检索结果-内蒙古大学图书馆

Metaheuristic with Deep Learning Enabled Biomedical Bone Age Assessment and Classification Model

computers, Materials & Continua 2022年第12期73卷 5473-5489页

作者： Mesfer Al Duhayyim Areej A.Malibari Marwa Obayya Mohamed K.Nour Ahmed S.Salama Mohamed I.Eldesouki Abu Sarwar Zamani Mohammed Rizwanullah Department of Computer Science College of Sciences and Humanities-AflajPrince Sattam bin Abdulaziz UniversitySaudi Arabia Department of Industrial and Systems Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Biomedical Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Sciences College of Computing and Information SystemUmm Al-Qura UniversitySaudi Arabia Department of Electrical Engineering Faculty of Engineering&TechnologyFuture University in EgyptNew Cairo11845Egypt Department of Information System College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia

The skeletal bone age assessment(BAA)was extremely implemented in development prediction and auxiliary analysis of medicinal issues.X-ray images of hands were detected from the estimation of bone age,whereas the ossification centers of epiphysis and carpal bones are important *** typical skeletal BAA approaches remove these regions for predicting the bone age,however,few of them attain suitable efficacy or *** BAA techniques with deep learning(DL)methods are reached the leading efficiency on manual and typical ***,this study introduces an intellectual skeletal bone age assessment and classification with the use of metaheuristic with deep learning(ISBAAC-MDL)*** presented ISBAAC-MDL technique majorly focuses on the identification of bone age prediction and classification *** attain this,the presented ISBAAC-MDL model derives a mask Region-related Convolutional Neural Network(Mask-RCNN)with MobileNet as baseline model to extract *** by,the whale optimization algorithm(WOA)is implemented for hyperparameter tuning of the MobileNet *** last,Deep Feed-Forward Module(DFFM)based age prediction and Radial Basis Function Neural Network(RBFNN)based stage classification approach is *** experimental evaluation of the ISBAAC-MDL model is tested using benchmark dataset and the outcomes are assessed over distinct *** experimental outcomes reported the better performances of the ISBAACMDL model over recent approaches with maximum accuracy of 0.9920.

关键词： Biomedical images bone age assessment age prediction computer vision deep learning image classification

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Medical Diagnosis system for Malaria and Typhoid Fever Using Genetic Neuro-Fuzzy system

An Enhanced Medical Diagnosis System for Malaria and Typhoid...

引用

International Conference on Artificial Intelligence and Smart Environment, ICAISE 2022

作者： Awotunde, Joseph Bamidele Imoize, Agbotiname Lucky Salako, Dotun Patrick Farhaoui, Yousef Department of Computer Science Faculty of Information and Communication Sciences University of Ilorin Kwara State Ilorin240003 Nigeria Department of Electrical and Electronics Engineering Faculty of Engineering University of Lagos Akoka Lagos100213 Nigeria STI Laboratory T-IDMS Faculty of Sciences and Techniques Moulay Ismail University of Meknès Errachidia Morocco

ISBN: (纸本)9783031262531

The major challenge of inadequate healthcare services in developing countries has been linked to the unavailability of qualified medical personnel and inefficient diagnostic techniques adopted. The advent of technology in medicine has aided the improvement of medical processes including diagnosis. Many computerized systems have been implemented over the years for medical diagnosis some of which included machine learning techniques. But the existing methods lack the power of selecting the most relevant signs and symptoms of malaria and typhoid fever. Therefore, this study develops a system capable of Malaria and Typhoid Fever diagnosis using a Genetic Algorithm, a Neuro-Fuzzy Inference system called GENFIS. In order to train the NFIS, the GA module determines the optimal set of network parameters, saves them, and then distributes them to the appropriate hidden layer nodes. The study made use of the MATLAB environment to test and evaluate the system. The accuracy performance of the proposed model revealed an accuracy of 97.2%, thus performing better than some of the existing systems. If completely adopted, the proposed approach has the potential to lessen the major issues with NFIS systems. Furthermore, it might be used to address difficult issues in different fields. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

The Optimal Shape of the Surface Hardening Head Obtained by Numerical Modeling 15

The Optimal Shape of the Surface Hardening Head Obtained by ...

