检索结果-内蒙古大学图书馆

Optimal Synergic Deep Learning for COVID-19 Classification Using Chest X-Ray Images

computers, Materials & Continua 2023年第6期75卷 5255-5270页

作者： JoséEscorcia-Gutierrez Margarita Gamarra Roosvel Soto-Diaz Safa Alsafari Ayman Yafoz Romany F.Mansour Departament of Computational Science and Electronic Universidad de la CostaCUCBarranquilla080002Colombia Biomedical Engineering Program Universidad Simón BolívarBarranquilla080002Colombia Department of Computer Science and AI Faculty of Computer Science and EngineeringUniversity of JeddahJeddahSaudi Arabia Department of Information Systems Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddahSaudi Arabia Department of Mathematics Faculty of ScienceNew Valley UniversityEl-Kharga72511Egypt

A chest radiology scan can significantly aid the early diagnosis and management of COVID-19 since the virus attacks the *** X-ray(CXR)gained much interest after the COVID-19 outbreak thanks to its rapid imaging time,widespread availability,low cost,and *** radiological investigations,computer-aided diagnostic tools are implemented to reduce intra-and inter-observer *** lately industrialized Artificial Intelligence(AI)algorithms and radiological techniques to diagnose and classify disease is *** current study develops an automatic identification and classification model for CXR pictures using Gaussian Fil-tering based Optimized Synergic Deep Learning using Remora Optimization Algorithm(GF-OSDL-ROA).This method is inclusive of preprocessing and classification based on *** data is preprocessed using Gaussian filtering(GF)to remove any extraneous noise from the image’s ***,the OSDL model is applied to classify the CXRs under different severity levels based on CXR *** learning rate of OSDL is optimized with the help of ROA for COVID-19 diagnosis showing the novelty of the *** model,applied in this study,was validated using the COVID-19 *** experiments were conducted upon the proposed OSDL model,which achieved a classification accuracy of 99.83%,while the current Convolutional Neural Network achieved less classification accuracy,i.e.,98.14%.

关键词： Artificial intelligence chest X-ray COVID-19 optimized synergic deep learning preprocessing public health

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Detection Using Breastnet-18 Augmentation with Fine Tuned Vgg-16

引用

Intelligent Automation & Soft Computing 2023年第5期36卷 2363-2378页

作者： S.J.K.Jagadeesh Kumar P.Parthasarathi Mofreh A.Hogo Mehedi Masud Jehad F.Al-Amri Mohamed Abouhawwash Department of Computer Science and Engineering Kathir College of EngineeringCoimbatore641062India Department of Computer Science and Engineering Bannari Amman Institute of TechnologySathyamangalam638401TamilnaduIndia Electrical Engineering Department Faculty of EngineeringBenha UniversityBenha13518Egypt Department of Computer Science College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif21944Saudi Arabia Department of Information Technology College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif21944Saudi Arabia Department of Mathematics Faculty of ScienceMansoura UniversityMansoura35516Egypt Department of Computational Mathematics Scienceand Engineering(CMSE)Michigan State UniversityEast LansingMI48824USA

Women from middle age to old age are mostly screened positive for Breast cancer which leads to *** over the past decades,the overall sur-vival rate in breast cancer has improved due to advancements in early-stage diag-nosis and tailored *** all hospital brings high awareness and early detection technologies for breast *** increases the survival rate of *** traditional breast cancer treatment takes so long,early cancer techniques require an automation *** research provides a new methodol-ogy for classifying breast cancer using ultrasound pictures that use deep learning and the combination of the best ***,after successful learning of Convolutional Neural Network(CNN)algorithms,data augmentation is used to enhance the representation of the feature *** it uses BreastNet18 withﬁne-tuned VGG-16 model for pre-training the augmented *** feature classiﬁcation,Entropy controlled Whale Optimization Algorithm(EWOA)is *** features that have been optimized using the EWOA were utilized to fuse and optimize the *** identify the breast cancer pictures,training classiﬁers are *** using the novel probability-based serial technique,the best-chosen characteristics are fused and categorized by machine learning *** main objective behind the research is to increase tumor prediction accuracy for saving human *** testing was performed using a dataset of enhanced Breast Ultrasound Images(BUSI).The proposed method improves the accuracy com-pared with the existing methods.

