检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Lu, Xin Cao, Yichao Chen, Shikun Li, Weixuan Zhou, Xin Lu, Xiaobo School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China Nanjing Enbo Technology Co. Ltd. Nanjing210007 China

Knowledge distillation (KD) is a promising approach to learning compact models for object detection with information inherited from intricate teacher networks. In this paper, we raise some shortcomings of existing KD methods for object detectors, e.g., ignoring knowledge selection, coarse feature imitation mask, etc. To address these issues, we present a novel KD framework to train efficient object detectors via Logit Mimicking and Feature Imitation (LMFI). First, we put forward a novel logit mimicking method for classification and localization heads. On the one hand, it first proposes to mimic the classification logits of one-category object detectors. On the other hand, we exploit the localization knowledge from teacher predictions and ground truths, which dynamically guides the learning of student's regression outputs by stages. Second, an adaptive positive teacher selection (APTS) strategy is designed to obtain high-quality teacher samples during distillation, which reduces the transmission of inferior knowledge. Moreover, we heuristically introduce a soft metric and fine-grained mask to reconcile the discrepancy between teacher and student features in a position-wise manner. Extensive experiments show that LMFI outperforms the state-of-the-art KD frameworks for object detection. It can significantly boost the performance of various detectors on different benchmarks, e.g., 2.83% and 2.58% MR-2 reduction of Cascade R-CNN on the S and All sets of CityPersons, and an improvement of ResNet-50 based ATSS from 36.7% to 40.5% mAP on the COCO benchmark. © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Development of a 3-RRS Micromanipulator Based on Origami-Inspired Spherical Joint

Development of a 3-RRS Micromanipulator Based on Origami-Ins...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Haoqi Han Xiaoming Liu Yan Chen Hao Pang Xiaoqing Tang Dan Liu Qiang Huang Tatsuo Arai Beijing Advanced Innovation Center for Intelligent Robots and Systems and School of Mechatronical Engineering Key Laboratory of Biomimetic Robots and Systems Ministry of Education State Key Laboratory of Intelligent Control and Decision of Complex System Beijing Institute of Technology Beijing China Department of Micro-Nano Electronics Shanghai Jiao Tong University China Center for Neuroscience and Biomedical Engineering The University of Electro-Communications Tokyo Japan

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

In recent years, micromanipulation technology has achieved extensive applications in industry and life science. Improving the precision and bandwidth of the micromanipulator and simultaneously reducing size, weight, and cost pose significant challenges to the existing micromanipulator design and fabrication methods. Here, we propose a 3-RRS micromanipulator with an origami-inspired spherical joint based on the PC-MEMS process, aiming for miniaturization and cost-effectiveness. The spherical joint allows rotations of 140° around the x-axis approximately, 140° around the y-axis approximately, and 20° around the z-axis approximately. The micromanipulator has weights of 0.8 g, dimensions of 16 mm × 16 mm × 22 mm, and workspace of 0.7 mm 3 . The end platform of the micromanipulator can be equipped with various effectors to accomplish different kinds of tasks. Experimental results validated its high precision and bandwidth, exhibiting its potential to perform intricate micromanipulation tasks.

关键词： Industries Fabrication Costs Micromanipulators Design methodology Bandwidth Life sciences

来源：评论

学校读者我要写书评

暂无评论

Experimental Study on Flexural Behaviour of Graphite Tailings Concrete Beam in Chloride Environment

SSRN

引用

SSRN 2022年

作者： Bo-Ya, Feng Qing-Yong, Xia Zhu, Xun-Guo Key Laboratory of disaster prediction & control of complex structure system Dalian University Dalian116622 China College of architectural engineering Dalian University Dalian116622 China

In order to study the influence of chlorine salt erosion on the bending performance of graphite tailings concrete beams, the bending performance tests of graphite tailings concrete beams with different substitution rates (0, 10%, 20%, 30%, 40%) in air, water and chlorine salt environments were carried out. The failure mode, crack development law, ultimate bearing capacity, mid-span deflection change law and concrete and steel strain of the test beams under three environments were mainly analyzed. The results show that the cracking load and ultimate load of graphite tailings concrete beams decrease after chlorine salt erosion. With the increase of the replacement rate of graphite tailings, the characteristic load of the test beam increases first and then decreases. The characteristic load of the test beam is the highest when the replacement rate is 20%. The bending performance of low-volume graphite tailings concrete beams is better than that of ordinary concrete beams after chlorine salt erosion. Deflection growth of test beams with replacement ratios of 10% and 20% is relatively slow. Graphite tailings concrete beams still conform to plane section assumption after chloride attack. Based on the test results, a formula for calculating the ultimate bearing capacity of concrete beams with different graphite tailings replacement ratios after chlorine salt erosion was established. © 2022, The Authors. All rights reserved.

关键词： Graphite

来源：评论

学校读者我要写书评

暂无评论

Adaptive tracking control of unknown state target for CPSs subjected to cyberattacks

Adaptive tracking control of unknown state target for CPSs s...

