检索结果-内蒙古大学图书馆

BIOMEDICAL signal processing AND CONTROL 2023年第0期81卷 000-000页

作者： Zhu, Fei Wang, Sheng Li, Dun Li, Qiang Huazhong Univ Sci & Technol Britton Chance Ctr Biomed Photon Wuhan Natl Lab Optoelect Wuhan Hubei Peoples R China Huazhong Univ Sci & Technol Collaborat Innovat Ctr Biomed Engn Sch Engn Sci MoE Key Lab Biomed Photon Wuhan Hubei Peoples R China United Imaging Surg Healthcare Co Ltd Shanghai Peoples R China

In recent years, deep learning (DL)-based registration technology has significantly improved the calculation speed of medical image registration. Existing DL-based registration methods generally use raw data features to predict the deformation field. However, this strategy may not be very effective for difficult registration tasks. Hence, in this study, we propose a similarity attention-based convolutional neural network (CNN) for accurate and robust three-dimensional medical image registration. We first introduce a similarity-based local attention model as an auxiliary module for building a displacement searching space, instead of a direct displacement prediction based on raw data. The proposed model can help the network focus on spatial correspondences with high similarities and ignore those with low similarities. A multi-scale CNN is then integrated with the similaritybased local attention for providing non-local attention, lightweight network, and coarse-to-fine registration. We evaluated the proposed method for various applications, such as the registration of large-scope abdominal computerized tomography (CT) images and chest CT images acquired at different respiratory phases, and atlas registration in magnetic resonance imaging. The experimental results demonstrate that the proposed method can provide a more accurate and robust registration performance than state-of-the-art registration methods.

关键词： Convolutional neural network Medical image registration Similarity Attention Multi -scale

来源：评论

学校读者我要写书评

暂无评论

A New Time Series Data Imaging Scheme for Mechanical Fault Diagnosis

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2024年 73卷 1-11页

作者： Lian, Chao Zhao, Yuliang Sun, Tianang Dong, Fanghecong Zhan, Zhikun Xin, Liming Northeastern Univ Sch Informat Sci & Engn Shenyang 110819 Peoples R China Hebei Key Lab Micronano Precis Opt Sensing & Measu Qinhuangdao 066004 Peoples R China Shanghai Univ Sch Comp Engn & Sci Shanghai 200444 Peoples R China

Fault diagnosis based on vibration signals is widely used in various industrial production processes to prevent catastrophic accidents and ensure timely repairs. However, traditional fault diagnosis methods provide limited accuracy due to their inability to visually represent fault characteristics and heavy reliance on expert involvement. In this study, we propose a time series image generation scheme that incorporates a convolutional neural network (CNN) to perform data-driven analysis and open-set classification on fault data to represent faults intuitively and diagnose them more accurately. In this study, based on the basic G image, we proposed two series of extended coding methods, gray-transform (G-TF) and transform-gray (TF-G) to convert the 1-D time series signal into a grayscale image from different perspectives for figurative expression, so as to adapt to different fault diagnosis scenarios. Then, a CNN is designed to maximize recognition accuracy based on faster calculation. To demonstrate the effectiveness of the proposed method, three types of faults are tested in this study, i.e., faults with motor bearings, self-priming centrifugal pumps, and hydraulic pumps. The experimental results demonstrate that, when the most suitable method is employed, the proposed approach achieves better recognition performance in diagnosing these three types of faults. The proposed method provides a new solution for future fault diagnosis tasks.

关键词： Acceleration sensor classification data processing deep learning fault diagnosis vibration signals

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral image denoising via self-modulating convolutional neural networks

引用

signal processing 2024年 214卷

作者： Torun, Orhan Yuksel, Seniha Esen Erdem, Erkut Imamoglu, Nevrez Erdem, Aykut Hacettepe Univ Inst Sci TR-06800 Ankara Turkiye Hacettepe Univ Dept Elect & Elect Engn TR-06800 Ankara Turkiye Hacettepe Univ Dept Comp Engn TR-06800 Ankara Turkiye Natl Inst Adv Ind Sci & Technol Digital Architecture Res Ctr Tokyo 1350064 Japan Koc Univ Dept Comp Engn TR-34450 Istanbul Turkiye Koc Univ Is Bank AI Ctr TR-34450 Istanbul Turkiye

