检索结果-内蒙古大学图书馆

2021 China Automation Congress, CAC 2021

作者： Pei, Fujun Miao, Zhu Wang, Jinghui Faculty of Information Technology Beijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing China

ISBN: (纸本)9781665426473

It is well known that the traditional visual SLAM systems have performed well in a relatively ideal environment, but for the dynamic environment, there are some problems in the instance segmentation algorithm such as incomplete segmentation or wrong segmentation which will result in outliers. Aiming at this problem, this paper proposed a dynamic SLAM system using Histogram-based Outlier Score (HBOS) to improve the reprojection residual constraint to increase the robustness in removing outliers. In this method, HBOS method is used to process the reprojection residual, and the feature association data obtained after the segmentation mask processing is further filtered to improve the robustness. This method can combine the semantic segmentation network with traditional geometric methods to solve the data association problem caused by the wrong information generated from the dynamic objects. To verify the effectiveness of the proposed method, the experiment is carried out on the public TUM data set and the results show that the proposed method improves the accuracy of SLAM positioning in the dynamic environment. © 2021 IEEE

关键词： Statistics

来源：评论

学校读者我要写书评

暂无评论

Construction and application of biological visual nerve computing model in robot 5

Construction and application of biological visual nerve comp...

引用

5th Asian Conference on Artificial intelligence Technology, ACAIT 2021

作者： Yu, Naigong Yu, Hejie Qiu, Tong Lin, Jia Beijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System Faculty of Information Technology Beijing China

ISBN: (纸本)9781665426305

Biological vision is very effective and accurate in scene classification and recognition. Based on this, this paper proposes a biological visual neural computing model based on the anatomical structure of rat brain, which is characterized by: constructing a biological visual scene memory model (visual word bag), imitating the biological brain's storage of environmental scene information, and calculating the similarity between the current scene information and the visual template;designing and constructing the object details located in the lateral entorhinal cortex and the peripheral olfactory cortex Cell discharge model. Experimental results show that the proposed model can effectively extract image features and generate visual word bag model based on image features. Compared with ratslam scan line strength model, the retrieval time of this model is greatly shortened;The object cell discharge model with image similarity information as input can show similar expression of discharge rate as physiological research, which verifies the effectiveness and efficiency of the proposed model. The research results lay a foundation for the research of robot environment cognition method based on brain cognitive mechanism. © 2021 IEEE.

关键词： Physiological models

来源：评论

学校读者我要写书评

暂无评论

An IT2FNN with a Novel Hierarchical Learning Algorithm for Nonlinear system Modeling

An IT2FNN with a Novel Hierarchical Learning Algorithm for N...

引用

2023 China Automation Congress, CAC 2023

作者： Sun, Zijian Meng, Xi Qiao, Junfei Beijing University of Technology Faculty of Information Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing China

ISBN: (纸本)9798350303759

Interval type-2 fuzzy neural networks (IT2FNNs) have been widely used for modeling in industrial processes, and the efficient parameter learning methods are crucial for obtaining accurate models. However, the problem of low computational efficiency and poor convergence performance still exists in existing learning methods. In this study, a novel hierarchical learning algorithm is proposed for constructing IT2FNN with better learning ability and generalization performance. Firstly, the improved recursive least square (RLS) method with an adaptive forgetting factor is designed to learn the consequent parameters. Next, the advanced stochastic gradient descent (SGD) method is adopted to learn the antecedent parameters. Finally, the proposed method is applied to real industrial processes and compared with various state-of-the-art IT2FNNs. Simulation results demonstrate the superiority of the proposed method. © 2023 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

A model of information circulation and transmission network of grid cells in entorhinal cortex and place cells in the hippocampus of rat 9

A model of information circulation and transmission network ...

