检索结果-内蒙古大学图书馆

IET International Radar Conference (IRC 2023)

作者： Changjun Wang Hanpu Zhou Jian Wang Jiake Gao Yunkai Deng Weiming Tian Beijing Building Research Institute Co. Ltd. of CSCEC Beijing 100076 People's Republic of China Radar Research Lab School of lnformation and Electronics Beijing lnstitute of Technology Beijing People's Republic of China Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing People's Republic of China Chongqing Innovation Center Beijing Institute of Technology People's Republic of China Advanced Technology Research Institute Beijing Institute of Technology Jinan 250300 People's Republic of China

ISBN: (数字)9781837240982

The deformation monitoring data of foundation pit is an important criterion for forecasting and strengthening measures in the field of building safety. During the construction period, the foundation pit will be affected by load, temperature change, random disturbance and other effects to produce deformation. Due to the complex deformation process of foundation pit, it is hard to accurately describe and separate the load trend deformation and elastic thermal deformation by mathematical expression. Excessive thermal deformation may cause cracks in the surrounding pavement and affect the judgment of load deformation. This paper first introduces the deformation measurement method of foundation pit based on differential interferometry technology using ground-based interferometric radar. Based on the obtained deformation type, the simulation verifies the separation effect of wavelet transform on different deformation trends and periodic components. Through the foundation pit deformation monitoring experiment of Tongzhou infrastructure project, the wavelet transform method is used to decompose the foundation pit deformation curve, and the extracted periodic component has good consistency with the temperature information.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pruning convolutional neural networks for remote sensing images 5

Pruning convolutional neural networks for remote sensing ima...

引用

IET International Radar Conference 2020, IET IRC 2020

作者： Qi, Baogui Xu, Yinsheng Chen, He Chen, Liang Beijing Key Laboratory of Embedded Real-Time Information Processing Technology Beijing Institute of Technology Beijing100081 China Beijing Institute of Technology Chongqing Innovation Center Chongqing401120 China Shanghai Institute of Satellite Engineering Shanghai200240 China

ISBN: (纸本)9781839535635

Deep convolutional neural networks (DCNNs) have shown excellent performance in remote sensing image processing. However, DCNNs contain many parameters and require many computational resources. It is very difficult to deploy DCNNs on spaceborne, airborne, or other mobile platforms with limited resources. It is necessary to compress the parameters of DCNNs. In this paper, we introduce a novel network pruning strategy that can prune redundant filters or weights of networks and preserve the performance of DCNNs in remote sensing image classification tasks. Unlike traditional pruning methods using a single criterion, this paper improves the pruning process based on the combined pruning method of multiple criteria. VGGNet and ResNet are used to validate our method. The dataset used in our experiments is the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset. The results demonstrate that our method is effective and can maintain the accuracy of a pruned model in remote sensing image classification tasks. © 2020 Institution of Engineering and technology. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

SAR Parameter Estimation Method for Rectangle Plane Based on information Geometry

SAR Parameter Estimation Method for Rectangle Plane Based on...

引用

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

作者： Wen, Yuhan Chen, Xinliang Wei, Yangkai Fan, Yujie Zeng, Tao DIng, Zegang Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing China

ISBN: (纸本)9781728123455

After establishing scattering models, the traditional synthetic aperture radar (SAR) parameter estimation methods usually utilize vanilla gradients to estimate target parameters from SAR echoes or images. However, the vanilla gradients will lead to lower iteration efficiency. Hence, in this paper, to take the rectangle plane as an example, we propose a SAR parameter estimation method based on the information geometry (SPEM-IG) to solve the above problem. The SPEM-IG adopts the natural gradient to estimate the parameters based on the information geometry optimization algorithm. The central objective of SPEM-IG is to project the least square function into probability distribution space and find the optimal solution in the new parameter space. In order to reduce the computational complexity caused by the multi-peak feature of least squares function, SPEM-IG utilizes the range of parameters rather than its exact value in calculating the value of least squares function, and takes the optimal solution in this range as the result of the current iteration process. By considering the geometric structure of manifolds, SPEM-IG calculates the optimal gradient direction called natural gradient to obtain faster convergence rate. The experimental results show that the SPEM-IG is effective for estimating target parameters. Besides, SPEM-IG has good performance even at low signal-to-noise ratios of SAR images. © 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

