检索结果-内蒙古大学图书馆

Harris Hawks Optimizer with Graph Convolutional Network Based Weed Detection in Precision Agriculture

computer Systems science & engineering 2023年第8期46卷 1533-1547页

作者： Saud Yonbawi Sultan Alahmari T.Satyanarayana Murthy Padmakar Maddala E.Laxmi Lydia Seifedine Kadry Jungeun Kim Department of Software Engineering College of Computer Science and EngineeringUniversity of JeddahJeddahSaudi Arabia King Abdul Aziz City for Science and Technology RiyadhKingdom of Saudi Arabia Chaitanya Bharathi Institute of Technology HyderabadTelanganaIndia Department of Civil Engineering Vignan’s Institute of Information and Technology(A)DuvvadaVisakhapatnamAP530049India Department of Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India Department of Applied Data Science Noroff University CollegeKristiansandNorway Artificial Intelligence Research Center(AIRC) College of Engineering and Information TechnologyAjman UniversityAjmanUnited Arab Emirates Department of Electrical and Computer Engineering Lebanese American UniversityByblosLebanon Department of Software Kongju National UniversityCheonan31080Korea

Precision agriculture includes the optimum and adequate use of resources depending on several variables that govern crop *** agriculture offers a novel solution utilizing a systematic technique for current agricultural problems like balancing production and environmental *** control has become one of the significant problems in the agricultural *** traditional weed control,the entire field is treated uniformly by spraying the soil,a single herbicide dose,weed,and crops in the same *** more precise farming,robots could accomplish targeted weed treatment if they could specifically find the location of the dispensable plant and identify the weed *** may lessen by large margin utilization of agrochemicals on agricultural fields and favour sustainable *** study presents a Harris Hawks Optimizer with Graph Convolutional Network based Weed Detection(HHOGCN-WD)technique for Precision *** HHOGCN-WD technique mainly focuses on identifying and classifying weeds for precision *** image pre-processing,the HHOGCN-WD model utilizes a bilateral normal filter(BNF)for noise *** addition,coupled convolutional neural network(CCNet)model is utilized to derive a set of feature *** detect and classify weed,the GCN model is utilized with the HHO algorithm as a hyperparameter optimizer to improve the detection *** experimental results of the HHOGCN-WD technique are investigated under the benchmark *** results indicate the promising performance of the presented HHOGCN-WD model over other recent approaches,with increased accuracy of 99.13%.

关键词： Weed detection precision agriculture graph convolutional network harris hawks optimizer hyperparameter tuning

来源：评论

学校读者我要写书评

暂无评论

Broad Federated Meta-Learning of Damaged Objects in Aerial Videos

引用

computer Modeling in engineering & sciences 2023年第12期137卷 2881-2899页

作者： Zekai Li Wenfeng Wang School of Aerospace Engineering Xi’an Jiaotong UniversityXi’an710049China Research Institute of Intelligent Engineering and Data Applications Shanghai Institute of TechnologyShanghai201418China Research Center for Ecology and Environment of Central Asia Chinese Academy of SciencesUrumqi830011China Applied Nonlinear Science Lab Anand International College of EngineeringJaipur391320India Department of Visual Engineering International Academy of Visual Art and EngineeringLondonCR26EQUK Institute of Intelligent Management and Technology Sino-Indian Joint Research Center of AI and RoboticsBhubaneswar752054India

We advanced an emerging federated learning technology in city intelligentization for tackling a real challenge-to learn damaged objects in aerial ***-learning system was integrated with the fuzzy broad learning system to further develop the theory of federated *** the mixed picture set of aerial video segmentation and the 3D-reconstructed mixed-reality data were employed in the performance of the broad federated meta-learning *** study results indicated that the object classification accuracy is up to 90%and the average time cost in damage detection is only 0.277 ***,the broad federated meta-learning system is efficient and effective in detecting damaged objects in aerial videos.

