检索结果-内蒙古大学图书馆

5th International Conference on Computer Science and Application engineering, CSAE 2021

作者： Peng, Xinfeng Tong, Shuzhen Lu, Xiaobo Wei, Yun School of Automation Southeast University Nanjing210096 China Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Nanjing210096 China Beijing Mass Transit Railway Operation Corporation Limited Beijing100044 China

ISBN: (纸本)9781450389853

In the automatic railway anomaly inspection technology based on image processing and deep learning, an effective algorithm used for high-precision detection of the fastening system is very important, especially in turnout sections. It is challenging because the background of the turnout sections is complicated with various types of targets. This paper improved the Faster R-CNN model, used multi-scale feature map fusion for small targets. And modified predefined anchor to generate region proposals, added attention module to make the network focus on meaningful feature. Besides, this paper used cross-entropy function and SmoothL1 loss function for training and labeled 1200 image samples as dataset. Compared with the original Faster R-CNN model, the experimental results (AP) of the improved model in this paper increased from 96.3% to 98.9%, which effectively reduced the fault detection and missed detection and improved the accuracy of location.. © 2021 Association for Computing Machinery. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Fault Detection Method of Photovoltaic System Based on Power Change of Array

Fault Detection Method of Photovoltaic System Based on Power...

引用

2021年第四届算法、计算和人工智能国际会议

作者： Chao Tan Chenxi Li Kanjian Zhang Haikun Wei Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of EducationSchool of AutomationSoutheast University

The fault detection of photovoltaic power generation system is of great significance in photovoltaic plant management. The conventional fault detection method of photovoltaic power system requires additional sensors, and the fault detection scheme needs to be redesigned if the parameters of the photovoltaic plant ***, for large photovoltaic plants, it is necessary to develop a method that does not require the use of external sensors or the detailed parameters of the photovoltaic plant. This paper proposes a photovoltaic system fault detection method based on photovoltaic array current and voltage data. This method does not require additional sensor data such as irradiance and temperature. The failure of photovoltaic system can be detected through the change of power,and the abnormal situation of photovoltaic power station can still be detected under cloudy and shaded conditions. The advantages of this method are that there is no need for complex and diverse sensor equipment, the calculation is simple and the fault detection ability is accurate. The experimental data of Padang Poverty Power Station of State Grid has been verified.

关键词： Photovoltaic System(PVS) Fault detection algorithm Electrical data Sensorless Power characteristics

来源：评论

学校读者我要写书评

暂无评论

A Robust Clock Synchronization Scheme for Wireless Sensor Networks against DoS Attacks

A Robust Clock Synchronization Scheme for Wireless Sensor Ne...

引用

第40届中国控制会议

作者： Xuxin Zhang Shiyu Chen Bingya Zhao Ya Zhang School of Automation Southeast University Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education

This paper investigates the clock synchronization problem of wireless sensor networks with time-varying noises and malicious denial of service（Do S） attacks. A robust and secure clock synchronization scheme based on filter is proposed in intermittent Do S attack case, which is composed of three steps: relative skew estimation, clock skew compensation and software clock reading compensation. Through the clock skew compensation, the synchronization error of the clock skew can be constrained into a bounded range. Through the software clock reading compensation, the possible error of the software clock reading can be compensated and the clock synchronization can be achieved completely. In addition, extensive simulations are conducted which validate that the proposed scheme outperforms the existing ones.

关键词： clock synchronization wireless sensor networks DoS attacks bounded noises filter

来源：评论

学校读者我要写书评

暂无评论

Distilling Object Detectors with Efficient Logit Mimicking and Mask-Guided Feature Imitation

SSRN

引用

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

Load peak-valley shape clustering and drift analysis for improving temporal pattern representation

引用

Sustainable Energy, Grids and Networks 2025年 43卷

作者： Ma, Yiwei Shen, Yimeng Tang, Xianlun Yan, Dong School of Automation Chongqing University of Posts and Telecommunications Chongqing400065 China Department of Electrical Engineering School of Automation and Industrial Internet Chongqing University of Posts and Telecommunications Chongqing400065 China Chongqing Key Laboratory of Complex Systems and Bionic Control Chongqing University of Posts and Telecommunications Chongqing400065 China