Compared to natural images, hyperspectral images (HSIs) consist of a large number of bands, with each band capturing different spectral information from a certain wavelength, even some beyond the visible spectrum. These characteristics of HSIs make them highly effective for remote sensing applications. That said, the existing hyperspectral imaging devices introduce severe degradation in HSIs. Hence, hyperspectral image denoising has attracted lots of attention by the community lately. While recent deep HSI denoising methods have provided effective solutions, their performance under real-life complex noise remains suboptimal, as they lack adaptability to new data. To overcome these limitations, in our work, we introduce a self-modulating convolutional neural network which we refer to as SM-CNN, which utilizes correlated spectral and spatial information. At the core of the model lies a novel block, which we call spectral self-modulating residual block (SSMRB), that allows the network to transform the features in an adaptive manner based on the adjacent spectral data, enhancing the network's ability to handle complex noise. In particular, the introduction of SSMRB transforms our denoising network into a dynamic network that adapts its predicted features while denoising every input HSI with respect to its spatio-spectral characteristics. Experimental analysis on both synthetic and real data shows that the proposed SM-CNN outperforms other state-of-the-art HSI denoising methods both quantitatively and qualitatively on public benchmark datasets. Our code will be available at https://***/orhan-t/SM-CNN.

关键词： HSIs Denoising Spectral self-modulation SM-CNN

来源：评论

学校读者我要写书评

暂无评论

stochastic BINARY-TERNARY QUANTIZATION FOR COMMUNICATION EFFICIENT FEDERATED COMPUTATION 29

STOCHASTIC BINARY-TERNARY QUANTIZATION FOR COMMUNICATION EFF...

引用

IEEE International Conference on image processing (ICIP)

作者： Goutham, Rangu Afrabandpey, Homayun Cricri, Francesco Zhang, Honglei Aksu, Emre Hannuksela, Miska Tavakoli, Hamed R. Nokia Technol Espoo Finland

ISBN: (数字)9781665496209

ISBN: (纸本)9781665496209

A stochastic binary-ternary (SBT) quantization approach is introduced for communication efficient federated computation;form of collaborative computing where locally trained models are exchanged between institutes. Communication of deep neural network models could be highly inefficient due to their large size. This motivates model compression in which quantization is an important step. Two well-known quantization algorithms are binary and ternary quantization. The first leads into good compression, sacrificing accuracy. The second provides good accuracy with less compression. To better benefit from trade-off between accuracy and compression, we propose an algorithm to stochastically switch between binary and ternary quantization. By combining with uniform quantization, we further extend the proposed algorithm to a hierarchical method which results in even better compression without sacrificing the accuracy. We tested the proposed algorithm using neural network Compression Test Model (NCTM) provided by MPEG community. Our results demonstrate that the hierarchical variant of the proposed algorithm outperforms other quantization algorithms in term of compression, while maintaining the accuracy competitive to that provided by other methods.

关键词： Federated learning neural network compression quantization

来源：评论

学校读者我要写书评

暂无评论

Simultaneous removal of noise and correction of motion warping in neuron calcium imaging using a pipeline structure of self-supervised deep learning models

引用

BIOMEDICAL OPTICS EXPRESS 2024年第7期15卷 4300-4317页

作者： Zhang, Hongdong Xu, Zhiqiang Chen, Ningbo Ma, Fei Zheng, Wei Liu, Chengbo Meng, Jing Qufu Normal Univ Sch Comp Rizhao 276826 Peoples R China Chinese Acad Sci Shenzhen Inst Adv Technol Inst Biomed & Hlth Engn Shenzhen 518055 Peoples R China

Calcium imaging is susceptible to motion distortions and background noises, particularly for monitoring active animals under low-dose laser irradiation, and hence unavoidably hinder the critical analysis of neural functions. Current research efforts tend to focus on either denoising or dewar ping and do not provide effective methods for videos distorted by both noises and motion artifacts simultaneously. We found that when a self-supervised denoising model of DeepCAD [Nat. methods 18 , 1359 (2021)] is used on the calcium imaging contaminated by noise and motion warping, it can remove the motion artifacts effectively but with regenerated noises. To address this issue, we develop a two-level deep-learning (DL) pipeline to dewarp and denoise the calcium imaging video sequentially. The pipeline consists of two 3D self-supervised DL models that do not require warp-free and high signal-to-noise ratio (SNR) observations for network optimization. Specifically, a high-frequency enhancement block is presented in the denoising network to restore more structure information in the denoising process;a hierarchical perception module and a multi-scale attention module are designed in the dewar ping network to tackle distortions of various sizes. Experiments conducted on seven videos from two-photon and confocal imaging systems demonstrate that our two-level DL pipeline can restore high-clarity neuron images distorted by both motion warping and background noises. Compared to typical DeepCAD, our denoising model achieves a significant improvement of approximately 30% in image resolution and up to 28% in signal-to-noise ratio;compared to traditional dewar ping and denoising methods, our proposed pipeline network recovers more neurons, enhancing signal fidelity and improving data correlation among frames by 35% and 60% respectively. This work may provide an attractive method for long-term neural activity monitoring in awake animals and also facilitate functional analysis of neural circ

