检索结果-内蒙古大学图书馆

Acoustics, Speech, and Signal processing Workshops (ICASSPW), IEEE International conference on

作者： Roman Jacome Brayan Monroy Jorge Bacca Henry Arguello Universidad Industrial de Santander Bucaramanga Colombia

The Deep image Prior (DIP) technique has been successfully employed in Compressive Spectral Imaging (CSI) as a non-data-driven deep model approach. DIP methodology updates the deep network’s weights by minimizing a loss function that considers the difference between the measurements and the forward operator of the network’s output. However, this method often yields local minima as all the measurements are evaluated at each iteration. This paper proposes a stochastic deep image prior (SDIP) approach, which stochastically trains DIP networks using random subsets of measurements from different CSI sensors in a CSI fusion (CSIF) setting, resulting in the improvement of the convergence through stochastic gradient descent optimization. The proposed SDIP method improves upon the deterministic DIP and requires less computational time since fewer forward operators are required per iteration. The SPID method provides comparable performance against the state-of-the-art CSF techniques based on supervised data-driven and unsupervised methods, achieving up to 5 dB in the reconstruction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Applications of Artificial Intelligence in Biomedical image processing 2

Applications of Artificial Intelligence in Biomedical Image ...

引用

2nd International conference on Artificial Intelligence and Smart Energy, ICAIS 2022

作者： Rajeyyagari, Sivaram Hung, Bui Thanh Chakrabarti, Prasun Shaqra University College of Computing and Information Technology Department of Computer Science Shaqra Saudi Arabia Thu Dau Mot University Data Analytics and Artificial Intelligence Laboratory Engineering Technology Faculty Thu Dau Mot Viet Nam Provost and Institute Endowed Distinguished Senior Chair Professor Techno India Njr Institute of Technology Rajasthan India

ISBN: (纸本)9781665400527

The biomedical applications of nanoparticles are growing in recent years. The uses range from diagnostic to therapeutic purposes, and researchers are constantly introducing new ways. Biosensors, miniaturization techniques, surface enhancement in implantable biomaterials, and better nanofibers in medical textiles are some of the contributions of biomedical nanotechnology. Therapeutic (medical) imaging successfully maps the anatomy of the human body. image enhancement, analysis, categorization, and image based representation are all possible areas of computer processing and analysis of medical images. Therapeutic image understanding uses computer vision, applied mathematics, signal analysis, and artificial intelligence to recognise objects in medical images. image processing is the use of computer algorithms to manipulate digital images. Hand-held transducers emit and receive pulsed acoustic waves for medical ultrasound imaging. In this study, a computer-aided diagnosis method is developed to help cytotechnicians locate and classify aberrant cells in cervical cytology images. With the outcomes of morphological and statistical edge based segmentation are compared to traditional segmentation techniques. The proposed segmentation methodology outperforms the other methods. This proposed technique's segmentation accuracy is 98%. © 2022 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Data-Based Cognition and Intelligent Communication Algorithm of Tourist Destination image Under the Internet Background 1

Data-Based Cognition and Intelligent Communication Algorithm...

引用

1st International conference on Applied Artificial Intelligence and Computing, ICAAIC 2022

作者： Sun, Sheng Shandong Youth University of Political Science Shandong Jinan250103 China

ISBN: (纸本)9781665497107

Based on the understanding of the tourist destination image as a whole system, this paper uses data cognition as the data source, uses the intelligent communication algorithm to explore the cognitive process of the tourist destination image elements, and establishes a cognitive process model of the tourist destination image elements., using statistical methods to study the dimensional differences in the cognitive process of tourist destination image elements. Both emotional image and overall image have a positive effect on word-of-mouth dissemination willingness. Among cognitive images, only tourism quality, natural resources and human resources have a significant positive impact on word-of-mouth dissemination willingness. © 2022 IEEE.