关键词： Fuzzy learning system mixed-reality 3D-reconstructed oblique photography

来源：评论

学校读者我要写书评

暂无评论

A deep learning fusion model for accurate classification of brain tumours in Magnetic Resonance images

引用

CAai Transactions on Intelligence Technology 2024年第4期9卷 790-804页

作者： Nechirvan Asaad Zebari Chira Nadheef Mohammed Dilovan Asaad Zebari Mazin Abed Mohammed Diyar Qader Zeebaree Haydar Abdulameer Marhoon Karrar Hameed Abdulkareem Seifedine Kadry Wattana Viriyasitavat Jan Nedoma Radek Martinek Department of Information Technology Lebanese French UniversityErbilIraq Department of Computer Science University of ZakhoZakhoKurdistan RegionIraq Department of Computer Science College of ScienceNawroz UniversityDuhokKurdistan RegionIraq Department of Artificial Intelligence College of Computer Science and Information TechnologyUniversity of AnbarRamadiIraq Department of Telecommunications VSB‐Technical University of OstravaOstravaCzech Republic Department of Cybernetics and Biomedical Engineering VSB‐Technical University of OstravaOstravaCzech Republic Department of Computer Network and Information Security Technical College of Informatics-AkreDuhok Polytechnic UniversityDuhokIraq Information and Communication Technology Research Group Scientific Research CenterAl‐Ayen UniversityThi‐QarIraq College of Computer Sciences and Information Technology University of KerbalaKarbalaIraq College of Agriculture Al‐Muthanna UniversitySamawahIraq Department of Applied Data Science Noroff University CollegeKristiansandNorway Faculty of Commerce and Accountancy Chulalongkorn Business SchoolChulalongkorn UniversityBangkokThailand

Detecting brain tumours is complex due to the natural variation in their location, shape, and intensity in images. While having accurate detection and segmentation of brain tumours would be beneficial, current methods still need to solve this problem despite the numerous available approaches. Precise analysis of Magnetic Resonance Imaging (MRI) is crucial for detecting, segmenting, and classifying brain tumours in medical diagnostics. Magnetic Resonance Imaging is a vital component in medical diagnosis, and it requires precise, efficient, careful, efficient, and reliable image analysis techniques. The authors developed a Deep Learning (DL) fusion model to classify brain tumours reliably. Deep Learning models require large amounts of training data to achieve good results, so the researchers utilised data augmentation techniques to increase the dataset size for training models. VGG16, ResNet50, and convolutional deep belief networks networks extracted deep features from MRI images. Softmax was used as the classifier, and the training set was supplemented with intentionally created MRI images of brain tumours in addition to the genuine ones. The features of two DL models were combined in the proposed model to generate a fusion model, which significantly increased classification accuracy. An openly accessible dataset from the internet was used to test the model's performance, and the experimental results showed that the proposed fusion model achieved a classification accuracy of 98.98%. Finally, the results were compared with existing methods, and the proposed model outperformed them significantly.

关键词： brain tumour deep learning feature fusion model MRI images multi‐classification

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Wireless Access Networks for IoT and E-Health-A Survey 3

Heterogeneous Wireless Access Networks for IoT and E-Health-...

引用

3rd International Conference on Advancement in Electronics and Communication engineering, AECE 2023

作者： Salama, Ramiz Altrjman, Chadi Al-Turjman, Fadi Yadav, Satya Prakash Vats, Satvik Ai and Robotics Institute Research Center for Ai and IoT Near East University Department of Computer Engineering Near East Boulevard TRNC Mersin 10 Nicosia99138 Turkey Waterloo University Department of Chemical Engineering ONN2L 3G1 Canada Ai and Robotics Institute Near East University Artificial Intelligence Engineering Dept Mersin10 Nicosia Turkey Department of Computer Science and Engineering Greater Noida201306 India Graphic Era Hill University Department of Computer Science and Engineering Dehradun India

ISBN: (纸本)9798350330724

In a heterogeneous wireless environment, there are many different radio access technologies (RATs), such as Wi-Fi and 2G, 3G, 4G, and 5G, which each have a different degree of coverage and processing power to meet various service requirements. A mobile user may have access to various access networks in such a situation. On the PC of each user, numerous programs with varied Quality of Service (QoS) requirements can operate simultaneously. It would be advantageous for a multi-interface terminal to use two or more interfaces simultaneously in order to improve performance. However, using multiple networks at once could use up more energy than just using one interface. Therefore, energy use must to be taken into account when analyzing the Flow/Interface Relationship (FIA). This paper presents a novel method for choosing the ideal FIA that achieves the best trade-off between all the characteristics taken into account, dubbed Smart Tabu Search (STS). STS considers user preferences, network circumstances, network expenses, application QoS specifications, and battery life of mobile devices. We use simulations and testbed experiments to validate our concept. Professionals are now able to diagnose and monitor patients remotely because to the growing use of healthcare monitoring devices. One of the most frequent occurrences that affects the reliability of information transmission in any network is congestion, which is defined as the unchecked increase in traffic relative to network capacity. With the use of a mesh network, wireless sensors, and some of the most significant models for vital signs, the article aims to provide a realistic simulation environment for a healthcare system. The simulator environment is a helpful tool for assessing the dependability and effectiveness of the healthcare system in a realistic setting. However, the system is not appropriate for real-time applications due to the sluggish network adaption caused by the end-to-end based traffic regulation deci

