检索结果-内蒙古大学图书馆

5th International Conference on Artificial Intelligence Technologies and Applications, ICAITA 2023

作者： Lai, Zhiqing Lian, Mingchang Chen, Songhang Chen, Guoqing Lai, Xiaoling Quanzhou Institute of Equipment Manufacturing Haixi Institutes Chinese Academy of Sciences Quanzhou362200 China Fujian Provincial Key Laboratory of Intelligent Identification and Control of Complex Dynamic System Quanzhou362200 China Jingwei Space Information Technology Co. Ltd Longyan364030 China

ISBN: (纸本)9781643684840

Urban and rural development poses significant threats to immovable cultural relics, leading to their degradation and potential extinction. To address this issue, 3D reconstruction has emerged as an effective preservation method. However, traditional radar-based techniques require close scanning and extensive manual intervention, limiting their efficiency. This paper explores the application of neural radiance fields (NeRF) for visually reconstructing immovable cultural relics. NeRF employs a fully connected non-convolutional neural network to generate high-quality 3D models from 2D images. The study discusses NeRF's sampling strategy, positional encoding, field architecture, and rendering process. Experimental investigations evaluate the impact of Fourier parameters on reconstruction quality. A case study reconstructing Tianhou Temple using NeRF is presented, comparing it with ContextCapture software. All results demonstrate that NeRF offers an efficient, and cost-saving solution for reconstructing and preserving immovable cultural relics, providing accurate and realistic models with superior structural integrity. © 2024 The Authors.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Subjective Evaluation and Objective Analysis of Timbre Fusion of Chinese and Western Musical Instruments

Subjective Evaluation and Objective Analysis of Timbre Fusio...

引用

2021 International Conference on Culture-Oriented Science and technology, ICCST 2021

作者： Liu, Jingyu Ran, Can Chen, Yuqu Xiang, Huiling Lin, Jiayu Huang, Yongzhan Jiang, Wei Ministry of Culture and Tourism Key Laboratory of Acoustic Visual Technology and Intelligent Control System China

ISBN: (纸本)9781665442541

Timbre fusion is the theoretical basis for the study of musical instrument acoustics and orchestration acoustics. At present, most of the research on timbre fusion is carried out on Western musical instruments. There are very few studies on the timbre fusion of Chinese musical instruments. The studies done are mainly studied from a qualitative perspective. Quantitative research on the timbre fusion of Chinese musical instruments will provide important theoretical support for the symphony research of the Chinese orchestra. Taking Chinese and Western musical instruments as research object, this paper constructs a Chinese and Western musical instrument fusion timbre database;a subjective experiment on timbre fusion is designed and implemented based on this database;45-dimensional objective acoustic parameters are extracted from the database. We use multiple linear regression, random forest, and multi-layer perceptron to correlate subjective and objective data and eventually construct a fusion model of Chinese and Western musical instruments. The accuracy of the models is tested, which shows that the model can predict the fusion of Chinese and Western musical instruments well. This study also found that the contribution rate of each objective acoustic parameter to fusion is different, and there are also differences between the timbre fusion models of Chinese musical instruments and Western musical instruments. © 2021 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

MovieEmotion-IMG: An Emotion Distribution Dataset of Movie Scene Images

MovieEmotion-IMG: An Emotion Distribution Dataset of Movie S...

引用

2021 International Conference on Culture-Oriented Science and technology, ICCST 2021

作者： Zhang, Jingjing Lin, Chen Wang, Chunxiao Dong, Yicong Jiang, Wei Ministry of Culture and Tourism Key Laboratory of Acoustic Visual Technology and Intelligent Control System China

