检索结果-内蒙古大学图书馆

DeepTQ: Predictive TSN Switch Queue Length Based on Deep Learning 1

7th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2023

作者： Jia, Yanxin Xu, Long Xiong, Wei Wang, Xin Shang, Zhijun Yuan, Zijun 3onedata Co. Ltd. Shenzhen China Ministry of Education School of Automation and the Key Laboratory of Measurement and Control of Complex Systems of Engineering Southeast University Nanjing China 3onedata Qitong Co. Ltd. Shanghai China University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9789819733361

ISBN: (纸本)9789819733354

With the rapid development of network technology, TSN (Time-Sensitive Networking) is in the stage of rapid development. It needs to ensure the deterministic transmission of time-sensitive flow, further improve the network throughput, and meet the increasing traffic demand. SDN (Software-Defined Networking) can realize the automatic management of network resources by decoupling the control plane and the data plane. Through global network information, it uses efficient route scheduling to achieve load balancing and improve network throughput. However, the prerequisite for route scheduling is that accurately predict the queue length of TSN switch, so that route scheduling can be carried out according to the predicted results. To address the queue length prediction problem of TSN switch, DeepTQ (Predictive TSN Switch Queue Length Based on Deep Learning) is proposed, which predicts the queue length of TSN switches in the next time slot using deep learning methods. It consists of the feature selection phase and the model prediction phase. In DeepTQ, the feature selection phase uses the Spearman rank correlation coefficient to remove redundant features in the datasets. The model prediction phase uses an improved Transformer Encoder and GRU (Gate Recurrent Unit) to construct the prediction model. Simulation results demonstrate that DeepTQ achieves superior performance compared to existing methods and individual components contribute to its overall effectiveness. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Software defined networking

来源：评论

学校读者我要写书评

暂无评论

Seismocardiographic Signals Detection Based on Circulant Singular Spectrum Analysis through Millimeter Wave Radar 6

Seismocardiographic Signals Detection Based on Circulant Sin...

引用

6th International Conference on Signal and Image Processing, ICSIP 2021

作者： Hu, Haiyang Chen, Yuhao Li, Shihua Yang, Jun Sun, Zhenxing Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Nanjing China

ISBN: (纸本)9780738133737

Aiming at the problem that Seismocardiography (SCG) signal detection cannot be promoted due to the bulkiness of the equipment and the SCG containing 7 fiducial points is difficult to extract, this paper proposes a non-contact SCG signal detection algorithm based on the circulant singular spectrum analysis (CiSSA) that runs on a millimeter-wave radar platform. In order to make the detection equipment portable and achieve non-contact detection, this paper uses a millimeter-wave radar working in the 60-64GHz frequency band to collect the signal returned from the surface of the human chest cavity. Then the signal is processed by static clutter elimination and maximum energy distance gate positioning algorithm to improve the signal-to-noise ratio, especially to reduce the interference problem caused by people's tiny movement. For the key problem that the SCG curve extracted by traditional filtering methods are fuzzy and the fiducial points are difficult to identify, the CiSSA method is used to improve the accuracy and completeness of SCG curve extraction. By CiSSA, the signal is embedded into trajectory matrix, and then decomposed into component matrices containing various frequency characteristics. Next, the component matrices are grouped according to the frequency distribution characteristics of the SCG signal, and finally the result of the grouping is reconstructed into a high-precision SCG signal with clear and distinguishable fiducial points. Experiments show that the proposed SCG detection method can accurately extract the SCG curve, clearly distinguish 7 fiducial points of the SCG, and the success rate of detection can reach 97%. This provides the possibility for the popularization of SCG signal detection. © 2021 IEEE.

关键词： Signal detection

来源：评论

学校读者我要写书评

暂无评论

A camera calibration method based on scene and human semantics 37

A camera calibration method based on scene and human semanti...

引用

37th Youth Academic Annual Conference of Chinese Association of automation, YAC 2022

作者： Shu, Yuan Wang, Yangang Southeast University Chien-Shiung Wu College Nanjing China Southeast University School of Automation Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China

ISBN: (纸本)9781665465366

Camera calibration is an important preliminary for many applications such as 3D reconstruction, motion capture and human-computer interactions. Although great achievements have been made in the past several years, it still remains two main problems. The one is that conventional calibration methods always depend on specific calibration tools (e.g., checkerboard). The other is that the calibration procedure is complex when these methods are used in multi-view large scenarios. In this paper, we propose a camera calibration method which can be applied to large-scale sports scenarios without a special calibration object. To tackle these challenges, our key-idea is to use scene and human semantics detected from RGB images to calibrate the intrinsic and extrinsic parameters of multi-view cameras. We first detect the scene and human keypoints, then the initial camera parameters are calculated with the static scene keypoints and a predefined sports field model. Finally, we combine the scene and human semantics to refine the camera intrinsic and extrinsic parameters. Experimental results demonstrate that our method successfully obtains accurate camera intrinsic and extrinsic parameters for large-scale sports scenarios. © 2022 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Research on Drag control Algorithm of Cooperative Robot Based on Torque Compensation

Research on Drag Control Algorithm of Cooperative Robot Base...