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Tensor Extended Kalman Filter and its application to Traffic Prediction

引用

IEEE Transactions on Intelligent Transportation Systems 2023年第12期24卷 13813-13829页

作者： Chang, Shih Yu Wu, Hsiao-Chun Kao, Yi-Chih San Jose State University Department of Applied Data Science San JoseCA95192 United States Louisiana State University School of Electrical Engineering and Computer Science Baton RougeLA70803 United States Yuan Ze University Innovation Center for Ai Applications Taoyuan32003 Taiwan National Yang Ming Chiao Tung University Information Technology Service Center Hsinchu30010 Taiwan

Traffic prediction is a very important mechanism in intelligent transportation systems for applications including routing planning and traffic control. In order to infer multifarious traffic information, one/two-relational traffic data in the vector/matrix form need to be expanded to multi-relational traffic data in an arbitrary tensor form. However, none of the existing approaches is capable of performing traffic prediction by characterizing and tracking the inherent nonlinear dynamics which are often encountered in realistic time-series analysis. Although the extended Kalman filter (EKF) has been proven to be quite promising in inferring nonlinear dynamics from time series, but the current EKF approach still suffers, unfortunately, from a serious drawback that state variables have to be represented in vector form. In fact, the characteristics of multi-relational states in practice can never been manifested accurately in practice and the performance of an EKF would be greatly restricted thereby. In this work, we introduce a new tensor extended Kalman filter (TEKF) approach to accommodate arbitrary input, output, and state variables all in arbitrary tensor forms. We also propose a new tensor-based expectation-maximization (EM) algorithm to estimate the nonlinear state-transition and observation-model mappings. The computational and memory complexities of the proposed TEKF approach are also studied in this paper. Finally, numerical experiments are conducted to evaluate the traffic prediction performance of the proposed new TEKF approach over the simulated and realworld traffic datasets in comparison with three other existing deep-learning prediction methods. © 2000-2011 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Lethal pulmonary thromboembolism in mice induced by intravenous human umbilical cord mesenchymal stem cell-derived large extracellular vesicles in a dose-and tissue factor-dependent manner

引用

中国药理学报（英文版） 2024年第11期45卷 2300-2312页

作者： Bian-lei Yang Yao-ying Long Qian Lei Fei Gao Wen-xiang Ren Yu-lin Cao Di Wu Liu-yue Xu Jiao Qu He Li Ya-li Yu An-yuan Zhang Shan Wang Hong-xiang Wang Zhi-chao Chen Qiu-bai Li Department of Rheumatology and Immunology Union HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430022China Department of Hematology Union HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430022China West China Biomedical Big Data Center West China HospitalSichuan UniversityChengdu 610041China Department of Hematology Key Laboratory for Molecular Diagnosis of Hubei ProvinceThe Central Hospital of WuhanTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430014China Department of Rheumatology and Immunology Union HospitalTongji Medical CollegeHuazhong University of Science and TechnologyWuhan 430022China Hubei Engineering Research Center for Application of Extracellular Vesicles Hubei University of Science and TechnologyXianning 437100China

