检索结果-内蒙古大学图书馆

1st International Artificial Intelligence Conference, IAIC 2023

作者： Han, Mengjie Cai, Daomeng Huo, Zhilin Shen, Zhao Tang, Lianghu Yang, Shan Wang, Cong School of Marxism University of Electronic Science and Technology of China Chengdu China University of Electronic Science and Technology of China Chengdu China School of Mechanical Engineering and Automation Beihang University Beijing China CSCC System Engineering Research Institute Beijing China The Intelligent Policing Key Laboratory of Sichuan Province Sichuan Police College Luzhou China Department of Chemistry Physics and Atmospheric Sciences Jackson State University JacksonMS United States

ISBN: (纸本)9789819712762

AI-assisted personal educational career planning holds immense promise, especially with artificial neural network algorithms demonstrating significant potential in predicting graduate admission probabilities for specific schools. However, issues like graduate admission probability prediction are typical instances of small-sample learning problems. Overcoming neural network overfitting in small-sample learning is a major challenge. To address this, we first introduce a method that cyclically runs shallow neural networks to avoid the traditional use of a high number of epochs called Cyclic-LightNet(CLN). Secondly, in previous research, a validation set is typically employed to promptly detect overfitting. However, this approach further depletes the actual training data in the dataset. Consequently, we employ a dynamic training method during the training process called Dynamic Training Set Augmentation(DTSA), supplementing the training set with the validation set. This method effectively mitigates the risk of overfitting. Finally, we put CLN and DTSA into practice on publicly available small-sample datasets, achieving precise predictions of graduate admission probabilities. Experimental results demonstrate a significant improvement in prediction accuracy and effective resistance against overfitting risk. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of High-precision Frame-type Optomechanical Gyroscope

Design and Analysis of High-precision Frame-type Optomechani...

引用

Progress in Electromagnetic Research Symposium (PIERS)

作者： Chengwei Xian Pengju Kuang Zihan Huang Senyu Zhang Zhe Li Guangjun Wen Yongjun Huang Sichuan Provincial Engineering Research Center of Communication Technology for Intelligent IoT School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China School of Electronic Engineering Chengdu Technological University Chengdu China School of Automation Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798350375909

ISBN: (纸本)9798350375916

In this paper, a new structure of high precision frame-type optomechanical gyroscope is proposed. Based on the basic theory of photonic crystal cavity optomechanical system, the working mechanism of the new high precision micro gyroscope is analyzed. Through the simulation optimization and numerical calculation of the mechanical structure and optical structure of the gyroscope, the theoretical measurement sensitivity of angular velocity is 261.9mV/(°/s), and the rate noise density is 0.011(°/s)/Hz 1/2 . Based on the micro-nano fabrication process, the sample of the cavity optomechanical gyroscope chip was fabricated on SOI, and the preliminary test of the gyroscope chip was carried out on the vacuum test platform. With the same magnitude of inertia mass, the precision of this new micro gyroscope is obviously better than that of the traditional microelectromechanical system (MEMS) gyroscope, which provides a new path for realizing a high-precision, easy-to-integrate-on-chip, and strongly anti-electromagnetic interference gyroscope, and has great potential application value in high precision inertial navigation, micro vibration detection and other technical fields.

关键词： Vibrations Sensitivity Optical device fabrication Noise Photonic crystals Optical variables measurement Adaptive optics

来源：评论

学校读者我要写书评

暂无评论

Coverage control for mobile sensor networks with unknown terrain roughness and nonuniform time-varying communication delays

引用

Science China(Information Sciences) 2023年第12期66卷 80-93页

作者： Peng WANG Cheng SONG Lu LIU Department of Biomedical Engineering City University of Hong Kong School of Automation Nanjing University of Science and Technology City University of Hong Kong Chengdu Research Institute

This paper investigates the coverage control problem on a circle with unknown terrain roughness and nonuniform time-varying communication delays. Adaptive coverage control laws are proposed for mobile sensors to collaboratively estimate the unknown roughness function using the basis function approximation approach. Moreover, contrary to existing studies, nonuniform time-varying communication delays are considered in this paper. Under the proposed adaptive coverage control laws, the sensor network can be driven to its optimal configuration minimizing the coverage cost function in the presence of nonuniform communication delays, and each sensor can learn the true roughness function. Finally, a simulation example is provided to show the effectiveness of the proposed control laws.

关键词： multi-agent systems cooperative control adaptive control cost function time-varying communication delays

来源：评论

学校读者我要写书评

暂无评论

A Chip-scale Magnetic Field Sensor Based on Frequency Readout Cavity Optomechanical System

A Chip-scale Magnetic Field Sensor Based on Frequency Readou...

