检索结果-内蒙古大学图书馆

International Conference on Pattern Recognition

作者： Jinting Wu Yujia Zhang Xiaoguang Zhao School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences

Hand gesture recognition plays a significant role in human-computer interaction for understanding various human gestures and their intent. However, most prior works can only recognize gestures of limited labeled classes and fail to adapt to new categories. The task of Generalized Zero-Shot Learning (GZSL) for hand gesture recognition aims to address the above issue by leveraging semantic representations and detecting both seen and unseen class samples. In this paper, we propose an end-to-end prototype-based GZSL framework for hand gesture recognition which consists of two branches. The first branch is a prototype-based detector that learns gesture representations and determines whether an input sample belongs to a seen or unseen category. The second branch is a zero-shot label predictor which takes the features of unseen classes as input and outputs predictions through a learned mapping mechanism between the feature and the semantic space. We further establish a hand gesture dataset that specifically targets this GZSL task, and comprehensive experiments on this dataset demonstrate the effectiveness of our proposed approach on recognizing both seen and unseen gestures.

关键词： Human computer interaction Target recognition Semantics Prototypes Human-robot interaction Gesture recognition Detectors

来源：评论

学校读者我要写书评

暂无评论

Adaptive Fusional Localization for Robot Fish Based on Dynamic-weight Fuzzy Inference

Adaptive Fusional Localization for Robot Fish Based on Dynam...

引用

Chinese Automation Congress (CAC)

作者： Yuzhuo Fu Xiaocun Liao Ben Lu Qianqian Zou Zhuoliang Zhang Yaming Ou Chao Zhou State Key Laboratory of Management and Control for Complex Systems Institute of Automation CAS Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665426480

Accurate localization of robots in a specific environment often requires the cooperation of multiple sensors, and how to establish a more general data fusion model is always a difficult problem. For the localization of robot fish in an indoor pool environment, this paper proposes an adaptive fusional algorithm based on fuzzy inference of dynamic weights. This paper firstly constructs a confidence probability table of sensors’ signals based on the calibration data sets of BLE and UWB nodes at different distances, as the basis for updating the weights of the BLE or UWB nodes; secondly, the data obtained by each node in a single sampling period in the robot fish movement is vectorized to form a judgment matrix, and then the estimated distance is obtained by fuzzy inference together with the sensor weight; finally, the coordinates are calculated by the four-point positioning method. In this paper, more than 40 sets of experiments have been carried out with a simplified carangidae-like robot fish. The results show that the average positioning error is about 0.189m, which is 88.3% and 31.8% lower than that of using BLE only and using UWB only. In this paper, the fusional positioning method based on statistics combines the advantages of different sensors to reduce the data scale and achieve data denoising while fusing sensor data, which provides a reference for indoor positioning of robot fish and multi-sensor data fusion.

关键词： Location awareness Fuzzy logic Robot kinematics Heuristic algorithms Data integration Sensor fusion Probability

来源：评论

学校读者我要写书评

暂无评论

Stress Detection Using Wearable Devices based on Transfer Learning

Stress Detection Using Wearable Devices based on Transfer Le...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Jinting Wu Yujia Zhang Xiaoguang Zhao The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665429825

Excessive stress will have a negative impact on people’s physical and mental health, especially for some special occupations. Because stressful stimuli can trigger a variety of physiological responses, analyzing physiological signals collected by wearable devices has become an important way to evaluate the stress state in recent years. However, the number of available subjects of a target group may be small, and collecting a large amount of data when the target group changes is costly and time-consuming. To solve this problem, we propose a stress detection framework for a small target group which uses adversarial transfer learning method to learn shared knowledge about stress between different groups. In order to verify the performance of the framework, we establish a dataset consisting of 264 ordinary college students and 32 police school students, aiming to evaluate the acute stress state of police school students under video stimuli for psychological training in the future. Comprehensive experiments show that our algorithm has achieved a significant improvement in the target group compared with the baseline methods.

关键词： Training Protocols Law enforcement Wearable computers Transfer learning Signal processing algorithms Feature extraction

来源：评论

学校读者我要写书评

暂无评论

MixedFusion: 6D Object Pose Estimation from Decoupled RGB-Depth Features

MixedFusion: 6D Object Pose Estimation from Decoupled RGB-De...

