检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Integrated Circuits and communication systems, ICICACS 2024

作者： Habelalmateen, Mohammed I. Archana Reddy, R. Reddy, Chetana Nagarjuna, N. Pradeep Kumar, S. Universiti Tun Hussein Onn Malaysia Parit Raja Faculty of Electrical and Electronic Engineering Johor Batu Pahat Malaysia The Islamic University College of Technical Engineering Department of Computer Technical Engineering Najaf Iraq Sr University School of Computer Science and Artificial Intelligence Telangana India Oxford College of Engineering Department of Electronics and Communication Bangalore India Cvr College of Engineering Department of Csit Hyderabad India Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Bengaluru India

ISBN: (纸本)9798350317558

In the landscape of optimization for mitigating the Peak-to-Average Power Ratio (PAPR) in Multiple-Input Multiple-Output and Orthogonal Frequency Division Multiplexing (MIMO-OFDM) systems, prevalent techniques like the tone reservation scheme and l-norm Cyclic Algorithm (LNCA) algorithm grapple with inherent challenges linked to computational complexity and iterative algorithm derivation. While strides have been made with models such as Twin Symbol Hybrid Optimization by the premise of Partial Transmit Sequence (TSHO-PTS) and Advanced Switching Differential Evolution (ASDE), persistent concerns related to symbol overlaps and algorithmic limitations underscore the need for further refinement in computational efficiency within OFDM-based communication systems. In response to these challenges, the proposed Nonlinear Inertia Weight Factor within the Whale Optimization Algorithm (NIWF-WOA) emerges as a solution. Comparative analysis against existing methods like LCNA, Modified Dragonfly Optimization algorithm (MDOA), TSHO-PTS, and ASDE reveals the superior performance of NIWF-WOA. Numerical validation affirms its efficacy, with a recorded in Bit Error Rate (BER) of 10-2.5, SNR 10-3.4 and PAPR of.10-4.2, underscoring the substantial improvement achieved by NIWF-WOA in optimizing PAPR reduction for MIMO-OFDM systems. © 2024 IEEE.

关键词： Landscape of optimization MIMO-OFDM system Non-linear weight factor Peak to Average Power Ratio Whale optimization

来源：评论

学校读者我要写书评

暂无评论

Pre-Impact and Impact Fall Detection Based on a Multimodal Sensor Using a Deep Residual Network

引用

Intelligent Automation & Soft Computing 2023年第6期36卷 3371-3385页

作者： Narit Hnoohom Sakorn Mekruksavanich Anuchit Jitpattanakul Image Information and Intelligence Laboratory Department of Computer EngineeringFaculty of EngineeringMahidol UniversityNakhon Pathom73170Thailand Department of Computer Engineering School of Information and Communication TechnologyUniversity of PhayaoPhayaoThailand Department of Mathematics Faculty of Applied ScienceKing Mongkut’s University of Technology North BangkokBangkok 10800Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Science and Technology Research Institute King Mongkut’s University of Technology North BangkokBangkok 10800Thailand

Falls are the contributing factor to both fatal and nonfatal injuries in the ***,pre-impact fall detection,which identifies a fall before the body collides with the floor,would be ***,researchers have turned their attention from post-impact fall detection to pre-impact fall ***-impact fall detection solutions typically use either a threshold-based or machine learning-based approach,although the threshold value would be difficult to accu-rately determine in threshold-based ***,while additional features could sometimes assist in categorizing falls and non-falls more precisely,the esti-mated determination of the significant features would be too time-intensive,thus using a significant portion of the algorithm’s operating *** this work,we developed a deep residual network with aggregation transformation called FDSNeXt for a pre-impact fall detection approach employing wearable inertial *** proposed network was introduced to address the limitations of fea-ture extraction,threshold definition,and algorithm *** training on a large-scale motion dataset,the KFall dataset,and straightforward evaluation with standard metrics,the proposed approach identified pre-impact and impact falls with high accuracy of 91.87 and 92.52%,*** addition,we have inves-tigated fall detection’s performances of three state-of-the-art deep learning models such as a convolutional neural network(CNN),a long short-term memory neural network(LSTM),and a hybrid model(CNN-LSTM).The experimental results showed that the proposed FDSNeXt model outperformed these deep learning models(CNN,LSTM,and CNN-LSTM)with significant improvements.

