检索结果-内蒙古大学图书馆

International Conference on Wavelet Active Media Technology and information processing (ICWAMTIP)

作者： Wang Gefeng Zhang Shibin Yan Lili Lv Zhiying Chang Yan Qin Zhi School of Cybersecurity (Xin Gu Industrial College) Chengdu University of Information Technology Chengdu China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu China SUGON Industrial Control and Security Center Chengdu China

ISBN: (数字)9798331519254

ISBN: (纸本)9798331519261

Clustering is a type of data mining algorithm aimed at discovering hidden patterns in the data, and spatial clustering is an important type of it. Density-based spatial clustering of applications with noise (DBSCAN) is a clustering algorithm that can discover clusters of arbitrary shapes and has robustness to noise. DBSCAN has been widely studied and applied due to its superior clustering quality, but its high complexity limits its performance on massive-scale datasets. This paper proposes a sampling-based grid-structured DBSCAN algorithm with linear complexity that can be processed in parallel. The algorithm first clusters the sampled dataset to discover the main features of the dataset; then it establishes grids and indexes to accelerate neighbor point queries; finally, through specially designed decoupled algorithm structure, it achieves lock-free parallel computation. Experiments show that this algorithm outperforms the state-of-the-art DBSCAN algorithm under various tested datasets and parameter conditions.

关键词： Shape Noise Clustering algorithms information processing Media Spatial databases Robustness Complexity theory Indexes Time complexity

来源：评论

学校读者我要写书评

暂无评论

Recognizing Human-object Interactions for a Home Assistive Robot

Recognizing Human-object Interactions for a Home Assistive R...

引用

Automation, control and Robotics Engineering (CACRE), International Conference on

作者： Liangliang Wang Guanglei Huo Xinwei Chen Chengxi Huang School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China Fujian(Quanzhou)-HIT Research Institute of Engineering and Technology Quanzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China

To enable robots to understand a specific assistive task during human-robot interactions under complex home scenes, at the center is the problem of human-object interaction (HOI) recognition. In particular, aiming at identifying efficiently, this paper proposes a graph convolutional network (GCN) by considering the similarity and proximity of human and object nodes, based on which the geometric positions and morphological relationships are explored. Also, a supplementary convolutional neural network (CNN) is fused to GCN to extract the global semantic features, which also ensures the recognition applicability for the cases where detectors fall into failure. Experiments on V-COCO demonstrate our approach, and results in real-world scenes on our assistive robot – Xiaozhi II verify its robustness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The improved neural network algorithm of license plate recognition

International Journal of Signal Processing, Image Processing...

引用

International Journal of Signal processing, Image processing and Pattern Recognition 2015年第5期8卷 49-54页

作者： Dong, Jingwei Sun, Meiting Liang, Gengrui Jin, Kui School of Measure-Control Technology and Communication Engineering The higher educational key laboratory for Signal and Information Processing of Heilongjiang Province Harbin University of Science and Technology Harbin China School of Electric and Electronic Engineering Harbin University of Science and Technology Harbin China

With high definition cameras are widely used in urban traffic monitoring, the resolution of vehicle and traffic monitoring image rises. As the main component of intelligent traffic system, the vehicle license plate recognition technique faces new challenges and some new demands are put forward. Aiming at the problems of cutting down the time delay and eliminating characters outside of vehicle license plate, a set of license plate recognition algorithm is developed in this paper. The process of recognition in this paper is divided into four parts: image preprocessing, license plate location, license plate segmentation and character recognition. In license plate location, an accelerating matching method based on particle image correlation method is employed. In character recognition, an improved BP neural network algorithm is employed. The principle, procedure and simulation of the algorithm is described in details. High definition images with 2 mega pixels are used as the input of simulation. © 2015 SERSC.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Single-Photon LiDAR Depth Estimation Based on Time Series Correlation

Single-Photon LiDAR Depth Estimation Based on Time Series Co...

