检索结果-内蒙古大学图书馆

Meta-heuristics for Feature Selection and Classification in Diagnostic Breast Cancer

Computers, Materials & Continua 2022年第10期73卷 749-765页

作者： Doaa Sami Khafaga Amel Ali Alhussan El-Sayed M.El-kenawy Ali E.Takieldeen Tarek M.Hassan Ehab A.Hegazy Elsayed Abdel Fattah Eid Abdelhameed Ibrahim Abdelaziz A.Abdelhamid Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt Communications and Computers Engineering Department Faculty of EngineeringDelta University for Science and TechnologyInternational Coastal RoadGamasa CityDakhliyaEgypt Faculty of Applied Health Science Technology Delta University for Science and TechnologyMansoura35712Egypt Faculty of Medicine Head of Internal Medicine DepartmentDelta University for Science and TechnologyMansouraEgypt Computer Engineering and Control Systems Department Faculty of EngineeringMansoura University35516MansouraEgypt Department of Computer Science Faculty of Computer and Information SciencesAin Shams University11566CairoEgypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia

One of the most common kinds of cancer is breast *** early detection of it may help lower its overall rates of *** this paper,we robustly propose a novel approach for detecting and classifying breast cancer regions in thermal *** proposed approach starts with data preprocessing the input images and segmenting the significant regions of *** addition,to properly train the machine learning models,data augmentation is applied to increase the number of segmented regions using various scaling *** the other hand,to extract the relevant features from the breast cancer cases,a set of deep neural networks(VGGNet,ResNet-50,AlexNet,and GoogLeNet)are *** resulting set of features is processed using the binary dipper throated algorithm to select the most effective features that can realize high classification *** selected features are used to train a neural network to finally classify the thermal images of breast *** achieve accurate classification,the parameters of the employed neural network are optimized using the continuous dipper throated optimization *** results show the effectiveness of the proposed approach in classifying the breast cancer cases when compared to other recent approaches in the ***,several experiments were conducted to compare the performance of the proposed approach with the other *** results of these experiments emphasized the superiority of the proposed approach.

关键词： Breast cancer image segmentation dipper throated optimization feature selection meta-heuristics

来源：评论

学校读者我要写书评

暂无评论

Image cyberbullying detection and recognition using transfer deep machine learning

引用

International Journal of Cognitive computing in Engineering 2024年第1期5卷 14-26页

作者： Almomani, Ammar Nahar, Khalid Alauthman, Mohammad Al-Betar, Mohammed Azmi Yaseen, Qussai Gupta, Brij B. School of Computing Skyline University College University City of Sharjah P.O. Box 1797 Sharjah United Arab Emirates I.T. department Al-Huson University College AlBalqa Applied University Irbid Jordan Computer Science Department Faculty of I.T. Yarmouk University Irbid Jordan Department of Information Security Faculty of Information Technology University of Petra Amman Jordan Ajman University Ajman United Arab Emirates Department of Computer Science and Information Engineering Asia University Taichung413 Taiwan Symbiosis International University Pune India Department of Electrical and Computer Engineering Lebanese American University Beirut1102 Lebanon Dehradun India

Cyberbullying detection on social media platforms is increasingly important, necessitating robust computational methods. Current approaches, while promising, have not fully leveraged the combined strengths of deep learning and traditional machine learning for enhanced performance. Moreover, online content complexity requires models that can capture nuanced contexts beyond text, which many current methods lack. This research proposes a novel hybrid approach using deep learning models as feature extractors and machine learning classifiers to improve cyberbullying detection. Extracting features using pre-trained deep learning models like InceptionV3, ResNet50, and VGG16, then feeding them into classifiers like Logistic Regression and Support Vector Machines, enhances understanding of the complex contexts where cyberbullying occurs. Experiments on an image dataset showed that combining deep learning and machine learning achieved higher accuracy than using either approach alone. This novel framework bridges the gap in existing literature and contributes to broader efforts to combat cyberbullying through more nuanced, context-aware detection methods. The hybrid technique demonstrates the potential of blending deep learning's representation learning strengths with machine learning's sample efficiency and interpretability. © 2023

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Utilizing a machine learning algorithm to choose a significant traffic identification system

