检索结果-内蒙古大学图书馆

DMFVAE:miRNA-disease associations prediction based on deep matrix factorization method with variational autoencoder

Frontiers of Computer Science 2024年第6期18卷 259-270页

作者： Pijing WEI Qianqian WANG Zhen GAO Ruifen CAO Chunhou ZHENG Information Materials and Intelligent Sensing Laboratory of Anhui Province Institutes of Physical Science and Information TechnologyAnhui UniversityHefei 230601China Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui UniversityHefei 230601China Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Artificial IntelligenceAnhui UniversityHefei 230601China

MicroRNAs(miRNAs)are closely related to numerous complex human diseases,therefore,exploring miRNA-disease associations(MDAs)can help people gain a better understanding of complex disease *** increasing number of computational methods have been developed to predict ***,the sparsity of the MDAs may hinder the performance of many *** addition,many methods fail to capture the nonlinear relationships of miRNA-disease network and inadequately leverage the features of network and neighbor *** this study,we propose a deep matrix factorization model with variational autoencoder(DMFVAE)to predict potential *** first decomposes the original association matrix and the enhanced association matrix,in which the enhanced association matrix is enhanced by self-adjusting the nearest neighbor method,to obtain sparse vectors and dense vectors,***,the variational encoder is employed to obtain the nonlinear latent vectors of miRNA and disease for the sparse vectors,and meanwhile,node2vec is used to obtain the network structure embedding vectors of miRNA and disease for the dense ***,sample features are acquired by combining the latent vectors and network structure embedding vectors,and the final prediction is implemented by convolutional neural network with channel *** evaluate the performance of DMFVAE,we conduct five-fold cross validation on the HMDD v2.0 and HMDD v3.2 datasets and the results show that DMFVAE performs ***,case studies on lung neoplasms,colon neoplasms,and esophageal neoplasms confirm the ability of DMFVAE in identifying potential miRNAs for human diseases.

关键词： miRNA-disease association deep matrix factorization self-adjusted nearest neighbor variational encoder network structure

来源：评论

学校读者我要写书评

暂无评论

Enhancing defocus blur in three-dimensional scenes via high-speed optical axial scanning and deep learning 2

Enhancing defocus blur in three-dimensional scenes via high-...

引用

2nd International Academic Conference on Optics and Photonics, IACOP 2024

作者： Li, Zilong Tang, Chenxi Dong, Jiaqing Liu, Xuan Lin, Jiabin Liu, Qiegen Song, Xianlin School of Information Engineering Nanchang University Nanchang330031 China Jiangxi Provincial Key Laboratory of Advanced Signal Processing and Intelligent Communications Nanchang University Nanchang330031 China

ISBN: (数字)9781510688827

ISBN: (纸本)9781510688810

Mitigating image defocus blur induced by the limited depth of field in imaging systems and reconstructing the three-dimensional depth of scenes represents a significant hurdle. In this paper, a method for enhancing defocus blur in three-dimensional scenes via high-speed optical axial scanning and deep learning was proposed. The optical axial scanning system functions by synchronizing a liquid electronically tunable lens and a CCD camera to capture multi-focus image sequences. The system efficiently captures real-world images with a fast acquisition time of ~50 ms per image. The multi-focus image sequences are then fused to all-in-focus images. The multi-focus images and all-in-focus images (ground truth) serve as the dataset for the deep learning neural network. Defocused images can be reconstructed using the trained deep learning network. Furthermore, by establishing a direct relationship between the focal depth and the driving current applied to the liquid electronically tunable lens, the three-dimensional depth of the scene can be rapidly determined. Experimental results validate the feasibility and effectiveness of this method. It is expected to expand the applications of image defocus enhancement in fields such as medical imaging, 3D shape measurement, and augmented reality. © 2025 SPIE.

关键词： CCD cameras

来源：评论

学校读者我要写书评

暂无评论

An Unambiguous Angle and Range Estimation Method using MR-FDA-MIMO Radar 2

An Unambiguous Angle and Range Estimation Method using MR-FD...

