorporated helps to enhance the visual quality by denoising the images and also removing fading effects. This novel formulation attains further improvement than existing schemes, and proves significant development in PSNR, SSIM and MSE values and visual quality perception. The presented scheme enhances the retinal image quality by improving the clarity. The MR-DCNN approach could deliver ophthalmologists with novel strategies to rectify retinal diseases from fundus images. This will lessen the amount of manual grading required, which will assist to cut down on pointless, expensive referrals. © 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

Sorting of Fresh and Damaged Apple Fruits using Machine learning Approach 5

Sorting of Fresh and Damaged Apple Fruits using Machine lear...

引用

5th IEEE International Conference for Emerging technology, INCET 2024

作者： Ghodeswar, Ujwala Puri, Chetan Shingade, Sharvari Waware, Teena Ladhe, Ajinkya Durge, Tejas Department of Electronics Engineering Yeshwantrao chavan College of Engineering Nagpur India Department of Computer Science & Design Faculty of Engineeering & Technology Wardha India

ISBN: (纸本)9798350361155

The research investigates how machine learning algorithms and Internet of Things (IoT) technologies might be combined to solve the crucial problem of separating fresh fruits from damaged apple fruits. Using Internet of Things (IoT) devices with sensors, the system collects extensive data on important characteristics, such as real-time apple picture analysis and available apple database. Convolutional neural networks (CNNs) and YOLO are two examples of sophisticated machine learning models that are used with this data to accurately classify the apples into different groups according to their quality. This initiative fosters enhanced efficiency, production, and profitability in the agricultural supply chain while providing a sustainable solution to the problems connected with fruit sorting. It represents a synergistic convergence of IoT, machine learning, and agriculture. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Intelligent Decision-Making in Cybersecurity Using Machine Learning 12th

Intelligent Decision-Making in Cybersecurity Using Machine L...

引用

12th International Conference on Frontiers of Intelligent Computing: Theory and Applications, FICTA 2024

作者： Sakhare, Nitin N. Maruthi Shankar, B. Kalnawat, Aarti Sharma, Abha Rege, P.R. Wagh, Kapil Adhar Department of Computer Engineering BRACT’s Vishwakarma Institute of Information Technology Maharashtra Pune India Department of Electronics and Communication Engineering Sri Krishna College of Engineering and Technology Tamil Nadu Coimbatore India Pune India Electronics and Communication Engineering Arya College of Engineering Rajasthan Jaipur India Department of Computer Engineering Vishwakarma Institute of Information Technology Maharashtra Pune India Nutan Maharashtra Institute of Engineering and Technology Maharashtra Pune India

ISBN: (纸本)9789819601462

In the constantly changing field of cybersecurity, the need for advanced decision-making tools is more crucial than ever. This study explores machine learning in order to introduce an innovative method for strengthening cybersecurity protocols. The methodology involves combining Random Forests (RF) and Support Vector Machines (SVM) using the AdaBoost algorithm in an ensemble framework. The ensemble model is intricately crafted to address the complexities of intrusion detection, utilizing the combined capabilities of Random Forest’s data handling and Support Vector Machine’s pattern discrimination. AdaBoost enhances the ensemble’s predictive abilities by iteratively adjusting weights to focus more on misclassified instances. This adaptive learning process enables the model to constantly develop and adjust to new cyber threats. Validation against benchmark datasets demonstrates an impressive accuracy rate of 97.78%, highlighting the strength of the ensemble methodology. The True Positive Rate (TPR) of 98.33% demonstrates the ensemble’s effectiveness in accurately detecting and responding to potential cyber threats. The results demonstrate the superior performance of the proposed ensemble method and highlight its ability to achieve a balance between accuracy and adaptability. This research significantly advances intelligent decision-making in cybersecurity by introducing a potent ensemble approach that smoothly integrates various machine learning algorithms. The method’s proven accuracy and sensitivity make it a powerful tool in combating the increasing complexity of cyber threats. The combination of RF, SVM, and AdaBoost sets a standard for future research in strengthening digital defenses and ensuring the resilience of critical information systems. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach Based on Hybrid Algorithm for Energy Efficient Cluster Head Identification in Wireless Sensor Networks

引用

computer Systems Science & engineering 2022年第10期43卷 259-273页

作者： C.Ram Kumar K.Murali Krishna Mohammad Shabbir Alam K.Vigneshwaran Sridharan Kannan C.Bharatiraja Department of Electronics and Communication Engineering Dr.N.G.P.Institute of TechnologyCoimbatore641048India Department of Electronics and Communication Engineering Vignan’s Institute of Information TechnologyDuvvadaVisakhapatnam530049India Department of Computer Science College of Computer Science and Information TechnologyJazan UniversityJizan45142Kingdom of Saudi Arabia Department of Electronics and Communication Engineering K.Ramakrishnan College of EngineeringTiruchirappalli621112India Department of Computer Science and Engineering JKK Munirajah College of TechnologyErode638506India Department of Electrical and Electronics Engineering SRM Institute of Science and TechnologyChennai603203India