引用

International Journal of Information Management Data Insights 2024年第1期4卷

作者： Natarajan, Rajesh Ranjith, Christodoss Prasanna Mohideen, M．Syed Khaja Gururaj, H.L. Flammini, Francesco Thangarasu, N. Information Technology Department College of Computing and Information Sciences University of Technology and Applied Sciences-Shinas Al-Aqr Shinas 324 Oman Information Technology Department College of Computing and Information Sciences University of Technology and Applied Sciences- Salalah Post Box No 608 Salalah 211 Oman Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India IDSIA USI-SUPSI University of Applied Sciences and Arts of Southern Switzerland Switzerland Department of Computer Science Karpagam Academy of Higher Education Tamil Nadu Coimbatore India

The tremendous advancements in computing, sensing, and cognitive-based revolution have made way for critical infrastructure needed to improve the internet for more extensive applications. However, the computation performed by devices and the ability to communicate is limited due to the use of numerous devices for storage. Among the most complex model scenarios, a framework based on a Traffic Identification System (TIS) is a crucial answer. The Web-based brute force and botnet attacks are linked in this initial phase. To forecast the samples using the adaptive bootstrap method, the second phase entails creating a classifier on the training dataset. The normalization model and features are combined in the model, which then identifies traffic attacks on the network. Based on voting mechanisms from several decision trees utilized in the mode, an ensemble model using the Adaptive Boosting Classifier and Random Forest Algorithm (ABC-RFA) method is employed to construct the classification model. According to the overhead analysis of the dataset used for testing, the suggested model's overall performance is approximately 98.90 %, much better than the conventional models currently in use. Overall Precision, Specificity, Rate of Detection, And Accuracy Were All Attained. © 2024 The Author(s)

关键词： Adaptive bootstrap Classification Ensemble Model Random Forest (RF)

来源：评论

学校读者我要写书评

暂无评论

An Integrated Deep Learning Framework for Fruits Diseases Classification

引用

Computers, Materials & Continua 2022年第4期71卷 1387-1402页

作者： Abdul Majid Muhammad Attique Khan Majed Alhaisoni Muhammad Asfand Eyar Usman Tariq Nazar Hussain Yunyoung Nam Seifedine Kadry Department of Computer Science HITEC University TaxilaTaxilaPakistan College of Computer Science and Engineering University of Ha’ilHa’ilSaudi Arabia Department of Computer Science Bahria UniversityIslamabad College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz UniversityAl-KhrajSaudi Arabia Department of Computer Science and Engineering Soonchunhyang UniversityAsanKorea Faculty of Applied Computing and Technology Noroff University CollegeKristiansandNorway

:Agriculture has been an important research area in the field of image processing for the last five *** affect the quality and quantity of fruits,thereby disrupting the economy of a *** computerized techniques have been introduced for detecting and recognizing fruit ***,some issues remain to be addressed,such as irrelevant features and the dimensionality of feature vectors,which increase the computational time of the ***,we propose an integrated deep learning framework for classifying fruit *** consider seven types of fruits,i.e.,apple,cherry,blueberry,grapes,peach,citrus,and *** proposed method comprises several important ***,data increase is applied,and then two different types of features are *** the first feature type,texture and color features,i.e.,classical features,are *** the second type,deep learning characteristics are extracted using a pretrained *** pretrained model is reused through transfer ***,both types of features are merged using the maximum mean value of the serial ***,the resulting fused vector is optimized using a harmonic threshold-based genetic ***,the selected features are classified using multiple *** evaluation is performed on the PlantVillage dataset,and an accuracy of 99%is achieved.A comparison with recent techniques indicate the superiority of the proposed method.

关键词： Fruit diseases data augmentation deep learning classical features features fusion features selection

来源：评论

学校读者我要写书评

暂无评论

Enhancing IoT-Edge Computation with Data Forwarding based Decentralized Deep Neural Networks 7

Enhancing IoT-Edge Computation with Data Forwarding based De...

