检索结果-内蒙古大学图书馆

CNN Based Features Extraction and Selection Using EPO Optimizer for Cotton Leaf Diseases Classification

computers, Materials & Continua 2023年第9期76卷 2779-2793页

作者： Mehwish Zafar JaveriaAmin Muhammad Sharif Muhammad Almas Anjum Seifedine Kadry Jungeun Kim Department of Computer Science COMSATS University IslamabadWah CampusWah Cantt47040Pakistan Department of Computer Science University ofWahWah Cantt47040Pakistan National University of Technology(NUTECH) Islamabad44000Pakistan Department of Applied Data Science Noroff University CollegeKristiansandNorway Artificial Intelligence Research Center(AIRC) College of Engineering and Information TechnologyAjman UniversityAjmanUnited Arab Emirates Department of Electrical and Computer Engineering Lebanese American UniversityByblosLebanon Department of Software Kongju National UniversityCheonan31080Korea

Worldwide cotton is the most profitable cash *** year the production of this crop suffers because of several *** an early stage,computerized methods are used for disease detection that may reduce the loss in the production of *** several methods are proposed for the detection of cotton diseases,however,still there are limitations because of low-quality images,size,shape,variations in orientation,and complex *** to these factors,there is a need for novel methods for features extraction/selection for the accurate cotton disease *** in this research,an optimized features fusion-based model is proposed,in which two pre-trained architectures called EfficientNet-b0 and Inception-v3 are utilized to extract features,each model extracts the feature vector of length N×*** that,the extracted features are serially concatenated having a feature vector lengthN×*** prominent features are selected usingEmperor PenguinOptimizer(EPO)*** method is evaluated on two publically available datasets,such as Kaggle cotton disease dataset-I,and Kaggle *** EPO method returns the feature vector of length 1×755,and 1×824 using dataset-I,and dataset-II,*** classification is performed using 5,7,and 10 folds *** Quadratic Discriminant Analysis(QDA)classifier provides an accuracy of 98.9%on 5 fold,98.96%on 7 fold,and 99.07%on 10 fold using Kaggle cotton disease dataset-I while the Ensemble Subspace K Nearest Neighbor(KNN)provides 99.16%on 5 fold,98.99%on 7 fold,and 99.27%on 10 fold using Kaggle cotton-leaf-infection dataset-II.

关键词： Deep learning cotton disease detection features selection classification efficientnet-b0 inception-v3 quadratic discriminant analysis subspace KNN

来源：评论

学校读者我要写书评

暂无评论

Learning to see speckle in the weak laser field through multimode fiber

引用

Optoelectronics Letters 2025年

作者： JI Yunqi SONG Binbin LI Xueqing LI Yonghui The Engineering Research Center of Learning-Based Intelligent System (Ministry of Education)， the Key Laboratory of Computer Vision and Systems (Ministry of Education)， and the School of Computer Science and Engineering， Tianjin University of Technology

Multimode fibers (MMFs) have great potential for endoscopic imaging due to the high number of modes and a small core diameter. Deep learning based on neural networks has received increasing attention in the field of scattering image reconstruction. However， most studies focus on designing complex network architectures to improve reconstruction， but these network models struggle to reconstruct images in a weak laser field. In the paper， a lightweight generative adversarial network model combined with a histogram specification algorithm is designed to reconstruct speckles in the weak laser field through MMF. Experimental results show that the reconstruction results of our algorithm have better metrics. Moreover， the model demonstrates excellent cross-domain generalization ability with regards to the Fashion-MNIST dataset. It is worth mentioning that we found that the speckles after inactivation still retain the ability to be reconstructed， which enhances the robustness of the model

关键词：

来源：评论

学校读者我要写书评

暂无评论

Calibrating Higher-Order Statistics for Few-Shot Class-Incremental Learning with Pre-trained vision Transformers

Calibrating Higher-Order Statistics for Few-Shot Class-Incre...