关键词： Biomedical imaging Deep learning Imaging systems Information processing Magnetic resonance imaging Nodal aberration theory

来源：评论

学校读者我要写书评

暂无评论

Communication-Efficient Federated Linear and Deep Generalized Canonical Correlation Analysis

引用

IEEE TRANSACTIONS ON signal processing 2023年 71卷 1379-1394页

作者： Shrestha, Sagar Fu, Xiao Oregon State Univ Sch Elect Engn & Comp Sci Corvallis OR 97331 USA

Classic and deep learning-based generalized canonical correlation analysis (GCCA) algorithms seek low-dimensional common representations of data entities from multiple "views" (e.g., audio and image) using linear transformations and neural networks, respectively. When the views are acquired and stored at different computing agents (e.g., organizations and edge devices) and data sharing is undesired due to privacy or communication cost considerations, federated learning-based GCCA is well-motivated. In federated learning, the views are kept locally at the agents and only derived, limited information exchange with a central server is allowed. However, applying existing GCCA algorithms onto such setting may incur prohibitively high communication overhead. This work puts forth a communication-efficient federated learning framework for both linear and deep GCCA under the maximum variance (MAX-VAR) formulation. The overhead issue is addressed by aggressively compressing (via quantization) the exchanging information between the computing agents and a central controller. Our synthetic and real-data experiments shows that the proposed algorithm enjoys a substantial reduction of communication overheads with virtually no loss in accuracy and convergence speed compared to the unquantized version. Rigorous convergence analyses are also presented, which is a nontrivial effort since generic federated optimization results do not cover the special problem structure of GCCA. Our result shows that the proposed algorithms for both linear and deep GCCA converge to critical points at a sublinear rate, even under heavy quantization and stochastic approximations. In addition, in the linear MAX-VAR case, the quantized algorithm approaches a global optimum in a geometric rate under reasonable conditions.

关键词： Convergence signal processing algorithms Optimization Federated learning Correlation Quantization (signal) Manifolds Generalized canonical correlation analysis communication-efficient federated learning nonconvex optimization convergence analysis

来源：评论

学校读者我要写书评

暂无评论

HCO-RLF: Hybrid classification optimization using recurrent learning and fuzzy for COVID-19 detection on CT images

引用

BIOMEDICAL signal processing AND CONTROL 2025年 100卷

作者： Balasamy, K. Seethalakshmi, V. Bannari Amman Inst Technol Dept Artificial Intelligence & Data Sci Sathyamangalam 638401 India KPR Inst Engn & Technol Dept ECE Coimbatore 641407 India

COVID-19 infection detection through initial lesion classification provides early diagnosis and prevents breathing difficulties. Detecting the infectious part of the lungs using computerized tomography (CT) images has become an instantaneous detection method. In this article, a Hybrid Classification Optimization (HCO) using Recurrent Leaning and Fuzzy (RLF) is proposed. The neural network classifies infected and non-infected regions using pixel distributions and their variations. This is performed by identifying missing features and training the recurrent network using regional differences. Based on the feature availability, recurrent learning classifies the region through the input dataset and recurrent training correlation. The fuzzy predicts missing features through substituted derivatives obtained between wide ranges of variations. In this process, the maximum fuzzy derivatives for feature substitution are used for infected region prediction. The least fuzzy derivatives are prevented from the training layer to reduce false rates in region classification. This joint process improves the training consistency to leverage the detection and region classification accuracies. The proposed HCO-RLF improves detection and classification accuracy, and precision by 11.96 %, 9.98 %, and 13.42 % for the varying classification rates. Besides, the results are obtained in comparison with the existing DR-MIL, DSAE, and BS-FSA methods discussed later in the article.

关键词： COVID detection CT image Feature extraction Fuzzy derivatives Recurrent network

来源：评论

学校读者我要写书评

暂无评论

Learning on JPEG-LDPC Compressed images: Classifying with Syndromes 32

Learning on JPEG-LDPC Compressed Images: Classifying with Sy...

