检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Liu, Minmin Li, Xuechen Gao, Xiangbo Chen, Junliang Shen, Linlin Wu, Huisi Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence of Robotics of Society Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China University of California Irvine United States

Due to the difficulty of cancer samples collection and annotation, cervical cancer datasets usually exhibit a long-tailed data distribution. When training a detector to detect the cancer cells in a WSI (Whole Slice Image) image captured from the TCT (Thinprep Cytology Test) specimen, head categories (e.g. normal cells and inflammatory cells) typically have a much larger number of samples than tail categories (e.g. cancer cells). Most existing state-of-the-art long-tailed learning methods in object detection focus on category distribution statistics to solve the problem in the long-tailed scenario, without considering the "hardness" of each sample. To address this problem, in this work we propose a Grad-Libra Loss that leverages the gradients to dynamically calibrate the degree of hardness of each sample for different categories, and re-balance the gradients of positive and negative samples. Our loss can thus help the detector to put more emphasis on those hard samples in both head and tail categories. Extensive experiments on a long-tailed TCT WSI image dataset show that the mainstream detectors, e.g. RepPoints, FCOS, ATSS, YOLOF, etc. trained using our proposed Gradient-Libra Loss, achieved much higher (7.8%) mAP than that trained using cross-entropy classification loss. Copyright © 2022, The Authors. All rights reserved.

关键词： Cytology

来源：评论

学校读者我要写书评

暂无评论

A Forest height estimation algorithm based on the random forests leaf mean encoding

A Forest height estimation algorithm based on the random for...

引用

第三十九届中国控制会议

作者： Jiangeng Li Yin Zhang College of Automation Faculty of Information TechnologyBeijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System

The forest height estimation systems with GeoScience Laser Altimeter system(GLAS) data have been demonstrated to yield an accurate estimation result in the topographically flat areas with simple forest conditions. However, because of the complex forest structures, the GLAS waveform data is difficult to consistently characterize the forest feature of different forest land cover classes. To obtain an effective and reliable estimation model without additional calibration steps, in this paper, we introduce a forest height estimation algorithm based on random forests leaf mean(FLM) encoding, which combines the decision tree model with linear regression, and obtain a better estimation performance than the single regression model. The experiment results show that the FLM encoding method proposed in this paper can implicitly characterize the complex forest information,and have a positive impact on the overall estimation system performance. The complex forest features can be extracted from GLAS waveform by our method and be used as a supplemental feature to improve the estimation of forest height.

关键词： FLM encoding GLAS IGBP forest height

来源：评论

学校读者我要写书评

暂无评论

Implementation of Person Tracking system in Panorama Based on Personalized Distribution

Implementation of Person Tracking System in Panorama Based o...

引用

第三十九届中国控制会议

作者： Jiangeng Li Zhibo Zang Haizheng Xie Guangsheng Wang College of Automation Faculty of Information TechnologyBeijing University of Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System

Panoramic video is a video collected by multi-channel fisheye lens and obtained by splicing and fusion. Compared with traditional video, panoramic video has better integrity, immersion and presence. Therefore, panoramic video has been widely used in the video field. In order to meet the client’s personalized tracking needs in the panoramic broadcast system and panoramic monitoring system, this system designs and implements a people-tracking system based on personalized distribution in the panorama, and provides personalized services for the client to select target objects. Compared with the traditional manual sliding screen for viewing, this automatic live broadcast mode with the target person as the video center greatly improves the user experience. This system uses the method of deep learning to process the panoramic video. After the video is processed by the detection unit based on YOLOv3 and the recognition unit based on ResNet50, the coordinates of the target person in the panoramic video will be obtained. According to the different objects selected by each client, the local video of the corresponding target object is distributed to each client through a streaming media server to meet the personalized tracking needs of different clients.

关键词： Personalized distribution Panoramic video Tracking

来源：评论

学校读者我要写书评

暂无评论

AGV multi-objective path planning method based on improved cuckoo algorithm 4

AGV multi-objective path planning method based on improved c...