ISBN: (纸本)9781665442541

One of the biggest challenges in sentiment analysis is to predict the complex feelings that humans evoke when viewing images. Due to the limitation of the quality and quantity of the dataset, the current learning-based algorithm mainly analyzes a single dominant emotion. Based on the above, this paper introduces an emotion distribution dataset of movie scene images with rich emotional semantics and professional aesthetic design, called MovieEmotion-IMG. Firstly nine labels, including eight emotional words and a 'neutrality' label, were identified, and a set of emotional evaluation rules were designed. Then, the emotion distribution annotation experiment was carried out on 17140 movie images, and an emotion annotation system was developed to assist the annotation work. Finally, two reliability test methods were designed based on the external reliability test method to verify the reliability of the results and ensure the availability of the dataset. This is the first large-scale emotion dataset of movie scene images and annotated distributed emotions to our knowledge. © 2021 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Optimal Sensor Placement for Full-Set TDOA Localization Accounting for Sensor Location Errors

引用

IEEE Transactions on Aerospace and Electronic systems 2025年

作者： Zhang, Chengjie Han, Xinyang Kong, He Ho, K.C. Southern University of Science and Technology Shenzhen Key Laboratory of Control Theory and Intelligent Systems Guangdong Provincial Key Laboratory of Fully Actuated System Control Theory and Technology Shenzhen518055 China University of Missouri Electrical Engineering and Computer Science Department ColumbiaMO65211 United States

The positioning accuracy of a signal source is influenced by where the sensors are deployed. Studies in the literature for the optimal sensor placement (OSP) of localization often ignore the presence of sensor position errors. In practice, however, it is impossible to place the sensors precisely at the desired locations. This work designs OSP by accounting for the presence of Gaussian sensor position errors that are independent and identically distributed (IID), with the full set of Time Difference of Arrival measurements corrupted by Gaussian IID noise. The criterion is the A-optimality equal to the trace of the source position Cramer-Rao Bound (CRB). We show that the presence of sensor position errors introduces a multiplication factor to the same criterion for the case without sensor position errors. The latter factor is dependent on the ratio of the sensor position error power to the range difference noise power but independent of the sensor positions, implying that the A-optimality OSP in the presence of sensor position errors is the same as in the absence. To our knowledge, this is the first time such results have been derived. Simulation studies validate the derived OSP, show the minimal OSP performance gap with sensor positioning error and without, and illustrate the better source localization accuracy by OSP. © 1965-2011 IEEE.

关键词： Cramer-Rao bounds

来源：评论

学校读者我要写书评

暂无评论

Q-Learning for Finite-Horizon H8Tracking control of Unknown Linear Discrete-Time systems 42

Q-Learning for Finite-Horizon H8Tracking Control of Unknown ...

引用

42nd Chinese control Conference, CCC 2023

作者： Liu, Mingxiang Cai, Qianqian Meng, Wei Li, Dandan Fu, Minyue Han, Zhimin School of Automation Guangdong University of Technology Guangzhou510006 China Guangdong Province Key Laboratory of Intelligent Decision and Cooperative Control Guangzhou510006 China School of System Design and Intelligent Manufacturing Southern University of Science and Technology Shenzhen518055 China School of Automation Hangzhou Dianzi University Hangzhou310018 China

ISBN: (纸本)9789887581543

In this paper, we present a Q-learning algorithm for finite-horizon H8 tracking control of unknown linear discrete-time systems. Finite horizon control is challenging due to its correspondence with a time-varying Riccati equation. The proposed algorithm can determine the solution of the time-varying Riccati equation with unknown system dynamics. We first establish the time-varying Q-function, then propose a corresponding Q-learning algorithm and prove its convergence. Finally, the proposed algorithm is proved to be effective through numerical examples. © 2023 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Riccati equations

来源：评论

学校读者我要写书评

暂无评论

Dunhuang murals image inpainting method based on fusion classification pre-training model

Dunhuang murals image inpainting method based on fusion clas...