关键词： image processing

来源：评论

学校读者我要写书评

暂无评论

stochastic Model of siRNA Endosomal Escape Mediated by Fusogenic Peptides in OVCAR-3

arXiv

引用

arXiv 2024年

作者： Yadav, Nisha Boulos, Jessica Cook, Keisha Alexander-Bryant, Angela School of Mathematical and Statistical Sciences Clemson University United States Department of Bioengineering Clemson University United States

Gene silencing via small interfering RNA (siRNA) represents a transformative tool in cancer therapy, offering specificity and reduced off-target effects compared to conventional treatments. A crucial step in siRNA-based therapies is endosomal escape, the release of siRNA from endosomes into the cytoplasm. Quantifying endosomal escape is challenging due to the dynamic nature of the process and limitations in imaging and analytical techniques. Traditional methods often rely on fluorescence intensity measurements or manual image processing, which are time-intensive and fail to capture continuous dynamics. This paper presents a novel computational framework that integrates automated image processing to analyze time-lapse fluorescent microscopy data of endosomal escape, hierarchical Bayesian inference, and stochastic simulations. Our method employs image segmentation techniques such as binary masks, Gaussian filters, and multichannel color quantification to extract precise spatial and temporal data from microscopy images. Using a hierarchical Bayesian approach, we estimate the parameters of a compartmental model that describes endosomal escape dynamics, accounting for variability over time. These parameters inform a Gillespie stochastic simulation algorithm, ensuring realistic simulations of siRNA release events over time. By combining these techniques, our framework provides a scalable and reproducible method for quantifying endosomal escape. The model captures uncertainty and variability in parameter estimation, and endosomal escape dynamics. Additionally, synthetic data generation allows researchers to validate experimental findings and explore alternative conditions without extensive laboratory work. This integrated approach not only improves the accuracy of endosomal escape quantification but also provides predictive insights for optimizing siRNA delivery systems and advancing gene therapy research. Copyright © 2024, The Authors. All rights reserved.

关键词： stochastic models

来源：评论

学校读者我要写书评

暂无评论

A Robust Large-scale Dataset for Assessing Light Field image Quality

A Robust Large-scale Dataset for Assessing Light Field Image...

引用

IEEE International conference on Signal and image processing (ICSIP)

作者： Jian Ma Zhuochi Liu Yaozong Xu Jiajun Yu Yang Wang Yuhao Liu School of Internet Anhui University Hefei China

ISBN: (数字)9798350350920

ISBN: (纸本)9798350350937

In recent years, light field imaging has gained significant attention in the scientific community due to its ability to provide a more immersive representation of the 3D world. However, ensuring the quality of light field images is crucial for their subsequent processing and applications. Deep learning methods, leveraging neural networks, have shown promising performance in image Quality Assessment (IQA). However, the unique characteristics of light field data pose a challenge for existing IQA methods. To address this challenge, we propose a Robust Large-scale Dataset for Assessing Light Field image Quality, named RLSD, specifically designed for evaluating the quality of light field images. The dataset comprises both real and synthetic scenes, covering a wide range of key low attributes and including three representative distortions: compression, noise, and blur. To obtain subjective evaluations, we adopt the single stimulus continuous quality evaluation (SSCQE) method and compute the Mean Opinion Score (MOS). We performed statistical analysis on the dataset and experimental results indicate that our proposed RLSD dataset includes various common scenes and distortion levels, making it suitable for designing and evaluating LF-IQA algorithms. The dataset is publicly available at the following link: “https://***/s/1kJmx4qsy8ywLPba-HwGCEg” (password: XY28).

关键词： image quality Three-dimensional displays image coding statistical analysis Noise Neural networks Imaging

来源：评论

学校读者我要写书评

暂无评论

Texture Classification Using RGGD statistical Model of CNN Feature Maps Encoding

Texture Classification Using RGGD Statistical Model of CNN F...

引用

European Signal processing conference (EUSIPCO)

作者： Zakariae Abbad Ahmed Drissi El Maliani Mohammed El Hassouni Mohamed Tahar Kadaoui Abbassi Lionel Bombrun Yannick Berthoumieu ENSIAS Mohammed V University in Rabat Morocco FS Mohammed V University in Rabat Morocco FLSH Mohammed V University in Rabat Morocco LMSA FSDM University Sidi Mohamed Ben Abdellah Fez Morocco Univ. Bordeaux CNRS Bordeaux INP IMS UMR 5218 Talence France Bordeaux Sciences Agro Gradignan France

