检索结果-内蒙古大学图书馆

Artificial Intelligence, Human-Computer Interaction and Robotics (AIHCIR), International Conference on

作者： Yefei Qian Mayire Ibrayim Askar Hamdulla Chunhu Zhang Xinjiang Key Laboratory of Signal Detection and Processing Urumqi China School of Computer Science and Technology Xinjiang University Xinjiang China

Although scene text recognition (STR) methods have made great progress, reading the text of irregularly shaped scenes remains a challenge. The current conversion of two-dimensional (2D) images to one-dimensional (1D) feature maps for sequence recognition may lose a large amount of spatial information and cannot recognize text with a large degree of curvature. In this paper, we propose an network infrastructure to recognize texts of arbitrary shapes, named COT2D Attention Text Recognition Network (COT2Net). Firstly, deformable convolution is added to the feature extraction module, which can perform feature extraction according to the shape of the character and expand the receptive field of feature extraction; Finally, in the Transformer encoding stage, the multi-head attention is changed to Contextual 2D Multi-head Attention (COT2D), which can make full use of the relationship between the input keys Q, K, and V to guide the learning of dynamic attention, thereby enhancing the visual expression ability of text images. The COT2DNet uses COT2D to learn the relevance of each character in a scene text image and achieves excellent results on public datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detection of interference in main lobe for two-dimensional monopulse antenna

Detection of interference in main lobe for two-dimensional m...

引用

IEEE MTT-S International Microwave Workshop Series on Advanced Materials and Processes for RF and THz Applications (IMWS-AMP)

作者： Yujiao Wang Weixing Sheng Array Antenna and Array Signal Processing Laboratory Nanjing University of Science and Technology

In this paper, an interference detection and angle estimation algorithm for two-dimensional monopulse antenna is proposed to solve the problem that the interference in the main lobe is difficult to be detected. Only the sum signal, difference signal and noise variance are required in this algorithm. We use the generalized likelihood ratio criterion (GLRT) to obtain a detection statistic, compare this statistic with the set threshold, and then realize the detection of interference according to the comparison result. The angle estimation formula is further derived. Simulation results show that the performance of interference detection and angle estimation is well achieved.

关键词： Microwave antennas Radio frequency Azimuth Simulation Conferences Estimation Interference

来源：评论

学校读者我要写书评

暂无评论

Target Range Angle And Velocity Estimation Method For FDA-MIMO Radar

Target Range Angle And Velocity Estimation Method For FDA-MI...

引用

IEEE International Conference on Radar

作者： Keyi Wang Guisheng Liao Jingwei Xu Yanhong Xu Qingyun Kan Kaiwei Wang National Key Laboratory of Radar Signal Processing Xidian University Xi’an China The School of Communication and Information Engineering Xi’an University of Science and Technology Xi’an China

ISBN: (数字)9798350362381

ISBN: (纸本)9798350362398

The frequency diverse array multiple-input and multiple-output (FDA-MIMO) radar has been widely applied in parameter estimation due to its additional range information introduced by FDA and increased transmit degrees-of-freedom (DOFs) brought by MIMO. However, the effect of frequency diversity on target Doppler has not been thoroughly investigated and exploited. In this paper, a three-stage search-based method is proposed for target range, angle and velocity estimation. In particular, the velocity ambiguity problem can be solved by exploiting the coupling relationship between the transmit carrier frequency and the target velocity. Furthermore, the multiple parameters estimation performance with respect to the signal-to-noise ratio (SNR) is evaluated. Numerical simulation results have demonstrated the effectiveness of the proposed method.

关键词： Couplings Simulation Estimation Search problems Numerical simulation Frequency diversity Frequency estimation Doppler radar Doppler effect signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Multi model fusion based prediction of human joint angles using sEMG and historical angles

Multi model fusion based prediction of human joint angles us...

引用

第42届中国控制会议

作者： Jiandong Han Haoping Wang Yang Tian Sino-French International Joint Laboratory of Automatic Control and Signal Processing (LaFCAS) School of AutomationNanjing University of Science and Technology

Active rehabilitation training for patients with lower limb motor dysfunction mainly depends on exoskeleton robots that can accurately and timely identify human motion intentions,which can be implemented by continues estimation of human joint *** this paper,a multi model fusion based ridge regression named as 'MMF-RR' for the prediction of human joint angles is ***,four selected basic learners are first end-to-end trained for the subsequent analysis from the data set composed of surface electromyography signals(sEMG) and historical *** the results are spliced into ridge regression with penalty terms for joint angle *** proposed MMF-RR was evaluated on publicly available dataset for 22 participants,where half of them were healthy participants,while the other half had various knee joint *** the results show that the proposed MMF-RR can significantly improve the predicting *** particular,the average mean absolute error(MAE) and average mean square error(MSE) of knee joint angle prediction of healthy participants and participants with knee joint lesions were 6.73%,2.36% and 8.97%,3.26%,respectively,which indicate that MMF-RR can provide more precise human motion intention information for lower limb motor under rehabilitation training than five comparison methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Remaining Useful Life Prediction of Bearing via a Double Attention-Based Deep Neural Network 19

Remaining Useful Life Prediction of Bearing via a Double Att...