引用

4th IEEE Advanced Information Technology, Electronic and Automation Control Conference, IAEAC 2019

作者： Yu, Jianjun Wang, Yang Ruan, Xiaogang Zuo, Guoyu Li, Chen Beijing University of Technology Faculty of Information Technology China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing China

ISBN: (纸本)9781728119076

In order to save time and reduce the energy loss of the AGV when transporting the objects, the discrete cuckoo algorithm is used to solve the path planning problem of multi targets points. Firstly, the cuckoo algorithm is applied to the path planning of the AGV single target point based on the grip map, and the optimal path of the AGV to each object and the optimal path of each object to the specified position are obtained. Secondly, discretizing the cuckoo algorithm, and in the process of discretization, multiple operators such as reverse sequence, insertion, substitution and double bridge are combined into different neighborhood structures, which will used to find the optimal solution through Levi flight mechanism. Finally, the discrete cuckoo algorithm is used to generate the global optimal path for AGV to transport multiple objects. Simulation results show that the proposed algorithm successfully solves the multi-target point path planning problem of AGV. Compared with other algorithms, the proposed algorithm can avoid partial optimality and achieve fast convergence speed. © 2019 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

An Accelerated PSO Based Self-organizing RBF Neural Network for Nonlinear system Identification and Modeling 4th

An Accelerated PSO Based Self-organizing RBF Neural Network ...

引用

4th International Conference on Machine Learning and intelligent Communications, MLICOM 2019

作者： Ahmad, Zohaib Yang, Cuili Qiao, Junfei Faculty of Information Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology Beijing100124 China

ISBN: (纸本)9783030323875

In this paper, an accelerated particle swarm optimization (APSO) based radial basis function neural network (RBFNN) is designed for nonlinear system modeling. In APSO-RBFNN, the center, width of hidden neurons, weights of output layer and network size are optimized by using the APSO method. Two nonlinear system modeling experiments are used to illustrate the effectiveness of the proposed method. The simulation results show that the proposed method has obtained good performance in terms of network size and estimation accuracy. © 2019, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Network layers

来源：评论

学校读者我要写书评

暂无评论

Fault detection of dissolved oxygen sensor in wastewater treatment plants

Fault detection of dissolved oxygen sensor in wastewater tre...

引用

Annual Conference of Industrial Electronics Society

作者： Xuemeng Li Wei Chai Tong Liu Junfei Qiao Faculty of Information Technology Beijing University of Technology Beijing China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing China

ISBN: (数字)9781728154145

ISBN: (纸本)9781728154152

In wastewater treatment processes, the monitoring of dissolved oxygen sensor is the key to ensure the quality of effluent. In this paper, a method for fault detection of dissolved oxygen sensor is proposed using set membership identification and radial basis function(RBF) neural network. The time series model of KLa5 is built by RBF neural network in virtue of its universal approximation ability. Considering the bounded modeling error, the set description of the output weights of the network is obtained by linear-in-parameters set membership identification algorithm. This built model can give a one-step prediction of the confidence interval of KLa5 under the fault-free case. If the real of KLa5 exceeds the predicted confidence interval, a failure of the dissolved oxygen sensor can be determined.

关键词： Fault detection Nitrogen Neural networks Time series analysis Energy consumption Wastewater treatment Standards

来源：评论

学校读者我要写书评

暂无评论

Sewage Treatment Control Method Based on Genetic-SOFNN 4th

Sewage Treatment Control Method Based on Genetic-SOFNN

引用

4th International Conference on Machine Learning and intelligent Communications, MLICOM 2019

作者： Yang, Zhuang Yang, Cuili Qiao, Junfei Faculty of Information Technology Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing University of Technology Beijing100124 China

ISBN: (纸本)9783030323875

In the sewage treatment process, the dissolved oxygen concentration is a very important control target, but it is difficult to be controlled. To solve this problem, a self-organizing fuzzy neural network controller based on genetic ideas (G-SOFNN) is proposed. In the controller structure reduction process, the deleted neuron information is merged with the remaining neurons to reduce the interference set. During the controller structure increasing phase, the information of new neurons is initialized to avoid overlapping of information. Then, the controller parameters are trained by the projection algorithm to improve the control precision. Experiments illustrate that the proposed method can accurately control the concentration of dissolved oxygen in the sewage treatment process. © 2019, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Fuzzy neural networks

来源：评论

学校读者我要写书评

暂无评论

Path Planning of Mobile Robot Based on an Improved Genetic Algorithm

Path Planning of Mobile Robot Based on an Improved Genetic A...

引用

Digital Twins and Parallel intelligence (DTPI), IEEE International Conference on

作者： Zenghua Chen Gang Xiong Sheng Liu Zhen Shen Yue Li State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China School of Automobile Chang'an University Xi'an China

ISBN: (数字)9781665492270

ISBN: (纸本)9781665492287

In order to solve the problem of premature convergence of the basic genetic algorithm when planning the robot running path, the basic genetic algorithm is improved and optimized. Different population initialization methods are used to initialize multiple populations randomly, so as to improve the diversity of populations; Improve the adaptive strategy and elite strategy of crossover and mutation operators to improve the convergence speed of the algorithm; Add the path tortuosity as the planning index in the fitness function to make the planned path smoother, and add constraints to the model to avoid obstacles; Finally, through the transformation of the coding paradigm of the above improved genetic algorithm, it can run on Flink distributed cluster to obtain faster solution speed, so as to meet the efficiency requirements of path planning in large-scale robot cluster system. The optimized algorithm is compared with the basic genetic algorithm. The simulation results show that the improved algorithm is efficient in robot path planning.

