检索结果-内蒙古大学图书馆

22nd International Conference on Man-Machine-Environment System Engineering, MMESE 2022

作者： Ding, Kai Zheng, Shoujun Qi, Xiaogang Huang, Shan Liu, Haoting Science and Technology on Near-Surface Detection Laboratory Wuxi214035 China School of Mathematics and Statistics Xidian University Xi’an710071 China Nanjing ATE Electronic Tech Co. Ltd. Nanjing China Beijing Engineering Research Center of Industrial Spectrum Imaging University of Science and Technology Beijing100083 China

ISBN: (纸本)9789811947858

Feature extraction and classification are the main body of acoustic target recognition. Firstly, amplitude extraction based on harmonic set, MFCC and wavelet packet decomposition are selected as feature selection methods to extract the features of four kinds of measured sound signals respectively. Then, the feature vectors extracted by MFCC method with the best clustering effect are combined with GMM classifier, BP neural network, OVO-SVMs and multi-layer support vector machine as classifiers, and MATLAB is used for simulation recognition and classification. Finally, the recognition results are compared and analyzed. The results show that BP neural network has the best recognition effect, but its robustness is poor, the experimental results are unstable, and the selection of training and test data has a great impact on the recognition rate. The multi classification algorithm based on support vector machine has a better stable recognition rate. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Thin Wide Range Varifocal Diffractive Alvarez Lens Actuated by Dielectric Elastomers

SSRN

引用

SSRN 2024年

作者： Cheng, Yang Hao, Qun Liu, Lin Cao, Jie Liu, Mengyao Ou, Yangqi Key Laboratory of Biomimetic Robots and Systems Ministry of Education Beijing Institute of Technology Beijing100081 China Yangtze Delta Region Academy of Beijing Institute of Technology Jiaxing314003 China National Key Laboratory of Science and Technology on Near-Surface Detection Beijing100012 China

A thin wide range varifocal diffractive Alvarez lens actuated by dielectric elastomers (DEs) is designed and proposed. The diffractive Alvarez lens is manufactured by the laser direct writing technique with four etching depths. The diffractive Alvarez lens consists of two diffractive phase plates, which can move laterally by applying an actuation voltage to the DEs, and then the focal length of the diffractive Alvarez lens changes. The thickness and the optical aperture of the proposed diffractive Alvarez lens are 4 mm and 10 mm, respectively. The focal length ratio is up to 10×, where the maximum the minimum focal lengths are 300 mm and 30 mm, respectively. The rise time and fall time are 134 ms and 206 ms. The average diffraction efficiency is 82% at 532 nm. Such a thin wide range varifocal diffractive Alvarez lens promises a potential solution for many applications, such as endoscopes, consumer electronics, and microscopies. © 2024, The Authors. All rights reserved.

关键词： Lenses

来源：评论

学校读者我要写书评

暂无评论

Research on Propagation Characteristics of Seismic Signal for Moving Armoured Targets 9

Research on Propagation Characteristics of Seismic Signal fo...

引用

9th International Conference on Environmental and Engineering Geophysics, ICEEG 2020

作者： Ding, Kai Zheng, Shoujun Li, Xinghua Rong, Yingjiao Science and Technology on Near-Surface Detection Laboratory Wuxi214035 China Army Engineering University of PLA Nanjing210007 China

This paper is focused on the Seismic Signal characteristics of wheel and track vehicles. The effect of vehicle speed of these two vehicles on the Seismic Signal was studied through experimental and theorical methods. The Seismic Signal s of these two vehicles with two different speeds were tested firstly. Then the measured signals were analyzed by means of the power spectrum method and the wavelet transform method, respectively. and the time- and frequency domain features of the signals were obtained subsequently. Finally, the influence of the speed and type of vehicle on the time- and frequency domain features of the signal and its propagation characteristic were investigated. The results show that, with the propagation of vehicle speed and distance, there is a similar varying law of the Seismic Signal for different vehicles. However, the difference of the time- and frequency domain feature between the two vehicles are striking. © Published under licence by IOP Publishing Ltd.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Medical Image Segmentation based on Coarse-Fine Dual Training Streams

Semi-supervised Medical Image Segmentation based on Coarse-F...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Lizhi Sun Yong Huang Zhengyu Qiao Boyu Yang Xiaochen Li Qun Hao School of Optics and Photonics Beijing Institute of Technology Beijing China Beijing Institute of Technology National Key Laboratory on Near Surface Detection Yangtze Delta Region Academy of Beijing Institute of Technology Jiaxing China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Commonly used semi-supervised medical segmentation networks usually use consistent learning under different data perturbations to regularise training, ignoring the multiscale information of the data itself. Therefore, this paper proposes a new network based on coarse and fine dual training streams(CF-UNet), which consists of a backbone network and auxiliary learning branches(ALB). Our approach has the following two novel designs: 1) We design a simple and effective coarse- fine dual training streams. Specifically, in the coarse training stream, we improve the robustness and generalisation of the model by establishing regularisation between different strong and weak perturbation views. In the fine training stream, we introduce an auxiliary learning branch to improve the prediction performance of the backbone network.2) In the ALB module, we design the channel spatial fusion attention module (CSMA) and multiscale large kernel convolutional attention (MS-LKA) to perform feature extraction and fusion from a variety of scales. We evaluate our proposed method on ACDC and DRIVE datasets and numerous experiments have shown that our CF-UNet outperforms state-of-the-art networks. Code is available at https://***/slz-bit/CF-UNet.