引用

15th International Conference on Electronics, computers and Artificial Intelligence, ECAI 2023

作者： Novac, Mihaela Cornelia Codrean, Marius Gordan, Mircea Codrean, Mihaela Oproescu, Mihai Novac, Ovidiu Constantin Slovac, Francisc University of Oradea Electrical Engineering and Information Technology Faculty Department of Electrical Engineering Oradea Romania National Geothermal Research Center Technology Transfer Center NGRC-TTC University of Oradea Oradea Romania Computers and Electrical Engineering University of Pitesti Faculty of Electronics Communication and Computer Science Department of Elecytronics Pitesti Romania University of Oradea Electrical Engineering and Information Technology Faculty Department of Computers and Information Technology Oradea Romania

ISBN: (纸本)9798350321388

This paper presents some aspects of the numerical modeling performed in order to study the process of induction heating applied to a workpiece, using Flux 2D and FEMM (Finite Element Method Magnetics), two software tools specifically designed for electromagnetic simulations. The paper presents a significant technical finding regarding the optimal shape of the surface hardening head. Various shapes of the inductor were analyzed, focusing on solving the eddy current problem using the commercial program FEMM. The induction heating process was numerically simulated using the FLUX 2D program for a semi-finished punch made of OLC 45 steel, specifically for hot surface heat treatment. The simulations were conducted utilizing the program's simulation capabilities. © 2023 IEEE.

关键词： Induction heating

来源：评论

学校读者我要写书评

暂无评论

Nanostructured Quadric-Confined Quantum Dot–Quantum Well Kesterite Solar Cell: A Pathway for Cost-Effective Photosensitive Devices

引用

Physica Status Solidi (A) Applications and Materials science 2025年

作者： Mohanty, Smruti Ranjan Palanisamy, Chandrasekar Sahoo, Sudarsan Routray, Soumyaranjan Department of Electronics and Instrumentation Engineering NIT Silchar Assam Silchar788010 India Department of Computer Science and Engineering Faculty of Engineering and Technology Parul University Gujarat Vadodara391760 India Department of Electronics and Communication Engineering SRM Institute of Science and Technology Kattankulathur Chennai603203 India

Nanostructure kesterite-based solar with a combination of multi-quantum dots (QDs) and multi-quantum well (QW) region is proposed to improve photoabsorption rate and conversion efficiency. The scope of kesterite hybrid-confined structure attracts researchers due to their environment-friendly, encouraging optic-electrical characteristics and carrier confinement properties. The optimal design of a quadric-confined QDQW solar cell (QCQDQW) focuses on nanostructures that improve the open-circuit voltage Voc. This article examines the overall performance of QCQDQW structure by implementing both QD (width 10 nm) and QW (10 nm barrier and 5 nm well width) layers (CZGSe/ (Formula presented.)) considering S/Se composition variations (x = 0.2–0.8). Moreover, a thin 5 nm barrier layer is engineered between QD and QW layers, enhancing effective carrier quantization and collection in solar cell. The remarkable efficiency of 17.37% and Voc of 0.945 V is obtained for three QW regions and five QD layers with the highest Jsc value of 21.06 mA. This study encourages a new direction in quantum-confined solar structure. © 2025 Wiley-VCH GmbH.

关键词： Semiconductor quantum dots

来源：评论

学校读者我要写书评

暂无评论

A Novel Ensemble Deep Learning Framework for Breast Cancer Prediction

A Novel Ensemble Deep Learning Framework for Breast Cancer P...

引用

2023 International Conference on Innovative Computing, Intelligent communication and Smart Electrical systems, ICSES 2023

作者： Shaker Reddy, Pundru Chandra Nithyapriya, S. Sharma, Nipun Maheswari, S. Jayaram, B. Katale, Tejaswini SR University School of Computer Science and Artificial Intelligence Telangana Warangal506371 India Anna University Artificial Intelligence and Data Science Bannari Amman Institute of Technology Tamil Nadu Chennai India Presidency University Bangalore Electronics and Communication Engineering Karnataka India Sathyabama Institute of Science and Technology Department of Mathematics Tamil Nadu Chennai India Computer Science and Business System RMK Engineering College Tamil Nadu Kavaraipettai India Vishwakarma Institute of Technology Department of Computer Engineering Maharashtra Pune India