关键词： Sociology Clustering algorithms Path planning Planning Trajectory Statistics Collision avoidance

来源：评论

学校读者我要写书评

暂无评论

arXiv

引用

arXiv 2024年

作者： Ren, Yingying Li, Qiuli Guo, Yangyang Pedrycz, Witold Xing, Lining Liu, Anfeng Song, Yanjie School of Computer Electronics and Information Guangxi University Nanning China Guangxi Key Laboratory of Multimedia Communications and Network Technology China Key Laboratory of Parallel Distributed and Intelligent Computing Guangxi University China School of Systems Science Beijing Jiaotong University Beijing China Department of Electrical and Computer Engineering University of Alberta Edmonton Canada Systems Research Institute Polish Academy of Sciences Poland Faculty of Engineering and Natural Sciences Department of Computer Engineering Sariyer Istanbul Turkey School of Electronic Engineering Xidian University Xian China School of Electronic Engineering Central South University Changsha China National Engineering Research Center of Maritime Navigation System Dalian Maritime University Dalian China

With the rapid development of the satellite industry, the information transmission network based on communication satellites has gradually become a major and important part of the future satellite ground integration network. However, the low transmission efficiency of the satellite data relay back mission has become a problem that is currently constraining the construction of the system and needs to be solved urgently. Effectively planning the task of satellite ground networking by reasonably scheduling resources is crucial for the efficient transmission of task data. In this paper, we hope to provide a task execution scheme that maximizes the profit of the networking task for satellite ground network planning considering feeding mode (SGNPFM). To solve the SGNPFM problem, a mixed-integer planning model with the objective of maximizing the gain of the link-building task is constructed, which considers various constraints of the satellite in the feed-switching mode. Based on the problem characteristics, we propose a distance similarity-based genetic optimization algorithm (DSGA), which considers the state characteristics between the tasks and introduces a weighted Euclidean distance method to determine the similarity between the tasks. To obtain more high-quality solutions, different similarity evaluation methods are designed to assist the algorithm in intelligently screening individuals. The DSGAalso uses an adaptive crossover strategy based on similarity mechanism, which guides the algorithm to achieve efficient population search. In addition, a task scheduling algorithm considering the feed-switching mode is designed for decoding the algorithm to generate a highquality scheme. The results of simulation experiments show that the DSGA can effectively solve the SGNPFM problem. Compared to other algorithms, the proposed algorithm not only obtains higher quality planning schemes but also has faster algorithm convergence speed. The proposed algorithm improves data trans

关键词： Profitability

来源：评论

学校读者我要写书评

暂无评论

CODH++: Macro-semantic differences oriented instance segmentation network

引用

Expert systems with Applications 2022年 202卷 1页

作者： Zhang, Wenchao Fu, Chong Cao, Lin Sham, Chiu-Wing School of Computer Science and Engineering Northeastern University Shenyang110819 China Engineering Research Center of Security Technology of Complex Network System Ministry of Education China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang110819 China School of Information and Communication Engineering Beijing Information Science and Technology University Beijing100101 China School of Computer Science The University of Auckland New Zealand

With the idea of divide and rule, there exist two different forms of semantic features flowing in the two stage instance segmentation paradigms. They are the global features at the image level and the instance features at the region-wise. The most significant distinction of the two macro-semantic morphological features lies in the different relevance of neighborhood features caused by background noise. Hence, we should consider different situations and make different schemes. Notice that the fields-of-view determines the range of local features that can be perceived in the convolution operation and implies the representation capability of the network. To this end, for FPN and Mask Head in two stage paradigms, we propose a more efficient methodology with Group-Inception and Asymmetric-Inception modules. This proposed methodology can act as a drop-in replacement to upgrade the plain convolution operation, which enables the network to look more via modeling long-range dependencies. Our method is simple yet effective. Quantitatively, we can significantly improve the state-of-the-art frameworks, including Mask R-CNN, Mask Scoring R-CNN, Cascade Mask R-CNN, and HTC by about 1.2%–2.2% AP on MS COCO test-dev yet with fewer parameters and FLOPs. Moreover, the proposed approach achieves competitive performances on the Scapes, KINS and SBD datasets. The source code of our method will be made available. © 2022 Elsevier Ltd

关键词： Semantics

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：