Mesenchymal stem cell-derived extracellular vesicles(MSC-EVs)have obvious advantages over MSC *** the strong procoagulant properties of MSC-EVs pose a potential risk of thromboembolism,an issue that remains insufficiently *** this study,we systematically investigated the procoagulant activity of large EVs derived from human umbilical cord MSCs(UC-EVs)both in vitro and in ***-EVs were isolated from cell culture *** were injected with UC-EVs(0.125,0.25,0.5,1,2,4 μg/g body weight)in 100μL PBS via the tail *** and mortality were monitored for 30 min after *** showed that these UC-EVs activated coagulation in a dose-and tissue factor-dependent ***-EVs-induced coagulation in vitro could be inhibited by addition of tissue factor pathway ***,intravenous administration of high doses of the UC-EVs(1 μg/g body weight or higher)led to rapid mortality due to multiple thrombus formations in lung tissue,platelets,and fibrinogen depletion,and prolonged prothrombin and activated partial thromboplastin ***,we demonstrated that pulmonary thromboembolism induced by the UC-EVs could be prevented by either reducing the infusion rate or by pre-injection of heparin,a known *** conclusion,this study elucidates the procoagulant characteristics and mechanisms of large UC-EVs,details the associated coagulation risk during intravenous delivery,sets a safe upper limit for intravenous dose,and offers effective strategies to prevent such mortal risks when high doses of large UC-EVs are needed for optimal therapeutic effects,with implications for the development and application of large UC-EV-based as well as other MSC-EV-based therapies.

关键词： mesenchymal stem cells extracellular vesicles tissue factor coagulation pulmonary thromboembolism heparin

来源：评论

学校读者我要写书评

暂无评论

Combined Effect of Concept Drift and Class Imbalance on Model Performance During Stream Classification

引用

computers, Materials & Continua 2023年第4期75卷 1827-1845页

作者： Abdul Sattar Palli Jafreezal Jaafar Manzoor Ahmed Hashmani Heitor Murilo Gomes Aeshah Alsughayyir Abdul Rehman Gilal Department of Computer and Information Sciences Universiti Teknologi PETRONAS(UTP)Seri Iskandar32610Malaysia Centre for Research in Data Science UTPPerak32610Malaysia High Performance Cloud Computing Centre(HPC3) UTPPerak32610Malaysia School of Engineering and Computer Science Victoria University of WellingtonWellington6012New Zealand AI Institute University of Waikato WellingtonHamilton3240New Zealand Anti-Narcotics Force Ministry of Narcotics ControlIslamabad46000Pakistan College of Computer Science and Engineering Taibah UniversityMadinah42353Saudi Arabia

Every application in a smart city environment like the smart grid,health monitoring, security, and surveillance generates non-stationary datastreams. Due to such nature, the statistical properties of data changes overtime, leading to class imbalance and concept drift issues. Both these issuescause model performance degradation. Most of the current work has beenfocused on developing an ensemble strategy by training a new classifier on thelatest data to resolve the issue. These techniques suffer while training the newclassifier if the data is imbalanced. Also, the class imbalance ratio may changegreatly from one input stream to another, making the problem more *** existing solutions proposed for addressing the combined issue of classimbalance and concept drift are lacking in understating of correlation of oneproblem with the other. This work studies the association between conceptdrift and class imbalance ratio and then demonstrates how changes in classimbalance ratio along with concept drift affect the classifier’s *** analyzed the effect of both the issues on minority and majority classesindividually. To do this, we conducted experiments on benchmark datasetsusing state-of-the-art classifiers especially designed for data stream ***, recall, F1 score, and geometric mean were used to measure theperformance. Our findings show that when both class imbalance and conceptdrift problems occur together the performance can decrease up to 15%. Ourresults also show that the increase in the imbalance ratio can cause a 10% to15% decrease in the precision scores of both minority and majority *** study findings may help in designing intelligent and adaptive solutionsthat can cope with the challenges of non-stationary data streams like conceptdrift and class imbalance.

关键词： Classification data streams class imbalance concept drift class imbalance ratio

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Coffee Bean Binary Classification Through Deep Learning Techniques 1

引用

International Conference on Innovative Technologies in Intelligent Systems and Industrial applications, CITISIA 2022

作者： Islamy, Fajrul Muchtar, Kahlil Arnia, Fitri Dawood, Rahmad Febriana, Alifya Elwirehardja, Gregorius Natanael Pardamean, Bens Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh23111 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Computer Science Department Master of Computer Science Program BINUS Graduate Program Bina Nusantara University Jakarta11480 Indonesia

ISBN: (数字)9783031290787

ISBN: (纸本)9783031290770

Coffee beans are one of the high-value commodities in Indonesia, but the sorting method for the quality of coffee beans still uses visual methods and sieves with mechanical machines. This study aims to provide an alternative to classifying coffee beans using Deep Learning algorithms, such as the ResNet-18 and MobileNetV2. The dataset used is USK-COFFEE which consists of two classes, the normal coffee bean class, and the defect coffee bean class. The models were trained using the balanced and imbalanced datasets, meaning that two scenarios were performed. From the results of this study, the accuracy value for the ResNet-18 model was 91.50% when trained on the balanced dataset and 90.87% on the imbalanced dataset. It outperformed the MobileNetV2 architecture, which only achieved 0.8125 and 0.8112 accuracy scores when trained on the balanced and imbalanced datasets, respectively. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Estimating Blood Glucose Levels Using Machine Learning Models with Non- ?nvasive Wearable Device data

Estimating Blood Glucose Levels Using Machine Learning Model...

