检索结果-内蒙古大学图书馆

Earthworm Optimization with Improved SqueezeNet Enabled Facial Expression Recognition Model

Computer Systems Science & engineering 2023年第8期46卷 2247-2262页

作者： N.Sharmili Saud Yonbawi Sultan Alahmari E.Laxmi Lydia Mohamad Khairi Ishak Hend Khalid Alkahtani Ayman Aljarbouh Samih M.Mostafa Computer Science and Engineering Department Gayatri Vidya Parishad College of Engineering for WomenVisakhapatnamAndhra PradeshIndia 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 Department of Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India School of Electrical and Electronic Engineering Engineering CampusUniversiti Sains Malaysia(USM)Nibong TebalPenang14300Malaysia Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11564Saudi Arabia Department of Computer Science University of Central AsiaNaryn722600Kyrgyzstan Faculty of Computers and Information South Valley UniversityQena83523Egypt

Facial expression recognition(FER)remains a hot research area among computer vision researchers and still becomes a challenge because of high intraclass *** techniques for this problem depend on hand-crafted features,namely,LBP,SIFT,and HOG,along with that a classifier trained on a database of videos or *** execute perform well on image datasets captured in a controlled condition;however not perform well in the more challenging dataset,which has partial faces and image ***,many studies presented an endwise structure for facial expression recognition by utilizing DL ***,this study develops an earthworm optimization with an improved SqueezeNet-based FER(EWOISN-FER)*** presented EWOISN-FER model primarily applies the contrast-limited adaptive histogram equalization(CLAHE)technique as a pre-processing *** addition,the improved SqueezeNet model is exploited to derive an optimal set of feature vectors,and the hyperparameter tuning process is performed by the stochastic gradient boosting(SGB)***,EWO with sparse autoencoder(SAE)is employed for the FER process,and the EWO algorithm appropriately chooses the SAE ***-ranging experimental analysis is carried out to examine the performance of the proposed *** experimental outcomes indicate the supremacy of the presented EWOISN-FER technique.

关键词： Facial expression recognition deep learning computer vision earthworm optimization hyperparameter optimization

来源：评论

学校读者我要写书评

暂无评论

Automating the Diagnosis of Cucumber Plant Diseases Using Machine Learning 25

Automating the Diagnosis of Cucumber Plant Diseases Using Ma...

引用

25th International Arab Conference on information technology, ACIT 2024

作者： Banimustafa, Ahmed Qattouz, Hazem Almatarneh, Sattam Mansour, Khalid Alazaidah, Raed Bulkrock, Olla Higher Colleges of Technology Computer Information Science Dept Abu Dhabi United Arab Emirates Princess Sumaya University for Technology Software Engineering Dept Amman Jordan Zarqa University Data Science & Artificial Intelligence Dept Zarqa Jordan University of Business and Technology College of Engineering Jeddah Saudi Arabia Arab-Open University Bahrain Faculty of Computer Studies Bahrain

ISBN: (纸本)9798331540012

Farmers all over the world struggle to fight plant diseases. However, the incorrect use of pesticides can waste time, effort, and money and can also be very harmful to the environment and human health. In this work, we present an empirical study that involves identifying two pathogens related to Cucumbers plant diseases: Powdery Mildew and Alternaria Cucumerina. The study aims to develop a computer-based solution based on deep learning and machine learning algorithms to detect these diseases. To achieve this, a dataset of hundreds of samples was collected from ordinary farms in Beqaa, an agricultural region 15 KM north of Amman, Jordan. Three machine learning models were created in this study using Support Vector Machines (SVM), Logistic Regression (LR), and Multi-layer perceptron algorithms. The constructed models were applied to the dataset after embedding the dataset images using the Convolutional Neural Networks (CNN) InceptionV3 pre-trained model. The model was tested and evaluated using cross-evaluation and F1-Score, CA, AUC, Precision, Recall, and Specificity, which all showed excellent results, particularly using the SVM algorithm. The constructed methods are intended to be deployed to farms in their field condition environments using a CCTV system that can capture images of plants during growth, which can help identify plant diseases at that right stage, which would save time, effort, and money and reduce the impact of wrong and overuse of pesticides on consumers and the environment. © 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

Cyberbullying Detection and Recognition with Type Determination Based on Machine Learning

引用

Computers, Materials & Continua 2023年第6期75卷 5307-5319页

作者： Khalid M.O.Nahar Mohammad Alauthman Saud Yonbawi Ammar Almomani Computer Science Department Yarmouk UniversityIrbidJordan Department of Information Security Faculty of Information TechnologyUniversity of PetraAmmanJordan Software Engineering Department University of JeddahJeddahKSA Research and Innovation Department Skyline University CollegeP.O.Box 1797SharjahUAE IT Department-Al-Huson University College Al-Balqa Applied UniversityP.O.Box 50IrbidJordan

