检索结果-内蒙古大学图书馆

IEEE International Conference on signal and Image processing (ICSIP)

作者： Xiaojia Chen Rihong Ye Miaohui Wang Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Institute of Artificial Intelligence and Robotics for Society and Shenzhen University (SZU) Shenzhen P.R. China

ISBN: (纸本)9781665446006

Table tennis serving (TTS) machine can effectively reduce the burden of coach and improve the training effect. However, most of the existing TTS systems are generally fixed on the table to serve the balls, and they are pre-programmed and lack of flexibility. To address above problems, we develop an orbital TTS system, which can flexibly move with the human body. Specifically, an improved face detection method is designed to track the human position by introducing the attention mechanism. Moreover, a single branch connection is adopted to reduce the running memory requirement, and a multi-threading scheme is employed to reduce the computing time. Practical experiments show that the developed TTS system has a better flexibility and a higher serving ball quality.

关键词： Training Tracking Multithreading Memory management Pose estimation Predictive models Orbits

来源：评论

学校读者我要写书评

暂无评论

Steady-state Analysis of Bipolar Transistor

Steady-state Analysis of Bipolar Transistor

引用

Progress in Electromagnetic Research Symposium (PIERS)

作者： Yeqiang Yan Xingang Ren Shuping He Xiaotao Huang Zhixiang Huang Anhui Province Key Laboratory of Target Recognition and Feature Extraction Luan China Information Materials and Intelligent Sensing Laboratory of Anhui Province Institute of Physical Science and Information Technology Anhui University Hefei China Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China Lingnan Normal University Zhanjiang China

ISBN: (纸本)9781665409889

Numerical simulation of semiconductor devices enable the quick obtain of the device physical characteristics. However, the trial productions of the semiconductor devices have the disadvantages of long cycle and high cost. Therefore, it is necessary to carry out numerical simulation investigating semiconductor devices. We propose the coupling approach and the decoupling-Gummel method to solve the semiconductor equations. The results of the two methods are compared with the commercial software. Numerical experiment indicates that the results obtained by our method are accurate. When the transistor is at a low voltage bias, the decoupling method converges faster than the coupling method. In the case of high voltage bias, the decoupling method has a slower convergence speed than the coupling method, even difficult to converge for higher voltage bias. However, the coupling method has higher memory requirements than the Gummel method. Therefore, we need to balance the advantages of the coupling method and the Gummel method when conduct the numerical simulation.

关键词： Couplings Bipolar transistors Voltage Production Numerical simulation Mathematical models Software

来源：评论

学校读者我要写书评

暂无评论

Low-resource dialogue summarization with domain-agnostic multi-source pretraining

arXiv

引用

arXiv 2021年

作者： Zou, Yicheng Zhu, Bolin Hu, Xingwu Gui, Tao Zhang, Qi Institute of Modern Languages and Linguistics Fudan University Shanghai Key Laboratory of Intelligent Information Processing Fudan University School of Computer Science Fudan UniversityShanghai China

With the rapid increase in the volume of dialogue data from daily life, there is a growing demand for dialogue summarization. Unfortunately, training a large summarization model is generally infeasible due to the inadequacy of dialogue data with annotated summaries. Most existing works for low-resource dialogue summarization directly pretrain models in other domains, e.g., the news domain, but they generally neglect the huge difference between dialogues and conventional articles. To bridge the gap between out-of-domain pretraining and in-domain fine-tuning, in this work, we propose a multi-source pretraining paradigm to better leverage the external summary data. Specifically, we exploit large-scale in-domain non-summary data to separately pretrain the dialogue encoder and the summary decoder. The combined encoder-decoder model is then pretrained on the out-of-domain summary data using adversarial critics, aiming to facilitate domain-agnostic summarization. The experimental results on two public datasets show that with only limited training data, our approach achieves competitive performance and generalizes well in different dialogue scenarios. Copyright © 2021, The Authors. All rights reserved.

关键词： signal encoding

来源：评论

学校读者我要写书评

暂无评论

An Octagonal Iterative Fractal Antenna with Notch Band and UWB Characteristics

An Octagonal Iterative Fractal Antenna with Notch Band and U...

引用

Progress in Electromagnetic Research Symposium (PIERS)

作者： Yong Cai Shuping He Xingang Ren Zhixiang Huang Anhui Province Key Laboratory of Target Recognition and Feature Extraction Luan China Key Laboratory of Electromagnetic Environmental Sensing Anhui University Hefei China Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Institute of Physical Science and Information Technology Anhui University Hefei China