引用

IEEE computer Society Conference on computer vision and Pattern Recognition Workshops (CVPRW)

作者： Dipam Goswami Bartłomiej Twardowski Joost Van de Weijer Department of Computer Science Universitat Autònoma de Barcelona Computer Vision Center Barcelona IDEAS-NCBR

ISBN: (数字)9798350365474

ISBN: (纸本)9798350365481

Few-shot class-incremental learning (FSCIL) aims to adapt the model to new classes from very few data (5 samples) without forgetting the previously learned classes. Recent works in many-shot CIL (MSCIL) (using all available training data) exploited pre-trained models to reduce forgetting and achieve better plasticity. In a similar fashion, we use ViT models pre-trained on large-scale datasets for few-shot settings, which face the critical issue of low plasticity. FSCIL methods start with a many-shot first task to learn a very good feature extractor and then move to the few-shot setting from the second task onwards. While the focus of most recent studies is on how to learn the many-shot first task so that the model generalizes to all future few-shot tasks, we explore in this work how to better model the few-shot data using pre-trained models, irrespective of how the first task is trained. Inspired by recent works in MSCIL, we explore how using higher-order feature statistics can influence the classification of few-shot classes. We identify the main challenge of obtaining a good covariance matrix from few-shot data and propose to calibrate the covariance matrix for new classes based on semantic similarity to the many-shot base classes. Using the calibrated feature statistics in combination with existing methods significantly improves few-shot continual classification on several FSCIL benchmarks. Code is available at https://***/dipamgoswami/FSCIL-Calibration.

关键词： Adaptation models computer vision Training data Benchmark testing Feature extraction Transformers Data models

来源：评论

学校读者我要写书评

暂无评论

The Expanding Scope of the Stability Gap: Unveiling its Presence in Joint Incremental Learning of Homogeneous Tasks

arXiv

引用

arXiv 2024年

作者： Kamath, Sandesh Soutif-Cormerais, Albin van de Weijer, Joost Raducanu, Bogdan Department of Computer Science Universitat Autònoma de Barcelona Spain Computer Vision Center Barcelona Spain

Recent research identified a temporary performance drop on previously learned tasks when transitioning to a new one. This drop is called the stability gap and has great consequences for continual learning: it complicates the direct employment of continually learning since the worse-case performance at task-boundaries is dramatic, it limits its potential as an energy-efficient training paradigm, and finally, the stability drop could result in a reduced final performance of the algorithm. In this paper, we show that the stability gap also occurs when applying joint incremental training of homogeneous tasks. In this scenario, the learner continues training on the same data distribution and has access to all data from previous tasks. In addition, we show that in this scenario, there exists a low-loss linear path to the next minima, but that SGD optimization does not choose this path. We perform further analysis including a finer batch-wise analysis which could provide insights towards potential solution directions. © 2024, CC BY-NC-SA.

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

On Error-Based Step Size Control for Discontinuous Galerkin Methods for Compressible Fluid Dynamics

引用

应用数学与计算数学学报 2025年第1期7卷 3-39页

作者： Hendrik Ranocha Andrew R.Winters Hugo Guillermo Castro Lisandro Dalcin Michael Schlottke-Lakemper Gregor J.Gassner Matteo Parsani Applied Mathematics University of HamburgBundesstr.5520146 HamburgGermany Department of Mathematics Applied Mathematics Linköping UniversityLinköpingSweden Extreme Computing Research Center(ECRC) Computer Electrical and Mathematical Science and Engineering Division(CEMSE)King Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Saudi Arabia Applied and Computational Mathematics RWTH Aachen UniversityAachenGermany High-Performance Computing Center Stuttgart University of StuttgartStuttgartGermany Department of Mathematics and Computer Science University of CologneCologneGermany Center for Data and Simulation Science University of CologneCologneGermany Extreme Computing Research Center(ECRC) Computer Electrical and Mathematical Science and Engineering Division(CEMSE)King Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Saudi Arabia Physical Science and Engineering Division(PSE) King Abdullah University of Science and Technology(KAUST)Thuwal 23955-6900Saudi Arabia

We study a temporal step size control of explicit Runge-Kutta(RK)methods for com-pressible computational fluid dynamics(CFD),including the Navier-Stokes equations and hyperbolic systems of conservation laws such as the Euler *** demonstrate that error-based approaches are convenient in a wide range of applications and compare them to more classical step size control based on a Courant-Friedrichs-Lewy(CFL)*** numerical examples show that the error-based step size control is easy to use,robust,and efficient,e.g.,for(initial)transient periods,complex geometries,nonlinear shock captur-ing approaches,and schemes that use nonlinear entropy *** demonstrate these properties for problems ranging from well-understood academic test cases to industrially relevant large-scale computations with two disjoint code bases,the open source Julia pack-ages *** with *** and the C/Fortran code SSDC based on PETSc.