引用

Progress in Electromagnetic Research Symposium (PIERS)

作者： Zhe Li Chengwei Xian Pengju Kuang Jinglong Xiong Zihan Huang Senyu Zhang Guangjun Wen Kai Chen Yongjun Huang School of Automation Engineering University of Electronic Science and Technology of China Chengdu China School of Information and Communication Engineering Sichuan Provincial Engineering Research Center of Communication Technology for Intelligent IoT University of Electronic Science and Technology of China Chengdu China School of Electronic Engineering Chengdu Technological University Chengdu China

ISBN: (数字)9798350375909

ISBN: (纸本)9798350375916

In this paper, the working principle of cavity optomechanical system is analyzed, and a new chip-scale magnetic field sensor based on frequency readout cavity optomechanical system is proposed. The relationship between the magnetic field and displacement of the mechanical part of the new chip-scale magnetic field sensor is verified, the structure and parameters of the new chip-scale magnetic field sensor are simulated and designed, the optical characteristics of two-dimensional photonic crystal microcavity are simulated and analyzed, and the mechanical resonant frequency of the cavity affected by the displacement and the input laser wavelength and intensity is demonstrated. Then, the whole magnetic field sensor is simulated and analyzed. The results show that when the input laser intensity is 199µW, the sensitivity is 7.9Hz/µT. The new chip-scale magnetic field sensor simulated in this paper has important application value in the fields of navigation, positioning, magnetic imaging, medical imaging and environmental monitoring.

关键词： Biomedical optical imaging Sensitivity Photonic crystals Optical imaging Microcavities Optical coupling Mathematical models

来源：评论

学校读者我要写书评

暂无评论

A Survey of Carbon Emission Forecasting Methods Based on Neural Networks

A Survey of Carbon Emission Forecasting Methods Based on Neu...

引用

IEEE Asia Power and Energy engineering Conference (APEEC)

作者： Wei Liu Dongsheng Cai Joseph Nkou Nkou Qi Huang School of Nuclear Technology and Automation Chengdu University of Technology Chengdu China School of Information Engineering Southwest University of Science and Technology Mianyang China

The emission of a large amount of carbon dioxide has led to the greenhouse effect. With further research into the hazards of the greenhouse effect, the world’s major economies have started implementing energy-saving and emission-reduction plans. Predicting carbon emissions is important for the formulation of effective energy-saving and emission-reduction policies. This paper mainly introduces methods for predicting carbon emissions by using BP neural networks, recurrent neural networks, and a combination of traditional forecasting models with neural networks. Firstly, the characteristics of different neural networks are compared for carbon emission prediction. Secondly, the LSTM network is used for carbon emission prediction, and the evaluation results show the effect of the LSTM network. Finally, conclusion is drawn that BP and recurrent neural network are not ideal for long sequences. Joseph Junior NKOU NKOU

关键词： Solid modeling Recurrent neural networks Greenhouse effect Biological system modeling Neural networks Carbon dioxide Predictive models

来源：评论

学校读者我要写书评

暂无评论

Construction of an Artificial Intelligence-Powered Practical Training Platform for Humanoid Robot-Assisted Design in the Context of Discipline-Specific Competitions

Construction of an Artificial Intelligence-Powered Practical...

引用

Information Science and Education (ICISE-IE), International Conference on

作者： Yuanyuan Zhang Xin Zhang Huoming Shen School of Mechanical and Electrical Engineering University Of Electronic Science And Technology Of China Chengdu China School of Automation Chendu University of Information Technology

ISBN: (数字)9798331506766

ISBN: (纸本)9798331506773

As a quintessential representative of physical general artificial intelligence systems, humanoid robots are a crucial manifestation of artificial intelligence in physical space and serve as key equipment. This paper, grounded in high-level academic competitions, focuses on the field of AI-enabled humanoid robot-assisted design. It aims to develop a virtual simulation engineering practice platform, establishing a new paradigm for talent development that is intelligent, efficient, and capable of sustainable iterative growth. This approach fosters a positive cycle between teaching, competition, and scientific research, thereby injecting new vitality into the reform and innovation of higher education.

关键词： Training Technological innovation Buildings Humanoid robots Entrepreneurship Market research Software Artificial intelligence Mechanical engineering Optimization

来源：评论

学校读者我要写书评

暂无评论

Damage quantitative assessment of spacecraft in a large-size inspection

引用

Frontiers of Information technology & Electronic engineering 2022年第4期23卷 542-554页

作者： Kuo ZHANG Jianliang HUO Shengzhe WANG Xiao ZHANG Yiting FENG School of Automation Engineering University of Electronic Science and Technology of ChinaChengdu611731China Norla Institute of Technical Physics Chengdu610041China

To ensure the safety and reliability of spacecraft during multiple space missions,it is necessary to conduct in-situ nondestructive detection of the spacecraft to judge the damage caused by the hypervelocity impact of micrometeoroids and orbital debris(MMOD).In this paper,we propose an innovative quantitative assessment method based on damage reconstructed image mosaic ***,a Gaussian mixture model clustering algorithm is applied to extract images that highlight damage ***,a mosaicking scheme based on the ORB feature extraction algorithm and an improved M-estimator SAmple Consensus(MSAC)algorithm with an adaptive threshold selection method is proposed which can create large-scale mosaicked images for damage ***,to create the mosaicked images,the damage characteristic regions are segmented and *** location of the damage area is determined and the degree of damage is judged by calculating the centroid position and the perimeter quantitative *** efficiency and applicability of the proposed method are verified by the experimental results.