ISBN: (纸本)9781665409889

In this paper, based on the rectangular iterative technique, we propose an omnidirectional UWB fractal antenna by using microstrip line as feed. The antenna takes regular octagonal shape as patch element. Meanwhile, the iterative fractal and notch technique has been adopted to optimize the UWB antenna performance. After multiple iterations of the configured octagonal patch element, the optimized UWB performance can be obtained. The simulation results reveal that the operating bandwidth of the antenna meets Federal Communications Commission (FCC) broadband standard. Moreover, in order to avoid the electromagnetic interference in the X-band identified by the IEEE 521-2002 standard, we further adopt notch techniques and add the U-shaped gap to the microstrip line to achieve electromagnetic shielding. The impedance matching has been achieved for the antenna by imposing the slot on the ground. After optimizing the slot structure, the reflection of the antenna has reduced in the whole operating frequency band. The overall size of the ultra-wideband fractal antenna was designed to $25 \times 35 mm^{2}$ and was composed of FR-4 material with the relative dielectric constant $\varepsilon_{r} = 4.4$ and loss tangent angle $\tan \theta = 0.02$. After optimization, the antenna has good impedance matching and meets the UWB antenna omnidirectional standard. In 3.1–15.4GHz (excluding X-band), and the reflection coefficient S 11 is lower than -10 dB, voltage standing wave ratio (VSWR) is less than 2, maximum gain reaches 6dB. The results indicated that our proposed fractal antenna is promising for UWB antenna applications.

关键词： Slot antennas Impedance matching Voltage FCC Ultra wideband antennas Fractals Microstrip

来源：评论

学校读者我要写书评

暂无评论

Multi-user Dual-function radar-communications System Based on Circulating Code Array

Multi-user Dual-function Radar-communications System Based o...

引用

IEEE International Conference on radar

作者： Qiuyue Zhang Cunqian Feng Yabin Gu Linrang Zhang Yu Zhou Zhanye Chen Air and Missile Defense College Air Force Engineering University Xi'an China Shannxi Huanghe Group Company Ltd. Xi'an China National Laboratory of Radar Signal Processing Xidian University Xi'an China Chongqing Key Laboratory of Space Information Network and Intelligent Information Fusion Chongqing University Chongqing China

ISBN: (纸本)9781665468893

To ease the shortage of the spectrum resource, a dual-function radar-communications (DFRC) system based on circulating code array is proposed in this paper. The relationship between the spectrum of the synthesized signal and the spatial angle is firstly analyzed. By utilizing this relationship, different frequency bands can be allocated to multiple different communication users located in different spatial directions. radar and communication receiving processing procedures are analyzed secondly. At the communication receiver, the relationship between the spectrum of the transmitted basic waveform and the spectrum of the synthesized waveform of circulating code array provides the possibility to demodulate the communication symbols from the received signal. The proposed DFRC system requires only one transmitted basic waveform to implement multi-user communication transmission and radar detection simultaneously. It is verified that the designed method can use different modulation schemes to simultaneously transmit information to multiple communication users located in different directions without sacrificing radar detection performance. Simulation results are presented to validate the performance of the designed DFRC system.

关键词： Codes Array signal processing Simulation radar detection Modulation radar Receivers

来源：评论

学校读者我要写书评

暂无评论

A novel non-stationary clutter compensation algorithm for ariborne radar with a yaw angle 5

A novel non-stationary clutter compensation algorithm for ar...

引用

IET International radar Conference 2020, IET IRC 2020

作者： Chen, Jiangyuan Huang, Penghui Liu, Xingzhao Liao, Guisheng Huo, Lihuan School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China National Lab of Radar Signal Processing Xidian University Xi'an China Hebei Key Laboratory of Electromagnetic Spectrum Cognition and Control The 54th Research Institute of CETC Shijiazhuang China

ISBN: (纸本)9781839535635

The yaw angle between the antenna panel and the flight velocity direction of an airplane causes the spatial steering of ground clutter changing with the range units, that is, the main-lobe clutter is non-stationary along range dimension, which will cause the performance deterioration of clutter suppression, degrading the ground slow-moving target detection ability. To solve this issue, a novel spatial-temporal compensation algorithm is proposed in this paper. In the proposed algorithm, a range compressed clutter signal is firstly transformed into Doppler domain. And then, a spatial-temporal filtering function is established using the prior radar system information to compensate the range-dependent spatial steering of the clutter signal. After eliminating the non-stationary of the observed clutter scene, the subsequent clutter rejection can be well accomplished by applying the multi-channel processing technique, improving the moving target detection performance. Simulation results are provided to validate the effectiveness of the proposed algorithm. © 2020 Institution of Engineering and Technology. All rights reserved.

关键词： Echo suppression

来源：评论

学校读者我要写书评

暂无评论

DINF: Dynamic Instance Noise Filter for Occluded Pedestrian Detection

arXiv

引用

arXiv 2023年

作者： Li, Xiang He, Miao Luo, Haibo Xiao, Jiajie Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Liaoning Shenyang110016 China Shenyang Institute of Automation Chinese Academy of Sciences Liaoning Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Liaoning Shenyang110169 China University of Chinese Academy of Sciences Beijing100049 China *** Group Shanghai200335 China