Social media networks are becoming essential to our daily activities,and many issues are due to this great involvement in our *** is a social media network issue,a global crisis affecting the victims and society as a *** results from a misunderstanding regarding freedom of *** this work,we proposed a methodology for detecting such behaviors(bullying,harassment,and hate-related texts)using supervised machine learning algo-rithms(SVM,Naïve Bayes,Logistic regression,and random forest)and for predicting a topic associated with these text data using unsupervised natural language processing,such as latent Dirichlet *** addition,we used accuracy,precision,recall,and F1 score to assess prior *** show that the use of logistic regression,support vector machine,random forest model,and Naïve Bayes has 95%,94.97%,94.66%,and 93.1%accuracy,respectively.

关键词： Cyberbullying social media naïve bayes support vector machine natural language processing LDA

来源：评论

学校读者我要写书评

暂无评论

M2UNet: MetaFormer Multi-scale Upsampling Network for Polyp Segmentation 31

M2UNet: MetaFormer Multi-scale Upsampling Network for Polyp ...

引用

31st European Signal Processing Conference, EUSIPCO 2023

作者： Trinh, Quoc-Huy Bui, Nhat-Tan Nguyen-Mau, Trong-Hieu Nguyen, Minh-Van Phan, Hai-Minh Tran, Minh-Triet Nguyen, Hai-Dang Faculty of Information Technology Software Engineering Laboratory International Training and Education Center John von Neumann Institute University of Science VNU-HCM Vietnam National University Ho Chi Minh City Viet Nam

ISBN: (纸本)9789464593600

Polyp segmentation has recently garnered significant attention, and multiple methods have been formulated to achieve commendable outcomes. However, these techniques often confront difficulty when working with the complex polyp foreground and their surrounding regions because of the nature of convolution operation. Besides, most existing methods forget to exploit the potential information from multiple decoder stages. To address this challenge, we suggest combining MetaFormer, introduced as a baseline for integrating CNN and Transformer, with UNet framework and incorporating our Multi-scale Upsampling block (MU). This simple module makes it possible to combine multi-level information by exploring multiple receptive field paths of the shallow decoder stage and then adding with the higher stage to aggregate better feature representation, which is essential in medical image segmentation. Taken all together, we propose MetaFormer Multi-scale Upsampling Network (M2UNet) for the polyp segmentation task. Extensive experiments on five benchmark datasets demonstrate that our method achieved competitive performance compared with several previous methods. © 2023 European Signal Processing Conference, EUSIPCO. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Optimal Scheduling of Graph States via Path Decompositions

arXiv

引用

arXiv 2024年

作者： Elman, Samuel J. Gavriel, Jason Mann, Ryan L. Centre for Quantum Software and Information School of Computer Science Faculty of Engineering & Information Technology University of Technology SydneyNSW2007 Australia Centre for Quantum Computation and Communication Technology Australia

We study the optimal scheduling of graph states in measurement-based quantum computation, establishing an equivalence between measurement schedules and path decompositions of graphs. We define the spatial cost of a measurement schedule based on the number of simultaneously active qubits and prove that an optimal measurement schedule corresponds to a path decomposition of minimal width. Our analysis shows that approximating the spatial cost of a graph is NP-hard, while for graphs with bounded spatial cost, we establish an efficient algorithm for computing an optimal measurement schedule. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph algorithms

来源：评论

学校读者我要写书评

暂无评论

A Smart RFID Based Automatic Toll Booth Management System Using Artificial Intelligence (AI) and Internet of Things Technologies

A Smart RFID Based Automatic Toll Booth Management System Us...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Ramkumar, G. Lakshmi, A. Audi Revathi, R.B. Babu, S.K. Anjaneyulu Bodkhe, Rajesh G. Aljawawdeh, Hamzeh J. Dept of Ece Chennai India Qis College of Engineering and Technology Department of S&h Pondur Road Vengamukkapalem Ongole Prakasam AndhraPradesh PrakasamDistrict523272 India Qis College of Engineering and Technology Department of Mca Pondur Road Vengamukkapalem Ongole Prakasam AndhraPradesh PrakasamDistrict523272 India Yeshwantrao Chavan College of Engineering Department of Mechanical Engineering Nagpur India Zarqa University Faculty of information technology Department software engineering Zarqa Jordan University of Business and Technology Jeddah21448 Saudi Arabia

