检索结果-内蒙古大学图书馆

17th IEEE International Conference on Mechatronics and Automation, ICMA 2020

作者： Zhai, Xiang Shi, Peng Xu, Liang Wang, Yalong Chen, Xi Tianjin University of Technology Binshui Xidao 391 Tianjin Key Laboratory for Control Theory Applications in Complicated Systems School of Electrical and Electronic Engineering Tianjin China Luoyang Institute of Electro-Optical Equipment Avic Luoyang471000 China

ISBN: (纸本)9781728164151

In recent years, with the continuous popularity of the Internet, the number of online shopping users in my country has reached 639 million, which contains huge commercial value. In order to maintain the prosperity, diversity and order of merchants, and fully meet consumers' one-stop shopping needs, it is necessary to analyze and predict user purchase behaviors more accurately. This article uses the interaction between users and products within a certain period of time provided by *** to predict whether users will place orders in designated categories and shops in the next week. First of all, we aim at the problem that the original features are not strongly related, and use feature fusion to construct strong features. For high-dimensional systems that are slow to calculate and prone to overfitting, we use random forests to filter features, reducing the complexity of the model. Finally, a fusion algorithm based on XGBoost and LightGBM is proposed to predict the purchase behavior of users, and the prediction effects of random forest and GBDT algorithm are compared at the same time. The results show that the fusion model has the best prediction effect, and can help merchants more accurately conduct marketing activities to potential customers based on the prediction results. © 2020 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Research on ECG Signal Denoising by Combination of EEMD and NLM

Research on ECG Signal Denoising by Combination of EEMD and ...

引用

第32届中国控制与决策会议

作者： Jiafan Yin Xiaoqi Chen Pengyuan Zhang Lei Shao Ji Li Hongli Liu Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Tianjin University of Technology

In modern medicine,it is necessary to collect signals to determine human’s health,such ECG signal,a fluorescent signal obtained by Polymerase Chain Reaction(PCR) in medicine,and the *** this article,in allusion to the myoelectric interference,baseline drift and common interference caused by machine power and external environment,A new signal denoising method based on the combination of Ensemble Empirical Mode Decomposition and Non-Local Mean is put *** method decomposed the ECG signal by EEMD to obtain a set of IMFS,then calculate the sample entropy of each component,and distinguish the signal dominant component between noise dominant component,and then denoise the noise dominant *** Non-Local Mean to obtain a new component,and finally reconstructs the new component and the signal dominant component to gain a denoised *** experimental verification,the new algorithm is compared with wavelet threshold denoising,EEMD-wavelet threshold denoising and normal Non-Local Mean *** to the experimental results we draw the conclusion that the new method can remove the noise influence effectively on the Signa Noise Ratio and Mean Square *** are better than several other algorithms.

关键词： ECG denoising Adaptive EEMD Non-Local Means

来源：评论

学校读者我要写书评

暂无评论

PCR Instrument Temperature control System Based on Multimodal control

PCR Instrument Temperature Control System Based on Multimoda...

引用

第32届中国控制与决策会议

作者： Ji Li Shihao Liu Shilin li Pengyuan Zhang Hongli Liu Lei Shao Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems Tianjin University of Technology

The core component of the PCR（Polymerase Chain Reaction）instrument is the temperature control system. The PCR reaction process also has high requirements for temperature control. At present, the most widely used PID temperature control system has been difficult to adapt to the high efficiency and high precision requirements of the PCR instrument. In this paper, the mathematical model of TEC（Thermo Electric Cooler） based PCR instrument is deduced, and the multi-modal control system of PCR instrument is designed by using multi-modal control idea combined with fuzzy control and fuzzy PID control. Compared with the traditional PID temperature control, the system has a short steady-state time, a small overshoot and a strong robustness. Based on the temperature control system, the PCR reaction cycle can be shortened and the system accuracy can be increased.