引用

9th IEEE Joint International Information Technology and Artificial intelligence Conference, ITAIC 2020

作者： Yu, Naigong Yu, Hejie Wang, Lin Liao, Yishen Yin, Chunlei Beijing University of Technology Department of Information Beijing China Beijing Key Laboratory of Computational Intelligence and Intelligent System China

Biological studies have found that the grid cells in the entorhinal cortex of the rat brain structure and the place cells in the hippocampus structure have a mutual input and output cyclic relationship in the process of information transmission, from entorhinal cortex-hippocampus information transfer loop. The traditional neural network model from grid cells to place cells is not enough to satisfy the information transmission relationships, ignores the information transfer from place cells to grid cells, to solve this problem, a neural network model based on grid cells in entorhinal cortex and place cells in hippocampus information transfer loop is proposed. The simulation results show that the model can simulate the firing characteristics of place cells and grid cells. © 2020 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection for Internet of things Using Self-supervised Pre-training on GRU

Intrusion Detection for Internet of things Using Self-superv...

引用

2022 Chinese Automation Congress, CAC 2022

作者： Pei, Fujun Chang, Yuke Shi, Mingjie Beijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System Faculty of Information Technology Beijing China

ISBN: (纸本)9781665465335

Intrusion detection is crucial in the Internet of Things (IoT) due to the scarcity of computing resources and the variability of the network environment when it is used in smart buildings, smart factories and other scenarios. Current intrusion detection solutions are mostly applicable to a single environment (or a single dataset) and require large amounts of labeled data for supervised training methods, which are not applicable to variable IoT network environments. In this paper, we investigate the recognition effect of GRU networks on the packet sequences made up of IoT network packets and suggest a self-supervised pre-training method based on GRU networks. In order to improve the effectiveness of supervised training in the following fine-tuning phase, the unlabeled data is utilized in the pre-training of this method to find sequence data correlations in the data flow and deeper representations of the data. The proposed model is evaluated on datasets such as TON-IoT, and it is observed that our method can significantly increase the model detection accuracy. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Progress and Challenge of Artificial intelligence

引用

Journal of Computer Science & Technology 2006年第5期21卷 810-822页

作者：史忠植郑南宁 Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100080 P.R. China The Laboratory of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi'an 710049 P.R. China

Artificial intelligence （AI） is generally considered to be a subfield of computer science, that is concerned to attempt simulation, extension and expansion of human intelligence. Artificial intelligence has enjoyed tremendous success over the last fifty years. In this paper we only focus on visual perception, granular computing, agent computing, semantic grid. Human-level intelligence is the long-term goal of artificial intelligence. We should do joint research on basic theory and technology of intelligence by brain science, cognitive science, artificial intelligence and others. A new cross discipline intelligence science is undergoing a rapid development. Future challenges are given in final section.

关键词： artificial intelligence visual perception machine learning agent computing semantic web intelligence science

来源：评论

学校读者我要写书评

暂无评论

intelligent Optimal Control for Wastewater Treatment Process with Flexible Objective Functions 5

Intelligent Optimal Control for Wastewater Treatment Process...

引用

5th International Conference on Information, Cybernetics, and Computational Social systems, ICCSS 2018

作者： Han, Hong-Gui Zhang, Lu Qiao, Jun-Fei Faculty of Information Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology Beijing China

ISBN: (纸本)9781538670880

In wastewater treatment process (WWTP), it is very challenging to realize the optimal control of the operation variables, since the process contains a changing number of objectives. In this paper, an intelligent optimal control with flexible objective functions (FOF-IOC)is proposed to deal with the optimal control problem for improving the operation performance. Compared with the previous optimal control methods, this proposed FOF-IOC has three main advantages. Firstly, an optimal control scheme is developed to describe the dynamics of the operation process. In this scheme, the different time-scale operation objectives are formulated to facilitate the optimal control. Secondly, a flexible objective functions strategy is designed for determining the appropriate objective functions, where the number of the objectives can be different under the distinct operation time. Thirdly, a dynamic multiobjective particle swarm optimization (DMOPSO)algorithm is investigated for optimizing the flexible objective functions, where a maximum dimension criterion is designed to cope with the nouniform optimization dimension. Finally, the proposed FOF-IOC is tested in benchmark simulation model No.1 (BSM1)to evaluate its effectiveness. The results demonstrate that the proposed FOF-IOC can achieve satisfied performance. © 2018 IEEE.

