检索结果-内蒙古大学图书馆

9th International Conference on Information, Cybernetics, and Computational Social systems, ICCSS 2023

作者： Liu, Hongxu Yang, Hongyan Han, Honggui Ministry of Education Beijing University of Technology Fac. of Info. Technol. Beijing Key Laboratory of Computational Intelligence and Intelligent System Eng. Res. Ctr. of Digit. Comm. Beijing Artif. Intell. Inst. and Beijing Lab. for Urban Mass Transit Beijing China

ISBN: (纸本)9798350342239

Fuzzy transfer learning has the potential to enhance the performance of a task in the target scene by leveraging knowledge from the source scene. However, the existence of scene discrepancies between the two scenes poses two major problems for fuzzy transfer learning: 1) the mismatch between the distribution of source knowledge and the target task, and 2) the mismatch between the learning ability of the target task and the source knowledge. To address these challenges, we propose a fuzzy transfer learning algorithm called Knowledge-Task Matching Fuzzy Transfer Learning (KTM-FTL), which aims to adaptively match the source knowledge and the target task. Firstly, we develop a knowledge matching mechanism that balances matching accuracy and diversity to reconstruct the knowledge from the source scene. This process enables the source knowledge to align more accurately with the requirements of the target scene's task. Secondly, we design a task matching mechanism that allows for learning the source knowledge at different levels of granularity. This approach enables the learning ability of the target Feedforward Neural Network (FNN) to match the complexity of the source knowledge, thereby improving its generalization performance. Thirdly, we conduct theoretical analysis of the proposed KTM-FTL, including an examination of its computational complexity and error bound. These analyses provide valuable insights for the successful application of KTM-FTL. Finally, we evaluate the performance of the proposed KTM-FTL on several benchmark problems as well as real-world problems. The experimental results demonstrate the significant improvements achieved by KTM-FTL when compared to state-of-The-Art algorithms. © 2023 IEEE.

关键词： Computational complexity

来源：评论

学校读者我要写书评

暂无评论

A Hierarchical Retrieval Method Based on Hash Table for Audio Fingerprinting 17th

A Hierarchical Retrieval Method Based on Hash Table for Audi...

引用

17th International Conference on intelligent computing, ICIC 2021

作者： Li, Tianhao Jia, Maoshen Cao, Xuan Beijing Key Laboratory of Computational Intelligence and Intelligent System Faculty of Information Technology Beijing University of Technology Beijing100124 China

ISBN: (纸本)9783030845216

The focus of audio retrieval research is to find the target audio faster and more accurately in the audio database according to a query audio. In this paper, a low-dimensional audio fingerprint extraction method based on local linear embedding (LLE) and an efficient hierarchical retrieval method are proposed. In the fingerprint extraction part, the audio fingerprint is computed by the energy comparison. The proposed method reduces the dimensionality of the energy vector and the number of energy comparisons by introducing the LLE algorithm, which results in a low-dimensional audio fingerprint. The retrieval part is divided into two stages, which are hash value retrieval for single-frame audio fingerprints and fingerprint block retrieval for consecutive multi-frame audio fingerprints. In the first stage, the reference audios with the same hash value as the query audio are filtered out as candidates. In the second stage, the exact retrieval result is found by calculating the similarity between the query fingerprint block and the reference fingerprint block. The proposed method reduces the computational complexity of fingerprint matching by narrowing the scope of retrieval, thus improving the retrieval speed. In the experimental part, the effectiveness of the proposed method is evaluated and compared with some state-of-the-art methods. The experiments prove that the retrieval accuracy and computation speed can reach a high level after using the proposed method. © 2021, Springer Nature Switzerland AG.

关键词： Data structures

来源：评论

学校读者我要写书评

暂无评论

Cooperative Hunting Method of Unmanned Surface Vehicle based on Attention Mechanism

Cooperative Hunting Method of Unmanned Surface Vehicle based...

