检索结果-内蒙古大学图书馆

Optimized neural network for vulnerable plaque detection in OCT images with noise tolerance and adaptive coefficient zeroing

引用

BIOMEDICAL signal processing AND CONTROL 2025年 100卷

作者： Sankar, S. Perumal Vinu, R. Sreelekshmi, S. Viswanath, N. ECE Dept Ernakulam Kerala India PG Dean Toc H Inst Sci & Technol Ernakulam Kerala India Elect & Commun Engn Dayananda Sagar Univ Bengaluru Karnataka India Toc H Inst Sci & Technol Elect & Commun Engn Ernakulam Kerala India Toc H Inst Sci & Technol Comp Sci & Engn Ernakulam Kerala India

Background: Optical Coherence Tomography (OCT) was a non-invasive imaging method that provides higher- resolution images of biological tissues. OCT is used in cardiovascular medicine to identify Astheroclerosis plaques, which are a kind of plaque in blood arteries that represent a significant chance of rupture along with subsequent cardiovascular problems. By analyzing OCT images, healthcare professionals can identify specific features of atherosclerosis plaques, including thin fibrous caps, fatty cores, and micro-calcifications. This allows early identification of life-threatening risks and targeted treatments. Still, the analysis method is subject to miscalculations and high workload. Objective: The objective of this research is to propose a novel approach called CVP-OCT-NTACZNN-PCBESA for detecting and classifying cardiovascular vulnerable plaques utilizing OCT imaging. The aim of CVP-OCTNTACZNN-PCBESA method is to provide healthcare practitioners with a more effective tool for early detection and better treatment of heart disease-causing plaques, by this reducing cardiovascular problems and advancing patient's life. methods: After removing noise and improving image quality with Data-adaptive Gaussian Average Filtering (DAGAF), the recovered features are fed into NTACZNN. This neural network recognizes some Cardiovascular Vulnerable Plaques, including fibrocalcific plaque, fibroatheroma, thrombus, fibrous plaque, and microvessels. Result: The results of this research show that the CVP-OCT-NTACZNN-PCBESA method outperforms existing approaches in terms of accuracy, precision, detection quality score, and recall rate for identifying cardiovascular susceptible plaques. Especially, the CVP-OCT-NTACZNN-PCBESA outperforms DL-based models and diagnostic systems that use intravascular OCT imaging by 27.36% to 38.27% in accuracy and 19.40% to 33.42% in precision. Conclusion: In conclusion, the proposed CVP-OCT-NTACZNN-PCBESA method outperforms other existing approaches for

关键词： Data-adaptive Gaussian Average Filtering Dual Tree Complex Discrete Wavelet Transform Noise tolerate and adaptive coefficient zeroing neural network Optical Coherence Tomography Polar Coordinate Bald Eagle Search Algorithm

来源：评论

学校读者我要写书评

暂无评论

Underwater target recognition based on adaptive multi-feature fusion network

引用

Multimedia Tools and Applications 2025年第10期84卷 7297-7317页

作者： Pan, Xiaoying Sun, Jia Feng, TianHao Lei, MingZhu Wang, Hao Zhang, WuXia Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an710121 China Xi’an Key Laboratory of Big Data and Intelligent Computing Xi’an710121 China School of Computer Science and Technology Xi’an University of Post & Telecommunications Xi’an710121 China

Due to the complexity of the underwater environment, underwater acoustic target recognition is more challenging than ordinary target recognition, and has become a hot topic in the field of underwater acoustics research. In recent years, deep learning has been widely used in underwater recognition due to its powerful feature learning capabilities. However, most deep learning-based underwater target recognition methods use only the time-frequency domain features of signals, ignoring the frequency domain image features of signals. Additionally, they only use simple summation or splicing strategies to fuse and discriminate the extracted features, which leads to limited improvement in the accuracy of underwater target recognition. To address these issues, this paper proposes an underwater target recognition method based on an adaptive multi-feature fusion network. The method consists of a data pre-processing module, a multi-dimensional feature extraction module, and an adaptive multi-feature fusion module. In the multi-dimensional feature extraction module, the long short time memory network (LSTM) and the one-dimensional convolutional neural network (1DCNN) are used to extract the time-frequency features of the underwater signal. Furthermore, the two-dimensional convolutional neural network (2DCNN) is used to extract the image features in the frequency domain. The adaptive multi-feature fusion module uses an attention mechanism for adaptive weighted fusion to make full use of the learned features. The effectiveness of the proposed method is validated on the ShipEar dataset, and the recognition accuracy reaches 94.92%, which is higher than other existing methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Application of Multi-Modal neural Networks in Verifying the Authenticity of News Text and images