ISBN: (纸本)9798350319200

Because of its high incidence and high mortality rate, breast cancer requires reliable means of early detection and diagnosis to improve survival rates for its patients. With advantages including increased accuracy and efficiency, deep learning (DL) and machine learning (ML) methods are quickly becoming indispensable in the fight against breast cancer. However, there is a need for additional study because existing approaches have scalability and performance constraints. Utilizing a pre-trained ResNet50V2 and ensemble-based ML approaches, we offer a hybrid approach to reliable breast cancer diagnosis in this study. Learning and extracting latent trends from complex breast-cancer(BC) images is made possible by DL's incorporation, with ML strategies contributing interpretability and generalizability. We performed wide experiments utilizing a openly accessible Invasive-Ductal-Carcinoma(IDC) dataset based on breast histopathology images of varying sample sizes. The resilience and great performance of our hybrid model are supported by the results of our extensive experiments. When compared to state-of-the-art models, our 95% accuracy rate, 94.5 precision, 94.2 recall, and 94.6 F1 score are all improvements. We also found that the best ML model to use with the ResNet50V2 architecture is the Light Boosting Classifier (LGB). This study's findings provide substantial contributions to the field of breast cancer diagnosis thanks to its novel approach, in-depth performance analysis, and trustworthy evaluation. In addition, it may help doctors make better decisions, provide better care, and boost results for people with breast cancer. © 2023 IEEE.

关键词： breast histopathology-image Breast-cancer DL ML transfer-learning

来源：评论

学校读者我要写书评

暂无评论

Optimal Deep Learning Model Enabled Secure UAV Classification for Industry 4.0

引用

computers, Materials & Continua 2023年第3期74卷 5349-5367页

作者： Khalid A.Alissa Mohammed Maray Areej A.Malibari Sana Alazwari Hamed Alqahtani Mohamed K.Nour Marwa Obbaya Mohamed A.Shamseldin Mesfer Al Duhayyim SAUDI ARAMCO Cybersecurity Chair Networks and Communications DepartmentCollege of Computer Science and Information TechnologyImam Abdulrahman bin Faisal UniversityP.O.Box 1982Dammam31441Saudi Arabia Department of Information Systems College of Computer ScienceKing Khalid UniversityAbhaSaudi Arabia Department of Industrial and Systems Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Information Technology College of Computers and Information TechnologyTaif UniversityTaif P.O.Box 11099Taif21944Saudi Arabia Department of Information Systems College of Computer ScienceCenter of Artificial IntelligenceUnit of CybersecurityKing Khalid UniversityAbhaSaudi Arabia Department of Computer Sciences College of Computing and Information SystemUmm Al-Qura UniversitySaudi Arabia Department of Biomedical Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Mechanical Engineering Faculty of Engineering and TechnologyFuture University in EgyptNew Cairo11835Egypt Department of Computer Science College of Sciences and Humanities-AflajPrince Sattam bin Abdulaziz UniversitySaudi Arabia

Emerging technologies such as edge computing,Internet of Things(IoT),5G networks,big data,Artificial Intelligence(AI),and Unmanned Aerial Vehicles(UAVs)empower,Industry 4.0,with a progressive production methodology that shows attention to the interaction between machine and human *** the literature,various authors have focused on resolving security problems in UAV communication to provide safety for vital *** current research article presents a Circle Search Optimization with Deep Learning Enabled Secure UAV Classification(CSODL-SUAVC)model for Industry 4.0 *** suggested CSODL-SUAVC methodology is aimed at accomplishing two core objectives such as secure communication via image steganography and image ***,the proposed CSODL-SUAVC method involves the following methods such as Multi-Level Discrete Wavelet Transformation(ML-DWT),CSO-related Optimal Pixel Selection(CSO-OPS),and signcryption-based *** proposed model deploys the CSO-OPS technique to select the optimal pixel points in cover *** secret images,encrypted by signcryption technique,are embedded into cover ***,the image classification process includes three components namely,Super-Resolution using Convolution Neural Network(SRCNN),Adam optimizer,and softmax *** integration of the CSO-OPS algorithm and Adam optimizer helps in achieving the maximum performance upon UAV *** proposed CSODLSUAVC model was experimentally validated using benchmark datasets and the outcomes were evaluated under distinct *** simulation outcomes established the supreme better performance of the CSODL-SUAVC model over recent approaches.