关键词： PCR instrument multimodal control fuzzy control fuzzy PID temperature control

来源：评论

学校读者我要写书评

暂无评论

A Multi-Feature Fusion Based Pedestrian Detection Method

A Multi-Feature Fusion Based Pedestrian Detection Method

引用

IEEE International Conference on Mechatronics and Automation

作者： Enzeng Dong Cunlei Jing Zufeng Zhang Tianjin Key Laboratory For Control Theory & Applications in Complicated Systems Tianjin University of Technology Tianjin China

ISBN: (数字)9781728164168

ISBN: (纸本)9781728164175

This paper proposes an improved pedestrian detection algorithm, the Haar-like feature and Adaboost cascade classifier Histogram of Oriented Gradient (HOG) feature are utilizing to construct hybrid features library, then the weak classifiers in Adaboost are trained by using the combined hybrid features. And the strong classifiers are built based on the weak classifiers. In the proposed algorithm, For improving the detection speed, the HOG feature is rapidly calculated by integral histogram instead of gradient histogram features, and the experimental results showed that the method proposed improved the detection performance and detection accuracy of pedestrians.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep fuzzy infrared handprint target extraction algorithm based on wave-particle duality mechanism

Deep fuzzy infrared handprint target extraction algorithm ba...

引用

Chinese Automation Congress (CAC)

作者： Xuejuan Bao Dahua Li Qiang Gao Xiao Yu Tianjin Key Laboratory for Control Theory and Applications in Complicated Systems Tianjin University of Technology Tianjin China

ISBN: (数字)9781728176871

ISBN: (纸本)9781728176888

In criminal cases, handprint information on-site is one of the most critical evidences in the detection of the case. When shooting with an infrared camera, the heat trace images collected are blurred and incomplete due to heat loss, which makes it difficult to detect. The wave-particle duality shows the particle property and volatility interaction between macroscopic objects and microscopic particles, a handprint target extraction algorithm based on the wave-particle duality mechanism is proposed. Through the wave-particle duality relation between adjacent pixels, the target area of the hand is obtained in the image of the deep- blurred infrared handprints through the matching of the hand skeleton template. The gray value is adjusted by the influence of the volatility between the pixels in the target area on the gray, at the same time according to the particle property relationship expands the pixels on the edge of the skeleton to obtain a clear target area in the deep blurred image. Finally, the K-means clustering segmentation algorithm is used to segment the handprint and the background in the blurred image, and to extract the handprint target. Experimental results show that the target positive extraction rate of the algorithm is 97%. Compared with other traditional algorithms, the algorithm can more effectively and accurately extract the handprint target in the deep blurred infrared image.

关键词： Image segmentation Infrared heating Image edge detection Microscopy Clustering algorithms Skeleton Data mining

来源：评论

学校读者我要写书评

暂无评论

Energy Consumption Data Prediction Analysis based on EEMD-ARMA Model 17

Energy Consumption Data Prediction Analysis based on EEMD-AR...

引用

17th IEEE International Conference on Mechatronics and Automation, ICMA 2020

作者： Li, Ji Jiang, Xudong Shao, Lei Liu, Hongli Chen, Chao Wang, Gang Du, Dongdong Tianjin University of Technology Tianjin Key Laboratory for Control Theory Applications in Complicated Systems Binshui Xidao 391 Tianjin300384 China Tianjin Co. Ltd Tianjin Economic and Technological Development Zone No.2 Bohai Road Binhai New Area Tianjin China Institute of Data Management and Application China Academy of Industrial Internet Beijing100020 China

ISBN: (纸本)9781728164151

Energy consumption data prediction model based on EEMD-ARMA prediction model is used to predict the nonlinear and non-stationary characteristics of industrial energy consumption data, which leads to the difficulty of data prediction and low prediction accuracy. This paper improves empirical mode decomposition (empirical mode decomposition, EMD) by ensemble empirical mode decomposition (ensemble empirical mode decomposition, EEMD) and predicts energy consumption by combining auto regressive sliding average model (auto regressive and moving average model, ARMA). Finally, the historical data of a certain system is selected as a sample, and the comparative analysis of EMD-ARMA and EEMD-ARMA prediction results is used to verify that the EEMD-ARMA algorithm used is more accurate than the prediction algorithm, and its prediction results have certain reference value for the control of energy consumption data in enterprises. © 2020 IEEE.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Role of strategy update rules in the spatial memory-based mixed strategy games

引用

The European Physical Journal B 2021年第1期94卷 1-11页

作者： Zhang, Fan Wang, Juan Gao, Hongyu Li, Xiaopeng Xia, Chengyi Tianjin Key Laboratory for Control Theory and Complicated Industry Systems Tianjin University of Technology Tianjin People’s Republic of China School of Electrical and Electronic Engineering Tianjin University of Technology Tianjin People’s Republic of China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Tianjin People’s Republic of China Engineering Research Center of Learning-Based Intelligent System Ministry of Education Tianjin People’s Republic of China