The Wireless Sensor Networks(WSN)is a self-organizing network with random deployment of wireless nodes that connects each other for effective monitoring and data *** clustering technique employed to group the collection of nodes for data transmission and each node is assigned with a cluster *** major concern with the identification of the cluster head is the consideration of energy consumption and hence this paper proposes an hybrid model which forms an energy efficient cluster head in the Wireless Sensor *** proposed model is a hybridization of Glowworm Swarm Optimization(GSO)and Artificial Bee Colony(ABC)algorithm for the better identification of cluster *** performance of the proposed model is compared with the existing techniques and an energy analysis is performed and is proved to be more efficient than the existing model with normalized energy of 5.35%better value and reduction of time complexity upto 1.46%.Above all,the proposed model is 16%ahead of alive node count when compared with the existing methodologies.

关键词： Wireless sensor network cluster cluster head hybrid model glowworm swarm optimization artificial bee colony algorithm energy consumption

来源：评论

学校读者我要写书评

暂无评论

Brain Imaging and GRU-CNN Hybrid Framework for Alzheimer's Disease Progression Analysis 4

Brain Imaging and GRU-CNN Hybrid Framework for Alzheimer's D...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Selvam, L. Dhamotharan, R. Krishnan, R. Santhana Francis Raj, J. Relin Sankar, G. Ram Yamini, G. Srm Madurai College for Engineering and Technology Department of Computer Science and Engineering Pottapalayam Sivaganga India Kalasalingam Academy of Research and Education Department of Computer Science and Information Technology Krishnankoil India Scad College of Engineering and Technology Department of Electronics and Communication Engineering Cheranmahadevi India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Electronics and Communication Engineering Chennai India Velammal College of Engineering and Technology Department of Computer Science and Engineering Madurai India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Avadi Department of English Chennai India

ISBN: (纸本)9798331523923

Alzheimer's disease detection and classification using deep learning techniques offer significant advancements in early diagnosis and progression analysis of this neurodegenerative disorder. This approach leverages various medical imaging modalities such as MRI, PET, CT, and fMRI, alongside clinical data like cognitive test results and biomarkers, to assess brain changes associated with Alzheimer's. The focus is on classifying the disease into three stages: Mild, Moderate, and Severe, using advanced machine learning models. Deep learning techniques, such as EfficientNet B7 for 2D imaging and 3D CNNs for volumetric data, enable efficient feature extraction from medical scans. Additionally, Recurrent Neural Networks (RNNs) with GRU layers are used to capture temporal patterns from longitudinal data, improving predictive accuracy. Hybrid models, combining CNNs with attention mechanisms, further enhance classification. The model uses a multi-class classification approach with Softmax activation to predict the likelihood of each stage of Alzheimer's disease. Performance evaluation includes key metrics such as accuracy, precision, recall, F1 score, and AUC (Area Under the Curve). AUC can be calculated in two ways: individual AUC scores for each disease stage or a combined AUC for overall classification. This analysis provides a comprehensive understanding of the model's effectiveness in distinguishing between different stages of Alzheimer's. The results can be integrated into clinical workflows to assist healthcare professionals in diagnosing and monitoring Alzheimer's disease progression, offering a potential path toward more efficient and early intervention strategies. © 2025 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Smart Home Automation with Smart Metering Using ZigBee technology and Deep Belief Networks - Optimization Using MB-ABCOA Algorithm 2

Smart Home Automation with Smart Metering Using ZigBee Techn...

引用

2nd IEEE International Conference on Contemporary Computing and Communications, InC4 2024

作者： Navaz, K. Mano Raja Paul, M. Yamuna Bee, J. Kavitha, S. Bhuvanesh, A. Mariappan, R. Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering Chennai India Nehru Institute of Engineering and Technology Department of Electrical and Electronics Engineering Coimbatore India PSN College of Engineering and Technology Department of Computer Science and Engineering Tirunelveli India Sri Eshwar College of Engineering Department of English Tamil Nadu Coimbatore India PSN College of Engineering and Technology Department of Electrical and Electronics Engineering Tirunelveli India