关键词： Wastewater treatment

来源：评论

学校读者我要写书评

暂无评论

Structural Reparameterization Network on Point Cloud Semantic Segmentation 12th

Structural Reparameterization Network on Point Cloud Semanti...

引用

12th International Conference on Image and Graphics, ICIG 2023

作者： Li, ZhiJian Jia, Kebin Zhao, YuXuan Huang, WeiWei Beijing Laboratory of Advanced Information Networks Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology Beijing100124 China

ISBN: (纸本)9783031463044

In recent years, 3D point cloud semantic segmentation has made remarkable progress. However, most existing work focuses on designing intricate structures to aggregate local features, resulting in a significant number of parameters and computational demands. In this Paper, we combine the idea of structural reparameterization in 2D convolution to propose RPNet, which can effectively reduce the number of parameters while fully extracting the point cloud features. Specifically. We first design the multi-branch structure SRLFA (Structure Re-parameterization Local Feature Abstract) module based on the reparameterization to fully extract the local features of the point cloud, and design the PFA (Point Feature Abstract) module to extract the features of the point itself. Then, by decoupling the training and inference phases, the multi-branch structure is fused into an equivalent single-branch structure through the idea of structural reparameterization during training and inference, which ensures the feature extraction capability while effectively reducing the number of parameters. Finally, the proposed method is trained and tested on several public data, and the results demonstrate that the proposed method achieves advanced performance in mIoU and OA with effective control of the number of model parameters. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Construction of Combustion Line Quantification Data Set for Municipal Solid Waste Incineration Process 4

Construction of Combustion Line Quantification Data Set for ...

引用

4th International Conference on Industrial Artificial intelligence, IAI 2022

作者： Guo, Haitao Tang, Jian Heng, Xia Qiao, JunFei Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing100124 China Beijing Laboratory of Smart Environmental Protection Beijing100124 China

ISBN: (数字)9781665451208

ISBN: (纸本)9781665451208

In municipal solid waste incineration (MSWI) process, combustion line is one of the key controlled variables to characterize the combustion stability and operation safety. Realizing the quantification of combustion line can replace 'manual fire monitoring', which can improve the intelligent degree of MSWI process through real-time feedback. However, the quantification of combustion line needs the combustion flame image data set. Currently, there is no standard flame image data set containing multiple combustion line locations. This paper constructs a flame image set containing multiple combustion line locations. First, the flame image acquisition process is introduced. Then, the combustion line level is divided by combining with the location information of three-dimensional space inside the furnace. Finally, a calibration algorithm facing the position of the combustion line is proposed. Thus, combustion flame image dataset was constructed, which provided a reference for relevant researchers to utilize this dataset in the future study. © 2022 IEEE.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

Modified bat algorithm with Otsu's method for multilevel thresholding image segmentation

引用

Journal of Computational and Theoretical Nanoscience 2015年第11期12卷 4560-4572页

作者： Zhou, Guo Zhou, Yongquan Li, Liangliang Ma, Mingzhi Institute of Computing Technology Chinese Academy of Sciences Beijing100081 China Guangxi High School Key Laboratory of Complex System and Computational Intelligence Nanning530006 China

The conventional multilevel thresholding methods are inefficient in determining the optimal thresholds due to the exponential growth in computation time. This paper a modified random location bat algorithm is proposed to overcome this shortcoming. The modified random localization (MRL) strategy can enable the bats cover the whole search space. Then, with the help of MRL strategy, the exploratory ability of the bats is improved, and the search efficiency and convergence speed is increased. The proposed algorithm is used to find the optimal thresholds by maximizing the Otsu's objective function, and its performance has been tested on nine standard test images. The experimental results of 100 independent runs illustrate the better solution quality and higher computation efficiency of modified random localization bat algorithm (MRLBA) when compared with the particle swarm optimization (PSO) and bat algorithm (BA). © 2015 American Scientific Publishers.

关键词： Image segmentation

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：