Occlusion issue is the biggest challenge in pedestrian detection. RCNN-based detectors extract instance features by cropping rectangle regions of interest in the feature maps. However, the visible pixels of the occluded objects are limited, making the rectangle instance feature mixed with a lot of instance-irrelevant noise information. Besides, by counting the number of instances with different degrees of overlap of CrowdHuman dataset, we find that the number of severely overlapping objects and slightly overlapping objects are unbalanced, which may exacerbate the challenges posed by occlusion *** to the noise issue, from the perspective of denoising, an iterable dynamic instance noise filter (DINF) is proposed for the RCNN-based pedestrian detectors to improve the signal-noise ratio of the instance feature. Simulating the wavelet denoising process, we use the instance feature vector to generate dynamic convolutional kernels to transform the RoIs features to a domain in which the near-zero values represent the noise information. Then, soft thresholding with channel-wise adaptive thresholds is applied to convert the near-zero values to zero to filter out noise information. For the imbalance issue, we propose an IoU-Focal factor (IFF) to modulate the contributions of the well-regressed boxes and the bad-regressed boxes to the loss in the training process, paying more attention to the minority severely overlapping objects. Extensive experiments conducted on CrowdHuman and CityPersons demonstrate that our methods can help RCNN-based pedestrian detectors achieve state-of-the-art performance. Copyright © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Estimation of Motor Imagination Based on Consumer-Grade EEG Device 3rd

Estimation of Motor Imagination Based on Consumer-Grade EEG ...

引用

3rd International Conference on Machine Learning for Cyber Security, ML4CS 2020

作者： Luo, Zhenzhen Hu, Zhongyi Li, Zuoyong College of Computer and Artificial Intelligence Wenzhou University Wenzhou China Intelligent Information Systems Institute Wenzhou University Wenzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou China

ISBN: (纸本)9783030624590

Nowadays, classifying electroencephalogram (EEG) signals based motor imagery tasks is extensively used to control brain-computer interface applications, as a communication bridge between humans and computers. In this paper, we propose signal-to-image transformation and feature extraction methods for the classification of motor imagery. Specifically, a continuous wavelet transform is applied to decompose EEG signals into five rhythms and generate time-frequency images. Then, a gray-level co-occurrence matrix is used to extract global texture features on time-frequency images. Finally, the SVM classification model is optimized by using a grid search algorithm to select optimal parameter pairs. To confirm the validity of the proposed methods, we experimented on self-collected data, which is obtained using a consumer-grade EEG device. The experimental result showed that this proposed method can achieve an acceptable classification accuracy of 90% for a two-class problem (left/right-hand motor imagery). © 2020, Springer Nature Switzerland AG.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Terahertz Image Super-Resolution Reconstruction Based on Complex Deconvolution Algorithm with Different Criteria 6

Terahertz Image Super-Resolution Reconstruction Based on Com...

引用

6th International Conference on information Systems Engineering, ICISE 2021

作者： Wang, Ying Qi, Feng Wang, Jinkuan School of Communication Science and Engineering Northeastern University Shenyang China Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Shenyang China Shenyang Institute of Automation Chinese Academy of Science Shenyang China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang China University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781450385220

Super-Resolution (SR) is one of the most fundamental issues in THz imaging processing. Deconvolution is widely used in THz imaging SR problems. Heavy-tailed distribution has good performance in deconvolution for its capability to preserve edges. By making use of the wave nature of THz waves, complex deconvolution is employed for solving THz images. A complex deconvolution algorithm based on criteria is proposed in this paper. And three criteria are discussed to get the most optimal result. Compared with the traditional methods, which are set the index as a fixed value, our method is more flexible for obtaining clear edges. The measured PSF is used to analyze the THz image by a complex image blurred model. Experiments illustrate the efficiency and accuracy of the proposed method. All three criteria can solve the LR problem well. Relative to Peak signal to Noise Ratio (PSNR) and information entropy, the SR result of Structural Similarity Index Measure (SSIM) is better visual. Thus, we prefer SSIM as the criterion in our work. © 2021 ACM.

关键词： Deconvolution

来源：评论

学校读者我要写书评

暂无评论

Student Behavior Recognition in Remote Video Classrooms 16th

Student Behavior Recognition in Remote Video Classrooms

引用

16th International Conference on intelligent information Hiding and Multimedia signal processing, IIH-MSP 2020 in conjunction with the 13th International Conference on Frontiers of information Technology, Applications and Tools, FITAT 2020

作者： Wang, Rongrong Zhang, Guanglong Zhang, Fuquan Dong, Zhiwei Qi, Mingzhu Computer School Beijing Institute of Technology Beijing100081 China Computer School Jilin University Changchun130012 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China Botou Vocational College Botou062150 China Shandong Dezhou Experimental Middle School Dezhou253000 China

ISBN: (纸本)9789813367562

With the development of high-definition camera equipment and Internet communication technology, remote video teaching methods have emerged. This new type of teaching method has led to changes in traditional classrooms. On the one hand, remote video teaching has broken the constraints of time and space and effectively improved the inequality of educational resources. On the other hand, in actual video courses, teachers cannot effectively monitor students’ learning actions and states, so they cannot communicate well. In order to solve this problem, this paper proposes an algorithm based on deep learning to monitor the behaviors of students in real time during the learning process, understand the learning status of students, and strengthen the real-time communication between teachers and students. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2021.

关键词： Students

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：