引用

International Conference on control, Automation, Robotics and Vision (ICARCV)

作者： Yizhou Sun Ya Zhang School of Cyber Science and Engineering Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China School of Automation Southeast University Nanjing China

ISBN: (纸本)9781665476881

In this study, an adaptive controller for Cyber-Physical systems(CPSs) subjected to cyberattacks is proposed to track a class of target system with unknown inputs and states. Firstly, an estimation strategy is proposed to adaptively estimate the unknown inputs and states of target on the basis of finite impulse response (FIR) filter. Secondly, due to the existence of cyberattacks in CPSs, an adaptive tracking control scheme with designed compensation signal is constructed to stabilize the system performance which might be damaged by attacks, where Lyapunov function related to adaptive estimated factor is adopted to prove that the CPSs are able to track the target under attacks. In the last part, a numerical experiment is implemented to demonstrate the validity of the theoretical results.

关键词： Target tracking Adaptive systems Finite impulse response filters system performance Estimation Lead control systems

来源：评论

学校读者我要写书评

暂无评论

MetaComp: Learning to Adapt for Online Depth Completion

arXiv

引用

arXiv 2022年

作者： Chen, Yang Zhao, Shanshan Ji, Wei Gong, Mingming Xie, Liping Key Laboratory of Measurement and Control of Complex System of Engineering Ministry of Education School of Automation Southeast University Nanjing210096 China JD Explore Academy Beijing China National University of Singapore Singapore School of Mathematics and Statistics University of Melbourne Australia

Relying on deep supervised or self-supervised learning, previous methods for depth completion from paired single image and sparse depth data have achieved impressive performance in recent years. However, facing a new environment where the test data occurs online and differs from the training data in the RGB image content and depth sparsity, the trained model might suffer severe performance drop. To encourage the trained model to work well in such conditions, we expect it to be capable of adapting to the new environment continuously and effectively. To achieve this, we propose MetaComp. It utilizes the metalearning technique to simulate adaptation policies during the training phase, and then adapts the model to new environments in a self-supervised manner in testing. Considering that the input is multi-modal data, it would be challenging to adapt a model to variations in two modalities simultaneously, due to significant differences in structure and form of the two modal data. Therefore, we further propose to disentangle the adaptation procedure in the basic meta-learning training into two steps, the first one focusing on the depth sparsity while the second attending to the image content. During testing, we take the same strategy to adapt the model online to new multi-modal data. Experimental results and comprehensive ablations show that our MetaComp is capable of adapting to the depth completion in a new environment effectively and robust to changes in different modalities. Copyright © 2022, The Authors. All rights reserved.

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

A Multi-Kernel Principal Component Analysis Method for Quality-Related Fault Detection

A Multi-Kernel Principal Component Analysis Method for Quali...

引用

Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Lingxia Mu Biyu Lei Ding Liu School of Automation and Information Engineering Xi’an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi’an University of Technology Xi’an China

ISBN: (纸本)9781665465373

In this paper, a multi-kernel principal component analysis (MKPCA) method for quality-related fault detection is proposed. The initial space is firstly mapped to a new space. The correlated information between the new space and output quality is then obtained by the kernel function. Meanwhile, with consideration of the advantage of global function and local function, a weight factor which combines them together is introduced to construct a multi-kernel function. In this way, the algorithm achieves better learning ability. The new space is projected to two mutually orthogonal subspaces, i.e., quality-related part and quality-unrelated part. In each subspace, fault information is expressed by different statistical indicators. The numerical example is presented to evaluate the performance of the MKPCA. The results show better reliability and high fault detection rate through proper spatial decomposition and kernel function construction.

关键词： Correlation Automation Fault detection Feature extraction Eigenvalues and eigenfunctions Reliability Matrix decomposition

来源：评论

学校读者我要写书评

暂无评论

ISAC Prototype system for Multi-Domain Cooperative Communication Networks

arXiv

引用

arXiv 2024年

作者： Yang, Jie Que, Hang Tao, Du Liang, Le Li, Xiao Wen, Chao-Kai Jin, Shi The Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China The National Mobile Communications Research Laboratory Southeast University Nanjing210096 China The Frontiers Science Center for Mobile Information Communication and Security Southeast University Nanjing210096 China The Institute of Communications Engineering National Sun Yat-sen University Kaohsiung80424 Taiwan

Future wireless networks are poised to transform into integrated sensing and communication (ISAC) networks, unlocking groundbreaking services such as digital twinning. To harness the full potential of ISAC networks, it is essential to experimentally validate their sensing capabilities and the role of sensing in boosting communication. However, current prototype systems fall short in supporting multiple sensing functions or validating sensing-assisted communication. In response, we have developed an advanced ISAC prototype system that incorporates monostatic, bistatic, and network sensing modes. This system supports multimodal data collection and synchronization, ensuring comprehensive experimental validation. On the communication front, it excels in sensing-aided beam tracking and real-time high-definition video transmission. For sensing applications, it provides precise angle and range measurements, real-time angle-range imaging, and radio-based simultaneous localization and mapping (SLAM). Our prototype aligns with the 5G New Radio standard, offering scalability for up to 16 user equipments (UEs) in uplink transmission and 10 UEs in downlink transmission. Real-world tests showcase the system’s superior accuracy, with root mean square errors of 2.3 degrees for angle estimation and 0.3 meters (m) for range estimation. Additionally, the estimation errors for multimodal-aided real-time radio SLAM localization and mapping are 0.25 m and 0.8 m, respectively. Copyright © 2024, The Authors. All rights reserved.

