检索结果-内蒙古大学图书馆

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Minqi Xu Xiaolong Zhang Xiaoli Lin Hubei Key Laboratory of Intelligent Information Processing and Real-time Industrial System School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China

ISBN: (数字)9781728162157

ISBN: (纸本)9781728162164

Computer-aided drug discovery can efficiently predict drug-target interactions, which helps biological researchers to narrow down the search space and reduce experimental consumption. However, the accuracy of existing prediction methods still needs to be further improved. This paper proposes a deep learning model that predicts drug-target interactions through effective strategies: the graphical representation of SMILES based on Graph Isomorphic Network (GIN) and word vector matrices of amino acid sequences based on one-dimensional convolution, which is used to extract features of drug-target pairs for classification prediction. Compared with the previous methods, the proposed method outperforms the existing work with AUC. A case study of predicting COVID-19 DTIs also shows that the proposed method can be invoked to be use for practical drug-target prediction.

关键词： Feature extraction Drugs Benchmark testing Predictive models Ions Compounds Amino acids

来源：评论

学校读者我要写书评

暂无评论

Moving target modelling and indication in MIMO GEO SAR

Moving target modelling and indication in MIMO GEO SAR

引用

IET International Radar Conference 2018, IRC 2018

作者： Cui, Chang Liu, Xiangrong Dong, Xichao Hu, Cheng Li, Yuanhao School of Information and Electronics Beijing Institute of Technology Beijing China National Key Laboratory of Science and Technology on Test Physics and Numerical Mathematics Beijing China Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing China

Multiple-input multiple-output geosynchronous synthetic aperture radar (MIMO GEO SAR), composed by several mini-satellites in GEO orbits, has more spatial degrees of freedom, which helps to suppress clutter and improves the performance of ground moving target indication (GMTI). However, in order to ensure the satellite safety, the satellite spacing in MIMO GEO SAR is very large. It results in the failure of far-field assumption and causes the moving target defocusing because of the mismatch between the steering vector in far-field sources and the moving target echo. Here, a new signal model based on the near-field sources is first given according to the GEO SAR satellite-ground geometry relationship. Then, considering the phase difference between the different channels, the spatial steering vector is derived and the weight vector for adaptive processing is proposed to suppress clutter and indicate the moving target. Finally, computer simulations are carried out for the validation of the proposed method. © 2019 Institution of Engineering and technology. All rights reserved.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Drug-target Interaction Prediction via Multiple Output Deep Learning

Drug-target Interaction Prediction via Multiple Output Deep ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Qing Ye Xiaolong Zhang Xiaoli Lin Hubei Key Laboratory of Intelligent Information Processing and Real-time Industrial System School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China

ISBN: (数字)9781728162157

ISBN: (纸本)9781728162164

Computational prediction of drug-target interaction (DTI) is very important for the new drug discovery. However, by connecting drugs and targets to form drug target pairs, the number of interactions is limit, most interactions focus on only a few targets or a few drugs, and the number of drug target pairs is far more than the number of interactions, which causes to be over fitting. To overcome the above problem, in this paper, a multiple output deep neural network (MODNN) based DTI prediction is designed. MODNN enhances its learning ability with a kind of auxiliary classifier layers. The parameters used in the training process are elaborated from the auxiliary and main classifier layers, which can increase the gradient signal that gets propagated back, utilize multi-level features to train the model, and use the features produced by the higher, middle or lower layers in a unified framework. The conducted experiments validate the effectiveness of our MODNN.

关键词： Drugs Feature extraction Diffusion tensor imaging Integrated circuits Training Deep learning Neural networks

来源：评论

学校读者我要写书评

暂无评论

UCS: A Universal Model for Curvilinear Structure Segmentation

arXiv

引用

arXiv 2025年

作者： Li, Dianshuo Chen, Li Cao, Yunxiang Zhu, Kai Cheng, Jun School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan430065 China 1 Fusionopolis Way #21-01 Connexis South Tower Singapore138632 Singapore

