检索结果-内蒙古大学图书馆

Design and analysis of series and parallel circuits based on plasmonic waveguides for high-performance computing devices

引用

Journal of Optical communications 2025年第1期46卷 193-200页

作者： Jain, Satyendra Choudhary, Kuldeep Kumar, Santosh Department of Electrical and Electronics & Communication Engineering DIT University Dehradun248009 India Shandong Key Laboratory of Optical Communication Science and Technology School of Physics Science and Information Technology Liaocheng University Shandong Liaocheng252059 China

Nowadays, mental-insulator-metal (MIM) waveguides are widely used in the design of optical plasmonic waveguides due to their superior ability to confine surface plasmons up to sub wavelength scale. This research proposes the design of series and parallel circuits using cascaded plasmonic Mach-Zehnder interferometers (PMZIs). Each PMZI employs a nonlinear arm to switch light across the output port via the insertion of the nonlinear Kerr material poly(2-methoxy-5-(28-ethylhexyloxy)-PPV). The proposed design is having footprint of 104 μm × 11 μm. The finite-difference time-domain method is used to study, design, and analysis all optical series and parallel circuit proposals. © 2022 Walter de Gruyter GmbH, Berlin/Boston.

关键词： Metal insulator boundaries

来源：评论

学校读者我要写书评

暂无评论

Automated liver segmentation from CT images using modified ResUNet

Gastroenterology and Endoscopy

引用

Gastroenterology and Endoscopy 2025年第2期3卷 93-104页

作者： Manjunath, R.V. Gowda N, Yashaswini Manu, H.M. Department of Electronics & Communication Engineering Dayananda Sagar Academy of Technology and Management Karnataka Bangalore 82 India Department of Electronics & Communication Engineering Dayananda Sagar College of Engineering Karnataka Bangalore-78 India

The Segmentation of liver from computed tomography (CT) images is a critical task in medical research particularly when employing deep learning methods. Most doctors prefer to use Computed tomography images for liver disease identification hence automatic liver segmentation plays a decisive role. To perform automatic segmentation of liver popular architectures such as modified ResUNet are specifically designed to capture multi-resolution features. In this study we proposed an automatic system that utilizes convolutional layers to efficiently extract features while maintaining spatial information. A modified Residual UNet model was developed for liver segmentation using the 3Dircadb dataset, the model demonstrated excellent performance by achieving a Dice Score of 93.08 %, accuracy of 98.57 %, Jaccard Index of 87.12 %, a volumetric overlap error of 12.87 %, and a relative volume difference of 14.91 % on 128x128 size images. These results highlight the effectiveness of the proposed method. The primary goal of this research is to apply deep learning techniques for liver segmentation and assess the model's performance using segmentation metrics. © 2025 The Authors

关键词： 128x128 Computed tomography Liver segmentation Resnet ResUNet Volumetric overlapping error

来源：评论

学校读者我要写书评

暂无评论

LOBO Optimization-Tuned Deep-Convolutional Neural Network for Brain Tumor Classification Approach

引用

Journal of Shanghai Jiaotong university(Science) 2025年第1期30卷 107-114页

作者： A.Sahaya Anselin Nisha NARMADHA R. AMIRTHALAKSHMIT.M. BALAMURUGAN V. VEDANARAYANAN V. School of Electrical and Electronics Sathyabama Institute of Science and TechnologyChennaiTamil Nadu600119India Department of Electronics and Communication Engineering SRM Institute of Science and TechnologyRamapuram CampusChennaiTamil Nadu600089India

The categorization of brain tumors is a significant issue for healthcare *** and timely identification of brain tumors is important for employing an effective treatment of this *** tumors possess high changes in terms of size,shape,and amount,and hence the classification process acts as a more difficult research *** paper suggests a deep learning model using the magnetic resonance imaging technique that overcomes the limitations associated with the existing classification *** effectiveness of the suggested method depends on the coyote optimization algorithm,also known as the LOBO algorithm,which optimizes the weights of the deep-convolutional neural network *** accuracy,sensitivity,and specificity indices,which are obtained to be 92.40%,94.15%,and 91.92%,respectively,are used to validate the effectiveness of the suggested *** result suggests that the suggested strategy is superior for effectively classifying brain tumors.

