检索结果-内蒙古大学图书馆

6th International conference on Frontiers of Signal processing, ICFSP 2021

作者： San, Kaung Myat Chernoyarov, Oleg Korableva, Larisa Makarov, Alexander National Research University MPEI Department of Electronics and Nanoelectronics Moscow Russia Tomsk State University International Laboratory of Statistics of Stochastic Processes Quantitative Finance National Research Tomsk Russia Moscow State University Department of Econometrics and Mathematical Methods of Economics of the Moscow School of Economics Moscow Russia

ISBN: (纸本)9781665413459

In this study, the problem is considered of determining the unknown abrupt change in the power and frequency parameters of the band fast fluctuating Gaussian processes. To solve it, new approximations of decision statistics are found under various hypotheses and their maximization is carried out by the unknown regular parameters. By the obtained results, the block diagrams are developed of the corresponding detectors and measurers in the form of relatively simple single-channel devices. With help of the analytical (local Markov approximation) and statistical computer simulation methods, the performance of the introduced detectors and measurers is established and agreement of the theoretical formulas for their characteristics with the corresponding experimental data is confirmed in a wide range of parameter values of the analyzed process. © 2021 IEEE.

关键词： Random processes

来源：评论

学校读者我要写书评

暂无评论

Tumorand Stroke Lesions Recognition and Investigation for Involuntary Detection of Brain irregularity

Tumorand Stroke Lesions Recognition and Investigation for In...

引用

International conference on image Information processing

作者： Trapti Sharma Hameed Hassan Khalaf Maki Mahdi Abdulhasan Ashraf Mohammed Shareef VIT Bhopal University Kothri KalanSehoreBhopal M.P Al-Manara College For Medical Sciences Maysan Iraq Department of Medical Laboratories Technology AL-Nisour University College Baghdad Iraq National University of Science and Technology Thi Qar Iraq

ISBN: (数字)9798350371406

ISBN: (纸本)9798350371413

Several computational features distinguish one type of abnormality from another, including the nature of the abnormality, its size, shape, volume, number of lesions, and distribution. Because it is challenging to classify distinct types of abnormalities using an automated approach, we use the term abnormalities to refer to tumours, blood clots, and strokes collectively. Segmentation of brain images is an attempt to assign tissue labels to individual pixels. Since MRI gives a greater contrast of soft tissue structures, it is the preferred approach for imaging the brain. Appropriate segmentation methods have a high correlation with image capture modality, the tissue of interest. In order to devise a suitable treatment plan, it is crucial to correctly diagnose brain abnormalities like tumour, stroke, or bleeding lesions. Studies have focused on developing better image processing algorithms for use in CAD systems, with the ultimate goal of assessing photos of various brain disorders. In this study, researchers employ an innovative automated method to examine brain MRIs for signs of disease. image segmentation, area and volume calculations, and localization are only a few of the many steps of the algorithm that has been put into place. The statistical comparison of the suggested method’s output with the reference image reveals encouraging results.

关键词： Location awareness image segmentation image recognition Shape Magnetic resonance imaging Information processing Stroke (medical condition)

来源：评论

学校读者我要写书评

暂无评论

Neighborhood-aware autoencoder for missing value imputation 28

Neighborhood-aware autoencoder for missing value imputation

引用

28th European Signal processing conference, EUSIPCO 2020

作者： Aidos, Helena Tomás, Pedro LASIGE Faculdade de Ciências Universidade de Lisboa Lisbon Portugal INESC-ID Instituto Superior Técnico Universidade de Lisboa Lisbon Portugal

ISBN: (纸本)9789082797053

Missing values are a fundamental issue in many applications by constraining the application of different learning methods or by impairing the attained results. Many solutions have been proposed by relying on statistical or machine learning techniques. However, in most cases, the results are not yet satisfactory. Hence, motivated by the advent of deep learning, different solutions have also been proposed, such as by adopting autoencoders and adversarial training. However, in most of these solutions, the results are impaired by the network structure and training strategy, constraining the accuracy of missing value imputation. In this paper, we revisit autoencoder networks and show that through a careful selection of network structure and optimization strategy we outperform other deep learning solutions. We further study the impact of a previously proposed technique, stochastic corruption of inputs, to show that when the network is well designed and trained, it actually impairs the results. © 2021 European Signal processing conference, EUSIPCO. All rights reserved.

关键词： stochastic systems

来源：评论

学校读者我要写书评

暂无评论

A Novel PSO-SGD with Momentum Algorithm for Medical image Classification

A Novel PSO-SGD with Momentum Algorithm for Medical Image Cl...