ISBN: (数字)9789464593617

ISBN: (纸本)9798331519773

The symmetric positive definite (SPD) matrices play an important role in diverse domains, including computer vision and signal processing, due to their unique ability to capture the intrinsic structure of nonlinear data using Riemannian geometry. Despite their significance, a notable gap exists in the absence of statistical distributions capable of effectively characterizing the statistical properties within the SPD matrices space. This paper addresses this gap by introducing a novel Riemannian Generalized Gaussian distribution (RGGD). The primary aspect of this work includes presenting the precise expression for the probability density function (PDF) of the RGGD model, along with the parameter estimation method based on the maximum likelihood for this distribution. The second aspect of this work entails harnessing the second-order statistical information captured in the feature maps originating from the initial layers of deep convolutional neural networks (DCNNs) using the RGGD stochastic model within an image classification framework. The third aspect of this work includes also the comparison of the three-parameter RGGD model with its two-parameter predecessors, namely the Riemannian Gaussian distribution (RGD) and the Riemannian Laplacian distribution (RLD). Besides the mathematical foundations, the model's efficiency is validated through experiments conducted on the three well-known datasets, showcasing its effectiveness in capturing the underlying statistics of SPD matrices.

关键词： Manifolds Measurement Support vector machines Maximum likelihood estimation Symmetric matrices Probability density function Feature extraction Mathematical models Convolutional neural networks image classification

来源：评论

学校读者我要写书评

暂无评论

stochastic Super-Resolution For Gaussian Textures

Stochastic Super-Resolution For Gaussian Textures

引用

International conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Émile Pierret Bruno Galerne Institut Denis Poisson – Université d’Orléans Université de Tours CNRS Institut Universitaire de France (IUF)

Super-resolution (SR) is an ill-posed inverse problem which consists in proposing high-resolution images consistent with a given low-resolution one. While most SR algorithms are deterministic, stochastic SR deals with designing a stochastic sampler generating any realistic SR solution. The goal of this paper is to show that stochastic SR is a well-posed and solvable problem when restricting to Gaussian stationary textures. Using Gaussian conditional sampling and exploiting the stationarity assumption, we propose an efficient algorithm based on fast Fourier transform. We also demonstrate the practical relevance of the approach for SR with a reference image. Although limited to stationary microtextures, our approach compares favorably in terms of speed and visual quality to some state of the art methods designed for a larger class of images.

关键词： Measurement Visualization Inverse problems Fast Fourier transforms Convolution Superresolution stochastic processes

来源：评论

学校读者我要写书评

暂无评论

2nd International conference on Sustainable Technology and Advanced Computing in Electrical Engineering, ICSTACE 2023

2nd International Conference on Sustainable Technology and A...

引用

2nd International conference on Sustainable Technology and Advanced Computing in Electrical Engineering, ICSTACE 2023

ISBN: (纸本)9789819992348

The proceedings contain 40 papers. The special focus in this conference is on Sustainable Technology and Advanced Computing in Electrical Engineering. The topics include: Performance Analysis of Various Converters in PV Systems Using PSO-Based MPPT;Ultra-Gain Two-Input Two-Output DC–DC Converter for Electric Vehicle Application;Modified Switched Capacitor-Based Non-isolated Bidirectional DC–DC Converter for Obtaining High VTR;wavelet-Based Quadrature Rule to Evaluating Quasi-Type Singular Integral Equations;Spherical Induction Motor—Speed Control Using VFD;a Machine Learning and Fuzzy-Based Reliable Data Collection and Communication in AioT—Fog Computing Environment;smart Home Energy Management with a Coordinated Neighborhood Energy Sharing;Dynamic Operation of Islanded DC Microgrid with Fuel Cell Using Hybrid Energy Storage Systems;fault Detection, Classification, and Identification of Shunt Compensated Distribution System Through Wavelet Transforms;Optimal Sizing of PV/Wind/Battery Grid-Connected Hybrid Renewable Energy Systems Using TLBO Algorithm;diagnosis of Clustered Microcalcifications in Breast Cancer Using Mammograms;stochastic Optimal Allocation of Photovoltaic-Based DG and DSTATCOM in Distribution System Considering Uncertainties of Loads and Solar Irradiance;breast Cancer: Automatic Detection from Mammogram images by Utilizing Deep Learning methods;Standalone Photovoltaic Fed Water Pumping System with Better Performance Using P&O MPPT Techniques;Accurate Estimation of Amplitude, Phase, and Frequency of a Sinusoidal Signal Contaminated with Harmonics and DC Decaying Components;experimental Investigation and Pollution Contaminant Severity Analysis of Glass and Porcelain Insulators Under Controlled Conditions;Classification of Dry and Wet Snow of Glaciers in Western Himalayas Using SAR Polarimetric Decomposition—An Application of Satellite image processing;optimum Overcurrent Relay Coordination for Radial Distribution Networks Using Improved Mathematical Fo

关键词：

来源：评论

学校读者我要写书评

暂无评论

Algorithms for image processing of Micro-Objects of Medical Diagnostics Systems

Algorithms for Image Processing of Micro-Objects of Medical ...