关键词： Deep learning classiﬁcation data augmentation feature extraction the fusion of features breast cancer optimization classiﬁcation

来源：评论

学校读者我要写书评

暂无评论

Marine Ecosystem Monitoring: Applying Remote Sensing and AI to Track and Predict Coral Reef Health

引用

Remote Sensing in Earth Systems sciences 2024年第4期7卷 486-499页

作者： Veeranjaneyulu, Rayavarapu Govindarajan, Dinesh Subramanian, Chandramohan Devi, Deva Uma Banerjee, Sudipta Edpuganti, Sai Krishna Upadhyay, Shrikant Department of Computer Science & amp Engineering PACE Institute of Technology and Sciences Andhra Pradesh Ongole India Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur (KTR) Chennai India Department of ECE SCSVMV Deemed University Tamil Nadu Kanchipuram India Department of Computer Science and Engineering Gayatri Vidya Parishad College of Engineering (A) Andhra Pradhesh Visakhapatnam India Department of Computer Science and Engineering Symbiosis Institute of Technology Symbiosis International (Deemed University) (SIU) Pune Campus Pune India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram Guntur Dist. India Department of Electronics and Communication Engineering MLR Institute of Technology Hyderabad India

Coral reefs are essential ecosystems, supporting a diverse range of marine life and offering considerable ecological, economic, and cultural benefits. However, they face increasing threats from climate change, pollution, and other human activities. Thus, effective monitoring and management of coral reefs are crucial for their conservation and sustainability. In this study, we employed a hybrid model, HCNN-SVM, which combines convolutional neural networks (CNNs) for feature extraction and support vector machines (SVMs) for classification. We utilized a coral-reef dataset from Kaggle, containing images from CoralNet and the Moorea Coral Reef Long Term Ecological Research (MCR LTER). To enhance image quality and ensure accurate reflectance values, we applied radiometric, geometric, and water column corrections during preprocessing. Feature extraction involved the use of spectral indices such as the Coral Bleaching Index (CBI) and Normalized Difference Vegetation Index (NDVI) to detect healthy and stressed corals, along with texture analysis to differentiate substrates. The model was trained on this diverse dataset, which captures various environmental conditions and reef types, achieving an accuracy of 98.55%. Cross-validation methods were employed to evaluate model performance, ensuring robustness and generalizability. The HCNN-SVM model demonstrated high accuracy in identifying and mapping coral reef components, making it a powerful tool for monitoring coral reef health and supporting conservation efforts. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Convolutional neural networks (CNNs) Coral Bleaching Index (CBI) Coral reef monitoring Feature extraction HCNN-SVM Moorea Coral Reef Long Term Ecological Research (MCR LTER) Normalized Difference Vegetation Index (NDVI) Support vector machines (SVMs)

来源：评论

学校读者我要写书评

暂无评论

Heat transfer analysis of TiO2-H2O based nanofluid flow across a porous stretching sheet with heat source/sink using Response Surface Methodology

Heat transfer analysis of TiO2-H2O based nanofluid flow acro...

引用

2024 International Conference on Thermofluids and Manufacturing science, ICTMS 2024

作者： Reshmi, V.P. Nagaraja, K.V. Shankara Department of Computer Science &engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India Computational Science Lab Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru India Department of Civil Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru India

Efforts are focused on optimizing thermal energy control and utilization within the system. The analysis is done on heat transmission characteristics of a TiO2.H2O nanofluid flowing over a stretching sheet with an integrated heat source/sink. Sensitivity analysis is performed using Response Surface Methodology (RSM) to understand heat transfer behaviour effectively. Governing equations are transformed into ordinary differential equations using suitable similarity variables. Mathematical formulation for steady two-dimensional flow of nanofluid in a porous medium along with a stretching sheet is established, and numerical outcomes are optimized using RSM. Influence of porous medium (A), volume fraction (φ), and heat source/sink (Hs) on Nusselt number (Nu) and skin friction factor (Cf) is analyzed through normal, response surface, and contour plots and it is found that for increasing Hs decreases Nu for higher φ values. © Published under licence by IOP Publishing Ltd.

关键词： Porous materials

来源：评论

学校读者我要写书评

暂无评论

Enhancing Solar Energy Harvesting Efficiency: A Dual-Axis Solar Tracking System 4

Enhancing Solar Energy Harvesting Efficiency: A Dual-Axis So...

引用

4th International Conference on Innovative Practices in Technology and Management, ICIPTM 2024

作者： Ravikumar, S. Eugene Berna, I. Vijay, K. Pradeep, R. Babu, R. R&d Institute of Science and Technology Vel Tech Rangarajan Dr.Sagunthala Department of Computer Science and Engineering Chennai India Bannari Amman Institute of Technology Department of Artificial Intelligence and Machine Learning Erode India Rajalakshmi Engineering College Department of Computer Science and Engineering Chennai India Srm Institute of Science and Technology Faculty of College of Engineering and Technology Department of Computational Intelligence Kattankulathur Chennai India