Load shape pattern clustering is an important foundation for developing appropriate tariff design and load management to achieve more economical and reliable benefits. However, the existing load shape pattern clustering methods mainly focus on the whole load shape and various clustering algorithms, which do not consider the peak-valley shape features and distribution drift issue of the load shapes. Therefore, peak-valley shape pattern clustering and drift measurement of daily load shapes are proposed to solve this problem. To accurately reveal the peak-valley electricity consumption behaviors, load peak-valley shape models and a hybrid distance measurement are proposed to obtain more representative temporal patterns that have more compact peak-valley shape distributions. Moreover, two measurement models for power drift and time drift are proposed to analyze the significant drift problem between daily load peak-valley shape patterns. The results showed that the proposed method outperformed other methods, as it not only achieved the best clustering effectiveness scores, such as DBI, WAS, CHI, SC, and DI scores of 0.5537, 0.2633, 502.3634, 0.8872, and 1.4730, respectively, but also accurately obtained the time drift values between different modes, such as the maximum backward shift of the two peak times by 90 and 150 minutes, and the maximum backward shift of the valley time by 45 and 60 minutes, respectively. © 2025 Elsevier Ltd

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

A Multi-population Integrated Approach for Capacitated Location Routing

arXiv

引用

arXiv 2024年

作者： He, Pengfei Hao, Jin-Kao Wu, Qinghua School of Automation Key Laboratory of Measurement and Control of Complex Systems of Engineering Ministry of Education Southeast University Nanjing210096 China Department of Computer Science LERIA University of Angers 2 Boulevard Lavoisier Angers49045 France School of Management Huazhong University of Science and Technology No. 1037 Luoyu Road Wuhan China

The capacitated location-routing problem involves determining the depots from a set of candidate capacitated depot locations and finding the required routes from the selected depots to serve a set of customers whereas minimizing a cost function that includes the cost of opening the chosen depots, the fixed utilization cost per vehicle used, and the total cost (distance) of the routes. This paper presents a multi-population integrated framework in which a multi-depot edge assembly crossover generates promising offspring solutions from the perspective of both depot location and route edge assembly. The method includes an effective neighborhood-based local search, a feasibility-restoring procedure and a diversification-oriented mutation. Of particular interest is the multi-population scheme which organizes the population into multiple subpopulations based on depot configurations. Extensive experiments on 281 benchmark instances from the literature show that the algorithm performs remarkably well, by improving 101 best-known results (new upper bounds) and matching 84 best-known results. Additional experiments are presented to gain insight into the role of the key elements of the algorithm. © 2024, CC BY-NC-ND.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Context-aware Emotion Recognition Based on Vision-Language Pre-trained Model

Context-aware Emotion Recognition Based on Vision-Language P...

引用

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： XingLin Li Xinde Li Chuanfei Hu 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 Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (数字)9798350385724

ISBN: (纸本)9798350385731

Given the difficulty of recognizing ambiguous emotions in facial expression recognition tasks, we propose a visual-language model named CAER-CLIP to address this challenge. The proposed CAER-CLIP standed for Context-Aware Emotion Recognition (CAER), and were incorporated structure of the Contrastive Language–Image Pre-training (CLIP) model as promising alternative to classifier. There are two parts in CAER-CLIP model. In the visual part, facial expressions and contextual information of the image are simultaneously extracted to obtain the final feature embeddings, which are then used as a learnable “class” token for text-image pairing with desired module. In the textual part, we use text labels for emotion recognition classes as input. The outputs were merged to participate the comparative study to generated parameters of the model. The experiments demonstrate the effectiveness of the proposed method and show that our CAER-CLIP outperforms the state-of-the-art results on the CAER benchmark. The ablation experiment verified the effectiveness of both the classifier-based and text-based (ours without classifier) models, demonstrating that our method with the CAER-CLIP structure performed better, and the incorporation of a text encoder in the deep network model architecture effectively enhancing recognition accuracy.

关键词： Training Emotion recognition Visualization Accuracy Text recognition Face recognition Benchmark testing Feature extraction Data mining Context modeling

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Object Detection Network for Industrial Robot Based YOLOv5

A Lightweight Object Detection Network for Industrial Robot ...