Curvilinear structure segmentation (CSS) is vital in various domains, including medical imaging, landscape analysis, industrial surface inspection, and plant analysis. While existing methods achieve high performance within specific domains, their generalizability is limited. On the other hand, large-scale models such as Segment Anything Model (SAM) exhibit strong generalization but are not optimized for curvilinear structures. Existing adaptations of SAM primarily focus on general object segmentation and lack specialized design for CSS tasks. To bridge this gap, we propose the Universal Curvilinear structure Segmentation (UCS) model, which adapts SAM to CSS tasks while enhancing its generalization. UCS features a novel encoder architecture integrating a pretrained SAM encoder with two innovations: a Sparse Adapter, strategically inserted to inherit the pre-trained SAM encoder’s generalization capability while minimizing the number of fine-tuning parameters, and a Prompt Generation module, which leverages Fast Fourier Transform with a high-pass filter to generate curve-specific prompts. Furthermore, the UCS incorporates a mask decoder that eliminates reliance on manual interaction through a dual-compression module: a Hierarchical Feature Compression module, which aggregates the outputs of the sampled encoder to enhance detail preservation, and a Guidance Feature Compression module, which extracts and compresses image-driven guidance features. Evaluated on a comprehensive multi-domain dataset, including an in-house dataset covering eight natural curvilinear structures, UCS demonstrates state-of-the-art generalization and open-set segmentation performance across medical, engineering, natural, and plant imagery, establishing a new benchmark for universal CSS. Copyright © 2025, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Ultrasound vascular image segmentation based on full convolutional aggregation neural network 2019

Ultrasound vascular image segmentation based on full convolu...

引用

Proceedings of the 2019 3rd International Conference on Computer Science and Artificial Intelligence

作者： Yan Li Jun Liu Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial Department of Computer Science and Technology Wuhan University of Science and technology Wuhan China

ISBN: (纸本)9781450376273

The concept of ultrasound therapy has been proposed long ago. However, most of the previous methods of ultrasound therapy destroy tissue through thermal effects and cause great damage to patients. In recent years, ultrasound cavitation therapy has caused extensive discussion and research due to its unique non-invasiveness. In order to achieve real-time access to the patient during treatment, the lesion area must be processed simultaneously and accurately. However, ultrasound images mostly have lower signal-to-noise ratio, contrast, and blurred edges. In order to solve the segmentation problem, this paper proposes a new segmentation model Du-net based on the full convolutional neural network. Under the premise of deepening the network depth to obtain more information, the Encoder-Decoder method and the layered aggregation mode are used to prevent the gradient explosion. Solving boundary segmentation problem by constructing joint network, In the case of a small data set, the data enhancement method using a suitable data set effectively increases the usable image features and achieves better results on the ultrasound blood vessel image.

关键词： layered aggregation mode Joint network ultrasonic therapy Full convolution network

来源：评论

学校读者我要写书评

暂无评论

Terminal Bulb Segmentation of Caenorhabditis Elegans under Small Samples Based on Two-stage U-Net Network 2019

Terminal Bulb Segmentation of Caenorhabditis Elegans under S...

引用

Proceedings of the 2019 3rd International Conference on Computer Science and Artificial Intelligence

作者： Si Cao Jun Liu Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial Department of Computer Science and Technology Wuhan University of Science and technology Wuhan China

ISBN: (纸本)9781450376273

Convolutional neural network based on machine learning has become one of the most popular methods of image recognition and segmentation, but it needs huge data samples to get better results. In this study, based on U-Net network, a two-stage convolution neural network method for automatic segmentation of Terminal bulb of Caenorhabditis elegans in small samples was proposed. The method solves the problem that traditional single-stage network cannot be implemented in small samples. The Dice coefficient reaches 89.5%, which is higher than that of the baseline U-Net method.

关键词： Convolutional Neural Network Computer Vision U-Net Caenorhabditis elegans

来源：评论

学校读者我要写书评

暂无评论

Robust space-time adaptive processing based on covariance matrix reconstruction and steering vector correction

Robust space-time adaptive processing based on covariance ma...

引用

IET International Radar Conference 2018, IRC 2018

作者： Hu, Xueyao Zhang, Xinyu Li, Yang Wang, Hongyu Wang, Yanhua Beijing Key Laboratory of Embedded Real-Time Information Processing Technology School of Information and Electronics Beijing Institute of Technology Beijing100081 China College of Electronic Sciences National University of Defence Technology Changsha410073 China

Clutter presents considerable heterogeneity in forward-looking airborne radar (FLAR) applications and conventional space-time adaptive processing (STAP) methods are sensitive to model mismatch. As a result, when a strong target signal contaminates the training samples, despite the use of guard cells, the performance of conventional STAP methods degrades significantly. In this study, a robust method, which involves reconstructing a target-free covariance matrix and correcting the presumed steering vector to prevent target cancellation in FLAR, is proposed. First, the target-free covariance matrix is reconstructed through integrating the spatial-temporal spectrum over a sector separated from the desired frequency and direction of targets. Subsequently, the mismatch between presumed steering vector and actual steering vector is corrected via quadratic optimisation. In addition, the processing scheme is applied to real-measured clutter data, and the experimental results validate the effectiveness of the proposed method. © 2019 Institution of Engineering and technology. All rights reserved.