Merging Clinical Knowledge into Large Language Models for Medical Research and Applications: A Survey

arXiv

引用

arXiv 2025年

作者： Li, Qiyuan Liu, Haijiang Guo, Caicai Chen, Deyu Wang, Meng Gao, Feng Gu, Jinguang College of Computer Science and Technology Wuhan University of Science and Technology Hubei Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Hubei Wuhan430065 China The Key Laboratory of Rich-Media Knowledge Organization Service of Digital Publishing Content Institute of Scientific and Technical Information of China Beijing100038 China School of Computer Science and Technology Huazhong University of Science and Technology Hubei Wuhan430074 China School of Cyber Science and Engineering Wuhan University Hubei Wuhan430072 China

Clinical knowledge is the collection of information learned from studies on the causes, prognosis, diagnosis, and treatment of diseases. This type of knowledge can improve curing performances, and promote physical health. With the emergence of large language models (LLMs), medical artificial intelligence (medical AI), which aims to apply academic medical AI systems to real-world medical scenarios, has entered a new age of development, resulting in excellent works such as DoctorGPT and Pangu-Drug from academic and industrial researches. However, the field lacks a comprehensive compendium and comparison of building medical AI systems from academia and industry. Therefore, this survey focuses on the building paradigms of medical AI systems including the use of clinical databases, datasets, training pipelines, integrating medical knowledge graphs, system applications, and evaluation systems. We hope that this survey can help relevant practical researchers understand the current performance of academic models in various fields of healthcare, as well as the potential problems and future directions for implementing these scientific achievements. Copyright © 2025, The Authors. All rights reserved.

关键词： Clinical research

来源：评论

学校读者我要写书评

暂无评论

SAR Target Recognition Using Improved Monogenic-Based Feature Extraction Framework

SAR Target Recognition Using Improved Monogenic-Based Featur...

引用

IEEE International Conference on Radar

作者： Feng Li Weijun Yao Yang Li Wei Chen Radar Research Laboratory School of Information and Electronics Beijing Institute of Technology Beijing Institute of Technology Chongqing Innovation Center Beijing China Radar Research Lab Beijing Key Laboratory of Embedded Real-time Information Processing Technology School of Information and Electronics Beijing Institute of Technology Beijing China

ISBN: (纸本)9781665468893

Applying computer vision methods to synthetic aperture radar (SAR) image recognition is a research trend in recent years, and a series of valuable results have been achieved. In order to use machine learning classifiers for recognition, it is necessary to extract effective features, and most of these features are directly extracted based on grayscale SAR images. SAR data is usually rare, and more difficult to collect than optical images. Therefore, the problem of recognition using a small-size training set for SAR is more challenging to practical pattern recognition methods. The monogenic signal is an extended version of analytic signals in high-dimensional space which has attracted attention. In this paper, a new recognition framework which is based on feature dimensionality augmentation using combined multi-scale monogenic components and histogram of oriented gradient (HOG) feature is proposed. Proposed feature is named as MONO-HOG. This letter focuses on recognition under both standard operating condition (SOC) and small-sample scene. Experiments on moving and stationary target automatic recognition (MSTAR) data set show that our proposed framework has satisfying performance.

关键词： Training Computer vision Image recognition Target recognition Feature extraction Optical imaging Radar polarimetry

来源：评论

学校读者我要写书评

暂无评论

Lightweight convolutional neural network for false alarm elimination in SAR ship detection 5

Lightweight convolutional neural network for false alarm eli...

引用

IET International Radar Conference 2020, IET IRC 2020

作者： Zheng, Xingfei Feng, Yangkai Shi, Hao Zhang, Bocheng Chen, Liang Radar Research Lab School of Information and Electronics Beijing Institute of Technology Beijing China Shanghai Institute of Satllite Engineering Shanghai China Beijing Key Laboratory of Embedded Real-Time Information Processing Technology Beijing China Beijing Institute of Technology Chongqing Innovation Center Chongqing China

ISBN: (纸本)9781839535635

SAR ship detection is an important task of SAR image interpretation and plays a significant role in global marine surveillance. However, since there are usually many false alarms in the detection results, a desirable performance is rarely achieved. Aiming at this problem, this paper proposes an improved method for the ship detection process, using the lightweight convolutional neural network EfficientNet-B0 as a false alarm elimination network, cascaded after the detection stage, to reduce the false alarm rate in the detection results and improve the overall detection accuracy. The results on the MSTAR data set show that EfficientNet-B0 has a good classification effect, and the experiments on the custom data set also verify the effectiveness of the network. © 2020 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

Implementation of Automatic Face Detection System Based on ARM

Implementation of Automatic Face Detection System Based on A...