关键词： Explicit Runge-Kutta(RK)methods Step size control Compressible fluid dynamics Adaptivity in space and time Shock capturing

来源：评论

学校读者我要写书评

暂无评论

A study of the leverage effect in Bitcoin Conditional Heteroskedasticity prediction 10

A study of the leverage effect in Bitcoin Conditional Hetero...

引用

10th International Conference on Artificial Intelligence and Robotics, QICAR 2024

作者： Abarghouie, Masoud Omidvari Alizadeh, Sasan H. Khademzadeh, Ahmad Department of Computer Engineering Science and Research branch Islamic Azad University Tehran Iran Faculty of Information Technology Iran Telecommunication Research Center Tehran Iran Iran Telecommunication Research Center Tehran Iran

ISBN: (纸本)9798350348873

In today's world, countries establish large companies specifically designed to effectively manage the risks associated with volatility exchange rates and leveraged assets. Bitcoin is widely recognized as the leading cryptocurrency, making it highly appealing to investors and traders. The recorded data reveals a growing number of transactions conducted using Bitcoin cryptocurrency. Consequently, accurately predicting the volatility of Bitcoin's conditional heteroskedasticity holds significant importance for the financial markets. Cryptocurrencies present a challenging situation due to their complex dynamics, extreme observations, asymmetry, and various other non-linear features. Modeling these cryptocurrencies accurately becomes difficult using statistical models, as they fail to consider the leverage effect and provide precise predictions. In this paper, we have employed a hybrid modeling approach by utilizing MLP neural network and GARCH statistical model. The experiments conducted on Bitcoin time series data have yielded promising results, showcasing a notable reduction in the prediction error of conditional heteroskedasticity volatility. ©2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Transfer Multi-task Learning Approach for Scene Classification 27th

Hierarchical Transfer Multi-task Learning Approach for Scen...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Khoshkangini, Reza Tajgardan, Mohsen Jamali, Mahtab Ljungqvist, Martin Georg Mihailescu, Radu-Casian Davidsson, Paul Internet of Things and People Research Center Department of Computer Science and Media Technology Malmö University Malmö Sweden Faculty of Electrical and Computer Engineering Qom University of Technology Qom Iran Axis Communications AB Lund Sweden

ISBN: (纸本)9783031781063

This paper presents a novel Hierarchical Transfer and Multi-task Learning (HTMTL) approach designed to substantially improve the performance of scene classification networks by leveraging the collective influence of diverse scene types. HTMTL is distinguished by its ability to capture the interaction between various scene types, recognizing how context information from one scene category can enhance the classification performance of another. Our method, when applied to the Places365 dataset, demonstrates a significant improvement in the network’s ability to accurately identify scene types. By exploiting these inter-scene interactions, HTMTL significantly enhances scene classification performance, making it a potent tool for advancing scene understanding and classification. Additionally, this study explores the contribution of individual tasks and task groupings on the performance of other tasks. To further validate the generality of HTMTL, we applied it to the Cityscapes dataset, where the results also show promise. This indicates the broad applicability and effectiveness of our approach across different datasets and scene types. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

BS3D: Building-Scale 3D Reconstruction from RGB-D Images 23rd

BS3D: Building-Scale 3D Reconstruction from RGB-D Images

引用

22nd Scandinavian Conference on Image Analysis, SCIA 2023

作者： Mustaniemi, Janne Kannala, Juho Rahtu, Esa Liu, Li Heikkilä, Janne Center for Machine Vision and Signal Analysis University of Oulu Oulu Finland Department of Computer Science Aalto University Espoo Finland Tampere University Tampere Finland

ISBN: (纸本)9783031314377

Various datasets have been proposed for simultaneous localization and mapping (SLAM) and related problems. Existing datasets often include small environments, have incomplete ground truth, or lack important sensor data, such as depth and infrared images. We propose an easy-to-use framework for acquiring building-scale 3D reconstruction using a consumer depth camera. Unlike complex and expensive acquisition setups, our system enables crowd-sourcing, which can greatly benefit data-hungry algorithms. Compared to similar systems, we utilize raw depth maps for odometry computation and loop closure refinement which results in better reconstructions. We acquire a building-scale 3D dataset (BS3D) and demonstrate its value by training an improved monocular depth estimation model. As a unique experiment, we benchmark visual-inertial odometry methods using both color and active infrared images. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Advanced BERT and CNN-Based Computational Model for Phishing Detection in Enterprise Systems