ISBN: (纸本)9798350383652

In the domain of smart homes and smart metering, ZigBee technology plays a pivotal role within the energy efficiency of homes, albeit facing challenges such as packet transmission delays and uneven energy consumption among nodes. To address these issues while emphasizing energy efficiency, we propose the Energy-efficient ZigBee Directionally Opportunistic Short-cut Trees Routings (EP-ZDOSTR), which optimizes network lifetimes and throughput by prioritizing energy-efficient packet transmission. Complemented by a hybrid Monarchy Butterfly and Artificial Bees Colonies Optimizations Algorithms (MB-ABCOA) approach, EP-ZDOSTR demonstrates significant improvements in network performances metric, including higher throughputs, increased packet delivery ratios, reduced transmission delays, and minimized energy consumption. Comparisons with existing methods like ZigBee shortcut tree routing (ZSTR), ZigBee opportunistic shortcut tree routing (ZOSTR), and Energy Efficient shortcut tree routing (EPSTR) validate its superiority in enhancing overall network efficiency and reliability. Furthermore, integrating ZigBee with Deep Belief Networks (DBNs) holds promise for further enhancing network intelligence, enabling predictive analysis of energy usage patterns and optimization of network operations, thereby advancing the capabilities of smart home in the context of smart homes and metering systems within the IoT landscape. © 2024 IEEE.

关键词： Zigbee

来源：评论

学校读者我要写书评

暂无评论

Robust Deep Transfer Learning Based Object Detection and Tracking Approach

引用

Intelligent Automation & Soft Computing 2023年第3期35卷 3613-3626页

作者： C.Narmadha T.Kavitha R.Poonguzhali V.Hamsadhwani Ranjan walia Monia B.Jegajothi Electronics and Communication Engineering Periyar Maniammai Institute of Science&Technology(PMIST)Thanjavur613403India Department of Computer Science and Engineering Periyar Maniammai Institute of Science&TechnologyThanjavur613403India Department of Electrical and Electronics Engineering Periyar Maniammai Institute of Science and TechnologyThanjavur613403India Electrical Engineering Department Model Institute of Engineering&Technology(Autonomous)Jammu181122India Department of Computer Science and Engineering Shri Mata Vaishno Devi UniversityKatra182320India Center for Energy Research Chennai Institute of TechnologyChennai600069India

At present days,object detection and tracking concepts have gained more importance among researchers and business ***,deep learning(DL)approaches have been used for object tracking as it increases the perfor-mance and speed of the tracking *** paper presents a novel robust DL based object detection and tracking algorithm using Automated Image Anno-tation with ResNet based Faster regional convolutional neural network(R-CNN)named(AIA-FRCNN)*** AIA-RFRCNN method performs image anno-tation using a Discriminative Correlation Filter(DCF)with Channel and Spatial Reliability tracker(CSR)called DCF-CSRT *** AIA-RFRCNN model makes use of Faster RCNN as an object detector and tracker,which involves region proposal network(RPN)and Fast *** RPN is a full convolution network that concurrently predicts the bounding box and score of different *** RPN is a trained model used for the generation of the high-quality region proposals,which are utilized by Fast R-CNN for detection ***,Residual Network(ResNet 101)model is used as a shared convolutional neural network(CNN)for the generation of feature *** performance of the ResNet 101 model is further improved by the use of Adam optimizer,which tunes the hyperparameters namely learning rate,batch size,momentum,and weight ***,softmax layer is applied to classify the *** performance of the AIA-RFRCNN method has been assessed using a benchmark dataset and a detailed comparative analysis of the results takes *** outcome of the experiments indicated the superior characteristics of the AIA-RFRCNN model under diverse aspects.

关键词： Object detection tracking deep learning deep transfer learning image annotation

来源：评论

学校读者我要写书评

暂无评论

Highly sensitive optical biosensor based on electromagnetically induced transparency in a graphene-dielectric metasurface

引用

Optical and Quantum electronics 2025年第4期57卷 1-17页

作者： Bagheritabar, Mohsen Molaei Zarasvand, Mahdi Yazdani, Afsoon Molaei Zarasvand, Melika Salemizadeh Parizi, Mohammad Bahadori-Haghighi, Shahram Department of Electrical Engineering University of Cincinnati CincinnatiOH45221-0030 United States Department of Electrical and Computer Engineering Clemson University ClemsonSC29634 United States Department of Electrical and Computer Engineering K. N. Toosi University of Technology Tehran Iran Department of Electrical Engineering Sharif University of Technology Tehran Iran Department of Biomedical Engineering Georgia Institute of Technology Emory University AtlantaGA30332 United States Department of Communication and Electronics Engineering Shiraz University Shiraz Iran