ISBN: (纸本)9798331543617

This work presents a Smart RFID-based Automatic Toll Booth Management System utilizing a Hybrid ResNetSVM model and IoT technologies to automate vehicle identification, classification, and toll payment. The system integrates an Impinj Speedway R420 RFID reader for automatic vehicle detection and a hybrid ResNet-50 and SVM model for real-time vehicle classification. By deploying IoT-enabled devices, such as Raspberry Pi and ESP8266, and connecting to cloud platforms like AWS IoT, the system efficiently processes vehicle data, facilitating seamless toll transactions. The RFID system achieved an impressive detection accuracy of 98% at vehicle speeds under 80 km/h. However, at higher speeds, detection accuracy decreased to 75% at 200 km/h. The hybrid ResNetSVM model performed exceptionally well, achieving an average vehicle classification accuracy of 95.5% across different vehicle types, including cars, trucks, and buses. System throughput was tested with traffic volumes of up to 50 vehicles per minute, maintaining a transaction success rate of 95.5% under heavy traffic conditions. This system not only reduces toll booth congestion and human intervention but also provides secure and automated toll payment options, utilizing payment gateways such as Stripe, UPI, and PayPal with success rates over 99%. Overall, this smart toll management system improves efficiency and user experience through the use of advanced technologies. © 2024 IEEE.

关键词： Radio frequency identification (RFID)

来源：评论

学校读者我要写书评

暂无评论

Enhanced Model for Brain Tumor Detection Accuracy Using Inceptionresnetv2 compared to VGG19 and MobileNet Models

Enhanced Model for Brain Tumor Detection Accuracy Using Ince...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Tamilselvi, M. Ashwini, R. Ravi, S. Rajalakshmi, S. Rajkumar, Chadge Fawareh, Hamed Saveetha University Department of Ece Chennai India R.M.K College of Engineering and Technology Department of Ece Chennai India Saveetha University Department of Vlsi Microelectronics Chennai India S.A. Engineering College Department of Ece Chennai India Yeshwantrao Chavan College of Engineering Department of Mechanical Engineering Nagpur India Zarqa University Faculty of Information Technology Software Engineering Dept Zarqa Jordan University of Business and Technology Jeddah21448 Saudi Arabia

ISBN: (纸本)9798331543617

Brain tumors, arising from unregulated and accelerated cellular proliferation, provide considerable health hazards if not promptly addressed. Notwithstanding significant progress, precise segmentation and classification continue to pose difficulties. Artificial intelligence (AI) and medical imaging technologies have advanced recently, greatly improving illness analysis and prediction, particularly with regard to brain tumor (BT) identification. Precise classification and segmentation of tumors in the brain are essential for creating individualized treatment plans, and early detection of brain tumors is essential for improving patient prognosis and available treatments. Even with the increasing usage of Magnetic Resonance Imaging (MRI) for brain imaging and the development of AI-based detection techniques, developing a reliable and effective model to identify and classify cancers from MRI images is still a difficult task. Brain tumor analysis is essential for timely diagnosis and effective patient management. Tumor morphology, encompassing features such as dimension, position, appearance, and heteromorphic shape in medical images, poses challenges for analysis. Advancements in DL approaches for the automatic identification of tumors present in the brain using MRI data have led to the utilization of numerous algorithms for this purpose. The InceptionResNetV2 model is employed due to its efficiency and efficacy;it is a simple deep learning architecture, rendering it a suitable candidate for medical image processing applications. The proposed model attains an accuracy rate of 100% at an epoch rate of 30 and surpasses the performance of both MobileNet and VGG19 models. © 2024 IEEE.

关键词： Medical image processing

来源：评论

学校读者我要写书评

暂无评论

Performance Optimization Blockchain-Enabled Fog Computing with Deep Reinforcement Learning 12

Performance Optimization Blockchain-Enabled Fog Computing wi...

引用

12th International Conference on Communication and Network Security, ICCNS 2022

作者： Zhang, Yihe Tu, Shanshan Zhang, Shengju Yang, Yongjie Wu, Aiming Bai, Xuetao Engineering Research Center of Intelligent Perception and Autonomous Control Faculty of Information Technology Beijing University of Technology Beijing100124 China Software Technology Co. Ltd Suzhou215153 China