关键词： Pre-impact fall detection deep learning wearable sensor deep residual network

来源：评论

学校读者我要写书评

暂无评论

PTS-LIC: Pruning Threshold Searching for Lightweight Learned Image Compression

PTS-LIC: Pruning Threshold Searching for Lightweight Learned...

引用

2023 IEEE International Conference on Visual communications and Image Processing, VCIP 2023

作者： Luo, Ao Sun, Heming Liu, Jinming Lin, Fangzheng Katto, Jiro Yokohama National University Faculty of Engineering Kanagawa Japan Shanghai Jiao Tong University China Waseda University Department of Computer Science and Communication Engineering Tokyo Japan Waseda Research Institute for Science and Engineering Tokyo Japan

ISBN: (纸本)9798350359855

Learned Image Compression (LIC), which uses neural networks to compress images, has experienced significant growth in recent years. The hyperprior-module-based LIC model has achieved higher performance than classical codecs. However, the LIC models are too heavy (in calculation and parameter amounts) to apply to edge devices. To solve this problem, some former papers focus on structural pruning for LIC models. However, they either cause noticeable performance decrement or neglect the appropriate pruning threshold for each LIC model. These problems keep their pruning results sub-optimal. This paper proposes a Pruning Threshold Searching on the hyperprior module for different-quality LIC models. Our method removes most parameters and calculations while keeping the performance the same as the models before pruning. We removed at least 49.8% of parameters and 28.5% of calculations for the Channel-Wise-Context-Model-based models and 29.1% of parameters for the Cheng-2020 models. © 2023 IEEE.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Hyper tension Detection for Diabetic Patients using Machine Learning 14

Hyper tension Detection for Diabetic Patients using Machine ...

引用

14th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2023

作者： Saranya, S. Thilak, K. Deepa Kalaiselvi, K. Kumar, T. Rajesh Kumaresan, K. Department of Electronics and communication Engineering EaswariEngineering College Ramapuram Chennai India Tamil Nadu Kattankulathur603 203 India Department of Computer Science and Engineering Saveetha school of Engineering Saveetha University Saveetha Institute of Medical and Technical Sciences Tamilnadu Chennai India Faculty of Computer Science and Engineering KSR College of Engineering India

Hypertension is the primary wellspring of passing and cardiovascular contaminations all over the planet addressing around 15 spending consistently. Hypertension revives the development of all-cause mortality, stroke, coronary course disease, and diabetes mellitus. The improvement of diabetes among hypertensive patients is generally on different occasions more progressive than in normotensive individuals. The two hypertensions similarly as diabetes are ordinary diseases which occur at a high repeat and deal standard causes. In like manner, there arises prerequisite for development of sensible models which can perform precise assumption for hyper-strain among diabetic patients. Along these lines, diabetes is the principal wellspring of visual hindrance, renal dissatisfaction;idiocy and diabetic foot issue whose reality can cause lower-limb removals. The large scale vascular traps of diabetes integrate cardiovascular infection, for instance. Coronary disappointments, strokes and cerebrovascular contamination. The inspiration driving standard extraction is because of adhering to two reasons: 1) To decipher the arrangement performed by the fundamental non-straight black-box model;2) To work on the presentation of rule acceptance methods. Hereafter, we focus in fostering a mutt rule-based model for finding of hypertension among diabetic individuals by joining of a non-rule-based characterization estimation with a standard based computation. The potential gains of the non-rule-based calculation are solidified into the standard based approach. © Grenze Scientific Society, 2023.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Lightweight Authentication of Devices in Industrial Control systems 14

Lightweight Authentication of Devices in Industrial Control ...