引用

2021 IEEE International conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Liu, Xiaojuan Feng, Ruiqi Zhou, Shangbo Yang, Ye Chongqing University College of Computer Science Chongqing China Southwest University College of Computer Information Science Chongqing China

ISBN: (纸本)9781665401265

In recent years, deep learning has been widely used in the field of medical image processing, such as identification of symptoms, detection of organ. Due to the complexity of medical images, in the model training, there are many parameters when deep learning is used for image classification, and it takes a long time. Therefore, the training process for neural networks needs to be optimized. The stochastic gradient descent with momentum (SGD) is a common optimization algorithm in deep learning, and the particle swarm optimization (PSO) is a classical and effective swarm intelligence optimization algorithm. These two methods have their own advantages and disadvantages. Combining the two algorithms to calculate parameters, this paper proposes a novel particle swarm optimization-stochastic gradient descent with momentum (PSO-SGD) algorithm, which can find the optimal solution of the network more quickly and improve the solution efficiency on the basis of ensuring the classification accuracy. This algorithm is verified on two data sets, namely Blood Cell images Data Set (BCIDS) and COVED-19 Radiography Data Set (COVED19RDS). Experiments prove the effectiveness of the algorithm. © 2021 IEEE.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Machine Learning in Medical image processing 4th

Machine Learning in Medical Image Processing

引用

4th International conference on Information and Communication Technology for Intelligent Systems, ICTIS 2020

作者： Kumar, Himanshu Hasija, Yasha Department of Biotechnology Delhi Technological University Shahbad Daulatpur Main Bawana Road Delhi110042 India

ISBN: (纸本)9789811570773

Machine Learning is the understanding of some rules or algorithms by the machine. It is the process of providing scientific algorithm and statistical model to computer system which utilizes it to perform specific task without using explicit instructions. image processing is the method used for quantitative analysis of digital image data by certain algorithm. With advancement in medical science, there are many sophisticated methods for medical imaging and some of them involve the use of machine learning. Machine learning employed on image processing of diseased images can help in earlier detection and diagnosis of developing chronic diseases. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Modified Reinhard Algorithm for Color Normalization of Colorectal Cancer Histopathology images 29

Modified Reinhard Algorithm for Color Normalization of Color...

引用

29th European Signal processing conference (EUSIPCO)

作者： Roy, Santanu Panda, Shubhajit Jangid, Mahesh Manipal Univ Jaipur Dept CSE Jaipur Rajasthan India

ISBN: (纸本)9789082797060

In recent trends, Computer Assisted Diagnosis (CAD) enables the pathologists to diagnose cancer disease from histopathology images very efficiently. Color normalization is a pre-processing step prior to cancer classification task which can reduce the computational complexity of the classifier. However, existing color normalization methods are fraught with the problems of data loss and huge computational complexity. The purpose of employing this color normalization method is to reduce the color variation among a set of histopathology images so that in the next step, the classifier can efficiently extract the prominent features for cancer grading. This color variation is generally occurred due to using different scanners, stain concentration variability and poor tissue sectioning, while preparing the histopathology slides. In this paper, a modified Reinhard algorithm is proposed for color normalization of Hematoxylin and Eosin (H&E) stained colorectal cancer histopathology images. The limitations of Reinhard algorithm are alleviated by the proposed algorithm. Moreover, a statistical analysis is provided to prove that proposed algorithm does not cause any data loss and subsequently, it satisfies all four hypotheses of color normalization. Furthermore, the performance of the proposed algorithm is compared with other existing color normalization methods both qualitatively and quantitatively.

关键词： Color Normalization Computer Assisted Diagnosis H&E stained histopathology images colorectal cancer image processing contrast enhancement correlation coefficient

来源：评论

学校读者我要写书评

暂无评论

Integration of Landsat-8 Multispectral Band and Cartosat-1 Digital Elevation Model using image Fusion Techniques 8

Integration of Landsat-8 Multispectral Band and Cartosat-1 D...

引用

8th International conference on Signal processing and Integrated Networks, SPIN 2021

作者： Bopche, Litesh Rege, Priti P. College of Engineering Pune India

ISBN: (纸本)9781665435642

Significant technical restrictions, such as limited data storage on the satellite platform in space and limited bandwidth for communication with the ground station, restrict satellite sensors from simultaneously recording images with higher spatial and spectral resolutions. image fusion and pan-sharpening have proved to be effective methods in remote sensing studies to handle these restrictions. image fusion combines Panchromatic and Multispectral band images to produce a composite or fused image with better spatial and spectral resolutions. In this paper, five different pan-sharpening approaches viz., the Intensity-Hue-Saturation transformation, the Brovey Transformation, the ESRI pan-sharpening transformation, the Gram-Schmidt method, and Simple Mean transformation are tested on the Landsat-8 MS band and Cartosat-1 Digital Elevation Model (DEM) PAN band. Results are analyzed visually and quantitatively to verify the spectral characteristics of the fused images in order to assess the efficiency of various image fusion techniques. A statistical index such as Root Mean Square Error (RMSE) is used to evaluate the fused image. © 2021 IEEE

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

A combined informative and representative active learning approach for plankton taxa labeling 13

A combined informative and representative active learning ap...