引用

2021 China automation Congress, CAC 2021

作者： Zhu, Dezhi Gan, Yahui Dai, Xianzhong School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China

ISBN: (纸本)9781665426473

At present, the teaching methods of collaborative robot drag based on joint current feedback mainly include integral and partial dynamics model, both of which can make robots dragged. However, there are few researches aimed at the advantages and disadvantages of the drag effect and the specific application requirements of the systematic comparative study. Based on the above problems, two zero-force control methods are used on the same 6 degree-of-freedom(DOF) cooperative robot in this paper. And method of torque compensation is improved by parameter identification. Firstly, both of the two methods need to model and analyse the robotic arm. However, processes of the method based on integral dynamics model are modeling, excitation trajectory, filtering, identification and vertification. The zero-force control based on partial dynamics model mainly focuses on the compensation of gravity torque and static friction torque. The gravity term in the dynamic equation is adopted by modeling. The difference in this part is that the parameters of gravity moment function are identified, that is, the weight moment is calculated under the condition of the mass and center of mass deviation are unknown. Finally, NaiWei robot which is a six-joints cooperative robot in China is taken as the experimental object to test and compare. The experimental results show that method of partial dynamics model needs smaller force than integral dynamics model. And the comparison of drag power can be displayed by sensor. © 2021 IEEE

关键词： Force control

来源：评论

学校读者我要写书评

暂无评论

Estimation of Metro Passenger Capacity Based on Passenger-Train Matching Model 3rd

Estimation of Metro Passenger Capacity Based on Passenger-Tr...

引用

3rd International Conference on Information control, Electrical engineering, and Rail Transit, ICEERT 2023

作者： Mei, Zhenkun Chen, Beijia Liu, Jiajun Shao, Jiayu Zhang, Ning Suzhou Rail Transit Group Co. Ltd. Jiangsu Suzhou215004 China School of Automation Southeast University Jiangsu Nanjing210096 China Key Laboratory of Measurement and Control of Complex Engineering Systems Ministry of Education Southeast University Jiangsu Nanjing210096 China ITS Engineering Research Center Ministry of Education Southeast University Jiangsu Nanjing211189 China

ISBN: (纸本)9789819788903

In the present scenario of the ‘one-tapin-one-tapout’ operation mode in urban rail transportation, determining passenger travel trajectories is challenging, thereby decreasing the effective counting of passengers on trains. In order to address this issue, a method for calculating passenger capacity on trains was developed by analyzing passenger travel information extracted from AFC data and train timetables. First, this research estimated the components of journey time to infer and reconstruct the passenger's specific spatiotemporal travel trajectory. The passenger-train matching model was then used to assign passengers to specific trains and calculate the passenger load of different trains at each station. At last, it took Suzhou Metro Line 3 as an example and analyzed the spatiotemporal distribution of urban rail transit passenger flow on a single line based on the proposed passenger-train model. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Urban transportation

来源：评论

学校读者我要写书评

暂无评论

Information Entropy Guided Height-aware Histogram for Quantization-friendly Pillar Feature Encoder

arXiv

引用

arXiv 2024年

作者： Zhou, Sifan Yuan, Zhihang Yang, Dawei Zhao, Ziyu Hu, Xing Shi, Yuguang Lu, Xiaobo Wu, Qiang School of Automation Southeast University the Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China Houmo AI Nanjing210046 China

Real-time and high-performance 3D object detection plays a critical role in autonomous driving and robotics. Recent pillar-based 3D object detectors have gained significant attention due to their compact representation and low computational overhead, making them suitable for onboard deployment and quantization. However, existing pillar-based detectors still suffer from information loss along height dimension and large numerical distribution difference during pillar feature encoding (PFE), which severely limits their performance and quantization potential. To address above issue, we first unveil the importance of different input information during PFE and identify the height dimension as a key factor in enhancing 3D detection performance. Motivated by this observation, we propose a height-aware pillar feature encoder, called PillarHist. Specifically, PillarHist statistics the discrete distribution of points at different heights within one pillar with the information entropy guidance. This simple yet effective design greatly preserves the information along the height dimension while significantly reducing the computation overhead of the PFE. Meanwhile, PillarHist also constrains the arithmetic distribution of PFE input to a stable range, making it quantization-friendly. Notably, PillarHist operates exclusively within the PFE stage to enhance performance, enabling seamless integration into existing pillar-based methods without introducing complex operations. Extensive experiments show the effectiveness of PillarHist in terms of both efficiency and performance. © 2024, CC BY-NC-ND.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Non-Smooth Speed control of Switched Reluctance Motor Based on Generalized Proportional Integral Observer

Non-Smooth Speed Control of Switched Reluctance Motor Based ...