引用

7th International Conference on Image Information Processing, ICIIP 2023

作者： Prasad, B.M.G. Jopate, Rachappa Savita, Pankaj Basi Reddy, A. Shankar, B. Prabu Arunkumar, M.S. Department of Cse Andhra Pradesh Kurnool518452 India University of Technology And Applied Sciences - Al Mussanah Department of Information Technology Al Muladha Muscat Oman Sagar Institute of Science & Technology Bhopal Organization-Sagar Institute of Science & Technology Department of Cse Madhya Pradesh Bhopal India Mohan Babu University School of Computing Department of Computer Science And Engineering Andhra Pradesh Tirupati India Alliance University Alliance College of Engineering And Design Department of Computer Science And Engineering Karnataka Banglore India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science And Technology Department of Computer Science And Engineering Tamilnadu Chennai India

ISBN: (纸本)9798350371406

The incorporation of edge computing has become essential in the big data and Internet of Things age to tackle issues related to latency, real-time processing, and data scale. This paper delves into the imperative need for edge computing within the context of big data environments. Distributed deep learning methodologies are explored, encompassing a diverse array of deep learning models. Particularly, a novel paradigm named Data Forwarding based Decentralized Deep Neural Network (DF-DDNN) is introduced to achieve low latency IoT-Edge computation. In order to reduce latency in Io T ecosystems, the DF-DDNN model makes use of edge devices' processing capabilities. By strategically distributing data processing and computation at the edge, this model seeks to overcome inherent limitations of conventional Io T architectures, with a keen focus on network, processing, and overall latencies. The research provides a thorough performance evaluation that compares the DF-DDNN model's performance versus conventional IoT models in a number of areas. The outcomes demonstrate how much better the suggested DF-DDNN model is than traditional IoT systems. Notably, improvements are evident in terms of reduced network latency, accelerated processing speeds, and overall latency mitigation. This research underscores the critical importance of embracing edge computing in the context of big data and deep learning applications. The DF-DDNN model emerges as a promising avenue for advancing IoT-Edge computation, effectively addressing latency concerns and augmenting the performance of IoT-enabled systems. © 2023 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

An Effective Approach for Detection of Racism and Abusive Memes Using CNN, Roberta and BERT Algorithm

An Effective Approach for Detection of Racism and Abusive Me...

引用

computing and Data Analytics (ICCDA), International Conference on

作者： V Joseph Raymond Geogen George Bhuvan Beera Amit Pimpalkar School of Computing SRM Institute of Science and Technology Kattankulathur India University of Technology and Applied Science Ibri Oman SRM Institute of Science and Technology Kattankulathur India Department of Computer Science (AIML) Sri Ramdeobaba College of Engineering and Management Nagpur

ISBN: (数字)9798331542573

ISBN: (纸本)9798331542580

Memetics, as a social media phenomenon, are a self-evident part of the rise and rise of social media through electrifying technologies. They are intricate to classify using traditional forms of technologies because they are mainly based on both visual and textual information and more often than not they are also funny or sarcastic. The work puts forward a deep learning-based solution for meme categorization that can be classified into multiple categories. The include girl, tame, politics, hard. It emphasizes the want for an automated system that can vet memes before they become the cause of controversy or become humorous. This investigation offers the three-step procedure to locate racism and abusive memes. Before the text is labeled as racist or not, it will be extracted from the supplied image first. Once the language has been pinpointed as unacceptable, the third step is to distribute the information to the specific groups: racist and abusive are: unoffensive, nonrelevant. We present a deep learning-based method for classifying memes that can be categorized into different themes. After the graphical theft of personal information for the marketing of products through social media meme posting, society had to confront the issue of these instance being posted on the social media platform. Racist and abusive memes can cause emotional harm to people and even divide communities since they are mainly genocidal or ridiculing. The constraint of the language complexity and the variety of artistic references used in memes leave some of them generally feting and removing racist and vituperative memes. We introduce a deep literacy- attained asseveration to classify wicked memes using CNNs, Roberta, as well as BERT. When we had the inflamed dataset of and thenon-racist and vituperative memes, we machined the models. Our experimental study was carried out through the adoption of several metrics like learning accuracy, precision, recall, and F1-score. Racist and abusive memes ar

关键词： Memetics Measurement Learning systems Visualization Data analysis Accuracy Social networking (online) Nails Virtual environments Complexity theory

来源：评论

学校读者我要写书评

暂无评论

Utilizing Deep Learning in Smart Cities for Environmental Monitoring

Utilizing Deep Learning in Smart Cities for Environmental Mo...