Based on a continuous mixed strategy game model considering the memory mechanism and the uncertainty of individual decision-making, we explore the influence of several different update rules on the spatial cooperation behavior. Here, we mainly investigate the role of the Moran-like process, Fermi rule and replicator dynamics in the evolution of cooperation. Meanwhile, we further compare the evolution of cooperation when the memory mechanism and individual uncertainty are taken into account. In particular, memory length M and strategy adjustment factor $$\delta $$ can promote the cooperation behavior in different ways. Extensive Monte Carlo simulations indicate that the Moran-like process can generally drive the expansion of cooperative clusters faster and finally achieve the highest frequency of cooperation although the Fermi update rule performs better under the same condition. Moreover, the replicator dynamics create the worst scenario as far as the evolution of cooperation is concerned. Therefore, the level of cooperation strongly depends on the strategy update rules; these findings may be helpful to understand and analyze the evolutionary process of cooperation in many real-world natural and social systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Gesture Recognition based on BP Neural Network and Data Glove

Gesture Recognition based on BP Neural Network and Data Glov...

引用

IEEE International Conference on Mechatronics and Automation

作者： Qiang Fu Jiajun Fu Jian Guo Shuxiang Guo Xun Li Tianjin Key Laboratory for Control Theory & Application in Complicated Systems and Biomedical Robot Laboratory Tianjin University of Technology Binshui Xidao 391 Tianjin China Kagawa University Takamatsu Kagawa Japan

ISBN: (数字)9781728164168

ISBN: (纸本)9781728164175

Various devices for hand data collection have been proposed for gesture recognition. In this paper, a method is proposed for gesture recognition based on data glove and BP neural network. This data glove can collect data of the hand and forearm, it gives a comprehensive description of all aspects of arm movement, and BP neural network algorithm is used to process and classify the collected data and compress the data. Experiments show that hand data can be classified effectively by BP neural network.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Output Regulation for Quadrotor UAV by Event-Triggered Mechanism

Output Regulation for Quadrotor UAV by Event-Triggered Mecha...

引用

Chinese control Conference (CCC)

作者： Shixing Che Qiang Gao Yuehui Ji Tianjin Key Laboratory for Control Theory & Applications in Complicated Systems School of Electrical and Electronic Engineering Tianjin University of Technology

ISBN: (数字)9789881563903

ISBN: (纸本)9781728165233

To accomplish the stable tracking of the quadrotor, an attitude controller based on output regulation and event triggered control (ETC) is proposed to save communication and computing resources effectively. Aiming at the problems of asymptotically tracking and rejecting disturbances, a dynamic compensator, i.e., an internal model is designed to convert the output regulation problem of the quadrotor system into the robust stabilization problem of the augmented system. The state-based event triggered control law (ETCL) and the event triggered mechanism (ETM) that exclude the Zeno phenomenon are adopted to solve the stabilization problem. The stability and boundedness of all signals in the control system are proved by Lyapunov method. Finally, simulation results verify the effectiveness of the controller in providing satisfactory tracking performance and saving communication resources.

关键词： Attitude control Unmanned aerial vehicles Mathematical model Computational modeling Observers Vehicle dynamics Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Output Regulation for Quadrotor UAV by Event-Triggered Mechanism

Output Regulation for Quadrotor UAV by Event-Triggered Mecha...

引用

第三十九届中国控制会议

作者： Shixing Che Qiang Gao Yuehui Ji Tianjin Key Laboratory for Control Theory ＆ Applications in Complicated Systems School of Electrical and Electronic EngineeringTianjin University of Technology

To accomplish the stable tracking of the quadrotor, an attitude controller based on output regulation and event triggered control（ETC） is proposed to save communication and computing resources effectively. Aiming at the problems of asymptotically tracking and rejecting disturbances, a dynamic compensator, i.e., an internal model is designed to convert the output regulation problem of the quadrotor system into the robust stabilization problem of the augmented system. The state-based event triggered control law（ETCL） and the event triggered mechanism（ETM） that exclude the Zeno phenomenon are adopted to solve the stabilization problem. The stability and boundedness of all signals in the control system are proved by Lyapunov method. Finally, simulation results verify the effectiveness of the controller in providing satisfactory tracking performance and saving communication resources.

关键词： quadrotor UAV attitude control output regulation event triggered control

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：