2021 33rd Chinese Control and Decision Conference (CCDC)最新文献_第9页

A Data-mining Method to Assess Automatic Generation Control Performance of Power Generation Units 发电机组自动发电控制性能评估的数据挖掘方法

2021 33rd Chinese Control and Decision Conference (CCDC) Pub Date : 2021-05-22 DOI: 10.1109/CCDC52312.2021.9601622

Zijiang Yang, Jiandong Wang, Song Gao, X. Pang

引用次数: 0

An Optimized Model based on Metric-Learning for Few-Shot Classification 基于度量学习的小样本分类优化模型

2021 33rd Chinese Control and Decision Conference (CCDC) Pub Date : 2021-05-22 DOI: 10.1109/CCDC52312.2021.9601665

Wencang Zhao, Wenqian Qin, Ming Li

{"title":"An Optimized Model based on Metric-Learning for Few-Shot Classification","authors":"Wencang Zhao, Wenqian Qin, Ming Li","doi":"10.1109/CCDC52312.2021.9601665","DOIUrl":"https://doi.org/10.1109/CCDC52312.2021.9601665","url":null,"abstract":"Few-shot learning makes up for the shortcomings of traditional deep learning that requires a large amount of labeled data, and has great potential in promoting machines to become more intelligent. Many existing few-shot learning methods have achieved benign performance in numerous classification tasks by training a classifier, yet some trained models are restricted by shallow networks which will gravely restrict their feature expression ability. In addition, what proves awful is that some previous few-shot learning methods do not use appropriate loss functions to train excellent models, which limits their performance to some extent. To settle above problems, we optimize the classical few-shot learning framework, that is, prototypical networks, from three aspects: data augmentation, increasing the network's feature expression ability and improving the training loss function. It is worth mentioning that besides keeping simple and efficient, our innovative metric-learning-based few-shot classification framework is capable to be integrated into the same model to achieve end-to-end training. Immense amounts of experimental results show that our model not only performs well in classification tasks, but also shows its amazing superiority and competitiveness compared with related technologies.","PeriodicalId":143976,"journal":{"name":"2021 33rd Chinese Control and Decision Conference (CCDC)","volume":"69 3 Pt 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126110151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimization of Underwater Cluster Operational Effectiveness Evaluation Based on Support Vector Machine 基于支持向量机的水下集群作战效能评估优化

2021 33rd Chinese Control and Decision Conference (CCDC) Pub Date : 2021-05-22 DOI: 10.1109/CCDC52312.2021.9602312

Ruixiang Hu, Yuanming Ding, Chengzhen Zhang

引用次数: 0

Photovoltaic power prediction model based on parallel dendritic neural model 基于并行树突神经模型的光伏发电功率预测模型

2021 33rd Chinese Control and Decision Conference (CCDC) Pub Date : 2021-05-22 DOI: 10.1109/ccdc52312.2021.9601958

Hao Li, Tengfei Zhang, Yang Yu, Chen Peng

引用次数: 0

Wear Detection of Metro Catenary Based on Binocular Vision 基于双目视觉的地铁接触网磨损检测

2021 33rd Chinese Control and Decision Conference (CCDC) Pub Date : 2021-05-22 DOI: 10.1109/CCDC52312.2021.9602791

Qingfeng Tang, Xiukun Wei, Siyang Jiang

引用次数: 0

Projective Lag Synchronization of Delayed Chaotic Systems via Intermittent Control with Two Sub-periods 基于两子周期间歇控制的延迟混沌系统的投影滞后同步

2021 33rd Chinese Control and Decision Conference (CCDC) Pub Date : 2021-05-22 DOI: 10.1109/CCDC52312.2021.9602668

Bin Zheng, Jianping Cai, Jin Zhou

引用次数: 0

The Research on Predictive Function Control of Double-Pendulum Overhead Crane 双摆桥式起重机预测函数控制研究

2021 33rd Chinese Control and Decision Conference (CCDC) Pub Date : 2021-05-22 DOI: 10.1109/CCDC52312.2021.9602406