引用

Chinese automation Congress (CAC)

作者： Tao Zhong Yahui Gan Zao Han Huan Gao Ang Li Key Laboratory of Measurement and Control of Complex Systems of Engineering School of Automation Southeast University Ministry of Education NanJing China Nanjing YingQi Intelligent Technology Co. Ltd. Intel Joint Research Institute on Intelligent Edge Computing NanJing China

With the rapid development of deep learning, it has been widely applied in fields such as computer vision, natural language processing, and robotics. Despite the superior performance of deep learning in object detection, most industrial vision robots still rely on traditional object detection methods due to computational constraints of robot controllers. In order to improve the performance of object detection for vision robots, a lightweight 3D object detection network based on You Only Look Once version 5 (YOLOv5) is proposed for satisfying industrial production. YOLOv5 work to efficiently object detection using deep convolutional networks. In terms of model deployment, we adopt a novel OpenVINO-based model deployment approach. The OpenVINO framework significantly enhances the inference speed of models by model optimization and compression. Our model achieves a 70% reduction in inference time compared to the baseline model on CPU. The effectiveness of the proposed method is demonstrated through experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Aeromagnetic Compensation Algorithm Based on Broad Learning System

An Aeromagnetic Compensation Algorithm Based on Broad Learni...

引用

Robotics, Artificial Intelligence and Intelligent control (RAIIC), International Conference on

作者： Qilong Wang Junlei Song Chao Zuo Kaifeng Dong Fang Jin School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo- Exploration Ministry of Education Wuhan China Wuhan Second Ship Design and Research Institute Wuhan China

ISBN: (数字)9798350352627

ISBN: (纸本)9798350352634

Aeromagnetic surveys, renowned for their operational flexibility and high efficiency, serve as a crucial technique for measuring the geomagnetic field. However, aeromagnetic surveys are easily affected by magnetic interference from navigation platforms, making the compensation of aeromagnetic interference a crucial step in the measurement process. To address the inadequate consideration of nonlinear magnetic field interference in traditional compensation algorithms, this paper introduces an aeromagnetic compensation approach based on broad learning system. The broad learning system employs an incremental learning mechanism aimed at enhancing the precision of the network alongside the increase in nodes. With each expansion of the network node, computation is streamlined to calculating the pseudo-inverse of the expansion node, eliminating the necessity for retraining the entire network structure. Leveraging the nonlinear fitting characteristics of the broad learning system, this paper improves the accuracy of aeromagnetic interference compensation. Through UAV flight experiments, the broad learning system is compared with methodologies using particle swarm optimization (PSO) and BP neural network. Compared with PSO, training time was reduced by $21.3 \%$ and magnetic interference by $33.6 \%$. Compared with BP neural networks, training time was reduced by $34.9 \%$ and magnetic interference by $28.6 \%$. This paper provides references and ideas for the selection of aeromagnetic interference compensation algorithms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neural-Dynamics-Based Active Steering control for Autonomous Vehicles with Noises

Neural-Dynamics-Based Active Steering Control for Autonomous...

引用

IEEE Symposium on Intelligent Vehicle

作者： Ying Liufu Long Jin Fei-Yue Wang School of Information Science and Engineering Lanzhou University Lanzhou China State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

This paper introduces a neural-dynamics-based active steering control (NDASC) scheme developed under artificial systems, computational experiments, and parallel execution (ACP) framework, aimed at enhancing the stability and reliability of autonomous vehicles in noisy environments. Based on the Taylor expansion theorem, noises can be represented in the form of polynomials for the desired accuracy, and therefore polynomial noises can be viewed as a more generalized representation of noises. Then, the proposed NDASC scheme includes a model predictive active steering control (MPASC) strategy solved by a polynomial noise resilience neural dynamics (PNRND) model. Computational experiments parallelly implemented upon the CarSim-Simulink platform substantiate the effectiveness and robustness of the proposed NDASC scheme, providing significant theoretical and practical insights for control strategies of autonomous vehicles under various noisy environments.

关键词： Noise Predictive models Polynomials Stability analysis Robustness Noise measurement Vehicle dynamics

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：