引用

2nd IEEE International Conference on signal, information and Data processing, ICSIDP 2024

作者： Wang, Zhengxi Zhu, Shengqi Li, Ximin Lan, Lan Liu, Congfeng Xidian University National Key Lab of Radar Signal Processing Xi'an China Xidian University Key Lab of Electronic Information Countermeasure and Simulation Technology Ministry of Education Xi'an China

ISBN: (纸本)9798331515669

Frequency diversity array (FDA) multiple-input multiple-output (MIMO) radar systems have drawn widespread focus due to their capacity for providing angular and range information simultaneously. Unfortunately, the estimation accuracy is constrained by the amount of physical sensors. This paper proposes a method for unambiguous angle and range estimation using a combination of the minimum redundancy array (MRA) and FDA-MIMO radar. The MRA is applied to extend array degrees of freedom by differential processing. Following the implementation of range compensation, a two-dimensional spatially smoothed algorithm is employed to address the rank deficit issue in the equivalent array. Finally, the target's angle, ambiguous zone and range offset are identified through a MUSIC algorithm. The efficacy for the designed methodology is corroborated by the simulated experimental outcomes. © 2024 IEEE.

关键词： Frequency estimation

来源：评论

学校读者我要写书评

暂无评论

A novel strategy for fine-grained semantic verification of civil aviation radiotelephony read-backs

引用

Chinese Journal of Aeronautics 2022年第12期35卷 266-277页

作者： Guimin JIA Junxian LI Tianjin Key Lab for Advanced Signal Processing Civil Aviation University of ChinaTianjin 300300China College of Electronic Information and Automation Civil Aviation University of ChinaTianjin 300300China

During the flight of the aircraft,the pilot must repeat the instruction sent by the controller,and the controller must further confirm these read-backs,in this way to further ensure the safety of air ***,fatigue,tension,negligence and other human factors may prevent the controller from realizing read-back errors in time,which is a huge hidden danger for the safety of civil aviation *** paper proposes a novel strategy to implement fine-grained semantic verification of radiotelephony read-backs by introducing interaction layer and attention mechanism at the output of BiLSTM *** with the traditional twochannel verification strategy,the interaction layer is added to obtain fine-grained semantic matching relation representation,rather than connecting the BiLSTM output vectors to obtain the overall semantic representation of the *** by adding attention layer,the new strategy can capture the potential semantic relation between the read-backs and the instructions,which is applicable to non-standard diction and abbreviated read-backs in real radiotelephony *** experiments are conducted and the results show that the proposed new strategy is more effective than the traditional method for read-backs checking,and the average test accuracy of the new strategy based on the Chinese ATC radiotelephony read-backs corpus can reach 93.03%.

关键词： Attention mechanism BiLSTM Interaction layer Radiotelephony read-backs Semantic verification

来源：评论

学校读者我要写书评

暂无评论

ϵ-π: A Nonparametric Model for Neural Power Spectra Decomposition

引用

IEEE Journal of Biomedical and Health Informatics 2024年第5期28卷 2624-2635页

作者： Hu, Shiang Zhang, Zhihao Zhang, Xiaochu Wu, Xiaopei Valdes-Sosa, Pedro A. Anhui University Anhui Provincial Key Lab of Multimodal Cognitive Computation Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Hefei230601 China University of Science and Technology of China School of Humanities and Social Science Department of Psychology Hefei230026 China University of Electronic Science and Technology of China MOE Key Lab for Neuroinformation School of Life Science and Technology Chengdu611731 China