引用

Chinese Control and Decision Conference, CCDC

作者： Guorong Sang Xiaoqing Zhu Xiaogang Ruan Xinyi Zheng Lu Chen Chunyang Li Department of Information Beijing University of Technology Beijing China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing 100124 China Beijing China

The hunting of dynamic targets by multi unmanned surface vehicle(USV) is an important problem in USV swarm operations. In this paper, aiming at the dynamic target oriented swarm hunting problem, by analyzing the shortcomings of the hunting mechanism based on MADDPG algorithm, we introduce the attention mechanism into the hunting process, and then design the cooperative hunting strategy based on the attention mechanism(Att-MADDPG), updating the corresponding hunting algorithm. Firstly, the attention module is added to critic network to process the information of all USVs according to different attention weights. Secondly, the attention module is added to actor network to promote other USVs to carry out cooperative hunting. Finally, establish obstacle-free and obstacle simulation environment according to the hunting task. The simulation results show that the training stability and timeliness of Att-MADDPG algorithm are significantly improved compared with MADDPG algorithm. After learning, the USV can cooperate to make the swarm emerge more intelligent behavior.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quadruped Robot Get Bionic Learning Method Based on intelligent Memory Soft Actor-Critic

Quadruped Robot Get Bionic Learning Method Based on Intellig...

引用

Chinese Control and Decision Conference, CCDC

作者： Chunyang Li Xiaoqing Zhu Xiaogang Ruan Borui Nan Lanyue Bi Xiaoyu Zhu Department of Information Beijing University of Technology Beijing China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing 100124China Beijing China

Quadruped robot gait control is a widely studied topic, with the advancements in artificial intelligence, reinforcement learning-based approaches provide a promising solution for bionic gait learning of quadruped robots. In this study, we propose an intelligent Memory Soft Actor-Critic (IM-SAC) algorithm that uses the Soft Actor-Critic algorithm as the basic framework and incorporates Long Short-Term Memory network (LSTM) and Gated Recurrent Unit (GRU) to extract time-sequence-related sequence information of the quadruped robot motion. The IM-SAC algorithm aims to maximize the motion reward by controlling the degree of memory and forgetting of sample information, giving priority to learning samples with high reward values, and achieving faster cumulative rewards and optimization models. We design a reward function using the quadruped robot's own speed, swing angle, and other information to train the robot, and use the 12 motor angles as output values to control the movement of the quadruped robot. We conducted experiments on the Pybullet platform to test the algorithm's performance in gait learning tasks of the quadruped robot. The results show that our study provides a promising solution for gait control of quadruped robots by integrating reinforcement learning and intelligent memory mechanisms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on synergy based on correlation analysis of weighted samples of grasping action

Research on synergy based on correlation analysis of weighte...

引用

2021 China Automation Congress, CAC 2021

作者： Yu, Jianjun Zhang, Zihao Zuo, Guoyu Liu, Gengyuan Li, Xuchen Beijing Key Laboratory of Computational Intelligence and Intelligent System College of Electronic and Control Engineering Beijing University of Technology Beijing China

ISBN: (纸本)9781665426473

The main research goal of underactuated manipulator is to reduce the number of controllers and improve the bionic ability. In this kind of research, underactuated hand design synergy is the mainstream research direction in recent years. Human hand synergy space is a parameterized representation of human hand motion based on a large number of human hand motion data In the past synergy meta-analysis, samples were selected only based on grasping classification without considering people's daily habits, which led to the lack of bionic ability. In this paper, based on the most authoritative 33 kinds of grabbing classification, the samples are weighted and reconstructed according to the daily use habits;Principal component analysis is used to analyze the reconstructed samples, and the correlation between joints is calculated to obtain the synergy of human hand The comparative experiments show that the underactuated transmission scheme based on the synergy design of reconstructed samples has higher similarity and stronger bionic ability than the ordinary sample scheme in most grasping scenes. On this basis, this paper studies the following ability between fingers through the calculation of correlation coefficient and clustering method, so as to further reduce the number of controllers. © 2021 IEEE

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

A Geometric Motion Mapping Algorithm from Master Human Arm to Heterogeneous Slave Robot Arm with Offset Joints 11

A Geometric Motion Mapping Algorithm from Master Human Arm t...