引用

International Conference on Pattern Recognition

作者： Hangtao Feng Lu Zhang Xu Yang Zhiyong Liu The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences

Estimating the 6D pose of objects is an important process for intelligent systems to achieve interaction with the real-world. As the RGB-D sensors become more accessible, the fusion-based methods have prevailed, since the point clouds provide complementary geometric information with RGB values. However, due to the difference in feature space between color image and depth image, the network structures that directly perform point-to-point matching fusion do not effectively fuse the features of the two. In this paper, we propose a simple but effective approach, named MixedFusion. Different from the prior works, we argue that the spatial correspondence of color and point clouds could be decoupled and reconnected, thus enabling a more flexible fusion scheme. By performing the proposed method, more informative points can be mixed and fused with rich color features. Extensive experiments are conducted on the challenging LineMod and YCB-Video datasets, which shows that our method significantly boosts the performance without introducing extra overheads. Furthermore, when the minimum tolerance of metric narrows, the proposed approach performs better for the high-precision demands.

关键词： Measurement Three-dimensional displays Image color analysis Fuses Pose estimation Color Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

An empirical evaluation of attention-based multi-head models for improved turbofan engine remaining useful life prediction

arXiv

引用

arXiv 2021年

作者： Ayodeji, Abiodun Wang, Wenhai Su, Jianzhong Yuan, Jianquan Liu, Xinggao State Key Laboratory of Industrial Control Technology Control Department Zhejiang University Hangzhou310027 China Tianjin Jinhang Technical Physics Institute Tianjin300192 China Science and Technology on Complex System Control and Intelligent Agent Cooperative Laboratory Beijing100074 China

A single unit (head) is the conventional input feature extractor in deep learning architectures trained on multivariate time series signals. The importance of the fixed-dimensional vector representation generated by the single-head network has been demonstrated for industrial machinery condition monitoring and predictive maintenance. However, processing heterogeneous sensor signals with a single-head may result in a model that cannot explicitly account for the diversity in time-varying multivariate inputs. This work extends the conventional single-head deep learning models to a more robust form by developing context-specific heads to independently capture the inherent pattern of each sensor reading in multivariate time series signals. Using the turbofan aircraft engine benchmark dataset (CMAPSS), an extensive experiment is performed to verify the effectiveness and benefits of multi-head fully connected neurons, recurrent networks, convolution network, the transformer-style stand-alone attention network, and their variants for remaining useful life estimation. Moreover, the effect of different attention mechanisms on the multi-head models is also evaluated. In addition, each architecture's relative advantage and computational overhead are analyzed. Results show that utilizing the attention layer is task-sensitive and model dependent, as it does not provide consistent improvement across the models investigated. The result is further compared with five state-of-the-art models, and the comparison shows that a relatively simple multi-head architecture performs better than the state-of-the-art models. The results presented in this study demonstrate the importance of multi-head models and attention mechanisms to improved understanding of the remaining useful life of industrial assets. © 2021, CC BY.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-View Spatio-Temporal Deep Graph Neural Network for Travel Demand Prediction

SSRN

引用

SSRN 2022年

作者： Zhao, Tianhong Huang, Zhengdong Tu, Wei Biljecki, Filip Chen, Long School of Architecture and Urban Planning Shenzhen University China Department of Architecture National University of Singapore Singapore Department of Real Estate National University of Singapore Singapore State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences China

Predicting travel demand is an essential task in urban mobility management. Previous methods use the spatio-temporal dependencies of travel demand to improve the prediction accuracy, but pay less attention to the cross-modal dependency among different transportation modes (bus, metro, taxi, etc.). We propose a multi-view spatio-temporal graph neural networks (MSTGNN) model to predict the travel demand. The development, bridging the gaps of the state of the art, emphasizes the ability to capture cross-view dependencies, derived from the interaction of multiple transportation modes. Specifically, a multi-view graph with the bus, metro, and taxi views is constructed according to spatial adjacency and transportation interaction adjacency. A multi-view attention temporal graph convolution module is designed to capture spatio-temporal and cross-view dependencies. Additionally, the cross-view features spatial consistency loss is presented to overcome the problem of uneven distribution of multi-view features. Taking the bus travel demand as an example, intensive experiments are conducted using real-world bus, metro, and taxi data in Shenzhen. The results indicate that the MAE of the MSTGNN model improves baseline methods by 9.13%. The contributions of different transportation modes and local/global cross-view dependencies are demonstrated in the ablation experiments. The attention mechanism in the MSTGNN model demonstrates certain interpretability of the interaction between different transportation modes. The dataset generated in this research has been released as open data. © 2022, The Authors. All rights reserved.

关键词： Smart cards

来源：评论

学校读者我要写书评

暂无评论

Perception for Coupler Rod of Freight Train Based on Image and Point Clouds

Perception for Coupler Rod of Freight Train Based on Image a...