ISBN: (数字)9798350307757

ISBN: (纸本)9798350307757

The photovoltaic effect has permanently transformed the landscape of renewable sources by making it possible to convert solar energy into useable power. This concept is based on solar photovoltaic (PV) cells, but current PV technology limits us to capturing just a small percentage of the sun's energy at any given time. However, productivity can be greatly increased by using solar monitoring equipment. Creating and validating a low-priced active dual-axis solar tracking system is a breeze if you follow the steps outlined in this article. The best orientation for solar panels is perpendicular to the sun because their production is directly related to the amount of light they receive. Conventional solar panels have trouble keeping up with the ever-changing ideal angle for sunlight absorption and energy gathering. By tracing the sun's movement across the sky, solar trackers can triple the effectiveness of solar panels. This technological advancement is expected to lead to an improvement in energy generation and overall efficiency. This state-of-the-art solar tracker is powered by LEDs and an Arduino Uno. These systems work together to follow the sun's motion and maintain the solar panels facing the appropriate way. To ensure that the solar panels receive the most amount of sunshine possible, the system will automatically adjust their angle. Data processing and analysis in LabVIEW demonstrated the improved efficiency of the novel architecture. Researchers discovered a remarkable 13.44% boost in energy production compared to conventional fixed solar PV systems. © 2024 IEEE.

关键词： Solar panels

来源：评论

学校读者我要写书评

暂无评论

FADA: Flooding Attack Defense AODV Protocol to counter Flooding Attack in MANET 5

FADA: Flooding Attack Defense AODV Protocol to counter Flood...

引用

5th IEEE International Conference on Advances in Electronics, computers and Communications, ICAECC 2023

作者： Kiruthika, M. Krishnasamy, Lalitha Samuel, Prithi Kanagaraj, Kaavya School of Computing SRM Institute of Science and Technology Department of Computational Intelligence Tamilnadu Kattankulathur India School of Engineering and Technology Christ University Department of Computer Science and Engineering Karnataka Bengaluru India

ISBN: (纸本)9798350305449

The intrinsic nature of a Mobile Ad hoc Network (MANET) makes it difficult to provide security and it is more vulnerable to network attacks. Denial of Service (DoS) attack can be executed using Flooding attack, that has the potential to bring down the entire network. This attack works by delivering an excessive number of unwanted packets that consumes too much battery life, storage space, and bandwidth, that eventually lowers the system's performance. In order to flood the network, the attacker injects fake packets into it. Both Control Packet flooding and Data flooding attacks are taken into account in this study. FADA (Flooding Attack Defense AODV) protocol is proposed to counter flooding attack that promotes greater utilization of existing resources. This research identifies the attack-causing node, isolates it and protects the network against flooding attack. Attack Detection Rate, Attack Detection Accuracy, End-to-end delay and Throughput are few metrics used for evaluation of the proposed model. NS-2.35 is used to demonstrate the efficiency of the suggested protocol and the results prove that the proposed model increases system's throughput while decreasing attack. The simulation results have shown that the proposed FADA protocol performs better than the existing models taken into consideration. © 2023 IEEE.

关键词： Mobile ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

Predictive Analysis of Consumer Behavior Using Supervised Learning Techniques 2

Predictive Analysis of Consumer Behavior Using Supervised Le...

引用

2nd International Conference computational and Characterization Techniques in engineering and sciences, IC3TES 2024

作者： Rekha, K. Sashi Amutha, T. Usharani, R. Pushparani, S. Sivagami, V.M. Saveetha Institute of Medical and Technical Sciences Simats Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Care College of Engineering Department of Artificial Intelligence & Data Science Tamil Nadu Trichy India Srm Institute of Science and Technology Faculty of Engineering and Technology Department of Computational Intelligence School of Computing Chennai India Meenakshi College of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Sri Venkateswara College of Engineering Department of Information Technology Tamil Nadu Chennai India

ISBN: (纸本)9798350364699

The study presented here consists of an entire framework for prediction of consumers behavior through the machine training of supervised learning methods. The strategy involves the following: data collection, preprocessing, exploration, feature selection, model selection, training, evaluation, interpretation and deployment. The systematic process is tailored to clear the pathway for combining data about customer taste, sophisticated habits, and purchasing trends. Primary components include data preprocessing, training of machine learning models, feature selection, and ethical issues regarding data privacy and transparency. The outcomes of the implementation are a high accuracy in consumers clustering, efficient classification of customers' behavior, as well as unveiling a bunch of crucial predictors that affect the customers mood and behavior. As a result, the report stresses the necessity of integrated monitoring and redirection strategies to realize the potential of the created models. The idea of predictive analysis as an evolving tool that enables marketers to tailor their campaigns more closely, and improve the overall customer experience therefore also receives attention. The proposed system methodology constitutes a solid process framework for business defined to aim at using predictive analytics to gain competitive edge in the current dynamic marketplace. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Image Reconstruction Via Autoencoding Sequential Deep Image Prior 38

Image Reconstruction Via Autoencoding Sequential Deep Image ...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Alkhouri, Ismail R. Liang, Shijun Bell, Evan Qu, Qing Wang, Rongrong Ravishankar, Saiprasad Department of Computational Mathematics Science & Engineering Michigan State University United States Department of Electrical Engineering & Computer Science University of Michigan Ann Arbor United States Department of Biomedical Engineering Michigan State University United States Department of Mathematics Michigan State University United States

