检索结果-内蒙古大学图书馆

12th International Conference on Computer engineering and Networks, CENet 2022

作者： Tong, Ziyu Deng, Xing Shao, Haijian Wang, Xia School of Computer Jiangsu University of Science and Technology Zhenjiang212003 China School of Automation Key Laboratory of Measurement and Control for CSE Ministry of Education Southeast University Nanjing Jiangsu210096 China School of Information Science and Technology Nantong University Nantong Jiangsu226019 China Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore

ISBN: (纸本)9789811969003

Deep learning algorithms, such as CNN, have been widely used on a variety of computer vision problems due to their powerful capacity to extract nonlinear features for medical picture analysis. However, due to the decreased identification rate for medical images, CNNs continue to fail to offer an interpretable depiction of the hidden-layers’ features. Furthermore, the enormous amount of redundant parameters from the convolutional to fully connected layers will surely add to the computational complexity. This work provides a set of fast deep learning architectures for visualizing and analyzing hidden-layer properties in medical images. The clustered feature map is used to simplify the model parameters and minimize redundancy parameters in order to meet the goal of a streamlined trade-off between model performance and architecture. The testing results on the medial images reveal that 41% of redundant channels may be removed while 100% of performance can be preserved. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Design of magnetic shielding structures for non-contact measurement of current in triangularly arranged cables

Design of magnetic shielding structures for non-contact meas...

引用

Electrical engineering (CIYCEE), IEEE China International Youth Conference on

作者： Xingyu Zhou Dongsheng Cai Zhengyuan Zhang Peng Wang Arsalan Habib Khawaja Qi Huang College of Nuclear Technology and Automation Engineering Chengdu University of Technology China Sichuan Provincial Key Lab of Power System Wide-Area Measurement and Control School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Chengdu China School of Information Engineering Southwest University of Science and Technology Mianyang China

The triangular arrangement of cables has the advantages of good magnetic field balance and compact structure, making it a commonly used arrangement in tunnel power cable lines. Accurate measurement of its current helps to make accurate judgment of the line operation status. However, the tunnel transmission method involves a complex line arrangement in a small space. Therefore, non-contact wide-range current measurement based on magnetic sensors is a better solution. In the face of uncertain magnetic interference in transmission tunnels, the use of magnetic shielding can suppress its effect on magnetic sensors. In this paper, an M-shaped magnetic shield structure is proposed for current measurement in a triangular arrangement with strong magnetic interference at random locations. Then, the thickness, position, axial length, gap width and location of the sensing areas of the structure were investigated. The effectiveness of the structure was verified by finite element analysis methods for measured currents of 200 to 2000 A. The structure was also validated by the finite element analysis method. The mean shielding uncertainty (MSU) of the shielding structure is verified to be 0.19% under the uncertainty of strong magnetic interference for a measured current of 2000 A. The M-shaped shielding structure is more resistant to interference than the C-shaped shielding structure and fits better into the triangular arrangement of the cable geometry.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on a micro-expression recognition algorithm based on 3D-CNN 3

Research on a micro-expression recognition algorithm based o...

引用

3rd International Conference on Intelligent control, measurement and Signal Processing and Intelligent Oil Field, ICMSP 2021

作者： Jiao, Yao Jing, Mingli Hu, Yuliang Sun, Kun Xi'An Shiyou University School of Electrical Engineering Xi'an China Shaanxi Provincial Key Lab of Oil and Gas Well Measurement and Control Technology Xi’an China

ISBN: (纸本)9781665437158

Micro expression is a kind of natural human expression, which lasts for a short time and is not easy to detect. Due to the subtle spatiotemporal variation of micro-expressions, the recognition of micro-expressions is still a big challenge. Although many scholars have made some attempts in the recognition of micro-expressions, the accuracy of the recognition problem is still not ideal. In order to take advantage of 3D convolution, we propose an improved model of micro expression recognition based on 3D convolution neural network (3D-CNN). In the sequential model based on the deep learning framework of Keras, 3D convolution, pooling, batch normalization and other layers are added to construct the sequence. The recognition rate of this model on SMIC database can reach 76.92%, and it also shows good recognition rate on other databases. This method is superior to or partially superior to the classical methods and the current mainstream methods. © 2021 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Images super-resolution using improved generative adversarial networks 3

Images super-resolution using improved generative adversaria...