关键词： Cooperative communication

来源：评论

学校读者我要写书评

暂无评论

DSTFormer: 3D Human Pose Estimation with a Dual-scale Spatial and Temporal Transformer Network

DSTFormer: 3D Human Pose Estimation with a Dual-scale Spatia...

引用

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Shaokun Zhang Xinde Li Chuanfei Hu Jianping Xu Huaping Liu School of Automation Southeast University Nanjing China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing China Nanjing Center for Applied Mathematics Nanjing China Southeast University Shenzhen Research Institute Shenzhen China Science and Technology on Information Systems Engineering Laboratory Nanjing China Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

Recent transformer-based methods for estimating 3D human pose have gained widespread attention, achieving state-of-the-art results. Previous methods have primarily focused on capturing motion patterns of the human body at a single scale or cascading multiple scales, such as joints, bones, and body-parts. However, they are difficult to simultaneously capture spatial-temporal motion patterns of the human body at different scales due to the complex motion patterns. To address this issue, we propose Dual-scale Spatial and Temporal transFormer (DSTFormer), which can concurrently explore the spatial dependencies and temporal motion patterns of human joints and bones. Additionally, we introduce a Gcn-Spatial Transformer Block (GSTB), which introduces Graph Convolutional Networks (GCN) into transformer to enhance the exploitation of local relationships and global information between adjacent joints or bones. Extensive experiments are conducted on the Human3.6M benchmark dataset, and superior results are reported when comparing to other state-of-the-art methods. More remarkably, our model achieves to-date the best published performance, with P1 errors of 37.9 mm and 15.6 mm, respectively.

关键词： Solid modeling Three-dimensional displays Mechatronics Graph convolutional networks Computational modeling Pose estimation Transformers Bones Joints Robots

来源：评论

学校读者我要写书评

暂无评论

Scene Classification Using Deep Networks Combined with Visual Attention

引用

Journal of Sensors 2022年第0期2022卷

作者： Shi, Jing Zhu, Hong Li, Yuxing Li, Yanghui Du, Sen School of Automation and Information Engineering Xi'An University of Technology Xi'an710048 China Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'An University of Technology Xi'an710048 China

In view of the scene's complexity and diversity in scene classification, this paper makes full use of the contextual semantic relationships between the objects to describe the visual attention regions of the scenes and combines with the deep convolution neural networks, so that a scene classification model using visual attention and deep networks is constructed. Firstly, the visual attention regions in the scene image are marked by using the context-based saliency detection algorithm. Then, the original image and the visual attention region detection image are superimposed to obtain a visual attention region enhancement image. Furthermore, the deep convolution features of the original image, the visual attention region detection image, and the visual attention region enhancement image are extracted by using the deep convolution neural networks pretrained on the large-scale scene image dataset Places. Finally, the deep visual attention features are constructed by using the multilayer deep convolution features of the deep convolution networks, and a classification model is constructed. In order to verify the effectiveness of the proposed model, the experiments are carried out on four standard scene datasets LabelMe, UIUC-Sports, Scene-15, and MIT67. The results show that the proposed model improves the performance of the classification well and has good adaptability. © 2022 Jing Shi et al.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Hot Spot Detection of Photovoltaic Module Infrared Near-field Image based on Convolutional Neural Network 4

Hot Spot Detection of Photovoltaic Module Infrared Near-fiel...

引用

2022 4th International Conference on Energy systems and Electrical Power, ICESEP 2022

作者： Fan, Fu Na, ZhiXiong Zhang, ChangZhi Li, HaoRan Tong, ChaoLiu School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China State Grid e-commerce Co. Ltd Beijing100053 China State Grid Tianjin Electric Power Company Tianjin300010 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education School of Automation Southeast University Nanjing210096 China

With the installation and use of large-scale photovoltaic systems around the world, the detection of photovoltaic system operation and maintenance has become increasingly important. This research uses a convolutional neural network training model to detect and classify the infrared near-field images of photovoltaic modules from small-scale photovoltaic plants in the laboratory. This model classifies the images into two categories: with and without hot spots, with a classification accuracy of 96.58%. The experimental results show that the convolutional neural network training model has a good classification result. © 2022 Institute of Physics Publishing. All rights reserved.

关键词： Convolutional neural networks

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：