引用

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and Computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable Computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy Computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Liu, Yongkang Pan, Donghui Zhang, Haifeng Zhong, Kai Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Mathematical Science Anhui Hefei230601 China Institutes of Physical Science and Information Technology Anhui University Anhui Hefei230601 China

ISBN: (纸本)9798350346558

Predicting the remaining useful life (RUL) of bearings is important for the secure running and reducing maintenance costs of rotating machinery. In this article, a novel feature extraction and RUL prediction framework of bearing is proposed by utilizing time-frequency representations (TFRs) and deep neural network with double attention (DA-DNN). Firstly, TFRs are employed to extract the degradation features associated with RUL prediction, which can effectively cope with the non-stationary properties of bearing vibration data. The reduced dimensional TFRs are then used as the DA-DNN model input. Afterwards, DA-DNN is developed by employing the double attention structure to extract the key degradation features more efficiently. The dual-attention structure has ability to capture the degradationrelated features from two aspects of channel attention and spatial attention, which enables the network to focus on high RUL-relevant information. Finally, the experimental results demonstrate the effectiveness of DA-DNN, which shows higher performance in terms of prediction accuracy compared to other deep learning (DL) methods. © 2022 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Model-free Based Nonsingular Fast Terminal Sliding Mode Control for Gough-Stewart platform

Model-free Based Nonsingular Fast Terminal Sliding Mode Cont...

引用

第42届中国控制会议

作者： Yunhua He Haoping Wang Yang Tian Xingyu Zhou Sino-French International Joint Laboratory of Automatic Control and Signal Processing (LaFCAS) School of AutomationNanjing University of Science and Technology

In this paper,a model-free based nonsingular fast terminal sliding mode control(MFNFTSMC) approach is presented to track the position and pose of an uncertain Gough-Stewart platform(GSP).Firstly,the kinematic and dynamic modeling of the GSP system is ***,a MFNFTSMC method is *** model uncertainty is compensated using a time-delay estimation(TDE) approach,and the error resulting from the delay estimate is then compensated using a Super-Twisting algorithm(STA).Thirdly,by integrating STA dynamics and NFTSMC dynamics,a model-free strategy based on the ultra-local model is provided to diminish the demand of acquiring the precise model of the ***,to verify the performance and effectiveness of the proposed MFNFTSMC method,the virtual prototype of Gough-Stewart platform is built in Solidworks,co-simulation is carried out with Matlab/Simulink on a Gough-Stewart platform in comparison with the NFTSMC method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Alignment for End-to-End Spoken Language Understanding Based on Momentum Contrastive Learning

Cross-Modal Alignment for End-to-End Spoken Language Underst...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Beida Zheng Mijit Ablimit Askar Hamdulla School of Computer Science and Technology Xinjiang University Urumqi China Xinjiang Key Laboratory of Signal Detection and Processing Urumqi China School of Future Technology Xinjiang University Urumqi China

The end-to-end spoken language understanding system extracts the semantic intent directly from an input speech. It effectively avoids problems such as semantic drift in traditional cascade models. However, the lack of semantically labeled speech data makes the model training process diffi-cult. Several recent multi-modal research perspectives have demonstrated that aligning speech and text embeddings based on space distance can improve the model’s performance. In this study, inspired by the work related to contrastive learning, a speech and text aligning method using momentum contrast learning is proposed, and a momentum distillation method is also used in the model to learn from imperfectly matched speech and text data. The proposed method has improved intent detection accuracy by 2.14% and 5.98% on Fluent Speech Command and SmartLights datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A fast deep-learning signal detection architecture for the short-wave band 6

A fast deep-learning signal detection architecture for the s...