关键词： brain tumor magnetic resonance imaging deep learning deep-convolutional neural network classifier LOBO optimization

来源：评论

学校读者我要写书评

暂无评论

A Coherent Analytical Model to Strengthen Vehicular communication in VANET Using Droptail Priority Queue

引用

Journal of The Institution of Engineers (India): Series B 2025年 1-12页

作者： Kumar, Satyam Sinha, Bam Bahadur Khare, Priyank Electronics and Communication Engineering Indian Institute of Information Technology Ranchi Jharkhand Ranchi834004 India Computer Science and Engineering National Institute of Technology Sikkim Sikkim Ravangla737139 India

People’s demand for vehicles has been increasing day by day over the last few decades. A survey tells us that over 50,000 vehicles run on the roads per day. Such a large number of vehicles causes traffic. A survey tells us that over 1200 road crashes occur everyday in India out of which 25% result in deaths. Most of these accidents occur due to a lack of communication between the vehicles. This has led to the attraction of researchers towards the Vehicular Ad Hoc Network (VANET) ensuring road safety by establishing an Intelligent Transportation System (Malhi in Comput Secur 89:101664, 2020). In VANET, due to the frequent movement of vehicles and rapid variations in topology, the communication link between vehicles may break. This paper analyzes these problems and comes up with a novel approach to overcome these and maintain the performance of the protocol. In order to assess the performance metrics for the proposed protocol, an analytical model has been created. Simulations have been carried out to validate it and have been compared against similar state of comparative methods. © The Institution of Engineers (India) 2025.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Optimized graph transformer with molecule attention network based multi class attack detection framework for enhancing privacy and security in WSN

引用

Multimedia Tools and Applications 2025年第15期84卷 14273-14304页

作者： Anoop, M. Mary, L. William Wilson, Allan J. Kiran, W.S. Department of Computer Science and Application SRM Institute of Science and Technology Ramapuram campus Chennai600089 India Department of Electronics and Communication Engineering Amrita College of Engineering and Technology Nagercoil India

In today's rapidly evolving network landscape, cybersecurity has become increasingly crucial. However, wireless sensor networks face unique challenges due to their limited resources and diverse composition, high computational demands, diminished accuracy rates, making them susceptible to a wide array of cyber threats. To tackle these challenges, this research introduced a novel method known as Optimized Graph Transformer with Molecule Attention Network (OGTMAN) on the fusion of Secure Multi-party Computation (SMC) and differential privacy aimed at enhancing privacy and security. This approach starts with data preprocessing, employing min–max normalization to address dataset imbalances. N-Tuple Contrastive Learning with Generative transformer(N-TCLG)feature extractor distinguish between different classes of data instances and effectively learns representations that capture relevant information about network traffic patterns Further, feature selection by enhanced chi-square statistics with kepler algorithm, is utilized to assess the significance of each feature in characteristic between normal network behavior and malicious activities further refines the feature selection method by optimizing the selection criteria based on the statistical properties of the dataset. Finally, the proposed OGTMAN classifies various attacks based on their behavioural patterns with the help of enhanced ant aphid optimization with adaptive step factor. Ultimately, this fine-tuning yield superior model training outcomes, resulting more accurate attack classification outcomes. To evaluate the effectiveness of this approach, datasets encompassing with KDD Cup 99 datasets are employed. The efficiency of the introduced method is demonstrated when compared with prevailing attack detection methods in terms of accuracy, recall, precision and F-measure of 99.98%, 99.5%.,99.9% and 99.5% respectively. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer N

关键词： Molecules

来源：评论

学校读者我要写书评

暂无评论

Sign Language Recognition with Image Processing using Deep Learning LSTM Model

Sign Language Recognition with Image Processing using Deep L...