引用

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

作者： Li, Keng Chen, He Beijing Key Laboratory of Embedded Real-Time Information Processing Technology Beijing China Beijing Key Laboratory of Embedded Real-Time Information Processing Technology Beijing Institute of Technology 5 South Zhongguancun Street Haidian District Beijing China

ISBN: (纸本)9781728123455

The embedded automatic face detection system is to locate the face region in the real scene. In order to reach a real-time performance, We adopt a cascaded structure of the convolution neural network model to solve face detection problem. In hardware implementation, the ARM Cortex-A9 processor is used to achieve the algorithm. And the Neon unit in ARM is used to achieve the parallel operation of the basic data of the algorithm, so the detection algorithm is accelerated to achieve the real-time operation of the automatic face detection system. © 2019 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Efficient and Lightweight Target Recognition for High Resolution Spaceborne SAR Images

Efficient and Lightweight Target Recognition for High Resolu...

引用

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

作者： Pan, Yu Tang, Linbo Jing, Donglin Tang, Wei Zhou, Shichao Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing China

ISBN: (纸本)9781728123455

Fast and reliable target recognition of the synthetic aperture radar (SAR) images has been widely used in the fields of the marine monitoring, military reconnaissance and strike all over the world. However, due to the difficulty of the intra-class difference and inter-class similarity of the multiclass targets in the high resolution SAR images, the existing methods are difficult to recognize the targets accurately when facing the spaceborne platforms with the high resource constraints. Therefore, in order to solve the above problems, we propose a novel recognition method based on the convolutional neural network (CNN). Firstly, we propose a lightweight CNN framework which regards densely connected convolutional network (DenseNet) as the baseline. Secondly, we advocate a strong discriminative loss function which efficiently improves the recognition accuracy of the targets in the spaceborne SAR images. Experiments are conducted on the TerraSAR dataset and MSTAR dataset to evaluate the proposed method. The results show that our method performs better than the baseline on the both benchmark datasets. © 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

FPGA-based accelerator for convolution operations

FPGA-based accelerator for convolution operations

引用

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

作者： Cao, Yunfei Wei, Xin Qiao, Tingting Chen, He Beijing Key Laboratory of Embedded Real-Time Information Processing Technology Beijing China Beijing Key Laboratory of Embedded Real-Time Information Processing Technology Beijing Institute of Technology 5 South Zhongguancun Street Haidian District Beijing China

ISBN: (纸本)9781728123455

Convolutional neural networks have been widely used in many deep learning applications. Convolutional neural networks have a large number of convolution operations, which poses a huge challenge to real-time performance. In recent years, FPGA implementations of convolutional accelerators have received much attention due to their high performance and energy efficiency. In this paper, we implement an accelerator for convolution operations through the systolic array architecture on Xilinx ZedBoard device. The experimental results show that ours designed accelerators achieving performance density of up to 0.032 Gop/s/DSP. © 2019 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Binary Separable Convolutional: An Efficient Fast Image Classification Method

Binary Separable Convolutional: An Efficient Fast Image Clas...

引用

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

作者： Jing, Donglin Tang, Linbo Pan, Yu Tang, Wei Zhou, Shichao Beijing Key Laboratory of Embedded Real-time Information Processing Technology Beijing Institute of Technology Beijing China

ISBN: (纸本)9781728123455

The training and running of neural network require large computational space and memory space, which makes it difficult to deploy on a resource-constrained embedded sys-tems. To address this limitation, we introduce a two-stage pipeline: Depth separable, local binary. Our method is divided into two steps. Firstly, a deep separable convolution is applied to each input channel. Then, point-by-point convolution is applied to the feature map obtained by the filter. In the second step, we use local binarization method to initialize the filter corresponding to the input channel into sparse binary. In network training, the sparse binary filter remains fixed and only needs to train convolution of 11 size. Our experimental results show that, on the basis of approximate accuracy with the original network, we have reduced the number of convolution parameters by 9x to 10x, and reduced the training time and testing time to by 2x. Our compression method helps to deploy complex neural networks on resource-constrained embedded platform. © 2019 IEEE.

关键词： Image classification

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：