引用

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

作者： Hoang, Dinh Cong Devi, Shova Koner, Jonardan Dhandayuthapani, Bala Choudhury, Susanta Kumar Sahoo, Deepali Rani Institute for South Asian West Asian and African Studies Department of Middle East & West Asia Studies India Amity Law School Lucknow Amity University Uttar Pradesh UP India Nicmar University Pune India College of Computing and Information Sciences University of Technology and Applied Sciences Department of It Shinas Campus Oman Gietu University Department of Civil Engineering Odisha Gunupur India Symbiosis Law School Noida India Pune India

ISBN: (纸本)9798331543617

The effectiveness and dependability of services provided by smart cities are significantly impacted by the significant and difficult issue of intrusion detection. Replay attacks, which weaken security via improper authentication in a smart city network, are among the most common threats to this infrastructure. For example, replay attacks have the potential to severely damage the smart city structure, leading to the loss of crucial data and substantial monetary losses. As a result, we have developed a model based on deep learning to predict where attacks in smart cities would be replayed. The proposed approach is intriguing since it uses deep learning-based models as an application to differentiate replay assaults and increase recognition accuracy. Replay attacks are simulated on a real-world smart city dataset, and the model's performance is assessed by using this dataset. Our findings demonstrate that the suggested model may reasonably accurately discriminate between normal and assault actions. Furthermore, our suggested model performs better than both deep learning and conventional classification models, per the findings. © 2024 IEEE.

关键词： Sustainable city

来源：评论

学校读者我要写书评

暂无评论

Intelligent Firefly Algorithm Deep Transfer Learning Based COVID-19 Monitoring System

引用

Computers, Materials & Continua 2023年第2期74卷 2889-2903页

作者： Mahmoud Ragab Mohammed W.Al-Rabia Sami Saeed Binyamin Ahmed A.Aldarmahi Information Technology Department Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah 21589Saudi Arabia Centre for Artificial Intelligence in Precision Medicines King Abdulaziz UniversityJeddah 21589Saudi Arabia Mathematics Department Faculty of ScienceAl-Azhar UniversityNaser City 11884CairoEgypt Department of Medical Microbiology and Parasitology Faculty of MedicineKing Abdulaziz UniversityJeddah 21589Saudi Arabia Health Promotion Center King Abdulaziz UniversityJeddah 21589Saudi Arabia Computer and Information Technology Department The Applied CollegeKing Abdulaziz UniversityJeddah 21589Saudi Arabia Basic Science Department College of Science and Health ProfessionsKing Saud Bin Abdulaziz University for Health SciencesJeddah 21423Saudi Arabia King Abdullah International Medical Research Center Ministry of National Guard-Health AffairsJeddah 21423Saudi Arabia

With the increasing and rapid growth rate of COVID-19 cases,the healthcare scheme of several developed countries have reached the point of *** important and critical steps in fighting against COVID-19 is powerful screening of diseased patients,in such a way that positive patient can be treated and isolated.A chest radiology image-based diagnosis scheme might have several benefits over traditional *** accomplishment of artificial intelligence(AI)based techniques in automated diagnoses in the healthcare sector and rapid increase in COVID-19 cases have demanded the requirement of AI based automated diagnosis and recognition *** study develops an Intelligent Firefly Algorithm Deep Transfer Learning Based COVID-19Monitoring System(IFFA-DTLMS).The proposed IFFADTLMSmodelmajorly aims at identifying and categorizing the occurrence of COVID19 on chest *** attain this,the presented IFFA-DTLMS model primarily applies densely connected networks(DenseNet121)model to generate a collection of feature *** addition,the firefly algorithm(FFA)is applied for the hyper parameter optimization of DenseNet121 ***,autoencoder-long short term memory(AE-LSTM)model is exploited for the classification and identification of *** ensuring the enhanced performance of the IFFA-DTLMS model,a wide-ranging experiments were performed and the results are reviewed under distinctive *** experimental value reports the betterment of IFFA-DTLMS model over recent approaches.

关键词： COVID-19 artificial intelligence intelligent systems deep learning decision making

来源：评论

学校读者我要写书评

暂无评论

Next Generation Optical Quantum State Synthesis: Observation of Fourfold Negativity in the Wigner Function

Next Generation Optical Quantum State Synthesis: Observation...