引用

11th IEEE Annual International Conference on CYBER Technology in Automation, Control, and intelligent systems, CYBER 2021

作者： Gong, Daoxiong Wang, Ruihua Yu, Jianjun Beijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System Faculty of Information Technology Beijing100124 China

ISBN: (纸本)9781665425278

In this paper, we presented a geometric motion mapping algorithm that translates the motor commands issued by the human master arm to a heterogeneous slave robot manipulator with offset joints for intuitive teleoperation. Firstly, we set up two spherical coordinate systems on the shoulder of the master tele-operator and the slave robotic arm, respectively. Then, we proposed a motion mapping algorithm comprising three phases of computations, i.e., to determine the positions of the wrist joints of the robot arm according to the target position and orientation of the slave end-effector (EE), to determine the configuration of the robotic arm for reaching the target position of the first wrist joint of the slave arm, and to determine the rotation angles of the wrist joints for realizing the expected position/orientation of the slave EE. Finally, we validate the proposed algorithm via simulations with the KIT human motion capture data. The proposed algorithm can achieve excellent motion mapping results, i.e., exactly attain the expected position/orientation of the slave EE and at the same time possess similar master/slave elbow motion. Therefore, the studied motion mapping algorithm is able to make the master human operator feeling natural and comfortable for intuitive and efficient teleoperation. © 2021 IEEE.

关键词： Remote control

来源：评论

学校读者我要写书评

暂无评论

Research on Forecasting Method for Effluent Ammonia Nitrogen Concentration Based on GRA-TCN 3

Research on Forecasting Method for Effluent Ammonia Nitrogen...

引用

3rd International Conference on Industrial Artificial intelligence, IAI 2021

作者： Kang, Li Cui-Li, Yang Jun-Fei, Qiao Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology Faculty of Information Technology Beijing100124 China

ISBN: (纸本)9781665435178

Aiming at the characteristics of high coupling degree, strong nonlinearity, and serious time delay in the measurement of ammonia nitrogen concentration in wastewater treatment process (WWTP), a prediction model of ammonia nitrogen concentration based on gray relational analysis (GRA) and time convolution network (TCN) was proposed. Firstly, based on the relevant water quality parameters collected in WWTP, the grey correlation analysis method was used to find out other characteristic variables highly related to the ammonia nitrogen concentration. Then, a new group of multivariate time series data was constructed by using the sliding window method. Finally, based on the advantages of the time convolution network in processing time series data, such as simple, flexible, and easy to parallel, the constructed time series data were modeled to predict the concentration of effluent ammonia-nitrogen. To verify the validity of the model, the predicted results were compared with the other four models. The experimental results show that the ammonia-nitrogen concentration prediction model based on GRA and TCN has good prediction performance, which is helpful to realize the accurate prediction of effluent ammonia-nitrogen concentration. At the same time, it can also provide timely and effective guidance for the control and optimization of the wastewater treatment process. © 2021 IEEE.

关键词： Effluents

来源：评论

学校读者我要写书评

暂无评论

Air Pollution Monitoring By Integrating Local and Global Information in Self-Adaptive Multiscale Transform Domain

引用

IEEE Transactions on Multimedia 2025年

作者： Gu, Ke Liu, Yuchen Liu, Hongyan Liu, Bo Qiao, Junfei Lin, Weisi Zhang, Wenjun Beijing University of Technology School of Information Science and Technology Engineering Research Center of Intelligent Perception and Autonomous Control of Ministry of Education Beijing Laboratory of Smart Environmental Protection Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing Artificial Intelligence Institute Beijing100124 China Massey University School of Mathematical and Computational Sciences New Zealand Nanyang Technological University College of Computing and Data Science Singapore Shanghai Jiao Tong University Institute of Image Communication and Information Processing Shanghai China