引用

Chinese control Conference (CCC)

作者： Qingzhao Yin Zheng Tian Shihua Li School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China

This paper investigates the speed regulation control of switched reluctance motor (SRM) systems. To improve the antidisturbance performance of SRM, a composite non-smooth control strategy is proposed. First, the structure of SRM is analyzed, and a simplified nonlinear model is obtained based on a segmented representation of the varying phase inductance. A virtual control function is introduced to represent the nonlinear part of the torque equation, whose inverse function is cascaded to linearized the nonlinear model. Second, a generalized proportional integral observer (GPIO) is constructed to estimate the lumped disturbance of the system, which is used for feedforward compensation design. Finally, a composite speed controller is designed based on a combination of finite time proportional feedback and feed-forward compensation based on GPIO (FTP+GPIO). The speed error closed-loop system can be regarded as a first-order finite time control system with bounded disturbances. Strict analysis shows that the proposed scheme can improve the anti-disturbance performance of the closed-loop system. The effectiveness of the proposed method is verified by simulation results. Moreover, it is compared with proportional feedback combining feed-forward compensation (P+GPIO) method and proportional integral (PI) control method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive control for Stochastic Nonlinear systems with Input Saturation Based on Multi-dimensional Taylor Network

Adaptive Control for Stochastic Nonlinear Systems with Input...

引用

IEEE International Conference on Mechatronics and automation

作者： Xiao-Yi Zheng Hong-Sen Yan Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China School of Automation Southeast University Nanjing China

For stochastic nonlinear systems with input saturation, few of the existing control methods use a suitable auxiliary system to solve input saturation problem, and most of them are for deterministic systems. In this study, according to the backstepping approach and the Lyapunov stability theorem, utilizing multi-dimensional Taylor network (MTN), an adaptive controller is presented to secure that all closed-loop signals keep bounded in probability, in which MTN is implemented to approach the uncertain function during the controller design. Moreover, the impact raised by input saturation is mitigated by designing an appropriate auxiliary system, in which the order of the auxiliary system is the same as that of the controlled system. Furthermore, unlike the majority of prior findings, the final output signal could be constrained in a mean quartic sense by an explicit expression of the input saturation error (the difference between the control signal and the saturation input) and the parameters used for design. Finally, the efficiency of the suggested control methodology is confirmed by providing an example.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CAPTURING THE MOTION OF EVERY JOINT: 3D HUMAN POSE AND SHAPE ESTIMATION WITH INDEPENDENT TOKENS

arXiv

引用

arXiv 2023年

作者： Yang, Sen Heng, Wen Liu, Gang Luo, Guozhong Yang, Wankou Yu, Gang School of Automation Southeast University China Key Lab of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing China Tencent PCG

In this paper we present a novel method to estimate 3D human pose and shape from monocular videos. This task requires directly recovering pixel-alignment 3D human pose and body shape from monocular images or videos, which is challenging due to its inherent ambiguity. To improve precision, existing methods highly rely on the initialized mean pose and shape as prior estimates and parameter regression with an iterative error feedback manner. In addition, video-based approaches model the overall change over the image-level features to temporally enhance the single-frame feature, but fail to capture the rotational motion at the joint level, and cannot guarantee local temporal consistency. To address these issues, we propose a novel Transformer-based model with a design of independent tokens. First, we introduce three types of tokens independent of the image feature: joint rotation tokens, shape token, and camera token. By progressively interacting with image features through Transformer layers, these tokens learn to encode the prior knowledge of human 3D joint rotations, body shape, and position information from large-scale data, and are updated to estimate SMPL parameters conditioned on a given image. Second, benefiting from the proposed token-based representation, we further use a temporal model to focus on capturing the rotational temporal information of each joint, which is empirically conducive to preventing large jitters in local parts. Despite being conceptually simple, the proposed method attains superior performances on the 3DPW and Human3.6M datasets. Using ResNet-50 and Transformer architectures, it obtains 42.0 mm error on the PA-MPJPE metric of the challenging 3DPW, outperforming state-of-the-art counterparts by a large margin. Code will be publicly available1 Copyright © 2023, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Single-Domain Generalization Combining Geometric Context Toward Instance Segmentation of Track Components

Single-Domain Generalization Combining Geometric Context Tow...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Shixiang Su Songlin Du Dezhou Wang Shuzhen Tong Xiaobo Lu School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China School of Instrument Science and Engineering Southeast University Nanjing China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

A stable track components segmentation model should have consistent performance across a broad spectrum of railroad conditions, particularly in unfamiliar locations. Despite this, satisfying this requirement proves challenging when working with a limited track dataset, as there is a substantial domain shift between the given dataset and unobserved distributions. The goal of this paper is to improve the generalization ability of track component segmentation in situations where single-domain training data is available. Toward this end, a novel track component instance segmentation method combining the geometric context is proposed. First, we design an initial mask prediction head (IMPH) that utilizes predicted box output from the object detector to generate initial masks by merging the geometric priors of track components. Meanwhile, a multiscale feature fusion structure is introduced to encourage IMPH to better capture the geometric context. Then, a final mask refinement head (FMRH) is introduced to get higher quality masks with a geometry-gated aggregation strategy. On the basis of experiments on track datasets, it was determined that the heads can be incorporated with several types of detection frameworks and have demonstrated consistent generalization enhancements across multiple object detectors. Furthermore, our method substantially enhances segmentation performance on various unobserved domains.

关键词： Instance segmentation Geometry Accuracy Neural networks Merging Training data Detectors

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：