引用

3rd International Conference on Intelligent control, measurement and Signal Processing and Intelligent Oil Field, ICMSP 2021

作者： Hu, Yuliang Jing, Mingli Jiao, Yao Sun, Kun Xi'An Shiyou University School of Electrical Engineering Xi'an China Shaanxi Provincial Key Lab of Oil and Gas Well Measurement and Control Technology Xi’an China

ISBN: (纸本)9781665437158

Image super-resolution (ISR) is an important image processing technology to improve image resolution in computer vision tasks. The purpose of this paper is to study the super-resolution reconstruction of single image based on the depth learning method. Aiming at the problem that the existing pixel loss-based super-resolution image reconstruction algorithms have poor reconstruction effect on high-frequency details, such as textures, a lighter algorithm is proposed on the basis of the existing deep learning method (SRGAN). Firstly, the feedback structure is applied in the generator to process the feedback information and enhance the high frequency information of the image. Secondly, a general residual feature aggregation framework (RFA), is applied to make full use of the residual information of each layer to improve the quality of the SR image. Finally, the solution space of the function is further reduced and the image quality is improved by using a new loss function. The algorithms are implemented on pytorch framework. The experimental results on VOC2012 data sets show that, compared with the original SRGAN algorithm, the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) of the proposed algorithm on the benchmark data set Set5 are improved by 0.83dB and 0.028, respectively, on Set14, the PSNR and SSIM of the proposed algorithm are improved by 0.56dB and 0.009, on Urban100, the PSNR and SSIM of the proposed algorithm are improved by 0.51dB and 0.031, on BSD100, the PSNR and SSIM of the proposed algorithm are improved by 0.33dB and 0.014, and compared with other improved algorithms, the effect of this algorithm is also better than other algorithms. © 2021 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Hough Circle Detection Method for Shaking Instruments in Drilling Field 4

Hough Circle Detection Method for Shaking Instruments in Dri...

引用

4th International Conference on Computer Network, Electronic and Automation, ICCNEA 2021

作者： Ma, Bo Liu, Hailong Zhang, Qizhi School Of Electronic Engineering Xi'an Shiyou University Xi’an China Shaanxi Provincial Key Lab Of Oil And Gas Well Measurement And Control Technology Xi’an China

ISBN: (纸本)9781665444866

At present, the real-time performance of data acquisition has become the key to the development of intelligent drilling. Due to the limitation of stay wire and power supply, the stability of data transmission is not high. In view of the data cannot be collected effectively, machine vision is introduced into the drilling field to automatically judge and read the instruments, there are often fuzzy images of vibration instability in the acquired instrument images. By analyzing the reasons and rules of instrument jitter, a new scheme is proposed. The dithering image is blurred by Wiener filter, and the template matching is made for the initial frame picture. The disc and the center of the circle are obtained from the matched stable image by improved Hough transform, and then they are drawn on the deblurring image. The experiment shows that the error of the circle obtained in this scheme is more stable than the traditional algorithm. © 2021 IEEE.

关键词： Hough transforms

来源：评论

学校读者我要写书评

暂无评论

Research of Boost Converter Sliding Mode control Method Based on Exponential Reaching Law 4

Research of Boost Converter Sliding Mode Control Method Base...

引用

4th International Conference on Computer Network, Electronic and Automation, ICCNEA 2021

作者： Dang, Chunyong Zhang, Qizhi Xi'an Shiyou University School Of Electronic Engineering Xi’an China Shaanxi Provincial Key Lab Of Oil And Gas Well Measurement And Control Technology Xi’an China

ISBN: (纸本)9781665444866

Due to the nonlinear structure of boost converter, the traditional PI controller can ensure the boost converter to work stably near the rated point, and achieve good dynamic and steady-state performance. When the working state of boost converter deviates greatly from the rated point, its stability cannot be guaranteed. Therefore, in order to solve the problem that the dynamic performance and stability of boost converter are insufficient when it deviates from the rated working state, the mathematical model of third-order sliding mode controller is established by adding voltage dynamic error state variable on the basis of second-order sliding mode boost converter. The exponential reaching law is applied to the third-order sliding mode controller, which can effectively reduce the overshoot in the start-up phase;when the input voltage changes suddenly, the load has strong robustness. The paper built the Simulink module, and through the Matlab/Simulink, the effectiveness of the algorithm is verified. © 2021 IEEE.