引用

2024 Laser Science, LS 2024

作者： Endo, Mamoru Takase, Kan Nomura, Takefumi Sonoyama, Tatsuki Takahashi, Kazuma Kashiwazaki, Takahiro Inoue, Asuka Umeki, Takeshi Takasu, Sachiko Fukuda, Daiji Marek, Petr Filip, Radim Asavanant, Warit Furusawa, Akira Department of Applied Physics School of Engineering The University of Tokyo 7-3-1 Hongo Tokyo Bunkyo113-8656 Japan Optical Quantum Computing Research Team RIKEN Center for Quantum Computing 2-1 Hirosawa Saitama Wako351-0198 Japan NTT Device Technology Labs. NTT Corporation 3-1 Morinosato Wakamiya Kanagawa Atsugi243-0198 Japan National Institute of Advanced Industrial Science and Technology Ibaraki Tsukuba305-8563 Japan AIST-UTokyo Advanced Operando-Measurement Technology Open Innovation Laboratory Ibaraki Tsukuba305-8563 Japan Department of Optics Palacky University 17. listopadu 1192/12 Olomouc77146 Czech Republic

An optical quantum state with fourfold Wigner negativity was generated without any loss correction. Generalized photon subtraction scheme, broadband squeezed light source, and high-temporal-resolution transition-edge sensor enabled generation rates of tens of counts per second. © 2024 The Author(s). © Optica Publishing Group 2024.

关键词： Squeezed light

来源：评论

学校读者我要写书评

暂无评论

A Novel Explainable CNN Model for Screening COVID-19 on X-ray Images

引用

Computer Systems Science & Engineering 2023年第8期46卷 1789-1809页

作者： Hicham Moujahid Bouchaib Cherradi Oussama El Gannour Wamda Nagmeldin Abdelzahir Abdelmaboud Mohammed Al-Sarem Lhoussain Bahatti Faisal Saeed Mohammed Hadwan EEIS Laboratory ENSET of MohammediaHassan II University of CasablancaMohammedia28820Morocco STIE Team CRMEF Casablanca-SettatThe Provincial Section of El JadidaEl Jadida24000Morocco Department of Information Systems College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Department of Information Systems King Khalid UniversityMuhayel Aseer61913Saudi Arabia College of Computer Science and Engineering Taibah UniversityMedina42353Saudi Arabia Department of Computer Science University of Sheba RegionMarib14400Yemen DAAI Research Group Department of Computing and Data ScienceSchool of Computing and Digital TechnologyBirmingham City UniversityBirminghamB47XGUK Department of Information Technology College of ComputerQassim UniversityBuraydah 51452Saudi Arabia Department of Computer Science College of Applied SciencesTaiz UniversityTaiz6803Yemen

Due to the rapid propagation characteristic of the Coronavirus(COVID-19)disease,manual diagnostic methods cannot handle the large number of infected individuals to prevent the spread of ***,new automated diagnostic methods have been brought on board,particularly methods based on artificial intelligence using different medical data such as X-ray *** imaging,for example,produces several image types that can be processed and analyzed by machine and deep learning methods.X-ray imaging materials widely exist in most hospitals and health institutes since they are affordable compared to other imaging *** this paper,we propose a novel Convolutional Neural Network(CNN)model(COV2Net)that can detect COVID-19 virus by analyzing the X-ray images of suspected *** model is trained on a dataset containing thousands of X-ray images collected from different *** model was tested and evaluated on an independent *** order to approve the performance of the proposed model,three CNN models namely Mobile-Net,Residential Energy Services Network(Res-Net),and Visual Geometry Group 16(VGG-16)have been implemented using transfer learning *** experiment consists of a multi-label classification task based on X-ray images for normal patients,patients infected by COVID-19 virus and other patients infected with *** proposed model is empowered with Gradient-weighted Class Activation Mapping(Grad-CAM)and Grad-Cam++techniques for a visual explanation and methodology debugging *** finding results show that the proposed model COV2Net outperforms the state-of-the-art methods.

关键词： Artificial intelligence intelligent diagnostic systems decisionmaking COVID-19 convolutional neural network

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：