引用

14th IEEE International Conference on Software engineering and Service science, ICSESS 2023

作者： Wang, Long Niu, Siqi Zhai, Henggao Fan, Jing Wang, Lei Engineering Research Institute of China National Computer System Beijing China University of Science and Technology Beijing Department of Computer and Communication Engineering Beijing China Coocaa Network Technology Co. Ltd. Guangdong China

ISBN: (纸本)9798350336269

A security authentication protocol based on number theory research unit (NTRU) for industrial control devices is proposed to address the security of data transmission in industrial control systems and the lack of resistance to attacks of security authentication protocols. Most of the original protocols contain complex encryption and decryption operations, which are difficult to run on industrial control devices with simple structures and cannot resist new types of network attacks. In this paper, the protocol takes advantage of the simple operation of NTRU public key encryption system and sets the authorization center to send only the public key of the device in a variant form to achieve the purpose of resisting new attacks such as quantum attacks and internal attacks, and the anti-attack capability is strengthened. © 2023 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

An Efficient Shortest Path Optimized Algorithm for Vehicle Adhoc Networks system 7

An Efficient Shortest Path Optimized Algorithm for Vehicle A...

引用

7th International Conference on Circuit Power and Computing Technologies, ICCPCT 2024

作者： Shalini, K. Reddy, K. Harinath Punati, Kondalarao Kavin, K.S. Veena, P. Pushpalatha, K. Vardhaman College of Engineering Department of Artificial Intelligence and Data Science Shamshabad India Annamacharya Institute of Technology and Sciences Department of Electrical and Electronics Engineering Rajampet India Hyderabad Institute of Technology and Management Faculty of Electronics and Communication Engineering Hyderabad500090 India Government College of Engineering Department of Electrical and Electronics Engineering Tamilnadu Tirunelveli India N. S. S. Polytechnic College Department of Computer Engineering Pandalam Pathanamthitta India Coimbatore Institute of Engineering and Technology Department of Computer Science and Engineering Coimbatore641109 India

ISBN: (纸本)9798350372816

VANET (Vehicular ad-hoc network) is a network of advanced automobiles designed to solve the problem of mobility and, as a result, reduce the number of accidents. Because VANET is a type of MANET (mobile ad hoc network) surrounded by human-driven nodes, the social concept can be used to explain VANET routing decisions. This motivates academics to look into the possibilities of using Social Network Analysis (SNA) to create routing strategies. The most critical problem in any system is parcel drop. Social characteristics-based architectures encounter comparable challenges, resulting in inefficient message delivery. In this research, the dragonfly method is used to the shortest path methodology for fixed line VANET with the purpose of reducing package drop and increasing network reliability. This is made achievable by sculpted system of values centralization analysis, which improves the decision via dragonfly optimization methodology. The behavior of the using nodes capability then be determined by the importance computation. In this study, the sustainability of the optimized shortest path system is measured in terms of End to End delay, Energy Consumption, Packet Loss, and Throughput. The dragonfly algorithm's throughput evaluation is 650 kbps as compared to the traditional way. © 2024 IEEE.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

High-Bandwidth,Low-Power CMOS Transistor Based CAB for Field Programmable Analog Array

引用

computers, Materials & Continua 2023年第3期74卷 5885-5900页

作者： Ameen Bin Obadi Alaa El-Din Hussein Samir Salem Al-Bawri Kabir Hossain Abdullah Abdulhameed Muzammil Jusoh Thennarasan Sabapathy Ahmed Jamal Abdullah Al-Gburi Mahmoud A.Albreem Advanced Communication Engineering(ACE) Centre of ExcellenceUniversiti Malaysia Perlis(UniMAP)Faculty of Electronic Engineering TechnologyKangar01000Malaysia Electrical Engineering King Fahd University of Petroleum and MineralsDhahranEastern31261Saudi Arabia Space Science Centre Climate Change InstituteUniversiti Kebangsaan MalaysiaBangi43600Malaysia Department of Electronics&Communication Engineering Faculty of Engineering&PetroleumHadhramout UniversityAl-MukallaHadhramout50512Yemen Faculty of Engineering Norwegian University of Science and Technology(NTNU)GjovikN-2815Norway Faculty of Electronic Engineering Technology Universiti Malaysia Perlis(UniMAP)Kampus Alam UniMAP Pauh PutraArau02600Malaysia Department of General Educational Development Faculty of Science and Information Technology(FSIT)Daffodil International UniversityDhaka1207Bangladesh Department of Electronics and Computer Engineering(FKEKK) Center for Telecommunication Research and Innovation(CeTRI)Universiti Teknikal Malaysia Melaka(UTeM)Durian Tungal76100Malaysia Department of Electrical Engineering University of SharjahSharjah27272United Arab Emirates