引用

Chinese Automation Congress (CAC)

作者： Renjie Guo Jun Feng Huachang Yang Dejie Luan Guodong Yang En Li State Key Laboratory of Management and Control for Complex Systems Institute of Automation CAS Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Signal & Communication Research Institute China Academy of Railway Sciences Corporation Limited Beijing China

In the construction of automated marshaling yards, the automatic uncoupling operation of freight trains has always been the research and development direction. The coupler rod is the operation object of the uncoupling operation. The identification of coupler rod type and estimating position and posture are the prerequisites to realizing automatic uncoupling operation. In this paper, we propose a perception method of coupler rod by RGB image combined with the point cloud. We use an RGBD camera to synchronously collect frame-aligned RGB and depth images and generate point cloud data with colors according to the mapping relationship. Then, we use the YOLOv5 neural network to detect the collected RGB images and recognize the type of coupler rod in the image. Clear clutter in the point cloud and the bounding box is mapped to a spatial coordinate system for straight-through filtering of the point cloud. We use RANSAC for coarse registration and ICP for fine registration. The result of registration is carried out with the lower sampling point cloud model to achieve the registration of the coupler rod. Experiments show that this method can effectively segment the point cloud of the region of interest with high robustness.

关键词： Point cloud compression Image segmentation Image recognition Image color analysis Filtering Neural networks Data integration

来源：评论

学校读者我要写书评

暂无评论

Consensus control of Leader-following Multi-agent system in Partial Directed Topology 2

Consensus Control of Leader-following Multi-agent System in ...

引用

2nd International Conference on Industrial Artificial Intelligence, IAI 2020

作者： Yan, Chunsheng Zheng, Yongjian Huang, Chuan Xue, Simeng Sun, Hongwei Wang, Xin Wei, Qinglai LiaoNing Electric Power Development Stock CO. LTD Shenyang China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728182162

ISBN: (纸本)9781728182162

In this paper, the consensus control of linear multi-agent system in partial directed topology is discussed. The key innovation of this paper is that we propose a novel consensus control by using partial directed topology with the external stochastic disturbance. Since the noise inference is unavoidable in real life, the external disturbance produced by the Gauss white noise through Brown motion is taken into account when the states of the leader and followers are described. To settle this kind of problem, a distributed controller based on Riccati inequalities with an adaptive law is designed for leader-following multi-agent systems. We give proof through Lyapunov function and get the result which is the same as the theory. Finally, a simulation example is given to support the Theorems. © 2020 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Parallel Vision and Learning for Intelligent Perception in Smart Driving

Parallel Vision and Learning for Intelligent Perception in S...

引用

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

作者： Hui Zhang Yidong Li Xuan Li Fei-Yue Wang Beijing Jiaotong University Beijing China Peng Cheng Laboratory Shenzhen China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

Modern vision models are built upon large-scale diversified dataset, which is labor-intensive and cost-ineffective to collect and label. They are usually effective under simple constrained conditions, while the performance gets worse under actual traffic scenes. To address aforementioned problems, we propose a visual analysis framework based on parallel vision and learning for intelligent perception in smart driving. Specifically, our framework first generate and select data exploiting artificial image system. Then, computational experiments are conducted with predictive learning for model design, learning, and evaluation. Our framework is powered with virtual-actual interactive ability through parallel execution, integrating information from different scenes. The difficulty of the visual model in the actual scene can be applied to guide the model training in the artificial scene. We also carried out a case study to preliminarily demonstrate the effectiveness of the proposed framework.

关键词： Training Learning systems Visualization Computational modeling Digital twin Conferences Learning (artificial intelligence)

来源：评论

学校读者我要写书评

暂无评论

The Quality Evaluation of Academic Papers in Carbon Capture, Utilization, and Storage

The Quality Evaluation of Academic Papers in Carbon Capture,...

引用

Machine Learning, control, and Robotics (MLCR), International Conference on

作者： Hangyue Zhang Jie Bai School of Computer Science and Technology Sun Yat-sen University Guangzhou P. R. China City State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing P. R. China

ISBN: (纸本)9781665454605

Carbon capture, utilization, and storage (CCUS) technology is a research hotspot worldwide owing to global climate change and warm gas control. CCUS papers from the last twenty years, derived from the Web of Science database, were analyzed to investigate the impact and citation of academic papers using machine learning methods. Firstly, nine author characteristics, keywords, and three other categories were extracted from the literature. Then, the natural logarithm distribution of the annual average number of citations was obtained, and five evaluation grades were decided based on the citations. Next, the keyword evolution of papers in the CCUS field is analyzed, and a model on the keyword evolution trend index is proposed. Data integration and imbalance processing were conducted after random sampling. A citation prediction model was proposed to evaluate the quality of CCUS academic papers and was verified on the recent five years' CCUS papers by comparing it with nine other mainstream machine learning models. The results indicate that the random forest model exhibits the best performance, with an accuracy rate reaching 88.7%; an ablation experiment was also conducted using the same algorithm. The results prove the effectiveness of our proposed method, shedding light on the quality of academic papers and technology development in CCUS.

关键词： Machine learning Climate change Random forests Modeling Energy storage

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：