Recently, Deep Image Prior (DIP) has emerged as an effective unsupervised one-shot learner, delivering competitive results across various image recovery problems. This method only requires the noisy measurements and a forward operator, relying solely on deep networks initialized with random noise to learn and restore the structure of the data. However, DIP is notorious for its vulnerability to overfitting due to the overparameterization of the network. Building upon insights into the impact of the DIP input and drawing inspiration from the gradual denoising process in cutting-edge diffusion models, we introduce Autoencoding Sequential DIP (aSeqDIP) for image reconstruction. This method progressively denoises and reconstructs the image through a sequential optimization of network weights. This is achieved using an input-adaptive DIP objective, combined with an autoencoding regularization term. Compared to diffusion models, our method does not require training data and outperforms other DIP-based methods in mitigating noise overfitting while maintaining a similar number of parameter updates as Vanilla DIP. Through extensive experiments, we validate the effectiveness of our method in various image reconstruction tasks, such as MRI and CT reconstruction, as well as in image restoration tasks like image denoising, inpainting, and non-linear deblurring. Our code is available at the GitHub repository aSeqDIP. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Deep Neural Operator Models Toward Ocean Forecasting

Evaluation of Deep Neural Operator Models Toward Ocean Forec...

引用

2023 MTS/IEEE U.S. Gulf Coast, OCEANS 2023

作者： Rajagopal, Ellery Babu, Anantha N. S. Ryu, Tony Haley, Patrick J. Mirabito, Chris Lermusiaux, Pierre F. J. Massachusetts Institute of Technology Department of Electrical Engineering and Computer Science CambridgeMA United States Center for Computational Science and Engineering Massachusetts Institute of Technology Department of Mechanical Engineering CambridgeMA United States

ISBN: (纸本)9798218142186

Data-driven, deep-learning modeling frameworks have been recently developed for forecasting time series data. Such machine learning models may be useful in multiple domains including the atmospheric and oceanic ones, and in general, the larger fluids community. The present work investigates the possible effectiveness of such deep neural operator models for reproducing and predicting classic fluid flows and simulations of realistic ocean dynamics. We first briefly evaluate the capabilities of such deep neural operator models when trained on a simulated two-dimensional fluid flow past a cylinder. We then investigate their application to forecasting ocean surface circulation in the Middle Atlantic Bight and Massachusetts Bay, learning from high-resolution data-assimilative simulations employed for real sea experiments. We confirm that trained deep neural operator models are capable of predicting idealized periodic eddy shedding. For realistic ocean surface flows and our preliminary study, they can predict several of the features and show some skill, providing potential for future research and applications. © 2023 The Marine Technology Society (MTS).

关键词： Flow of fluids

来源：评论

学校读者我要写书评

暂无评论

Enhanced Diagnosis of Schizophrenia Using Integrated Node Embedding and Causal Discovery on Imbalanced fMRI Data 10

Enhanced Diagnosis of Schizophrenia Using Integrated Node Em...

引用

10th International Conference on Signal Processing and Intelligent Systems, ICSPIS 2024

作者： Sabzevar, Sina Masoudnia, Saeed Araabi, Babak N Nazemzadeh, MohammadReza Tavakoli, Hosna University of Tehran Department of Electrical and Computer Engineering Tehran Iran Monash University Department of Neuroscience Melbourne Australia Institute of Cognitive Science Studies Computational and Artificial Intelligence Department Tehran Iran

ISBN: (纸本)9798331532543

This study introduces a novel diagnostic method for schizophrenia using causal discovery and node embedding techniques on resting-state fMRI data. Data from 148 subjects (27 schizophrenia patients, 121 healthy controls) were analyzed across 116 brain regions, applying several causal discovery techniques to assess directional connectivity and uncover schizophrenia-related patterns. By combining advanced causal discovery with node embedding techniques and a rigorous data-balancing pipeline, our method improves sensitivity to subtle network variations critical for schizophrenia diagnosis. Our approach addresses key challenges in the literature: the difficulty of extracting effective neurobiological markers from noisy and complex fMRI data, the limited interpretability of connectivity networks, and the imbalance in datasets that often skews classification performance. Experimental results demonstrate the pipeline's effectiveness in overcoming imbalanced data challenges and extracting features from noisy and complex data, with Regression Dynamic Causal Modeling (RDCM) achieving the highest classification metrics, including 90.06% accuracy and 89.09% sensitivity. This method identified 15 brain regions with strong diagnostic potential, offering improved sensitivity and specificity for schizophrenia diagnosis Compared to contemporary domain techniques. © 2024 IEEE.

关键词： Diseases

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：