This article presents an integrated current mode configurable analog block(CAB)system for field-programmable analog array(FPAA).The proposed architecture is based on the complementary metal-oxide semiconductor(CMOS)transistor level design where MOSFET transistors operating in the saturation region are *** proposed CAB architecture is designed to implement six of thewidely used current mode operations in analog processing systems:addition,subtraction,integration,multiplication,division,and pass *** functionality of the proposed CAB is demonstrated through these six operations,where each operation is chosen based on the user’s selection in the CAB interface *** architecture of the CAB system proposes an optimized way of designing and integrating only three functional cells with the interface circuitry to achieve the six ***,optimized programming and digital tuning circuitry are implemented in the architecture to control and interface with the functional ***,these designed programming and tuning circuitries play an essential role in optimizing the performance of the proposed *** of the proposed CMOS Transistor Based CAB system is carried out using Tanner EDA Tools in 0.35μm standard CMOS *** design uses a±1.5 V power supply and results in maximum 3 dB bandwidth of 34.9 MHz and an approximate size of 0.0537 *** demonstrates the advantages of the design over the current state-of-the-art designs presented for comparison in this ***,the proposed design has a clear aspect of simplicity,low power consumption,and high bandwidth operation,which makes it a suitable candidate for mobile telecommunications applications.

关键词： CMOS field programmable analog array configurable analog block current mode circuit

来源：评论

学校读者我要写书评

暂无评论

An Efficient Stacked Ensemble Model for Heart Disease Detection and Classification

引用

computers, Materials & Continua 2023年第10期77卷 665-680页

作者： Sidra Abbas Gabriel Avelino Sampedro Shtwai Alsubai Ahmad Almadhor Tai-hoon Kim Department of Computer Science COMSATS UniversityIslamabadPakistan College of Computer Studies De La Salle UniversityManila1004Philippines Faculty of Information and Communication Studies University of the Philippines Open UniversityLos Banos4031Philippines College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz UniversityAlkharjSaudi Arabia Department of Computer Engineering and Networks College of Computer and Information SciencesJouf UniversitySakaka72388Saudi Arabia School of Electrical and Computer Engineering Yeosu CampusChonnam National UniversityYeosu-si59626Korea

Cardiac disease is a chronic condition that impairs the heart’s *** includes conditions such as coronary artery disease,heart failure,arrhythmias,and valvular heart *** conditions can lead to serious complications and even be life-threatening if not detected and managed in *** have utilized Machine Learning(ML)and Deep Learning(DL)to identify heart abnormalities swiftly and *** approaches have been applied to predict and treat heart disease utilizing ML and *** paper proposes a Machine and Deep Learning-based Stacked Model(MDLSM)to predict heart disease *** approaches such as eXtreme Gradient Boosting(XGB),Random Forest(RF),Naive Bayes(NB),Decision Tree(DT),and KNearest Neighbor(KNN),along with two DL models:Deep Neural Network(DNN)and Fine Tuned Deep Neural Network(FT-DNN)are used to detect heart *** models rely on electronic medical data that increases the likelihood of correctly identifying and diagnosing heart ***-known evaluation measures(i.e.,accuracy,precision,recall,F1-score,confusion matrix,and area under the Receiver Operating Characteristic(ROC)curve)are employed to check the efficacy of the proposed *** reveal that the MDLSM achieves 94.14%prediction accuracy,which is 8.30%better than the results from the baseline experiments recommending our proposed approach for identifying and diagnosing heart disease.

关键词： Deep neural network heart disease healthcare machine learning stacking

来源：评论

学校读者我要写书评

暂无评论

Optimizing Inventory Management using Demand Forecasting based Ensemble Stacking Model with Hyperparameter Tuning 1

Optimizing Inventory Management using Demand Forecasting bas...