引用

Culture-Oriented Science and technology (CoST), International Conference on

作者： Hui Ren Chengya Zhang Ke Sun Chenyu Ye School of Information and Communication Engineering Communication University of China Beijing China Key Laboratory of Audiovisual Technology and Intelligent Control System Ministry of Culture and Tourism Beijing China Beijing Key Laboratory of Modern Performing Arts Technology Beijing China School of Engineering and Applied Science University of Pennsylvania PA USA

ISBN: (数字)9798350380347

ISBN: (纸本)9798350380354

Murals are an important part of China’s cultural heritage. Because of their age, Dunhuang murals have suffered from discoloration, fading and damage. With the development of computer image restoration technology, digital image processing provides strong support for mural restoration. Although there are many research results in the field of ancient mural images, there is no pre-trained model based on ancient mural images available for migration. There is a method for Dunhuang murals image restoration based on Generative Adversarial Network (GAN) with improved ResNet50 structure as an encoder in the generator. This research result proposes a generative adversarial network model with a parallel double convolutional extraction of deep features for the generator, combined with a ternary heterogeneous joint discriminator. On this basis, this paper proposes a binary classification task to distinguish ancient mural images from modern natural style images, so that the model pre-learns features such as color, texture, and structure of mural images, which are inputted into the restoration network as a priori information, in order to achieve the effect of reducing the probability of incomplete restoration of the model, and better generalization ability. The experimental results show that the method proposed in this paper has an overall improvement in the evaluation indexes such as Peak Signal to Noise Ratio(PSNR) and Structural Similarities(SSIM) when compared with other methods, and the restored images are more in line with human subjective vision, which proves the validity of the method.

关键词： Training Uncertainty Noise Maintenance engineering Generative adversarial networks Feature extraction Generators

来源：评论

学校读者我要写书评

暂无评论

Graph-based Selection-Activation Reinforcement Learning for Heterogenous Multi-agent Collaboration

Graph-based Selection-Activation Reinforcement Learning for ...

引用

第43届中国控制会议

作者： Hao-Xiang Chen Xi-Wen Zhang Jun-Nan Shen State Key Laboratory of Intelligent Control and Decision of Complex System School of Automation Beijing Institute of Technology Chongqing Innovation Center Beijing Institute of Technology

ISBN: (数字)9789887581581

ISBN: (纸本)9798350366907

In practical applications of multi-agent systems, agents are often heterogeneous, and each type of them typically has different task objectives. For heterogeneous multi-agent reinforcement learning(HMARL), the diversity of agent types and the unbalanced agent number of each type can lead to the curse of dimensionality and non-stationary. Moreover, the increase in the number of heterogeneous agents may result in slow convergence during training. This paper proposes a graph-based selection-activation reinforcement learning(GSARL) method for training heterogenous multi-agent collaboration strategies. It first constructs agents based on their types, then extracts the global adjacency matrices and the ally adjacency matrices from the agents' observations, and calculates the global feature matrices. Afterwards, GSARL utilizes hierarchical graph convolutional network to sequentially convolve the global information and ally information, obtaining action logits based on agent types. By using the neural topology graph and the selection-activation method, the optimal multi-agent collaboration configuration is obtained through combinatorial optimization. Experiments are conducted in an adversarial combat simulation environment involving collaborative Unmanned Aerial Vehicles(UAVs) and Unmanned Ground Vehicles(UGVs). Simulation results show that the proposed method can accelerate convergence while allowing that each type of heterogeneous agents can leverage its unique advantages.

关键词： Multi-Agent system Hierarchical Graph Convolutional Network Heterogenous Multi-Agent Collaboration

来源：评论

学校读者我要写书评

暂无评论

Trajectory Optimization and control Method Based on Multistage Nonlinear Model Predictive control 4

Trajectory Optimization and Control Method Based on Multista...