关键词： Space time adaptive processing

来源：评论

学校读者我要写书评

暂无评论

Dual Polarimetric HRRP Sequence Recognition Based on H|α Features

Dual Polarimetric HRRP Sequence Recognition Based on H|α Fe...

引用

2019 IEEE International Conference on Signal, information and Data processing, ICSIDP 2019

作者： Zhang, Liang Long, Teng Li, Yang Wang, Yanhua Radar Research Lab School of Information and Electronics Beijing Institute of Technology Beijing100081 China Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing100081 China Beijing Institute of Technology Chongqing Innovation Center Chongqing401120 China

ISBN: (纸本)9781728123455

Dual polarimetric high resolution range prole (HRRP) is able to provide polarimetric and high resolution scattering characteristics information of radar target, which are very useful for automatic target recognition (ATR). In this paper, a novel feature extraction method, which combines both polarimetric and high resolution information, is proposed for dual polarimetric HRRP sequence based on H/alpha decomposition. In this method, the Halpha decomposition is applied on HRRP sequence by temporal average instead of traditional spatial average, which retains the full resolution of HRRP data and provides efficient polarimetric characteristics information of target scattering centers. This paper also presents a scattering mechanisms classification method using the extracted H and α features, and analyzes the effect of noise and clutter on the two features as well as classification performance. The application and effectiveness of the proposed method are demonstrated via outfield experiments. Results show that scattering mechanisms and structural components of a volumetric target are recognized over high resolution range cells, and the proposed method is able to provide support for HRRP sequence-based radar ATR. © 2019 IEEE.

关键词： Automatic target recognition

来源：评论

学校读者我要写书评

暂无评论

Radar Anti-Retransmitted Jamming technology Based on Agility Waveforms

Radar Anti-Retransmitted Jamming Technology Based on Agility...

引用

2019 IEEE International Conference on Signal, information and Data processing, ICSIDP 2019

作者： Wang, Hongyu Yang, Xinkun Li, Yang Radar Research Lab School of Information and Electronics Beijing Institute of Technology Beijing100081 China Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing100081 China Beijing Institute of Technology Chongqing Innovation Center Chongqing401120 China

ISBN: (纸本)9781728123455

An anti-retransmitted jamming technique is proposed by utilizing phase and frequency-coded waveform techniques. To generate the effective agility waveforms, improved Logistic-Map chaotic sequences generation and optimization algorithm are proposed to obtain sets of orthogonal polyphase codes. The simulated ambiguity function of the agility waveform shows that the agility waveform presents a high resolution in the range domain. The performance of the waveform under different signal-to-interference ratios(SIR) is analyzed. Compared to conventional LFM waveforms, the agility waveform is capable of suppressing the retransmitted jamming effectively, by up to 30dB when the SIR is -5dB. © 2019 IEEE.

关键词： Jamming

来源：评论

学校读者我要写书评

暂无评论

Polarimetric SAR Image Scattering Center Estimation via Atomic Norm Minimization

Polarimetric SAR Image Scattering Center Estimation via Atom...

引用

2019 IEEE International Conference on Signal, information and Data processing, ICSIDP 2019

作者： Xi, Ying Wang, Yanhua Chen, Wei Liu, Haibo Li, Yang Radar Research Lab School of Information and Electronics Beijing Institute of Technology Beijing100081 China Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing100081 China Beijing Institute of Technology Chongqing Innovation Center Chongqing401120 China

ISBN: (纸本)9781728123455

Polarization is one of the most important characteristics of electromagnetic wave, which offers another dimension of information to radar automatic target recognition (RATR). The combination of polarization and SAR technology is a vital research direction for RATR. Fusing the polarization information into the scattering center model is able to refine the scattering structural information. This paper proposes a fully-polarimetric SAR images scattering center estimation method based on multiple measurement vector (MMV) atomic norm minimization (ANM) model. The experimental results indicate the superiorities of the proposed method in terms of accuracy and robustness. © 2019 IEEE.

关键词： Synthetic aperture radar

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：