引用

1st International Conference on Intelligent systems and Computational Networks, ICISCN 2025

作者： Pavithra, V. Abbas, Haayder M. Manjula, B.M. Chidambaram, P.K. Jothilakshmi, S. Srm Institute of Science and Technology Faculty of Science and Humanities Department of Computer Science and Applications Ramapuram Chennai India The Islamic University of Al Diwaniyah College of Technical Engineering Department of Computers Techniques Engineering Al Diwaniyah Iraq Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Bengaluru India New Prince Shri Bhavani College of Engineering and Technology Department of Mechanical Engineering Chennai India Dhanalakshmi Srinivasan College of Engineering and Technology Department of Information Technology Mamallapuram India

ISBN: (纸本)9798331529246

In recent days, the effective inventory management relies on accurate demand forecasting for effective management of business balance stocks. However, the traditional forecasting methods often struggled with different complexities such as variability, overstocking and wasted resources. In this research, the Ensemble Stacking Model with Hyperparameter Tuning (En-Stacking-HT) is proposed for effective optimized inventory management. Initially, the data is collected from M5 accuracy completion dataset and further preprocessed with data imputation, z-score normalization. These preprocessing techniques handles the missing values in data and standardizes the data in significant range. Then, Seasonal and Trend Decomposition (STL) is employed for extracting seasonality and trend features from preprocessed data by using Locally Estimated Scatterplot Smoothing (LOESS). Finally, the proposed En-Stacking-HT is utilized for inventory management prediction and optimized through hyperparameter tuning for predicting effective optimized inventory management for demand forecasting. From the results, the proposed En-Stacking-HT attained better results in terms of Mean Absolute Error (MAE) (16.82), Root Mean Square Error (RMSE) (22.85) and Mean Absolute Percentage Error (MAPE) (4.97%) when compared to existing Random Forest (RF). © 2025 IEEE.

关键词： demand forecasting ensemble stacking model hyperparameter tuning optimized inventory management seasonality and trend decomposition

来源：评论

学校读者我要写书评

暂无评论

Surveillance and Intruder Detection using Pyramid Vision Transformer You Only Look Once Enhanced with Gradient Weighted Class Activation Mapping 4

Surveillance and Intruder Detection using Pyramid Vision Tra...

引用

4th IEEE International Conference on Mobile Networks and Wireless communications, ICMNWC 2024

作者： Arunachalam, Sripriya Almusawi, Muntather Rafikiran, Shaik. Sivagami, S. Praveena, Hirald Dwaraka Srm Institute of Science and Technology Faculty of Science and Humanities Department of Computer Science and Applications Vadapalani City Campus Chennai India College of Technical Engineering The Islamic University of Al Diwaniyah Department of Computers Techniques Engineering Al Diwaniyah Iraq Sri Venkateswara College of Engineering Department of Electrical & Electronics Engineering Tirupati India New Prince Shri Bhavani College of Engineering and Technology Department of Chemistry Chennai India Department of Electronics and Communication Engineering Tirupati India

ISBN: (纸本)9798350352931

In this era, wireless networks are economically feasible and flexible to establish in healthcare, defense, surveillance, and traffic monitoring, fire detection. Effective intruder detection systems utilize advanced technologies like Artificial Intelligence (AI), sensors, and cameras. Traditional approaches for surveillance and intruder detection had faced several challenges which include false alarms, high costs, privacy concerns, and vulnerabilities. To overcome these challenges, a Gradient-weighted Class Activation Mapping (Grad CAM) with Pyramid Vision Transformer-You Only Look Once Enhanced (PViT-YOLOE) namely GRADCAM-PViT-YOLOE is proposed to detect intruders in public places using images and videos. For preprocessing, noise reduction, image resizing, and image segmentation are considered to reduce false positives, enhance memory efficiency, and to reduce complexity. Then, PViT-YOLOE is considered for feature extraction to enhance detection of small objects, enhance robustness to variations. At last, Grad CAM is employed as classifier to detect intruders in public places with improved interpretability, robustness to noise, and flexibility. The results demonstrate the efficacy of the proposed GRADCAM-PViT-YOLOE in terms of accuracy (99.25%), precision (96.75%) recall (89.82%) and F1-Score (87.92%) when compared to the existing method like Faster Regions Convolutional Neural Networks (FR-CNN). © 2024 IEEE.

关键词： Noise abatement

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：