引用

13th International conference on Digital image processing (ICDIP)

作者： Haug, Martin Lund Saad, Aya Stahl, Annette Norwegian Univ Sci & Technol Dept Engn Cybernet NTNU Trondheim Norway

ISBN: (数字)9781510646018

ISBN: (纸本)9781510646018

With an ever-increasing amount of image data, the manual labeling process has become the bottleneck in many machine learning applications. Plankton taxa labeling is especially a challenge due to its complex nature, and the manual labeling effort places a large burden on the domain experts. The Active Learning (AL) paradigm is a promising research direction adopted in the literature to minimize the manual labeling effort exerted by domain experts. Many approaches for AL have been proposed over the recent years to improve the labeling task by supporting the construction of large datasets suitable to train machine learning models while minimizing human involvement in the process. Our empirical study suggests that many modern active learning methods fail to incorporate both the samples that represent the statistical pattern of the data and the samples in which the machine learning model is not confident about. Inspired by these limitations, we propose an algorithm that combines these two types of sampling in order to capture the data distribution of the whole feature space, prevent redundant sampling from correlated uncertainty queries and finetune the inter-class decision boundary. Our experiments show that the proposed method outperforms each of the methods separately. Further, it also proves to be efficient on both the CIFAR dataset and the more complex Kaggle plankton dataset.

关键词： image analysis deep learning plankton taxa distribution active learning

来源：评论

学校读者我要写书评

暂无评论

The MOGN Distribution Applied to Medical imagery processing

引用

JOURNAL OF statistical THEORY AND PRACTICE 2023年第1期17卷 4-4页

作者： Cordeiro, Gauss M. Nascimento, Abraao D. C. Ferreira, Jodavid A. Univ Fed Pernambuco Dept Estat Recife PE Brazil

The generalized normal (GN) distribution is one of the most used models for imagery feature processing. Alternatives more flexible than the GN are sought in some real phenomena. We propose a new four-parameter distribution for modeling medical imagery called the Marshall-Olkin generalized normal (MOGN). Some of its properties are derived, including quantile function, expansions for the density and cumulative functions and ordinary and incomplete moments. We estimate the model parameters using maximum likelihood and provide a stochastic expectation- maximization (SEM)-based segmentation algorithm for features in medical images. The performance of our proposals is quantified in an application to real data in contrast to those furnished by the well-known segmentation methods: k-means and other based on the generalized normal SEM. Results indicate that the segmenter which is induced from the MOGN distribution may be an efficient tool for processing medical images.

关键词： Marshall and Olkin's family Generalized normal Medical image processing stochastic expectation-maximization Segmentation

来源：评论

学校读者我要写书评

暂无评论

Group-wise Semantic-enhanced Interaction Network for Remote Sensing Spatio-Temporal Fusion

Group-wise Semantic-enhanced Interaction Network for Remote ...

引用

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

作者： Baoluo Zhu Shenglong Hu Huihui Song Kaihua Zhang Nanjing University of Information Science and Technology Nanjing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Remote sensing spatio-temporal fusion (STF) aims at fusing temporally-dense coarse-resolution images and temporally-sparse fine-resolution images to reconstruct high spatio-temporal resolution images. Multi-band remote sensing images are often accepted as inputs for STF that have complementary characteristics for high-fidelity land surface reconstruction, yet the existing STF framework often treats different bands uniformly without considering the statistical correlation between different bands, resulting in unsatisfying results. To address this problem, this paper presents a group-wise semantic-enhanced interactive network for STF, dubbed as GSINet. Based on statistical observations, the feature correlation between the visible-light group and the invisible-light group is weak, while the intra-group correlation is strong. Therefore, the GSINet first separates the inputs into visible-light and invisible-light groups, which are fed into different branches with independent encoders for feature extraction and fusion. Afterwards, to address the issue of land cover changes between the prediction coarse- and reference fine-resolution images, a Semantic-Enhancement Fusion Module (SEFM) is designed to interact with the features from the same group with enhanced semantic information captured in an unsupervised learning manner. Then, the semantic-enhanced fused features from different bands are fed into an Interleaved Cross-attention Module (ICM) for further fusion. Finally, the output fusion features fully encode the intra- and inter-group information, which are fed into the decoder, reconstructing the spatio-temporal high-resolution images. Extensive experiments on CIA and LGC benchmark datasets demonstrate that the GSINet outperforms a variety of state-of-the-art methods in terms of multiple metrics.

关键词： Surface reconstruction Correlation Land surface Benchmark testing Speech enhancement Signal processing Remote sensing image reconstruction Unsupervised learning Surface treatment

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：