引用

TRAITEMENT DU signal 2023年第6期40卷 2397-2407页

作者： Li, Feng Xu, Meiling Rosli, Marshima Mohd Univ Teknol MARA Coll Comp Informat & Math Shah Alam 40450 Malaysia Hebei Finance Univ Coll Comp & Informat Engn Baoding 071051 Peoples R China

In the digital information era, the authenticity of news media is crucial for shaping public opinion and maintaining social stability. The verification of authenticity, especially in news content rich in both text and images, has become a significant task in safeguarding online information security. Traditional methods, often relying on single-modality analysis, are ineffectual against the complex interplay and manipulation techniques possible between news text and accompanying images. Addressing this, research in multi-modal neural networks has emerged, aiming to enhance verification effectiveness by integrating information from both text and images. However, limitations exist in existing research regarding key issue resolution and modality fusion strategies, including inadequate exploration in searching for anomalously similar image blocks, reducing false alarms, and post-processing of tampered images. This study systematically investigates these challenges in news text and image authenticity verification, proposing a novel multi-modal fusion method. This method encompasses three components: a joint gated co-attention mechanism, a filtering gate mechanism, and a joint cooperative representation. These effectively combine text and image information, enhancing the model's ability to discern complex manipulations. The findings of this study not only advance theoretical research in multi -modal fusion but also provide a powerful tool for news media to verify authenticity, significantly contributing to the fight against fake news and maintaining the integrity of information dissemination.

关键词： multi-modal neural networks news authenticity verification anomalous image block search gated cooperative attention, tampered and forged images modality fusion information security

来源：评论

学校读者我要写书评

暂无评论

HYPERSPECTRAL image RECONSTRUCTION USING HIERARCHICAL neural ARCHITECTURE SEARCH FROM A SNAPSHOT image 49

HYPERSPECTRAL IMAGE RECONSTRUCTION USING HIERARCHICAL NEURAL...

引用

49th IEEE International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Han, Xian-Hua Jiang, Huiyan Chen, Yen-Wei Rikkyo Univ Grad Sch Aritificial Intelligence & Sci Tokyo 1718501 Japan Northeastern Univ Software Coll Shenyang Peoples R China Ritsumeikan Univ Kyoto Japan

ISBN: (纸本)9798350344868;9798350344851

Hyperspectral imaging is a promising imaging modality, and has attracted increasing research attention by compressive sensing such as coded aperture snapshot spectral imaging (CASSI), for simultaneously capturing abundant information in spatial, spectral and temporal domains. Hyperspectral image (HSI) reconstruction in the CASSI aims to retrieve the original 3D signal upon the 2D compressed snapshot. Recently, deep learning has extensively been employed for HSI reconstruction via manually designing network architectures, and usually causes complicated and massive-computational models, which are difficult for being embedding in the real imaging systems. This study aims to leverage network architecture search to automatically design effective and efficient network architectures for HSI reconstruction. Specifically, we exploit gradient-based search strategies and prepare optional operations (cells) with adaptive receptive field such as dilate and deformable convolutional layers to construct a flexible hierarchical search space. Through sharing cells within different levels of features and utilizing an early stopping technique, we achieve a computational and memory efficient NAS strategy to automatically design an effective lightweight model for HSI reconstruction. Extensive experimental results have demonstrated that the network architecture achieved by our proposed NAS has much smaller model size and a lower computational cost while produce better or comparable HSI reconstruction performance compared with the state-of-the-art methods.

关键词： Hyperspectral image reconstruction Network architecture search Gradient-based search Hierarchical search space Lightweight model

来源：评论

学校读者我要写书评

暂无评论

Multi-label chest X-ray image classification based on long-range dependencies capture and label relationships learning

引用

BIOMEDICAL signal processing AND CONTROL 2025年 100卷

作者： Zhao, Xiangxin Wang, Xin Qingdao Univ Sci & Technol Sch Informat Sci & Technol Qingdao 266061 Peoples R China