The power spectra estimated from the brain recordings are the mixed representation of aperiodic transient activity and periodic oscillations, i.e., aperiodic component (AC) and periodic component (PC). Quantitative neurophysiology requires precise decomposition preceding parameterizing each component. However, the shape, statistical distribution, scale, and mixing mechanism of AC and PCs are unclear, challenging the effectiveness of current popular parametric models such as FOOOF, IRASA, BOSC, etc. Here, was proposed to decompose the neural spectra by embedding the nonparametric spectra estimation with penalized Whittle likelihood and the shape language modeling into the expectation maximization framework. was validated on the synthesized spectra with loss statistics and on the sleep EEG and the large sample iEEG with evaluation metrics and neurophysiological evidence. Compared to FOOOF, both the simulation presenting shape irregularities and the batch simulation with multiple isolated peaks indicated that improved the fit of AC and PCs with less loss and higher F1-score in recognizing the centering frequencies and the number of peaks;the sleep EEG revealed that produced more distinguishable AC exponents and improved the sleep state classification accuracy;the iEEG showed that approached the clinical findings in peak discovery. Overall, offered good performance in the spectra decomposition, which allows flexible parameterization using descriptive statistics or kernel functions. is a seminal tool for brain signal decoding in fields such as cognitive neuroscience, brain-computer interface, neurofeedback, and brain diseases. © 2013 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Pencil beam based on the computational holography method 2

Pencil beam based on the computational holography method

引用

2nd International Academic Conference on Optics and Photonics, IACOP 2024

作者： Luo, Tianlei Lv, Anzhi Liu, Minghao Dong, Jiaqing Liu, Guolin Li, Zilong Song, Xianlin School of Information Engineering Nanchang University Nanchang330031 China School of Advanced Manufacture Nanchang University Nanchang330031 China Jiangxi Provincial Key Laboratory of Advanced Signal Processing and Intelligent Communications Nanchang University Nanchang330031 China

ISBN: (数字)9781510688827

ISBN: (纸本)9781510688810

This paper presents a novel pencil beam generation method based on computational holography. The method generates intensity maps through computer simulation, obtains a computed hologram using a computational holographic method, and simulates near-field diffraction using computer simulation to simulate the role of a spatial light modulator (SLM) in a real holographic system. The theoretical effects of the computed hologram are simulated using computer simulation, and finally, a pencil-shaped beam with a focus position that can be flexibly adjusted at all depths is generated. Through experimental simulations, the feasibility of adjusting the focus position of the beam within a certain depth range is verified, showing its potential application value in fluorescence excitation and biomedical fields. © 2025 SPIE.

关键词： Holograms

来源：评论

学校读者我要写书评

暂无评论

Joint Angle and Range Estimation with Two-Level Nested FDA-MIMO Radar 6

Joint Angle and Range Estimation with Two-Level Nested FDA-M...

引用

6th International Conference on information Communication and signal processing, ICICSP 2023

作者： Wang, Zhengxi Zhu, Shengqi Li, Ximin Wei, Fa Liu, Congfeng Lan, Lan Xidian University National Key Lab of Radar Signal Processing Shannxi Xi'an China Xidian University Key Lab of Electronic Information Countermeasure of the Ministry of Education Shannxi Xi'an China

ISBN: (纸本)9798350339994

The parameter estimation accuracy and the estimated sources number of multiple-input-multiple-output (MIMO) radar with frequency diversity array (FDA) are limited by the number of array elements. In this paper, combining the advantages of nested arrays to expand the array aperture, the signal model of the monostatic two-level nested FDA-MIMO radar is derived. A modified MUSIC algorithm is proposed to solve the rank deficit problem in parameter estimation and realize the joint estimation of angle and range. The effectiveness of the proposed algorithm is verified by simulation results. © 2023 IEEE.

关键词： frequency diversity array modified MUSIC algorithm nested array parameter estimation

来源：评论

学校读者我要写书评

暂无评论

MB-CapsNet: An Efficient Fusion of MobileNetV3 and Matrix Capsule Networks

MB-CapsNet: An Efficient Fusion of MobileNetV3 and Matrix Ca...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Han, Wenxing Zou, An-Min Shantou University Guangdong Provincial Key Laboratory of Digital Signal and Image Processing Dept. of Electronic and Information Engineering Shantou China