关键词： Unmanned Aerial Vehicles Artificial Intelligence emerging technologies Deep Learning Industry 4.0 image steganography

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter Tuned Deep Learning Enabled Intrusion Detection on Internet of Everything Environment

引用

computers, Materials & Continua 2022年第12期73卷 6579-6594页

作者： Manar Ahmed Hamza Aisha Hassan Abdalla Hashim Heba G.Mohamed Saud S.Alotaibi Hany Mahgoub Amal S.Mehanna Abdelwahed Motwakel Department of Electrical and Computer Engineering International Islamic University MalaysiaKuala Lumpur53100Malaysia Department of Computer and Self Development Preparatory Year DeanshipPrince Sattam bin Abdulaziz UniversityAlKharjSaudi Arabia Department of Electrical Engineering College of EngineeringPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Information Systems College of Computing and Information SystemUmm Al-Qura UniversitySaudi Arabia Department of Computer Science College of Science&Art at MahayilKing Khalid UniversitySaudi Arabia Faculty of Computers and Information Computer Science DepartmentMenoufia UniversityEgypt Department of Digital Media Faculty of Computers and Information TechnologyFuture University in EgyptNew Cairo11845Egypt

Internet of Everything(IoE),the recent technological advancement,represents an interconnected network of people,processes,data,and *** recent times,IoE gained significant attention among entrepreneurs,individuals,and communities owing to its realization of intense values from the connected *** the other hand,the massive increase in data generation from IoE applications enables the transmission of big data,from contextawaremachines,into useful *** and privacy pose serious challenges in designing IoE environment which can be addressed by developing effective Intrusion Detection systems(IDS).In this background,the current study develops Intelligent Multiverse Optimization with Deep Learning Enabled Intrusion Detection system(IMVO-DLIDS)for IoT *** presented IMVO-DLIDS model focuses on identification and classification of intrusions in IoT *** proposed IMVO-DLIDS model follows a three-stage *** first,data pre-processing is performed to convert the actual data into useful *** addition,Chaotic Local Search Whale Optimization Algorithm-based Feature Selection(CLSWOA-FS)technique is employed to choose the optimal feature ***,MVO algorithm is exploited with Bidirectional Gated Recurrent Unit(BiGRU)model for ***,the novelty of the work is the application of MVO algorithm in fine-turning the hyperparameters involved in BiGRU *** experimental validation was conducted for the proposed IMVO-DLIDS model on benchmark datasets and the results were assessed under distinct *** extensive comparative study was conducted and the results confirmed the promising outcomes of IMVO-DLIDS approach compared to other approaches.

关键词： Internet of everything deep learning feature selection classification intrusion detection cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Analysis and Optimization of Neural Networks for Image and Speech Recognition

Analysis and Optimization of Neural Networks for Image and S...

引用

2023 International Conference on Innovative Computing, Intelligent communication and Smart Electrical systems, ICSES 2023

作者： Komala, C.R. Purushothaman, R. Ande, Pavan Kumar Dinesh, P.M. Anitha Rani, K.S. Yamuna, P. HKBK College of Engineering Department of Information Science and Engineering Karnataka Bengaluru560045 India Sri Ramachandra Institute of Higher Education and Research Faculty of Engineering and Technology Tamil Nadu Chennai600116 India KoneruLakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh Guntur522502 India Sona College of Technology Department of Electronics and Communication Engineering Tamil Nadu Salem636005 India REVA University School of Computer Science and Applications Karnataka Bengaluru560064 India Acharya Institute of Graduate Studies Department of Computer Applications Karnataka Soladevanahalli 560107 India

ISBN: (纸本)9798350319200

The strategy of transforming vocal discourse signals into text using records is known as programmed discourse acknowledgment (ASR). In the ongoing time of the PC unrest, the ASR has a huge impact in further developing the client experience while communicating with the PCs in a characteristic manner. Conventional instruments like a console and mouse can't be utilized, and the client might do a limitless number of undertakings like controlling of contraptions and correspondence with client care. This study presents an air terminal enquiry framework in view of ASR. The program was made solely for the Telugu language. In view of the most generally posed inquiries about air terminals, a data set was created. Convolutional Brain Organization (CNN) has been utilized for preparing and testing the information base in view of its extraordinary exhibition. Convolution brain organizations (CNNs) have as of late been demonstrated to perform better on the telephone discovery test than regular completely associated profound brain networks when utilized in a half and half profound brain organization/stowed away Markov model (DNN/Gee) design. © 2023 IEEE.