In this paper, a graphene-dielectric metasurface is proposed for effective optical biosensing. The structure is composed of a periodic array of double-slit split-ring resonators (SRRs) adjacent to silicon bars over a sheet of graphene and silicon dioxide substrate. Interactions between electric dipoles (bright modes) in silicon bars and magnetic dipoles (dark modes) excited in SRRs lead to a high quality factor resonance based on the phenomenon of electromagnetically induced transparency (EIT). High electric field confinement is achieved within the two gaps of SRRs at the resonance frequency, which result in strong light-analyte interaction. The structural parameters of the proposed metasurface are optimized to achieve the best performance. The biosensor is analyzed using the finite-element method (FEM) and the results are presented. Owing to the high Q-factor EIT resonance and the enhanced light-matter interaction inside the gaps, a high sensitivity of 496 nm/RIU and figure-of-merit (FOM) of as high as 741 RIU−1 are achieved that are higher than those reported in recently published works. The resolution and the linearity R2 value of the proposed biosensor are calculated to be 2.02e-4 and 0.999, respectively. The reported characteristics could be promising for sensing of various biomolecules such as hemoglobin. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Q factor measurement

来源：评论

学校读者我要写书评

暂无评论

Securing IoT Systems with AI-Infused Software and Virtual Replica Models 2

Securing IoT Systems with AI-Infused Software and Virtual Re...

引用

2nd IEEE International Conference on Integrated Intelligence and Communication Systems, ICIICS 2024

作者： Supriya, K. Sangeetha Jeno Lovesum, S.P. Arora, Renuka Bhatia, Rishu Yadwad, Sunita Natrayan, L. Department of Computer Science & Engineering Christ University Bengaluru India Department of Computer Science & Engineering Jagannath University NCR Bahadurgarh India Department of Electronics and Communication Engineering Ganga Institute of Technology and Management Jhajjar India Department of Computer Science and Engineering Faculty of Engineering and Technology Parul institute of Engineering and Technology Parul University Vadodara India Department of Mechanical Engineering Saveetha School of Engineering SIMATS Chennai India

ISBN: (纸本)9798331504960

The proliferation of Internet of Things (IoT) devices has introduced significant security challenges due to the increased attack surface and the inherent vulnerabilities of interconnected systems. This paper proposes a novel security framework that integrates Artificial Intelligence (AI)-infused software and Virtual Replica Models, or Digital Twins, to enhance the robustness of IoT systems. The framework leverages AI-driven anomaly detection and predictive analysis to identify potential threats in real-time, while Digital Twins provide a virtual replica of the IoT ecosystem for continuous monitoring and simulation-based threat assessment. By fusing these technologies, the proposed solution enables proactive security measures, ensuring rapid response to cyberattacks and continuous system optimization. Extensive simulations and experimental results demonstrate the system’s ability to reduce attack detection times by 30%, while improving overall system resilience and minimizing false positive rates. This approach provides a scalable and adaptable solution for securing IoT infrastructures in various industries. © 2024 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Dipper Throated Algorithm for Feature Selection and Classification in Electrocardiogram

引用

computer Systems Science & engineering 2023年第5期45卷 1469-1482页

作者： Doaa Sami Khafaga Amel Ali Alhussan Abdelaziz A.Abdelhamid Abdelhameed Ibrahim Mohamed Saber El-Sayed M.El-kenawy Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Science Faculty of Computer and Information SciencesAin Shams University11566CairoEgypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Electronics and Communications Engineering Department Faculty of EngineeringDelta University for Science and TechnologyMansouraEgypt Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt

Arrhythmia has been classified using a variety of *** of the dynamic nature of electrocardiogram(ECG)data,traditional handcrafted approaches are difficult to execute,making the machine learning(ML)solutions more *** with cardiac arrhythmias can benefit from competent monitoring to save their *** arrhythmia classification and prediction have greatly improved in recent *** are a category of conditions in which the heart's electrical activity is abnormally rapid or *** year,it is one of the main reasons of mortality for both men and women,*** the classification of arrhythmias,this work proposes a novel technique based on optimized feature selection and optimized K-nearest neighbors(KNN)*** proposed method makes advantage of the UCI repository,which has a 279-attribute high-dimensional cardiac arrhythmia *** proposed approach is based on dividing cardiac arrhythmia patients into 16 groups based on the electrocardiography dataset’s *** purpose is to design an efficient intelligent system employing the dipper throated optimization method to categorize cardiac arrhythmia *** method of comprehensive arrhythmia classification outperforms earlier methods presented in the *** achieved classification accuracy using the proposed approach is 99.8%.

关键词： Feature selection electrocardiogram metaheuristics dipper throated algorithm

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：