引用

International Russian Smart Industry conference (SmartIndustryCon)

作者： Isroil I. Jumanov Rustam A. Safarov Department of “Artifical intellegence and information systems” Samarkand State University named after Sharof Rashidov Samarkand Uzbekistan Department of Control Theory and Information Security Samarkand State University named after Sharof Rashidov Samarkand Uzbekistan

ISBN: (数字)9798331511241

ISBN: (纸本)9798331511258

Constructive approaches, principles, models for optimizing the identification of micro-objects based on the use of statistical, dynamic models with mechanisms for filtering noise, foreign particles on images of medical objects and pollen grains have been developed. methods for optimizing the identification of micro-objects with the selection of characteristic objects in the image, the combination of image models with the mechanisms of segmentation, filtering, transformation, and alignment of the laser image processing zone with the CAD model are proposed. Algorithms for selecting the contours of objects on an image using a border detector in the transverse direction to each vector of the CAD model have been developed. Modeling of images of microsamples for medical diagnostics of chest diseases was carried out. The width, straightness of the boundaries of structural objects, local defects, parameters of regulation and synchronization of the components of the vision system are determined. Algorithms for image processing under conditions of a priori insufficiency, uncertainty of parameters, and low accuracy of data processing are studied. A mechanism for suppressing impulse noise and noise is implemented based on various filtering methods, preserving the boundaries of objects and small-sized parts. Mathematical expressions for estimating identification errors due to non-stationarity, inadequacy of approximation, interpolation, extrapolation of the image contourare obtained, which are synthesized with cubic, biquadratic, interpolation spline functions and wavelet transforms. A software package for recognition and classification of micro-objects has been developed.

关键词： Solid modeling Interpolation image segmentation Filtering Measurement by laser beam Laser modes Vectors Object recognition Synchronization Medical diagnosis

来源：评论

学校读者我要写书评

暂无评论

14th International conference on Optimization and Applications, OPTIMA 2023

14th International Conference on Optimization and Applicatio...

引用

14th International conference on Optimization and Applications, OPTIMA 2023

ISBN: (纸本)9783031478581

The proceedings contain 27 papers. The special focus in this conference is on Optimization and Applications. The topics include: One Segregation Problem for the Sum of Two Quasiperiodic Sequences;Parameter Estimation via Time Modeling for MLIR Implementation of GEMM;Reliable Production Process Design Problem: Compact MILP Model and ALNS-Based Primal Heuristic;reciprocal Import Tariffs in the Monopolistic Competition Open Economy;numerical Modelling of Mean-Field Game Epidemic;models of Decision-Making in a Game with Nature Under Conditions of Probabilistic Uncertainty;application of Optimization methods in Solving the Problem of Optimal Control of Assets and Liabilities by a Bank;an Endogenous Production Function in the Green Solow Model;two Balanced Growth Paths Based on an Endogenous Production Function;the pth-Order Karush-Kuhn-Tucker Type Optimality Conditions for Nonregular Inequality Constrained Optimization Problems;analysis of Import Substitution Processes Taking into Account Industry Specifics in the Regional Economy;features of Optimal Drilling in Gas Fields;on Solving the Robust Transfer Line Balancing Problem with Parallel Tasks and Interval processing Times;on Cluster Editing Problem with Clusters of Small Sizes;limiting the Search in Brute Force Method for Subsets Detection;bicentered Interval Newton Operator for Robot’s Workspace Approximation;statistical Performance of Subgradient Step-Size Update Rules in Lagrangian Relaxations of Chance-Constrained Optimization Models;the Customization of the Geodesic Algorithm for Optimal Fastener Arrangement;convergence Rate of Gradient-Concordant methods for Smooth Unconstrained Optimization;a Derivative-Free Nonlinear Least Squares Solver for Nonsmooth Functions;stochastic Adversarial Noise in the "Black Box" Optimization Problem;Accelerated Zero-Order SGD Method for Solving the Black Box Optimization Problem Under "Overparametrization" Condition;algorithms for Euclidean-Regularised Optimal Transport;real Accel

关键词：

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：