关键词： Training Image segmentation Perturbation methods Biological system modeling Streaming media Robustness Multiaccess communication Kernel Streams Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

A novel variable structure multi-model approach based on error-ambiguity decomposition

引用

Chinese Journal of Aeronautics 2020年第6期33卷 1731-1746页

作者： Han SHEN-TU Yingjiao RONG Dongliang PENG Mengfan XUE Yunfei GUO Institution of Information and Control Hangzhou Dianzi UniversityHangzhou 310018China Science and Technology on Near-Surface Detection Laboratory Wuxi 214035China

Model Set Adaptation(MSA)plays a key role in the Variable Structure Multi-Model tracking approach(VSMM).In this paper,the Error-Ambiguity Decomposition(EAD)principle is adopted to derive the EAD-MSA criterion that is optimal in the sense of minimizing the square error between the estimate and the ***,the EAD Variable Structure first-order General Pseudo Bayesian(EAD-VSGPB1)algorithm and the EAD Variable Structure Interacting Multiple Model(EAD-VSIMM)algorithm are *** proposed algorithms are tested in two groups of maneuvering target tracking scenarios under different modes and observation error *** simulation results demonstrate the effectiveness of the EAD-VSMM approach and show that,compared to some existing multi-model algorithms,the proposed EAD-VSMM algorithms achieve more robust and accurate tracking results.

关键词： Error-ambiguity decomposition Maneuvering target tracking Model sequence set adaptation Multi-model estimation Variable structure

来源：评论

学校读者我要写书评

暂无评论

Novel radome design for RF integration 4

Novel radome design for RF integration

引用

4th International Applied Computational Electromagnetics Society Symposium in China, ACES-China 2021

作者： Ren, Jinjing Zheng, Yezhen Jing, Shenhui Tang, Qi Research Center for Electromagnetic Environmental Effects Southeast University Nanjing China Science and Technology on Near-surface Detection Laboratory Wuxi China

ISBN: (纸本)9781733509619

RF integration is widely needed by modern shipborne radars. A novel dual-band FSS radome with mathrm{S}+mathrm{X} passband is designed and simulated with angular stability. The passband are 1.55~3.4GHz and 9.2~9.7GHz. This radome achieves good performance in the finite large FSS simulation and cylindrical radome simulation. © 2021 Applied Computational Electromagnetics Society (ACES).

关键词： Radomes

来源：评论

学校读者我要写书评

暂无评论

Orbital angular momentum spectrum diagnostic from a powermeter

引用

Optics Letters 2025年第11期50卷 3784-3787页

作者： Ruitao Lu Chunqing Gao Shiyao Fu School of Optics and Photonics Beijing Institute of Technology Beijing 100081 China Key Laboratory of Information Photonics Technology Ministry of Industry and Information Technology of the People’s Republic of China Beijing 100081 China Key Laboratory of Photoelectronic Imaging Technology and System Ministry of Education of the People’s Republic of China Beijing 100081 China National Key Laboratory on Near-Surface Detection Beijing 100072 China

Orbital angular momentum (OAM) spectrum is one of the identity characteristics of laser beams and determines the performance of OAM based advanced applications. Therefore, diagnosing the OAM spectrum of a beam is of great significance. In this Letter, we show that a common commercial powermeter, rather than an array detector such as the charge coupled device, can be employed to accurately measure OAM spectra for beams. In our proposal, a series of probe single OAM modes are introduced to interfere with the incident beam to be measured. Then, a power value sequence is measured through a powermeter. Finally, the OAM spectrum is acquired by analyzing the power value sequence. The favorable experimental results illustrate the effectiveness of our proposal, where the OAM spectra of both single-mode and multiplexed OAM beams are well diagnosed. This work provides a new, to the best of our knowledge, insight of the OAM spectrum diagnostics and is expected to reduce the cost of the measuring system, thereby facilitating the widespread and advanced application of OAM.

关键词： Charge-coupled devices Diffractive optical elements Laser beams Orbital angular momentum multiplexing Spatial light modulators Vertical cavity surface emitting lasers

来源：评论

学校读者我要写书评

暂无评论

Camouflaged target tracking based on a scale-adaptive correlation filter algorithm

Camouflaged target tracking based on a scale-adaptive correl...