Xuan Li, Xuejuan Shao, Zhimei Chen

{"title":"The Research on Predictive Function Control of Double-Pendulum Overhead Crane","authors":"Xuan Li, Xuejuan Shao, Zhimei Chen","doi":"10.1109/CCDC52312.2021.9602406","DOIUrl":"https://doi.org/10.1109/CCDC52312.2021.9602406","url":null,"abstract":"When the quality of crane hook cannot be ignored, the system presents double-pendulum effect with higher underactuation, and the corresponding complexity and non-linearity increase, which makes the control of the system more difficult. In order to solve this problem, this article fully considers the error between the actual output and the predicted output, and applies the predictive function control (PFC) strategy to the positioning and anti-sway system of the double-pendulum overhead crane. According to the nonlinear mathematical model, the T-S fuzzy model is designed, and the linear quadratic regulator (LQR) is used to obtain the state feedback matrix to stabilize the controlled object, obtain the generalized controlled object, and discretize the obtained generalized controlled object. And using it as a predictive model to design a predictive function controller for a double-pendulum overhead crane. Simulation results show that the proposed method can not only realize rapid positioning, but also effectively suppress the pole swing and residual swing, and it still has good stability and robustness under the condition of adding disturbance or changing parameters.","PeriodicalId":143976,"journal":{"name":"2021 33rd Chinese Control and Decision Conference (CCDC)","volume":"288 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132042378","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Optic Disc and Fovea Localization based on Anatomical Constraints and Heatmaps Regression 基于解剖约束和热图回归的视盘和中央凹定位

2021 33rd Chinese Control and Decision Conference (CCDC) Pub Date : 2021-05-22 DOI: 10.1109/CCDC52312.2021.9601379

Ling Luo, Feng Pan, Dingyu Xue, Xinglong Feng, Jiwei Nie

引用次数: 0

Trajectory Tracking for Underactuated Unmanned Surface Vessel Based on Limit Segmentation 基于极限分割的欠驱动无人水面船轨迹跟踪

2021 33rd Chinese Control and Decision Conference (CCDC) Pub Date : 2021-05-22 DOI: 10.1109/CCDC52312.2021.9602661

Dongdong Mu, Guofeng Wang, Yunsheng Fan, Xuguo Jiao, Bingbing Qiu, Xiaojie Sun, Yutong Sun

引用次数: 1

An improved unified online multi-object tracking algorithm combined with attention mechanism 结合注意机制的一种改进的统一在线多目标跟踪算法

2021 33rd Chinese Control and Decision Conference (CCDC) Pub Date : 2021-05-22 DOI: 10.1109/CCDC52312.2021.9602096

Jianning Chi, Changqing Ma, Xing Wu

{"title":"An improved unified online multi-object tracking algorithm combined with attention mechanism","authors":"Jianning Chi, Changqing Ma, Xing Wu","doi":"10.1109/CCDC52312.2021.9602096","DOIUrl":"https://doi.org/10.1109/CCDC52312.2021.9602096","url":null,"abstract":"At present, the mainstream paradigm of multi-target tracking is still tracking-by-detection, which includes two parts: the detector for locating the target and the appearance embedding model for data association. Most methods implement the two modules separately, without considering the relationship between them. However, the biggest problem of this two-stage methods is the large amount of calculation, leading to slow running speed. In this paper, we build a unified online multi-object tracking system. By integrating the object detector and the apparent embedding model into the same shared model, we can get the bounding box and the embedding model simultaneously, so as to reduce the network complexity and speed up the operation. To further improve the performance of the detector, we add an attention mechanism to weight each dimension of the output channel, so as to highlight the important foreground information and ignore the influence of the background as much as possible. The experimental results demonstrate that we can achieve competitive results on MOT16 dataset, and the best trade-off between accuracy and speed.","PeriodicalId":143976,"journal":{"name":"2021 33rd Chinese Control and Decision Conference (CCDC)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129976802","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0