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

IR Net: information restriction and information recovery for accurate binary neural networks

引用

Neural Computing and Applications 2023年第19期35卷 14449-14464页

作者： Xue, Ping Lu, Yang Chang, Jingfei Wei, Xing Wei, Zhen School of Computer Science and Information Engineering Hefei University of Technology Hefei China Anhui Mine IOT and Security Monitoring Technology Key Laboratory Hefei China Engineering Research Center of Safety Critical Industrial Measurement and Control Technology Ministry of Education Hefei University of Technology Hefei China Intelligent Manufacturing Institute of Hefei University of Technology Hefei China

Weight and activation binarization can efficiently compress deep neural networks and accelerate model inference, but they cause severe accuracy degradation. Existing optimization methods for binary neural networks (BNNs) focus on fitting full-precision networks to reduce quantization errors and suffer from a tradeoff between accuracy and efficiency. In contrast, considering information loss and the mismatch between model capacity and input information quantity caused by network binarization, we propose Information Restriction and Information Recovery Network (IR $$^2$$ Net) to stimulate the potential of BNNs and achieve improved network accuracy by restricting the input information and recovering feature information. The proposed approach includes (1) information restriction, which evaluates the feature information extracted from the input by a BNN, discards some of the information it cannot focus on, and reduces the amount of the input information to match the model capacity; and (2) information recovery: due to the information loss incurred during forward propagation, the extracted feature information of the network is not sufficient for supporting accurate classification. Shallow feature maps with richer information are selected, and these feature maps are fused with the final feature maps to recover the extracted feature information and further enhance the model capacity to match the amount of input information. In addition, the computational cost is reduced by streamlining the information recovery method to strike a better tradeoff between accuracy and efficiency. Experimental results demonstrate that our approach still achieves comparable accuracy even with a $$\sim$$ 10x floating-point operations (FLOPs) reduction for ResNet-18. The models and code are available at https://***/pingxue-hfut/IR2Net .

关键词：

来源：评论

学校读者我要写书评

暂无评论

Parameters Estimation of Cole-Cole Bio-Impedance Model with a Minimum Number of Frequencies

Parameters Estimation of Cole-Cole Bio-Impedance Model with ...

引用

IEEE Instrumentation and measurement technology Conference

作者： Nour Ammar Cherif Ouni Ahmed Yahia Kallel Ahmed Fakhfakh Nabil Derbel Olfa Kanoun Measurement and Sensor Technology Faculty of Electrical Engineering and Information Technology Chemnitz University of Technology Chemnitz Germany Control and Energy Management Laboratory National Engineering School of Sfax University of Sfax Sfax Tunisia Laboratory of Signals Systems Artificial Intelligence and Networks Digital Research Centre of Sfax National School of Electronics and Telecommunications of Sfax Sfax Tunisia

ISBN: (数字)9798350380903

ISBN: (纸本)9798350380910

Wearable bioimpedance devices are becoming increasingly popular due to their portability and non-invasiveness. However, these devices consume a lot of energy during measurement time, limiting the operating time. The number of frequencies must be reduced to reduce the measurement time and energy. In this paper, we propose using three frequencies and investigating their optimal values for accurate measurement. The remaining two frequencies at high frequencies are chosen by eliminating the high frequencies that have a high deviation. Lastly, a third frequency is optimally chosen based on a combination of the frequencies whose non-linear least-squares fitting parameters results lead to the smallest deviations. First, a simulation is used to validate the results, where a Cole-Cole model is used with different noise levels. Two high frequencies in combination with a frequency close to the characteristic frequency yielded the best results, regardless of the presence of noise. Second, the measurement was experimentally validated in STM32 with a physical Cole-Cole model, which confirmed the results, where 7.94 kHz, close to the characteristic frequency, had mean deviations of 2.43% in $R_{l}$ , 3.7% in $R_{E}$ , and 2.55% in C. Using three points reduces the measurement time from 9.7 ms to 0.41 ms.