引用

2025 IEEE International Students' Conference on Electrical, electronics and Computer Science, SCEECS 2025

作者： Alaimahal, A. Vasuki, S. Harini, T.P. Niranjana, B. Lavaniya, M. Velammal College of Engineering and Technology Dept. of Electronics and Communication Engineering Madurai India

ISBN: (数字)9798331529833

ISBN: (纸本)9798331529833

In contemporary society, effective communication remains a cornerstone of human interaction. However, bridging the communication gap presents significant challenges for individuals who are mute or unable to communicate through conventional means, such as sign language. This paper proposes a novel solution leveraging the power of Deep Learning (DL) techniques, specifically Long Short-Term Memory (LSTM) networks, to address this issue. Our approach focuses on predicting and detecting actions performed by mute individuals based on sequential frames of interactions. This innovative application of DL and LSTM technologies not only provides a practical solution for overcoming communication barriers but also contributes to advancing inclusive technologies. Through meticulous analysis and training, the DL-LSTM model achieves an impressive 98% accuracy in both action prediction and detection. This work underscores the transformative potential of artificial intelligence in facilitating empathetic and inclusive communication practices, ultimately enriching the fabric of human connection in diverse societal contexts. © 2025 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Contrastive Learning for Personalized Cardiovascular Risk Prediction from Multi-Lead ECG Signal 2

Contrastive Learning for Personalized Cardiovascular Risk Pr...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Kumar, Santosh Saranya, M. Dheepak, G. Muniraj, Ashokkumar Baalakumar, N.N. Pradeep, K.K. New Horizon College of Engineering Department of Computer Science and Engineering Bengaluru560103 India Department of Electronics and Communication Engineering Karur639113 India Rajalakshmi Institute of Technology Department of Electronics and communication Engineering Chennai600124 India Department of Electronics and Communication Engineering Hosur635109 India Sona college of technology Department of Biomedical Engineering Salem636005 India Velalar College of Engineering and Technology Department of Electronics and communication Engineering Erode638012 India

ISBN: (纸本)9798331505745

Despite multiple efforts, cardiovascular diseases (CVDs) still top the list of leading causes of mortality worldwide and require early and personalised risk prediction strategies. Current ECG based risk assessment models are limited to generalizing to varying patient populations and suffer poor interpatient variability. The contribution of this paper is a personalized cardiovascular risk prediction from multi lead ECG signals using a contrastive learning framework. The model learns robust patient specific representations via a self-supervised learning technique that does not require large amounts of labeled data. The deep neural network trained with the contrastive loss function effectively discriminates high and low risk ECG patterns by maximizing the similarity of positive pairs (ECG signals from the same patient or similar risk profile) and minimizing negative pair similarity. Evaluation of the proposed approach is carried out on publicly available ECG datasets resulting in better predictive performance than traditional supervised learning methods. Improved generalization obtained with this framework makes it a promising early diagnosis and personalized cardiovascular health monitoring tool. © 2025 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

DESIGN AND ANALYSIS OF A SLOTTED PLANAR ANTENNA WITH PARASITIC RING PATCH FOR EFFICIENT 5G MICROWAVE APPLICATIONS

引用

Telecommunications and Radio engineering (English translation of Elektrosvyaz and Radiotekhnika) 2025年第1期84卷 71-82页

作者： Yadav, Swati Varun Yadav, Manish Varun Gupta, Ridhi Yadav, Dinesh Bhati, Kirti Panwar Ali, Tanweer Singh, Vikas Department of Instrumentation and Control Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal Karnataka India Department of Aeronautical and Automobile Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal Karnataka India Department of Electronics and Communication Engineering Manipal University Jaipur Rajasthan Jaipur India School of Electronics Devi Ahilya University M.P Indore India Department of Electronics and Communication Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal Karnataka India

Design and analysis of a slotted planar antenna with a parasitic ring patch for efficient 5G microwave applications is presented. The antenna design aims to strike a balance between complexity and size efficiency. Its front side features a rectangular patch at the center, comprising L-shaped, T-shaped, and inverse T-shaped elements, alongside four parasitic rings on top. The central feed utilizes a 50-ohm strip line connected to a microstrip line. On the back side, the antenna incorporates three parasitic rings on top, four horizontal strips arranged in an increasing order, and a ground plane with a small rectangular slot. To evaluate its performance, the antenna is simulated using CST Microwave Studio on an FR-4 substrate with overall dimensions measuring 13 × 15 × 1.5 mm3. The results demonstrate an impressive impedance bandwidth of 60.8% and a return loss of –28 dB within the frequency range of 3.2–6 GHz, with a central frequency of 4.6 GHz. Throughout its operational range, the radiation patterns remain constant, exhibiting stable polar patterns and efficient performance with a wide gain of 4.81 dBi and an efficiency of 82%;the proposed antenna proves to be suitable for 5G microwave applications. © 2025 by Begell House, Inc.