Diagnosing chest diseases from X-ray images using convolutional neural networks (CNNs) is an active area of research. However, existing methods mostly focus on extracting feature information from local regions for prediction, while ignoring the larger-scale image contextual information. Moreover, anatomical segmentation knowledge and co-occurrence relationships among labels, which are important for classification, are not fully utilized. To address the above problems, we proposed a method to capture long-range dependent information in chest X-ray images using a CNN with large kernel convolution. Furthermore, it captures the detailed features of the interest region through anatomical segmentation and builds the potential relationships of different diseases using a graph convolutional network (GCN). Firstly, we pre-trained UNet from a dataset with organ-level annotations for segmenting anatomical regions of interest in the images. Secondly, we build a four-stage backbone network using the large kernel attention (LKA) mechanism and superimpose anatomically segmented regions on the feature maps of each stage to obtain different scales of feature maps for the regions of interest. Thirdly, we utilized a GCN to obtain a co-occurrence matrix representing the potential relationships between all disease labels in the training dataset. Finally, we get the disease diagnosis by combining the label co-occurrence matrix and the visual feature maps. We experimentally show that our proposed method achieves excellent AUC scores of 91.5%, 84.5%, and 82.5% on three publicly available CXR datasets-NIH, Stanford CheXpert, and MIMIC-CXRJPG, respectively.

关键词： Chest X-ray Chest Disease Classification Multi-label Classification Attention Mechanism Graph Convolutional Network

来源：评论

学校读者我要写书评

暂无评论

X-Ray medical image super-resolution via self-organization neural networks and geometric directional gradient

引用

IET image processing 2022年第14期16卷 3910-3928页

作者： Ahmadian, Khodabakhsh Reza-Alikhani, Hamid-reza Islamic Azad Univ Mahshahr Branch Dept Elect & Comp Engn Mahshahr Iran Natl Univ Tafresh Branch Dept Elect & Comp Engn Tafresh *** Iran

Nowadays, due to the rapid development of the Internet and communication networks, remote disease diagnosis by physicians utilizing medical images such as X-rays have increased. However, the transmitted images lose their true quality and resolutions due to several factors, including noise and image compression techniques used to conserve memory space. This paper presents a novel clinical X-ray image enhancement method based on self-organizing neural networks, the ability of first-order derivative operators to detect edges, and improved classification methods by enhancing image features and extending the nearest neighbor algorithms selection of the best similarity feature vector among all sample feature vectors. The proposed method employs first-order image derivation operators to extract edge details and features from images. The feature vectors were preprocessed and segmented into various classes using self-organizing neural networks. The best matching and most similar vectors among the feature vectors are retrieved via the nearest neighbor algorithm. In contrast to conventional and contemporary image super-resolution techniques, the proposed method does not rely on the cost function. It is independent of error backpropagation methods because the competitive nature of the neural network is used to update the weight vectors rather than the gradient descent method. In addition, the performance and accuracy of the proposed image super-resolution method were improved by increasing the number of feature components in the feature vectors through the use of the two-dimensional image gradient. Furthermore, numerous image quality measurement criteria, such as structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR), were used to compare the reconstructed images of the proposed algorithm with those of other image enhancement algorithms. The results show that the proposed image enhancement algorithms' high-resolution and high-quality reconstructed image signif

关键词： nearest neighbor algorithms selection image super-resolution method neural network clinical X-ray image enhancement method two-dimensional image gradient image reconstruction feature components self-organization neural networks nearest neighbor algorithm classification methods medical image enhancement algorithms image features backpropagation contemporary image super-resolution techniques most similar vectors data compression edge detection medical images sample feature vectors first-order image derivation operators gradient methods similarity feature vector weight vectors X-ray imaging feature extraction communication networks image segmentation geometric directional gradient Ray medical image super-resolution image enhancement conventional image super-resolution techniques reconstructed images image compression techniques medical image processing image coding error backpropagation methods remote disease diagnosis gradient descent method first-order derivative operators numerous image quality measurement criteria transmitted images image resolution diseases

来源：评论

学校读者我要写书评

暂无评论

SINCO: A Novel Structural Regularizer for image Compression Using Implicit neural Representations 48

SINCO: A Novel Structural Regularizer for Image Compression ...