引用

Academic International Symposium on Optoelectronics and Microelectronics Technology (AISOMT)

作者： Lin Ruobin Sun Jianfeng Jiang Peng Ma Le Zhou Xin Ren Zhen Ding Ji National Key Laboratory of Laser Spatial Information Harbin Institute of Technology Harbin Heilongjiang China Zhengzhou Research Institute Harbin Institute of Technology Zhengzhou Henan China National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Beijing China Tianjin Jinhang Technical Physics Institute Tianjin China Beijing Aerospace Automatic Control Institute Beijing China

ISBN: (数字)9798331542283

ISBN: (纸本)9798331542290

With advancements in science and technology, photon-counting LiDAR applications are growing due to long-range measurement, high-definition imaging, and accuracy. Geiger-mode avalanche photodiodes (Gm-APD) provide single-photon sensitivity and picosecond resolution, but noise in depth estimation affects imaging accuracy. This study introduces a novel depth estimation method using time series correlation to mitigate these noise issues, improving accuracy in LiDAR imaging. Utilizing a photon-counting LiDAR system and time-correlated single photon counting (TCSPC), this study capture target echo photon flight times to maintain depth information. The proposed denoising approach incorporates multiple time series windows and Bayesian estimation to enhance depth accuracy, alongside a pruning algorithm to optimize computational efficiency. Evaluation metrics show significant improvements: RSNR improved by 4% and MAE decreased by 43 % compared to traditional methods. The findings demonstrate the robustness of this method across various scenarios, enhancing depth estimation and noise mitigation in photon-counting LiDAR technology, thereby providing practical improvements for a range of applications.

关键词： Correlation Laser radar Accuracy Filtering Depth measurement Time series analysis Noise reduction Imaging Bayes methods Photonics

来源：评论

学校读者我要写书评

暂无评论

Attractor flow analysis for recurrent neural network with back-to-back memristors

Attractor flow analysis for recurrent neural network with ba...

引用

IEEE Symposium on Foundations of Computational Intelligence, FOCI

作者： Gang Bao Zhigang Zeng School of Automation Huazhong University of Science and Technology Wuhan Hubei China Key Laboratory of Image Information Processing and Intelligent Control Ministry of Education Wuhan China college of Electrical Engineering and New Energy China Three Gorges University Yichang China

ISBN: (纸本)9781479944903

Memristor is a nonlinear resistor with the character of memory and is proved to be suitable for simulating synapse of neuron. This paper introduces two memristors in series with the same polarity (back-to-back) as simulator for neuron's synapse and presents the model of recurrent neural networks with such back-to-back memristors. By analysis techniques and fixed point theory, some sufficient conditions are obtained for recurrent neural network having single attractor flow and multiple attractors flow. At last, simulation with numeric examples is presented to illustrate our results.

关键词： Memristors Stability analysis Recurrent neural networks Resistance Numerical models

来源：评论

学校读者我要写书评

暂无评论

DeepACC:Automate Chromosome Classification based on Metaphase Images using Deep Learning Framework Fused with Prior Knowledge

arXiv

引用

arXiv 2020年

作者： Luo, Chunlong Yu, Tianqi Luo, Yufan Wang, Manqing Yu, Fuhai Li, Yinhao Tian, Chan Qiao, Jie Xiao, Li Key Laboratory of Intelligent Information Processing Advanced Computer Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing China Peking University Third Hospital Beijing China School of Computer and Control Engineering University of Chinese Academy of China

Chromosome classification is an important but difficult and tedious task in karyotyping. Previous methods only classify manually segmented single chromosome, which is far from clinical practice. In this work, we propose a detection based method, DeepACC, to locate and fine classify chromosomes simultaneously based on the whole metaphase image. We firstly introduce the Additive Angular Margin Loss to enhance the discriminative power of model. To alleviate batch effects, we transform decision boundary of each class case-by-case through a siamese network which make full use of prior knowledges that chromosomes usually appear in pairs. Furthermore, we take the clinically seven group criterion as a prior knowledge and design an additional Group Inner-Adjacency Loss to further reduce inter-class similarities. 3390 metaphase images from clinical laboratory are collected and labelled to evaluate the performance. Results show that the new design brings encouraging performance gains comparing to the state-of-the-art baselines. Copyright © 2020, The Authors. All rights reserved.

关键词： Chromosomes

来源：评论

学校读者我要写书评

暂无评论

Study on the Preparation and Application of Vector Reference Map

Study on the Preparation and Application of Vector Reference...