关键词： Microwave antennas

来源：评论

学校读者我要写书评

暂无评论

Social Media-Based Travel Planning: Integrating Content-Based and Collaborative Filtering for Personalized Suggestions

Social Media-Based Travel Planning: Integrating Content-Base...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Naveen, S. Raikumar, G. Vinoth Krishnan, R. Santhana Umesh, R. Blessie, A. Alice Paulraj, Kruthika Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Mechanical Engineering Chennai India J.P. College of Engineering Department of Electronics and Communication Engineering Tenkasi India Scad College of Engineering and Technology Department of Electronics and Communication Engineering Cheranmahadevi India Velammal College of Engineering and Technology Department of Information Technology Madurai India Government College of Engineering Department of Electronics and Communication Engineering Tirunelveli India Sona College of Technology Department of Information Technology Salem India

ISBN: (纸本)9798331509828

This research presents a data-driven approach for providing personalized travel and stay recommendations by integrating social media data., machine learning models., and time-series analysis. Data is collected from social media platforms using APIs., including textual data (captions., hashtags., and comments)., multimedia data (images and videos)., and engagement metrics (likes.,shares., and comments). Textual data is preprocessed using advanced NLP techniques such as BERT for keyword extraction and TextBlob for sentiment analysis., while multimedia data is classified using a pre-trained ResNet model. A comprehensive user travel history is built from geotags and timestamps., and seasonal travel patterns are analyzed using Prophet. User preferences are derived by combining engagement metrics., sentiment scores., and multimedia classification results. Unexplored destinations are identified using K-Means clustering., and similarity scores are computed using cosine similarity between user preferences and destination features. Recommendations for destinations and accommodations are generated using content-based filtering and collaborative filtering with Singular Value Decomposition (SVD). This integrated system ensures context-aware., relevant., and personalized travel and stay suggestions based on user interests and travel history. © 2025 IEEE.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Precision Measurement of Thin Dielectric Coatings on CFRP Composites Using Microwave-Based CSRR Sensors for Aerospace Applications

引用

Progress in Electromagnetics Research B 2025年 111卷 99-110页

作者： Ambika, Arunachalam Tharini, Chandrapragasam Chakraborty, Paransree Lohar, Fateh L. Prabhu, S. Sadhish Arjun, Kanakam K. Muzzammil, Kader J. Mohamed Department of Electronics and Communication Engineering B.S. Abdur Rahman Crescent Institute of Science and Technology TamilNadu India Engineering College Bharatpur Rajastan India

This project proposal addresses the critical need for precise measurement of thin dielectric coatings, which are essential in industries such as aviation, aerospace, and automotive for enhancing structural integrity and protecting against environmental factors. Manual application of these coatings often results in uneven thickness, necessitating a streamlined measurement method. Leveraging advancements in microwave technology, particularly the use of complementary split ring resonators (CSRR), this project introduces a novel measurement approach for coatings on Carbon Fiber Reinforced Polymer (CFRP) composites. By employing electric field coupling of a leaky wave antenna between a cylindrical dielectric-loaded sensor and the coatings on CFRP through a double circular ring slot, the method identifies a correlation between resonance frequency and coating thickness. The cavity is integrated with a Vector Network Analyzer (VNA) to detect S11 peaks at the resonance frequency, enabling precise measurement. Initial design comparisons using CST software resulted in a sensor antenna with optimal impedance matching and sensitivity, which was subsequently fabricated and tested in a microwave lab. Remaining objectives include developing a 4th-order regression model to predict coating thickness ranging from 0 to 2 mm for Polyethylene Terephthalate (PET) on CFRP composites and validating the method for industrial applications in aero-engine parts, gas turbines, and automotive structures. Future enhancements will focus on refining the technique for very thin coatings and exploring drone-based inspection methods for comprehensive aircraft analysis. This innovative approach promises a reliable solution for measuring coating thickness, which is crucial for maintaining the performance and safety of advanced composite materials. © (2025), (Electromagnetics Academy). All rights reserved.

关键词： Carbon phenolic composites

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：