ISBN: (纸本)9781665465335

The capsule network constructs the relationship between the part and the whole in an image through feature coding, which shows excellent performance in the image classification. However, the original capsule network is weak in extracting useful feature information, because it tends to explain all the information in a graph and the advantages of the capsule network cannot be reflected in the face of complex background datasets. By using MobileNetV3 as the backbone to replace the simple primary convolutional network layer, an improved capsule network named MB-CapsNet is proposed in this paper. The advanced network reducing the interference of invalid features to focus on effective features. At the same time, a variety of parameter sets are employed and extensive experiments are proceeded on four kinds of datasets. After that, an optimal network configuration is obtained which is suitable for different datasets. The experimental results illustrate that the advanced MB-CapsNet is more effectively than the original capsule network in the feature extraction, showing its advantages and potential in complex datasets. © 2022 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Off-grid DOA estimation via a deep learning framework

引用

Science China(information Sciences) 2023年第12期66卷 222-237页

作者： Yan HUANG Yanjun ZHANG Jun TAO Cai WEN Guisheng LIAO Wei HONG State Key Lab of Millimeter Waves Southeast University Key Laboratory of Underwater Acoustic Signal Processing of Ministry of Education Southeast University School of Information Science and Technology Northwest University National Key Lab of Radar Signal Processing Xidian University

Direction-of-arrival(DOA) estimation problem is one of the most important tasks for array signal processing. Conventional methods are limited by either the computational complexity or the resolution. In this paper, a novel deep learning(DL) framework for super-resolution DOA estimation is developed, where the grid mismatch problem is fully considered into the DL DOA estimation and the offset between the real DOA and the discrete sampling grid is thereby trained as a part of the network output. Specifically, we first model the DOA estimation problem as a multi-classification task and obtain the on-grid estimation result with a resolution of 1° as the first output. Then we designed another regression module to estimate the offset between target angles and the corresponding grids. By combining both on-grid and offset estimation results, the accurate off-grid estimation is achieved. In addition, the method of fusing low-level features and high-level features by skip connection is adopted between the on-grid estimation module and the offset estimation module. The high-level features in the first part of the network are combined with the original input to improve the training speed and the estimation accuracy. Herein, our training dataset contains a large number of off-grid signal data, which is close to the practical application. Also, the utilization of the off-grid part information improves DOA estimation performance compared to existing DL-based methods,achieving more accurate DOA estimations. Numerous simulation results have demonstrated the superiority of the proposed method in DOA estimation precision, and a good performance advantage maintains even when using a limited number of snapshots. Further, we test the proposed method on the real millimeter-wave radar system, and it outperforms the other state-of-the-art methods, especially for two adjacent targets in the same range and Doppler bin.

关键词： direction-of-arrival (DOA) estimation deep learning (DL) off-grid array signal processing

来源：评论

学校读者我要写书评

暂无评论

FAE-MSLKNet: Multi-Scale Large Kernel Network With Fourier Adaptive Enhancement for Automatic Modulation Recognition

引用

IEEE Transactions on Cognitive Communications and Networking 2024年

作者： Lin, Xiaobing Zhang, Jiashu Wang, Hao Zhang, Heying Southwest Jiaotong University Sichuan Province Key Lab of Signal and Information Processing School of Computing and Artificial Intelligence Chengdu611756 China Southwest Jiaotong University Sichuan Province Key Lab of Signal and Information Processing Chengdu611756 China

Automatic Modulation Recognition (AMR) is vital in wireless communication systems. Recently, a number of deep learning(DL) architectures have been developed for AMR. However, existing methods have limitations in frequency analysis and long-range temporal dependencies extraction. Moreover, most models have high computational costs and large model sizes. To overcome these limitations, this paper proposes FAE-MSLKNet, a Multi-Scale Large Kernel Network with Fourier Adaptive Enhancement. First, we introduced a Fourier Adaptive Enhancement (FAE) module to adaptively enhance features and model long-term temporal dependencies in the frequency-domain. Furthermore, a Multi-Scale Large Kernel (MSLK) module is employed to extract local features with small convolution kernels and capture long-range temporal dependencies with large convolution kernels in the time-domain. Experiments on RML2016.10a, RML2016.10b, and RML2018.01a datasets demonstrate that FAE-MSLKNet achieves state-of-the-art performance with improved parameter efficiency and reduced computational complexity, highlighting its potential for practical wireless communication applications. © 2024 IEEE.

关键词： Frequency domain analysis

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：