As the deadliest form of pollution, air pollution had a prolonged severe damage to the human health and life safety of nearly 99% of the world's population. Facing to the problem that billions of tons of pollutants discharged into the air per year by industrial activities, this paper proposed a novel image-based air pollution monitor (IAPM) by incorporating local and global information in the self-adaptive multiscale transform domain, so as to achieve the timely and effective leakage detection of typical air pollutants from a single image. To be specific, this paper first developed a screen-shaped module according to two significant findings in visual neuroscience, which include the high sensitivity of human eyes to horizontal and vertical stimuli and the center-surround inhibition, by designing and fusing the square module, horizontal strip module and vertical strip module parallelly for simulating the behaviour of human eyes to extract local features. Second, the learnable weights and proportional mapping were applied to incorporate the screen-shaped module and lightweight vision transformer as backbone, towards more richly exploiting and fusing local and global information just as the way a brain perceives external stimuli. Third, a new self-adaptive multiscale transform domain method was devised based on two motivations from the visual characteristics of multiscale perception and the brain characteristics of self-adaptive domain transform to modify the backbone by using the operations of pooling and pointwise convolution. Extensive experiments implemented on the datasets of carbon particulate matters and ethylene leakage confirmed the superior monitoring performance of the proposed IAPM model beyond the state-of-the-art (SOTA) peers by an accuracy gain of about 4%. Furthermore, the proposed IAPM model only required 0.089 GFLOPs and 0.15 million model parameters, remarkably outperforming SOTA competitors in computational efficiency and storage resources. © 1999-2

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Vehicle Re-identification Based on Multi-Scale Attention Feature Fusion 22

Vehicle Re-identification Based on Multi-Scale Attention Fea...

引用

Proceedings of the 2022 11th International Conference on computing and Pattern Recognition

作者： Geyan Su Zhonghua Sun Kebin Jia Jinchao Feng Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology China and Faculty of Information Technology Beijing University of Technology China

ISBN: (纸本)9781450397056

It is important to extract vehicle appearance features for vehicle re-identification. The appearance variation of the same vehicle from different viewpoints and the appearance similarity between vehicles from different classes bring challenges for capturing the descriptive features. Considering these, we propose a multi-scale attention feature fusion network (MSAF) for vehicle re-identification. It uses ResNet50 as the backbone, and introduces a scalable channel attention module for each feature channel. Then a multi-scale fusion module is designed to output the final extracted vehicle features. Experimental results on the VERI-Wild dataset indicate that the proposed MSAF achieves high Rank-1 index of 91.20% with mAP of 80.20%.

关键词： Attention mechanism ResNet Vehicle Re-identification Multi-scale fusion

来源：评论

学校读者我要写书评

暂无评论

USV Path Planning Under Marine Environment Simulation Using DWA and Safe Reinforcement Learning 19

USV Path Planning Under Marine Environment Simulation Using ...

引用

19th IEEE International Conference on Automation Science and Engineering, CASE 2023

作者： Qu, Tianci Xiong, Gang Ali, Hub Dong, Xisong Han, Yunjun Shen, Zhen Institute of Automation Chinese Academy of Sciences The State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Institute of Automation Chinese Academy of Sciences Beijing Engineering Research Center of Intelligent Systems and Technology Beijing100190 China Chinese Academy of Sciences Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Dongguan523808 China Qingdao Academy of Intelligent Industries Qingdao266109 China

ISBN: (纸本)9798350320695

It is a challenge for USV navigation due to uncertainties and disturbances in the complex marine environment, which may lead to tilting or collision. However, current path planning methods for USVs lack dynamic environment adaptivity and timeliness. We formulate this problem as a Markov Decision Process (MDP) and combine the advantages of Dynamic Window Approach (DWA) and Safe Reinforcement Learning (RL) to solve it. First, the state encoding output by DWA is employed as observation to reduce the state dimension. Second, a safety-ensured reward function is designed to avoid collision areas. Then, the actor-critic network based on RL algorithm is used. Along with the RL training, the parameters in DWA is adaptively adjusted. Simulation experiments with dynamic waves and ocean currents demonstrate the adaptivity of our method, with avg. trajectory length decreased by 10%, avg. time cost decreased by 17%, and avg. speed increased by 18%, compared to the case using only DWA. © 2023 IEEE.

关键词： Reinforcement learning

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：