引用

4th International Seminar on Artificial Intelligence, Networking and Information technology, AINIT 2023

作者： Zheng, Qingchun Peng, Zhi Zhu, Peihao Zhai, Ran Tianjin University of Technology Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin China School of Mechanical Engineering Tianjin University of Technology Tianjin China Tianjin University of Technology National Demonstration Center for Experimental Mechanical and Electrical Engineering Education Tianjin China

ISBN: (纸本)9798350314526

To improve the trajectory optimization efficiency of robot manipulators, this paper proposes a novel approach for trajectory optimization and control of manipulators based on multistage nonlinear model predictive control (msNLMPC). This approach is realized by using a neural state space model as the prediction model of nonlinear model predictive control (NLMPC). The simulation results show that the actual trajectory of the manipulator in our proposed scheme coincides with the desired trajectory. The manipulator achieves the control task of following the optimal trajectory. Our proposed method improves the trajectory optimization efficiency of the robot manipulator. © 2023 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Design of an Embedded Leg Capsule Robot 20

Design of an Embedded Leg Capsule Robot

引用

20th IEEE International Conference on Mechatronics and Automation, ICMA 2023

作者： Wang, Yihui Xue, Tao Wang, Jing Yueliwasi, Yimuranjiang Tianjin University of Technology Tianjin Key Laboratory for Advanced Electromechanical System Design and Intelligent Control 391 Binshui Xidao Tianjin China Tianjin University of Technology National Demonstration Center for Experimental Mechanical and Electrical Engineering Education 391 Binshui Xidao Tianjin China

ISBN: (纸本)9798350320831

The capsule robot enters the patient's intestinal system directly by swallowing and takes continuous images using the miniature camera unit it carries, but during its travel, its own gravity and the peristaltic movement of the intestine make the physician limited in obtaining images of the intestine and making a diagnosis. In order to solve this problem, a capsule endoscope with an embedded leg mechanism is proposed. Compared to commercially available capsule robot. This capsule robot can easily move through the intestine autonomously by means of the relationship between the leg, the screw nut and the linkage, enabling forward, backward and stationary functions. The capsule robot has a diameter of 14 mm, a length of 30 mm and a maximum diameter of 26.66 mm with the legs spread out. The hollow space is allocated to include basic endoscopic components such as a miniature camera and a rotating motor. A series of tests, including in vitro tests, were carried out to test the feasibility of the leg mechanism of this capsule robot. Based on the results of the experiments, the proposed leg mechanism can effectively act on the Micro-capsule endoscope, and is able to move effectively through the intestine. © 2023 IEEE.

关键词： Machine design

来源：评论

学校读者我要写书评

暂无评论

Design of Multi-Channel Gas Sensor Circuit with Large Dynamic Range and High-Precision 3

Design of Multi-Channel Gas Sensor Circuit with Large Dynami...

引用

3rd International Conference on Electrical Engineering and Mechatronics technology, ICEEMT 2023

作者： Li, Kun Meng, Jiaheng Liu, Yuzhe Shi, Jingli Liu, Kaicheng Liu, Qing Tianjin University of Technology Tianjin Key Laboratory of Film Electronic and Communication Device Tianjin China Tianjin Space Power Technology Co. Ltd Tianjin China Tianjin Lantian Solar Tech Co. Ltd. China Tianjin University of Technology Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control Tianjin China

ISBN: (纸本)9798350303698

In order to realize a multi-channel exhalation detection device with large dynamic range and high precision, a well designed signal processing and sampling circuit is essential for gas sensors. In this paper, a particular circuit is designed to meet above requirement. The proposed circuit uses a constant current source to achieve linear transformation of resistance value and output voltage, and uses a voltage follower for impedance transformation to minimize the impact of the AD acquisition on the front-end circuit. Since the gas sensor can be regarded as a variable resistor, the proposed circuit is tested with variable resistors varying from 10kΩ to 50MΩ, over three orders of magnitude. In order to increase the sensitivity of the gas sensors, it is need to heat the sensor. Then a multi-channel heating circuit is designed with independent adjustable heating current in each channel, which can be controlled with multi-channel PWM signal from the MCU. With simulation and experiment, the performance of the proposed circuit has been verified to be excellent. Furthermore, the circuit has the advantage of being used in various fields. © 2023 IEEE.

关键词： Timing circuits

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：