关键词： Image Networks Neural Optimization Speech Recognition

来源：评论

学校读者我要写书评

暂无评论

First wetland mapping at 10-m spatial resolution in South America using multi-source and multi-feature remote sensing data

引用

science China Earth sciences 2024年第10期67卷 3252-3269页

作者： Weiwei SUN Gang YANG Yuling HUANG Dehua MAO Ke HUANG Lin ZHU Xiangchao MENG Tian FENG Chao CHEN Yong GE Department of Geography and Spatial Information Techniques Ningbo UniversityNingbo 315211China State Key Laboratory of Resources and Environmental Information System Institute of Geographic Sciences&Natural Resources ResearchChinese Academy of SciencesBeijing 100101China Natural Resources and Planning Bureau Shanghai Pudong New DistrictShanghai 200100China Key Laboratory of Wetland Ecology and Environment Northeast Institute of Geography and AgroecologyChinese Academy of SciencesChangchun 130102China Faculty of Electrical Engineering and Computer Science Ningbo UniversityNingbo 315211China School of Geography Science and Geomatics Engineering Suzhou University of Science and TechnologySuzhou 215009China

Wetland degradation has been accelerating in recent years globally. Accurate information on the geographic distribution and categories of wetlands is essential for their conservation and management. Despite being the world′s fourth largest continent, South America has limited research on wetland mapping, and there is currently no available map that provides comprehensive information on wetland distribution and categories in the region. To address this issue, we used Sentinel-1, Sentinel-2 and SRTM data, developed a sample collection method and a wetland mapping method with a collection of multi-source features such as optical features, polarization features and shape features for South American wetlands. We produced a 10-m resolution wetland map based on the Google Earth Engine(GEE) platform. Our Level-1 wetland cover map accurately captured six wetland sub-categories with an overall accuracy of 96.24% and a kappa coefficient of 0.8649, while our Level-2 water cover map included five sub-categories with an overall accuracy of 97.23% and a kappa coefficient of0.9368. The results show that the total area of existing wetlands in South America is approximately 1,737,000 km~2, which is6.8% of the total land area. Among the ten wetland categories, shallow sea had the largest area(960,527.4 km~2), while aquaculture ponds had the smallest area 1513.6 km~2. Swamp had the second largest area(306,240.1 km~2). Brazil, Argentina,Venezuela, Bolivia, and Colombia were found to have the largest wetland areas, with Brazil and Colombia having the most diverse wetland categories. This product can serve as baseline data for subsequent monitoring, management, and conservation of South American wetlands.

关键词： Wetland mapping Google Earth Engine Sentinel imagery South America

来源：评论

学校读者我要写书评

暂无评论

Implementing Machine Learning Techniques to Enhance Real-Time Data Analysis Services 3

Implementing Machine Learning Techniques to Enhance Real-Tim...

引用

3rd International Conference on Smart Generation Computing, communication and Networking, SMART GENCON 2023

作者： Jaisudha, J. Dhabliya, Dharmesh Narasimhayya, B.E. Singh, Akhilendra Pratap Sinha, Sanjay Kumar Vashisht, Nitish Prince Shri Venkateshwara Padmavathy Engineering College Department of Electronics and Communication Engineering Chennai127 India Vishwakarma Institute of Information Technology Department of Information Technology Maharashtra Pune India Computer Science and Engineering Faculty of Engineering and Technology Karnataka Bangalore India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh India Vivekananda Global University Department of Computer Science & Engineering Jaipur India Chitkara University Institute of Engineering and Technology Chitkara University Centre of Interdisciplinary Research in Business and Technology Punjab India

ISBN: (纸本)9798350319125

system learning techniques have emerged to automatically extract data from massive volumes of statistics and enable predictive analytics. Gadget-gaining knowledge has, in particular, been applied to records-driven real-time analytics offerings to facilitate accurate, short, and efficient selection-making. This paper discusses how machine studying strategies can be implemented to improve the accuracy and speed of real-time facts analysis. Conventional statistics analysis models are regularly misguided because of latency troubles and the absence of contextual statistics. Machine getting-to-know techniques have been followed to lessen latency issues, contain contextual facts, and enhance the accuracy of predictions. The paper offers a top-level view of some commonly used machine learning algorithms, such as supervised getting to know, unsupervised mastering, decision timber, neural networks, and support vector machines. It also explains how they can beautify actual-time analytics services. It also covers how strategies, including regularization and dimensionality discount, may be applied to enhance the model's overall performance. The paper gives case research of real-time analytics packages in finance, healthcare, and retail to illustrate the efficacy and added cost of gadget learning in facts analytics offerings. © 2023 IEEE.

关键词： Support vector machines

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：