关键词： Hypervelocity impact Damage information extraction Image mosaicking Damage localization Quantitative assessment

来源：评论

学校读者我要写书评

暂无评论

Fixed-Time Fault-Tolerant Control of Robotic Manipulators with Actuator Faults Based on Fixed-Time Extended State Observer

Fixed-Time Fault-Tolerant Control of Robotic Manipulators wi...

引用

IEEE Conference on Decision and Control

作者： Xing Ren Jiange Kou Yuanchao Cao Qing Guo Zhenlei Chen Yan Shi Tieshan Li School of Automation Engineering University of Electronic Science and Technology of China Chengdu China School of Automation Science and Electrical Engineering Beihang University (BUAA) Beijing China School of Aeronautics and Astronautics University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798350316339

ISBN: (纸本)9798350316346

This paper proposes a fixed-time fault-tolerant controller for n-DOF robotic manipulators with actuator partial loss of effectiveness (LOE) faults, external disturbances, and unknown nonlinearities. A novel fixed-time extended state observer (FxTESO) is designed to estimate joint velocities and lumped uncertainty, and the estimation error can theoretically be arbitrarily small by increasing the bandwidth. An adaptive law is designed to estimate an upper bound related to FxTESO error, which can enhance the controller robustness. The proposed controller can guarantee practical fixed-time stability of the manipulator, and require no velocity measurement and prior information about lumped uncertainty. The comparative experiments with the other state-of-the-art controllers on a 4DOF manipulator under different external disturbances and actuator faults verify the superiority of the proposed controller.

关键词： Actuators Fault tolerance Uncertainty Upper bound Fault tolerant systems Noise Manipulators Robustness Velocity measurement State estimation

来源：评论

学校读者我要写书评

暂无评论

Seismic landslide detection based on Transformer and RNN algorithm

Seismic landslide detection based on Transformer and RNN alg...

引用

Sensors, Electronics and Computer engineering (ICSECE), IEEE International Conference on

作者： Qingru Yang Xin Zhang Yuxuan Xie Shuhong Huang Junfeng Kong Xiaoyu Zhang College of Computer Science and Cyber Security (Oxford Brookes College) Chengdu University of Technology Chengdu China College of Mechanical and Electrical Engineering Chengdu University of Technology Chengdu China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu China

This paper proposes a seismic landslide detection method based on Transformer and RNN algorithm. This method uses seismic data and topographic data as inputs, encodes the data through the Transformer model, and then inputs the encoded data into the RNN model for classification. In the training process, we use the cross entropy loss function and Adam optimizer. To verify the effectiveness of the method, we used public data sets for experiments, and the results show that our proposed method can significantly improve the accuracy of seismic landslide detection. In addition, we interpret the results by visualization method and analyze the performance of the model under different parameters. Our method is expected to provide effective support for earthquake landslide prediction and early warning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-Time Human Pose Estimation on Embedded Devices Based on Deep Learning

Real-Time Human Pose Estimation on Embedded Devices Based on...

引用

International Conference on Wavelet Active Media technology and Information Processing (ICWAMTIP)

作者： HE Caishi WU Sijia Lu Yan Dou Zihao Yang Feng School Of Automation Engineering University of Electronic Science and Technology of China Chengdu

Human posture detection plays an important role in areas such as human behavior analysis and human-computer interaction. Deep learning based methods are one of the mainstream approaches. In practice, detection models are often deployed in resource-constrained edge devices for privacy protection, increased realtime, etc. However, most of the pose detection is for dynamic scenes, which requires high detection speed and accuracy, and thus models are mostly complex in structure and decentralized computation. Aiming at the above difficulties, this paper proposes a multi-person pose detection method, implements a lightweight detection network-RepPose, and deploys it on an embedded device. Specifically, this paper proposes a branch pruning scheme based on the reparameterized structure; and designs a high-performance post-processing operator for the post-processing part; in addition, we also propose a multi-threaded parallel accelerated inference scheme. Finally, it is deployed on Huawei Atlas200DK, and the result reaches 26FPS in the multi-target detection experiment, and achieves more than 90% classification accuracy in pedestrian state detection experiment in simple traffic scenarios.

关键词：

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：