ISBN: (纸本)9781450397520

With the rapid development of Internet of Things technology and cloud computing technology, Fog Computing emerges with the demand of distributed and decentralized. Blockchain is considered to be an advanced technology, which enables Fog Computing data to be stored and shared safely, greatly improving the security and privacy of Fog Computing. However, the Blockchain technology currently applied in Fog Computing still has some significant disadvantages, one of which is the low throughput performance. In order to meet the demand of improving throughput, this paper proposes a Blockchain-Enabled Fog Computing performance optimization framework based on Deep Reinforcement Learning (DRL), which can dynamically adjust according to the system state to improve throughput. Dueling Deep Reinforcement Learning is adopted to obtain the optimal configuration, which can be dynamically adjusted according to Fog node status, network bandwidth and user's quality of service (QoS) requirements, including dynamic selection of block producers, block size and network bandwidth allocation. Simulation results show that the proposed scheme can effectively improve throughput performance. © 2022 ACM.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Exact Quantum Sensing Limits for Bosonic Dephasing Channels

引用

PRX Quantum 2024年第2期5卷 020354-020354页

作者： Zixin Huang Ludovico Lami Mark M. Wilde School of Mathematical and Physical Sciences Centre for Quantum Software and Information Faculty of Engineering and Information Technology Science Park 123 Amsterdam 1098 XG the Netherlands Korteweg–de Vries Institute for Mathematics Institute for Theoretical Physics School of Electrical and Computer Engineering

Dephasing is a prominent noise mechanism that afflicts quantum information carriers, and it is one of the main challenges toward realizing useful quantum computation, communication, and sensing. Here, we consider discrimination and estimation of bosonic dephasing channels, when using the most general adaptive strategies allowed by quantum mechanics. We reduce these difficult quantum problems to simple classical ones based on the probability densities defining the bosonic dephasing channels. By doing so, we rigorously establish the optimal performance of various distinguishability and estimation tasks and construct explicit strategies to achieve this performance. To the best of our knowledge, this is the first example of a non-Gaussian bosonic channel for which there are exact solutions for these tasks.

关键词： Non-gaussian quantum states Quantum channels Quantum fluctuations & noise Quantum information theory Quantum parameter estimation Quantum sensing

来源：评论

学校读者我要写书评

暂无评论

Brain Tumor Auto-Segmentation on Multimodal Imaging Modalities Using Deep Neural Network

引用

Computers, Materials & Continua 2022年第9期72卷 4509-4523页

作者： Elias Hossain Md.Shazzad Hossain Md.Selim Hossain Sabila Al Jannat Moontahina Huda Sameer Alsharif Osama S.Faragallah Mahmoud M.A.Eid Ahmed Nabih Zaki Rashed Department of Software Engineering Daffodil International UniversityDhaka 1207Bangladesh Department of Computing and Information System Daffodil International UniversityDhaka 1207Bangladesh Department of Computer Science&Engineering BRAC UniversityDhaka 1212Bangladesh Department of Information and Communication Engineering Bangladesh University of Professionals(BUP)Dhaka 1216Bangladesh Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif 21944Saudi Arabia Department of Information Technology College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif 21944Saudi Arabia Department of Electrical Engineering College of EngineeringTaif UniversityP.O.Box 11099Taif 21944Saudi Arabia Electronics and Electrical Communications Engineering Department Faculty of Electronic EngineeringMenouf 32951Egypt

Due to the difficulties of brain tumor segmentation, this paper proposes a strategy for extracting brain tumors from three-dimensional MagneticResonance Image (MRI) and Computed Tomography (CT) scans utilizing3D U-Net Design and ResNet50, taken after by conventional classificationstrategies. In this inquire, the ResNet50 picked up accuracy with 98.96%, andthe 3D U-Net scored 97.99% among the different methods of deep *** is to be mentioned that traditional Convolutional Neural Network (CNN)gives 97.90% accuracy on top of the 3D MRI. In expansion, the imagefusion approach combines the multimodal images and makes a fused image toextricate more highlights from the medical images. Other than that, we haveidentified the loss function by utilizing several dice measurements approachand received Dice Result on top of a specific test case. The average mean scoreof dice coefficient and soft dice loss for three test cases was 0.0980. At thesame time, for two test cases, the sensitivity and specification were recordedto be 0.0211 and 0.5867 using patch level predictions. On the other hand,a software integration pipeline was integrated to deploy the concentratedmodel into the webserver for accessing it from the software system using theRepresentational state transfer (REST) API. Eventually, the suggested modelswere validated through the Area Under the Curve–Receiver CharacteristicOperator (AUC–ROC) curve and Confusion Matrix and compared with theexisting research articles to understand the underlying problem. ThroughComparative Analysis, we have extracted meaningful insights regarding braintumour segmentation and figured out potential gaps. Nevertheless, the proposed model can be adjustable in daily life and the healthcare domain to identify the infected regions and cancer of the brain through various imagingmodalities.

关键词： Brain cancer segmentation 3D U-Net ResNet50 Dice measurement ROC-AUC

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：