引用

21st International Conference on Informatics, Management, and Technology in Healthcare, ICIMTH 2023

作者： Aziz, Sarah Ahmed, Arfan Abd-Alrazaq, Alaa Qidwai, Uvais Farooq, Faisal Sheikh, Javaid AI Center for Precision Health Weill Cornell Medicine-Qatar Doha Qatar Department of Computer Science and Engineering Qatar University Qatar Center for Digital Health and Precision Medicine Qatar Computing Research Institute Doha Qatar

ISBN: (纸本)9781643684000

In 2019 alone, Diabetes Mellitus impacted 463 million individuals worldwide. Blood glucose levels (BGL) are often monitored via invasive techniques as part of routine protocols. Recently, ai-based approaches have shown the ability to predict BGL using data acquired by non-invasive Wearable Devices (WDs), therefore improving diabetes monitoring and treatment. It is crucial to study the relationships between non-invasive WD features and markers of glycemic health. Therefore, this study aimed to investigate accuracy of linear and non-linear models in estimating BGL. A dataset containing digital metrics as well as diabetic status collected using traditional means was used. data consisted of 13 participants data collected from WDs, these participants were divided in two groups young, and Adult Our experimental design included data Collection, Feature engineering, ML model selection/development, and reporting evaluation of metrics. The study showed that linear and non-linear models both have high accuracy in estimating BGL using WD data (RMSE range: 0.181 to 0.271, MAE range: 0.093 to 0.142). We provide further evidence of the feasibility of using commercially available WDs for the purpose of BGL estimation amongst diabetics when using Machine learning approaches. © 2023 The authors and IOS Press.

关键词： Wearable technology

来源：评论

学校读者我要写书评

暂无评论

Detection of Number Plate in Vehicles using Deep Learning based Image Labeler Model

Detection of Number Plate in Vehicles using Deep Learning ba...

引用

2023 IEEE International Conference on Recent Trends in Electronics and Communication, ICRTEC 2023

作者： Gupta, Shashi Kant Saxena, Surabhi Khang, Alex Hazela, Bramah Dixit, Chandra Kumar Haralayya, Bhadrappa Eudoxia Research University Department of Cse United States Pes University Department of Computer Applications Bengaluru560085 India University of Science and Technology Ai and Data Scientist Department of Information Technology Viet Nam University of Science and Technology Ai and Data Scientist Department of Information Technology United States Amity School of Engineering and Technology Lucknow Amity University Computer Science and Engineering Uttar Pradesh India Dr. Shakuntala Misra National Rehabilitation University Department of Physics UP Lucknow226017 India Lingaraj Appa Engineering College Bidar Department of Mba Karanataka Bidar585403 India

ISBN: (纸本)9798350396195

Deep learning is playing a vital role in most of the applications being used in today's technological era. There seems to be no application where the use of deep learning concepts has not been used yet. One such application is the detection of number plates of vehicles on roads. The incidence of automobile crashes has greatly expanded along with the population growth. Their needs to be system that could automatically detect the vehicle's number plate whenever necessary. The situation arises when any of the rider does not obey to the traffic rules, or skips the traffic signals or indulges in any other sort of activities such as accidents. In these situations, the rider tries to run away. In order to detect the person, these kind of deep learning models helps us to detect the vehicle. Image labelers on the roadsides. Need of sensors are required to store the data and they need to be deployed on the roadside. These labelers are used to track the vehicles that are not obeying the traffic rules. With the use of sensors, it could be stated that the use of IoT also plays in the deployment of the current work when it comes to real-time. The model initially is trained with numerous number plates. The number plates have various patterns of texts and numbers and it is essential for the deep learning model to get trained. With successful training, the model is able to detect the new number plates. The model proposed in the current paper is compared with the other existing systems and proves to be efficient and cost-efficient than them. © 2023 IEEE.

关键词： Vehicles

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：