引用

IEEE information Technology and Mechatronics Engineering Conference (ITOEC)

作者： Yaqiang Shi Jingyuan Bao Li Xu Zhenpo Tian Delie Ming National Key Laboratory of Science and Technology on Multispectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China The Second Navy Representative Office Wuhan China Beijing Aerospace Automatic Control Institute Beijing China

ISBN: (数字)9781728143231

ISBN: (纸本)9781728143248

In scene matching, we use vector data instead of raster data to prepare a reference map. The BSP -algorithm is used to manage the vector data and then it is loaded on the aircraft. During the guidance process, reference maps are real-time prepared based on the track information and camera parameters. As the vector reference map is very different from the real-time map, conditional generation adversarial networks are used to convert the real-time map to a vector-style image and then match it to the vector reference map, which can achieve 86% matching accuracy.

关键词： Real-time systems Aircraft Cameras Buildings Generators Aircraft navigation Roads

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Graph Convolutional Network for Visual Reinforcement Learning of Action Detection

Heterogeneous Graph Convolutional Network for Visual Reinfor...

引用

Automation, control and Robotics Engineering (CACRE), International Conference on

作者： Liangliang Wang Chengxi Huang Xinwei Chen School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China Fujian(Quanzhou)-HIT Research Institute of Engineering and Technology Quanzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China

Existing action detection approaches do not take spatio-temporal structural relationships of action clips into account, which leads to a low applicability in real-world scenarios and can benefit detecting if exploited. To this end, this paper proposes to formulate the action detection problem as a reinforcement learning process which is rewarded by observing both the clip sampling and classification results via adjusting the detection schemes. In particular, our framework consists of a heterogeneous graph convolutional network to represent the spatio-temporal features capturing the inherent relation, a policy network which determines the probabilities of a predefined action sampling spaces, and a classification network for action clip recognition. We accomplish the network joint learning by considering the temporal intersection over union and Euclidean distance between detected clips and ground-truth. Experiments on ActivityNet v1.3 and THUMOS14 demonstrate our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Capacity Analysis of Finite Scatterer MIMO Wireless Channels

Capacity Analysis of Finite Scatterer MIMO Wireless Channels

引用

IEEE International Conference on Communications

作者： Shangbin Wu Cheng-Xiang Wang Bo Ai Yejun He Joint Research Institute for Signal and Image Processing Heriot-Watt University Edinburgh UK State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing China College of Information Engineering Shenzhen University Shenzhen Guangdong China

This paper analyzes the capacity of the finite scatterer (FS) multiple-input multiple-output (MIMO) channel model with finite angular resolution. The rank of the channel is bounded by not only the number of antennas but also the finite angular resolution of antenna arrays. The probability mass function (PMF) of rank is studied and derived based on the Stirling number of the second kind. As a result, the closed-form expression of the capacity of a FS MIMO channel model is obtained. Furthermore, asymptotic analyses such as the large-scale system analysis, infinite scatterer analysis, and the multiplexing gain analysis are investigated.

关键词： MIMO Antenna arrays Channel models Directive antennas Channel capacity Receivers Multiplexing

来源：评论

学校读者我要写书评

暂无评论

Simulation and analysis of classification optimization model of temperature sensing big data in intelligent building 2016

Simulation and analysis of classification optimization model...

引用

3rd Multidisciplinary International Social Networks Conference, MISNC 2016, 5th ASE International Conference on Social Informatics, SocialInformatics 2016 and 7th ASE International Conference on Data Science, DS 2016

作者： Zhang, Fuquan Mao, Zijing Ding, Gangyi School of software Beijing Institute of Technology Beijing100081 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou350121 China Department of Electrical Engineering University of Texas at San Antonio One UTSA Circle San AntonioTX78249 United States School of software Beijing Institute of TechnologyBeijing 10008 1 China Software Building Beijing Institute of Technology 5 South Zhongguancun Street Haidian Beijing100081 China

ISBN: (纸本)9781450341295

The temperature sensor network in intelligent building classified collection of big data processing has the problem of big data redundancy interference, which results in unable to determine the fixed filter thresholds. This paper proposed Chaos differential disturbance based fuzzy C-means clustering model for big temperature sensing data classification tasks. It requires to analyze temperature sensor in the intelligent building big distributed structure model of data in a database storage system, the big data information flow feature fusion and time series analysis. Based on traditional fuzzy c-means clustering processing, we introduced chaos disturbance to avoid the classification into local convergence and local optimum, and therefore improve the performance of data clustering. The testing results show that our proposed classification method effectively reduces the error rate for classification tasks of temperature data in intelligent building and have achieved the best performance among the existing algorithms. © 2016 ACM.

关键词： Temperature sensors

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：