引用

32nd European signal processing Conference (EUSIPCO)

作者： Aliouat, Ahcen Dupraz, Elsa IMT Atlantique CNRS Lab STICC UMR 6285 Brest France

ISBN: (纸本)9789464593617;9798331519773

In goal-oriented communications, the objective of the receiver is often to apply a Deep-Learning model, rather than reconstructing the original data. In this context, direct learning over compressed data, without any prior decoding, holds promise for enhancing the time-efficient execution of inference models at the receiver. However, conventional entropic-coding methods like Huffman and Arithmetic break data structure, rendering them unsuitable for learning without decoding. In this paper, we propose an alternative approach in which entropic coding is realized with Low-Density Parity Check (LDPC) codes. We hypothesize that Deep Learning models can more effectively exploit the internal code structure of LDPC codes. At the receiver, we leverage a specific class of Recurrent neural Networks (RNNs), specifically Gated Recurrent Unit (GRU), trained for image classification. Our numerical results indicate that classification based on LDPC-coded bit-planes surpasses Huffman and Arithmetic coding, while necessitating a significantly smaller learning model. This demonstrates the efficiency of classification directly from LDPC-coded data, eliminating the need for any form of decompression, even partial, prior to applying the learning model.

关键词： Goal-oriented communications image coding for Machines Entropic coding LDPC codes RNN

来源：评论

学校读者我要写书评

暂无评论

Learning Compact DNN Models for Behavior Prediction from neural Activity of Calcium Imaging

引用

JOURNAL OF signal processing SYSTEMS FOR signal image AND VIDEO TECHNOLOGY 2022年第5期94卷 455-472页

作者： Wu, Xiaomin Lin, Da-Ting Chen, Rong Bhattacharyya, Shuvra S. Univ Maryland College Pk MD 20742 USA NIDA Intramural Res Program NIH Baltimore MD USA Univ Maryland Sch Med Baltimore MD 21201 USA

In this paper, we develop methods for efficient and accurate information extraction from calcium-imaging-based neural signals. The particular form of information extraction we investigate involves predicting behavior variables linked to animals from which the calcium imaging signals are acquired. More specifically, we develop algorithms to systematically generate compact deep neural network (DNN) models for accurate and efficient calcium-imaging-based predictive modeling. We also develop a software tool, called NeuroGRS, to apply the proposed methods for compact DNN derivation with a high degree of automation. GRS stands for Greedy inter-layer order with Random Selection of intra-layer units, which describes the central algorithm developed in this work for deriving compact DNN structures. Through extensive experiments using NeuroGRS and calcium imaging data, we demonstrate that our methods enable highly streamlined information extraction from calcium images of the brain with minimal loss in accuracy compared to much more computationally expensive approaches.

关键词： neural signal processing Machine learning Calcium imaging neural network pruning

来源：评论

学校读者我要写书评

暂无评论

Architectural Works of the Early Republic Period from an Artificial Intelligence Perspective 32

Architectural Works of the Early Republic Period from an Art...

引用

32nd IEEE signal processing and Communications Applications Conference (SIU)

作者： Yilmaz, Emirkan Burak Akgul, Yusuf Sinan Tan, Funda Gebze Tekn Univ Bilgisayar Muhendisligi Bolumu Kocaeli Turkiye Gebze Tekn Univ Mimarlik Bolumu Kocaeli Turkiye

ISBN: (纸本)9798350388978;9798350388961

This study presents a versatile approach integrating various neural network architectures with a focus on classifying architectural works. To address the lack of suitable datasets in the literature, a custom dataset has been created and made publicly available. The study aims to determine the most effective model, taking into account fine details in architectural styles. In this context, a comparative analysis has been conducted on four different convolutional neural network (CNN) architectures, including a baseline model trained from scratch and models using transfer learning methods with VGG, ResNet, and EfficientNet architectures. Through experiments, the EfficientNet architecture was fine-tuned, achieving an accuracy of %84.65 for 3 architects and %74.08 for 16 architects. Additionally, the two obtained models were used as feature extractors to visualize relationships among architects in a 2D space using t-SNE dimension reduction technique. These promising results indicate that these techniques can significantly contribute to architectural style analysis and serve as valuable tools for creating innovative designs through the use of generative artificial intelligence.

关键词： image classification deep learning convolutional neural network architectural style

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：