引用

2021 China Automation Congress, CAC 2021

作者： Liu, Yang Wang, Congqing Zhou, Yongjun College of Automation Engineering Nanjing University of Aeronautics and Astronautics Nanjing China Science and Technology on Near-Surface Detection Laboratory Wuxi China

ISBN: (纸本)9781665426473

Catering the continuous development of intelligent technology and the wide application prospects of unmanned aerial vehicles (UAVs), the target tracking technology will be applied in future combat. In order to deal with the complex battlefield environment and the scale change of the target during tracking, an improved scale-adaptive correlation filter algorithm based on fusion features is proposed to realize the tracking of military personnel. First, the fast histogram of oriented gradient (FHOG) features and the local binary pattern (LBP) features are adaptively weighted and fused to achieve the target location. Then the translation filter of kernelized correlation filters(KCF) and the scale filter of discriminative scale space tracking(DSST) are combined to comprehensively improve the calculation speed and scale adaptation performance of the algorithm and track the target in time. The experimental results prove the robustness and practicability of the proposed method, which can accurately track military targets in real time. © 2021 IEEE

关键词： Local binary pattern

来源：评论

学校读者我要写书评

暂无评论

Aerial Tracking of Camouflaged People in Woodlands Via Unsupervised Learning

SSRN

引用

SSRN 2023年

作者： Liu, Yang Wang, Congqing Xu, Bin Zhou, Yongjun College of Automation Engineering Nanjing University of Aeronautics and Astronautics Nanjing211106 China Science and Technology on Near-Surface Detection Laboratory Wuxi214000 China

With the widespread use of unmanned aerial vehicles (UAVs) and computer vision, much attention has been devoted to aerial tracking. Previous tracking methods were mostly implemented in clean and well-lit environments, making it challenging to track camouflaged people rapidly and accurately in woodlands. In this work, we develop a novel unsupervised learning framework for camouflaged people aerial tracking (named UCAT) based on transformer. Specifically, a camouflaged people discovery strategy is proposed to rapidly generate training samples from the unlabeled videos captured by the UAV. Dynamic programming is also employed to filter noises to generate smooth candidate frames. To make full use of multi-level feature information, a transformer fusion framework is designed to integrate shallow spatial information and in-depth semantic features. For reducing computing consumption, the spatial attention reduction mechanism is embedded to the multi-head attention for fast tracking. Further, we build a dataset for evaluating the effect of camouflaged people tracking called Cam235, which consists of 85 manually labeled test sequences and over 100k frames of the unlabeled training set. Comprehensive experiments on Cam235-test and popular tracking benchmarks show that the UCAT learned from unlabeled videos performs well in camouflaged people tracking, demonstrating the practical value of the tracker. © 2023, The Authors. All rights reserved.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Microstructural analysis and nonlinear optical properties of PP/PA6/Clay composites: a comparative study with and without compatibilizer

引用

Optical and Quantum Electronics 2025年第5期57卷 1-27页

作者： Orshesh, Z. Dehghani, Z. Moghaddasi, M. Bagheri, R. Abrinaei, F. Department of Materials Science and Engineering Ahvaz Branch Islamic Azad University Ahvaz Iran Department of Materials Science and Engineering Central Tehran Branch Islamic Azad University Tehran Iran Department of Physics University of Neyshabur P. O. Box *** Neyshabur Iran National Key Laboratory on Near-Surface Detection School of Optics and Photonics Beijing Institute of Technology Beijing100081 China Department of Materials Science and Engineering Sharif University of Technology P. O. Box 11365-9466 Tehran Iran Department of Physics Central Tehran Branch Islamic Azad University Tehran Iran Department of Physics East Tehran Branch Islamic Azad University Tehran Iran

Ternary polypropylene/polyamide6/organoclay composites were successfully synthesized through a melt-mixing process, with and without a compatibilizer. The chemical-bond, structural, and morphological characteristics of composites were thoroughly investigated utilizing Fourier-transform infrared spectroscopy, wide-angle X-ray diffraction, and scanning electron microscopy analyses. The morphological investigations showed that the addition of a compatibilizer to the composite leads to a reduction in the size of the dispersed PA6/clay domains and a decrease in the distance between them due to the formation of a PP-g-PA copolymer at the interface, which improves compatibility between the PP and PA6 phases. Furthermore, the differential scanning calorimetry technique was employed to assess the crystallization and thermal action of the composites. The results revealed that the addition of a compatibilizer resulted in a slight increase in the crystallization temperature of PP and a reduction in the overall crystallinity of the composite, attributed to the compatibilizer’s interaction with both the clay and PA6/clay islands, limiting PP chain mobility and hindering crystallization. The band gap energies were determined in a range of 4.17–4.34 eV by diffuse reflectance spectroscopy and utilizing the Tauc method. Notably, this study marks the first instance of exploring the nonlinear optical properties of these composites. This was achieved by employing Z-scan technique by subjecting the samples to a continuous-wave Nd:YAG laser functioning at a wavelength of 532 nm. A positive nonlinearity of the order of 10–8 cm2W−1 was observed across all samples studied. Particularly noteworthy was the significant enhancement in nonlinear refractive index and absorption coefficients for polypropylene/polyamide6/organoclay ternary composites upon the addition of the compatibilizer. These findings strongly indicate the potential of these composites for applications in nonlinear optical devic

关键词： Fourier transform infrared spectroscopy

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：