关键词： Time-frequency analysis Accuracy Biological system modeling Fitting Energy measurement Time measurement Frequency estimation

来源：评论

学校读者我要写书评

暂无评论

Task Offloading and Primary Node Selection in Blockchain, Digital Twin, and MEC Enabled Internet of Vehicles

Task Offloading and Primary Node Selection in Blockchain, Di...

引用

IEEE Conference on Vehicular technology (VTC)

作者： Jianbo Du Huifang Fang Shulei Li Pengfei Du Ziwen Kong Jiawen Kang Dusit Niyato Shaanxi Key Laboratory of Information Communication Network and Security School of Communications and Information Engineering Xi’an University of Posts and Telecommunications Xi’an China School of Communications Engineering Xidian University Xi’an China Tianyuan Ruixin Communication Technology Co. LTD. Xi’an China Engineering Research Center of Intelligent Airground Integrated Vehicle and Traffic Control Ministry of Education Xihua University Chengdu China School of Automation Guangdong University of Technology China School of Computer Science and Engineering Nanyang Technological University Singapore

ISBN: (数字)9798331517786

ISBN: (纸本)9798331517793

In this paper, we investigate the safe task offloading and primary node selection in blockchain, digital twin (DT) and Multi-access Edge Computing (MEC) enabled Internet of Vehicles (IoV). Edge servers centers provide computing power for task processing for Mobile Vehicles (MVs), while blockchain can provide security guarantees for MVs during task offloading. Based on the above system, we propose a joint optimization scheme for vehicle task offloading decision and the Practical Byzantine Fault Tolerance (PBFT) consensus process. Due to the large number of optimization variables and constraints, the problem becomes more complex. Traditional convex optimization and dynamic programming methods are difficult to effectively solve this problem. To address this issue, we propose a deep reinforcement learning based algorithm that utilizes Proximal Policy Optimization (PPO). The experimental results show that the algorithm proposed in this paper outperforms the benchmark algorithm in terms of convergence and other aspects.

关键词： Fault tolerance Vehicular and wireless technologies Heuristic algorithms Simulation Fault tolerant systems Blockchains Digital twins Servers Optimization Internet of Vehicles

来源：评论

学校读者我要写书评

暂无评论

AI-aided power electronic converters automatic online real-time efficiency optimization method

引用

Fundamental Research 2023年第3期5卷 1111-1116页

作者： Tang, Yuanhong Cao, Di Xiao, Jian Jiang, Chenying Huang, Qi Li, Yunwei Chen, Zhe Blaabjerg, Frede Hu, Weihao Power System Wide-area Measurement and Control Sichuan Provincial Key Laboratory School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Chengdu 611731 China MORNSUN Guangzhou Science & Technology Co. Ltd. Guangzhou 510663 China School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu 611731 China Yangtze Delta Region Institute (Quzhou) University of Electronic Science and Technology of China Quzhou 324000 China Department of Chengdu State Grid Corporation of China Chengdu 610599 China Southwest University of Science and Technology Mianyang 621010 China Department of Electrical and Computer Engineering University of Alberta Edmonton AB T6G 2V4 Canada Department of Energy Technology Aalborg University Aalborg 9220 Denmark

Energy losses during the conversion and supply of electric power are considered a significant issue and cannot be estimated. Improvement in the efficiency of energy conversion systems is highly restricted because of their internal nonlinearity and complexity. Thus, inspired by the successful utilization of robotic chemists, we demonstrate a pioneering concept of artificial intelligence (AI)-aided automatic online real-time optimization of a power electronics converter using a dual active bridge (DAB) converter as an example. An optimal modulation strategy was obtained through repeated automatic exploration experiments on a practical DAB converter platform. Specifically, the DAB experimental platform operated autonomously around the clock for approximately 71 h. It performed 120,000 consecutive experiments (12,000 episodes) within a six-variable experimental space driven by a deep deterministic policy gradient (DDPG) algorithm. The proposed AI-aided automatic online real-time optimization method achieved significantly improved efficiency of power conversion and supply. Consequently, zero carbon emissions may be obtained in the future. © 2023

关键词： Artificial intelligence Automatic online real-time exploration DC-DC converter Dual active bridge converter Energy conversion system Power electronics

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：