引用

6th Annual International Conference on Network and Information Systems for Computers, ICNISC 2020

作者： Wang, Keren Li, Weihao National Key Laboratory of Science and Technology on Blind Signal Processing Chengdu China Information Engineering University Zhengzhou China

Wideband signal detection plays an important role in wireless communication systems. In recent years, deep learning (DL) has been introduced, and many trial efforts have been posed. In this paper, a fast deep-learning signal detection architecture is proposed for the short-wave band, which consists of the GPU-based Down Digital Converter (DDC), the DL-based signal detector, and the signal data viewer & recorder. Wideband signal data are taken directly as the input, and detected signals are automatically recorded as the output of the architecture. Experimental results suggest that our architecture is capable of detecting signals in the whole short-wave band in quasi-real-time, and specifically, with single GPU device. © 2020 Journal of Physics: Conference Series.

关键词： signal detection

来源：评论

学校读者我要写书评

暂无评论

Performer: A High-Performance Global-Local Model-Augmented with Dual Network Interaction Mechanism

引用

IEEE Transactions on Cognitive and Developmental Systems 2024年

作者： Tan, Dayu Hao, Rui Hua, Linfeng Xu, Qi Su, Yansen Zheng, Chunhou Zhong, Weimin Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Institutes of Physical Science and Information Technology Hefei230601 China East China University of Science and Technology Key Laboratory of Smart Manufacturing in Energy Chemical Process Ministry of Education Shanghai200237 China Dalian University of Technology School of Computer Science and Technology Dalian116024 China

In deep learning, Convolutional Neural Networks (CNNs) focus on local information through convolutional kernels, while transformers attend to global information using self-attention mechanisms. The union of these distinct approaches enables a more comprehensive extraction of image features. However, the feature map dimensions of CNN and Transformer differ, leading to dimension mismatch issues when combining these architectures. Additionally, the parameter size of the hybrid model integrating both architectures remains large, making it difficult to train. To further augmenting the interpretation of complex image patterns, we present Performer, a dual-network architecture that seamlessly combines CNNs and transformers, resulting in a novel and efficient representation learning model. In the Performer model, we innovate by devising a unique interaction methodology for CNN and transformer architectures to enhance the image feature extraction capabilities mutually. To counteract issue of dimensionality mismatch, we also introduce a refined transformer block, a advancement over the transformer block of ViT. To validate the effectiveness of Performer, we conduct extensive experiments on both classification and segmentation tasks. Performer achieve an accuracy of 83.37% on the ImageNet-200 dataset. For semantic segmentation, Performer excels on the CamVid and Hippocampus datasets. On CamVid, our model achieves a mean Intersection over Union (mIoU) of 63.27% and Pixel Accuracy of 92.11%, demonstrating superior performance in capturing fine details and handling complex scenes effectively. The code is available at https://***/hlfthh/ Performer. © 2016 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Spatial Undersampling SAS Imaging Algorithm Utilizes Dual Carrier Frequency Azimuth Compressed Sensing

Spatial Undersampling SAS Imaging Algorithm Utilizes Dual Ca...

引用

OCEANS

作者： Kun Ji Peng Wang Yanbo Jiao Pengfei Zhang Shiping Chen Lulu Ren Linzhe Wei Insititute of Acoustics Chinese Academy of Sciences Key Laboratory of Science and Technology on Advanced Underwater Acoustic Signal Processing Chinese Academy of Sciences The University of Chinese Academy of Sciences

ISBN: (数字)9798350362077

ISBN: (纸本)9798350362084

Restricted by factors such as sonar carrier size, carrier velocity, underwater sound velocity and sound propagation characteristics, there are certain limitations in the mapping efficiency of synthetic aperture sonar(SAS). Spatial undersampling occurs in the azimuth when the moving speed of SAS is too high, resulting in grating lobe, pseudo-targets and blurred imaging azimuths. To address this problem, this paper proposes a spatial undersampling SAS imaging algorithm based on dual carrier frequency azimuth compressed sensing, the algorithm introduces the scene sparse a priori information in azimuth, transmits dual carrier frequency signals, and improves the traditional range doppler(RD) algorithm based on the theory of compressed sensing, which achieves a better undersampling imaging. Then, the grating lobe and pseudo target caused by high-speed undersampling is further suppressed by using the property that the position of the grating lobe is related to the carrier frequency. The simulated imaging results and experiments show that when the mapping speed exceeds the theoretical limit speed of SAS, i.e., when there is serious spatial undersampling in azimuth, the proposed algorithm still achieves high-resolution imaging, effectively suppresses the grating lobe and pseudo targets caused by the undersampling, and greatly improves the mapping efficiency.

关键词： Azimuth Oceans Imaging High-resolution imaging Apertures Frequency conversion Sensors

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：