引用

computer Modeling in Engineering & sciences 2024年第12期141卷 2165-2183页

作者： Brij B.Gupta Akshat Gaurav Varsha Arya Razaz Waheeb Attar Shavi Bansal Ahmed Alhomoud Kwok Tai Chui Department of Computer Science and Information Engineering Asia UniversityTaichung413Taiwan Symbiosis Centre for Information Technology(SCIT) Symbiosis International UniversityPune411057India Center for Interdisciplinary Research University of Petroleum and Energy Studies(UPES)Dehradun248007India University Centre for Research and Development(UCRD) Chandigarh UniversityChandigarh140413India Computer Engineering Ronin InstituteMontclairNJ 07043USA Department of Business Administration Asia UniversityTaichung413Taiwan Department of Electrical and Computer Engineering Lebanese American UniversityBeirut1102Lebanon College of Business Administration Management DepartmentPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Research and Innovation Insights2TechinfoJaipur302001India Department of Computer Sciences Faculty of Computing and Information TechnologyNorthern Border UniversityRafha91911Saudi Arabia Department of Electronic Engineering and Computer Science Hong Kong Metropolitan University(HKMU)Hong Kong518031China

Phishing attacks present a serious threat to enterprise systems,requiring advanced detection techniques to protect sensitive *** study introduces a phishing email detection framework that combines Bidirectional Encoder Representations from Transformers(BERT)for feature extraction and CNN for classification,specifically designed for enterprise information ***’s linguistic capabilities are used to extract key features from email content,which are then processed by a convolutional neural network(CNN)model optimized for phishing *** an accuracy of 97.5%,our proposed model demonstrates strong proficiency in identifying phishing *** approach represents a significant advancement in applying deep learning to cybersecurity,setting a new benchmark for email security by effectively addressing the increasing complexity of phishing attacks.

关键词： Phishing BERT convolutional neural networks email security deep learning

来源：评论

学校读者我要写书评

暂无评论

Structural and functional connectivity of the whole brain and subnetworks in individuals with mild traumatic brain injury:predictors of patient prognosis

引用

Neural Regeneration research 2024年第7期19卷 1553-1558页

作者： Sihong Huang Jungong Han Hairong Zheng Mengjun Li Chuxin Huang Xiaoyan Kui Jun Liu Department of Radiology The Second Xiangya HospitalCentral South UniversityChangshaHunan ProvinceChina Department of Computer Science Aberystwyth UniversityAberystwythCeredigionUK Shenzhen Institutes of Advanced Technology Chinese Academy of SciencesShenzhenGuangdong ProvinceChina School of Computer Science and Engineering Central South UniversityChangshaHunan ProvinceChina Department of Radiology Quality Control Center of Hunan ProvinceChangshaHunan ProvinceChina Clinical Research Center for Medical Imaging of Hunan Province ChangshaHunan ProvinceChina

Patients with mild traumatic brain injury have a diverse clinical presentation,and the underlying pathophysiology remains poorly *** resonance imaging is a non-invasive technique that has been widely utilized to investigate neuro biological markers after mild traumatic brain *** approach has emerged as a promising tool for investigating the pathogenesis of mild traumatic brain injury.G raph theory is a quantitative method of analyzing complex networks that has been widely used to study changes in brain structure and ***,most previous mild traumatic brain injury studies using graph theory have focused on specific populations,with limited exploration of simultaneous abnormalities in structural and functional *** that mild traumatic brain injury is the most common type of traumatic brain injury encounte red in clinical practice,further investigation of the patient characteristics and evolution of structural and functional connectivity is *** the present study,we explored whether abnormal structural and functional connectivity in the acute phase could serve as indicators of longitudinal changes in imaging data and cognitive function in patients with mild traumatic brain *** this longitudinal study,we enrolled 46 patients with mild traumatic brain injury who were assessed within 2 wee ks of injury,as well as 36 healthy ***-state functional magnetic resonance imaging and diffusion-weighted imaging data were acquired for graph theoretical network *** the acute phase,patients with mild traumatic brain injury demonstrated reduced structural connectivity in the dorsal attention *** than 3 months of followup data revealed signs of recovery in structural and functional connectivity,as well as cognitive function,in 22 out of the 46 ***,better cognitive function was associated with more efficient ***,our data indicated that small-worldness in the acute sta

关键词： cognitive function cross-section follow-up functional connectivity graph theory longitudinal study mild traumatic brain injury prediction small-worldness structural connectivity subnetworks whole brain 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：