引用

48th IEEE International Conference on Acoustics, Speech and signal processing, ICASSP 2023

作者： Gao, Harry Gan, Weijie Sun, Zhixin Kamilov, Ulugbek S. Washington University Computational Imaging Group St. LouisMO63130 United States

ISBN: (纸本)9781728163277

Implicit neural representations (INR) have been recently proposed as deep learning (DL) based solutions for image compression. An image can be compressed by training an INR model with fewer weights than the number of image pixels to map the coordinates of the image to corresponding pixel values. While traditional training approaches for INRs are based on enforcing pixel-wise image consistency, we propose to further improve image quality by using a new structural regularizer. We present structural regularization for INR compression (SINCO) as a novel INR method for image compression. SINCO imposes structural consistency of the compressed images to the groundtruth by using a segmentation network to penalize the discrepancy of segmentation masks predicted from compressed images. We validate SINCO on brain MRI images by showing that it can achieve better performance than some recent INR methods. © 2023 IEEE.

关键词： deep learning image compression implicit neural representations neural radiance fields

来源：评论

学校读者我要写书评

暂无评论

Dual-Input Type Convolutional neural Networks Employing Color Normalized and Nuclei Segmented Data for Histopathology image Classification 22

Dual-Input Type Convolutional Neural Networks Employing Colo...

引用

22nd IEEE Statistical signal processing Workshop (SSP)

作者： Demirel, Osman Akhtar, Muhammad Tahir Nazarbayev Univ Sch Engn & Digital Sci Dept Elect & Comp Engn Kabanbay Batyr Ave 53 Astana Kazakhstan

ISBN: (纸本)9781665452458

Improvements in Convolutional neural Network (CNN) have been widely successful for histopathology image classification. However, color normalization for data preprocessing and nuclei segmentation for feature extraction should also be considered for further performance boost, data redundancy elimination, and provision of distinguishing information. These techniques are known to improve generalizability. However, there is a need to find ways to use the data obtained from color normalized and segmented data for training. In this work, dual-input CNN (DiCNN), concatenated-input CNN (CiCNN), and ensemble CNN (ECNN) are trained and tested with color normalized and nuclei segmented data. The normalization technique is chosen based on correlation and structural similarity. The segmentation method is chosen based on the best-performing normalization technique for consistency and generalizability. The results show that normalized and segmented inputs results in better binary classification with CiCNN outperforming other methods. However, for multiclass

关键词： Histopathology Color Normalization Nuclei Segmentation Dual Input CNN image Classification

来源：评论

学校读者我要写书评

暂无评论

SPECTRAL GROUPING DRIVEN HYPERSPECTRAL SUPER-RESOLUTION 30

SPECTRAL GROUPING DRIVEN HYPERSPECTRAL SUPER-RESOLUTION

引用

30th IEEE International Conference on image processing (ICIP)

作者： Hussain, Sadia Lall, Brejesh IIT Delhi BSTTM Delhi India IIT Delhi Dept EE Delhi India

ISBN: (纸本)9781728198354

Convolutional neural networks have proven to be proficient when extracting low-level concepts in an image. With the wonderful performance of transformers in exploiting the long-range correlations in an image, many methods have been explored where one exploit benefits of both the architectures. Therefore, in order to strengthen our network we add an important feature to transformers wherein single image super-resolution (SISR) is exploited using band grouping leveraging a simple CNN architecture. This paper aims to train a set of simple residual modelling architectures and then integrate them into a transformer architecture to solve super-resolution problem in HSI. We take a step forward to analyse how to adapt swinIR to fully exploit the information derived from band grouping for efficient SISR.

关键词： hyperspectral restoration image super-resolution transformers convolutional neural networks spatial super-resolution

来源：评论

学校读者我要写书评

暂无评论

Satellite signal recognition algorithm based on Doppler shift features 4

Satellite signal recognition algorithm based on Doppler shif...

引用

4th International Conference on signal image processing and Communication, ICSIPC 2024

作者： Li, Huaijin North University of China Shanxi Province Taiyuan China

ISBN: (纸本)9781510682467

Aiming at the problem of high-precision recognition of satellite signals, this paper proposes a Doppler-shift oriented dynamically optimised LSTM satellite signal recognition method, which utilises the effect of Doppler shift on satellite communication signals of different orbits and combines the differences in the modulation methods of communication signals of different regimes to realise the identification of satellite signals, and constructs a satellite signal recognition model using a neural network combination of CNN-LSTM, and the satellite signal recognition accuracy performance reaches 99% in the presence of In the presence of Doppler shift, the simulation is based on the signal samples collected from the air port, and the accuracy performance of satellite communication signal recognition for typical regimes such as BPSK, QPSK, QAM, etc. reaches 99.02%. © 2024 SPIE.

关键词： signal modulation

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：