检索结果-内蒙古大学图书馆

9th International Conference on Computer Engineering and Networks, CENet2019

作者： Song, Chunhe Wang, Zhongfeng Liu, Shuji Xu, Libo Zhou, Dapeng Zeng, Peng Key Laboratory of Networked Control Systems Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110016 China State Grid Liaoning Electric Power Co. Ltd. Shenyang110000 China

ISBN: (纸本)9789811537523

Peak load management is very important for the electric power system. This paper analyzes the impact of residential swimming pool pumps (RSPPs) on the peak load. First, this paper analyzes the challenges of non-intrusive energy consumption estimation for SPPs. Second, a novel reference-based change-point (RCP) model is proposed for non-intrusive SPPs energy consumption estimation. The advantages of the proposed RCP model are that it does not require high sampling rate data or prior information of the appliance. We show that during pool season, under the assumption that the ratio of base loads (defined as the power consumption which is independent of the outdoor temperature) of houses with and with PPs remains the same during no-pool season and pool season, 6.3% of the total energy is consumed by PPs, while under the assumption that for houses with and without PPs, the ratio of base loads is equal to the ratio of the temperature-dependent power consumption during pool season, 9.08% of the total energy is consumed by PPs. Furthermore, we show that by shifting PPs activity period, under the first assumption, at least 1.27% of peak demand can be reduced, while under the second assumption, at least 4.53% of peak demand can be reduced. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Electric power utilization

来源：评论

学校读者我要写书评

暂无评论

Research on Target Detection Method Based on Improved YOLOv5 19th

Research on Target Detection Method Based on Improved YOLOv5

引用

19th International Conference on Web Information systems and Applications, WISA 2022

作者： Wang, Rongzhuang Liu, Jun Zhang, Hualiang School of Computer Science and Technology Shenyang University of Chemical Technology Shenyang110142 China Liaoning Key Laboratory of Intelligent Technology for Chemical Process Industry Shenyang110142 China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China

ISBN: (纸本)9783031203084

At present, various target detection algorithms are used in detection and classification. It is a problem to improve the accuracy and speed of target detection by using deep learning and neural network model to train the parameters of the data set. Aiming at the problems of insufficient detection, inaccurate detection of complex background and loss of small target feature information in yolov5 target detection, an improved method combining hole convolution, moving exponential average and retraining of positive samples is proposed in this paper. This method effectively solves the problems of complex background, occlusion and incomplete feature extraction, reduces the loss rate of target features, and improves the detection accuracy of each category. The improved yolov5 target detection algorithm in this paper can not only use multi feature fusion and accelerate positive sample matching, but also use cavity convolution to increase receptive field, improve the detection effect of small targets and reduce the occurrence of missed detection and false detection. Experiments show that the improved yolov5 algorithm has better detection rate and lower loss rate than many existing target detection algorithms. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Knowledge-aware Graph Transformer for Pedestrian Trajectory Prediction

arXiv

引用

arXiv 2024年

作者： Liu, Yu Zhang, Yuexin Li, Kunming Qiao, Yongliang Worrall, Stewart Li, You-Fu Kong, He Shenzhen518055 China Department of Mechanical Engineering City University of Hong Kong Hong Kong School of Automation Guangdong Polytechnic Normal University Guangzhou510665 China Australian Centre for Field Robotics The University of Sydney NSW2006 Australia Australian Institute for Machine Learning The University of Adelaide SA5005 Australia Shenzhen Key Laboratory of Control Theory and Intelligent Systems SUSTech Shenzhen518055 China Guangdong Provincial Key Laboratory of Human-Augmentation and Rehabilitation Robotics in Universities SUSTech Shenzhen518055 China

Predicting pedestrian motion trajectories is crucial for path planning and motion control of autonomous vehicles. Accurately forecasting crowd trajectories is challenging due to the uncertain nature of human motions in different environments. For training, recent deep learning-based prediction approaches mainly utilize information like trajectory history and interactions between pedestrians, among others. This can limit the prediction performance across various scenarios since the discrepancies between training datasets have not been properly incorporated. To overcome this limitation, this paper proposes a graph transformer structure to improve prediction performance, capturing the differences between the various sites and scenarios contained in the datasets. In particular, a self-attention mechanism and a domain adaption module have been designed to improve the generalization ability of the model. Moreover, an additional metric considering crossdataset sequences is introduced for training and performance evaluation purposes. The proposed framework is validated and compared against existing methods using popular public datasets, i.e., ETH and UCY. Experimental results demonstrate the improved performance of our proposed scheme. © 2024, CC BY.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Semi-parametric Memory Consolidation: Towards Brain-like Deep Continual Learning

arXiv

引用

arXiv 2025年

作者： Liu, Geng Zhu, Fei Feng, Rong Yi, Zhiqiang Wang, Shiqi Meng, Gaofeng Zhang, Zhaoxiang State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science and Innovation Chinese Academy of Sciences Hong Kong Department of Computer Science City University of Hong Kong Hong Kong School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China The Department of Neurosurgery Peking University First Hospital Beijing China

Humans and most animals inherently possess a distinctive capacity to continually acquire novel experiences and accumulate worldly knowledge over time. This ability, termed continual learning, is also critical for deep neural networks (DNNs) to adapt to the dynamically evolving world in open environments. However, DNNs notoriously suffer from catastrophic forgetting of previously learned knowledge when trained on sequential tasks. In this work, inspired by the interactive human memory and learning system, we propose a novel biomimetic continual learning framework that integrates semi-parametric memory and the wake-sleep consolidation mechanism. For the first time, our method enables deep neural networks to retain high performance on novel tasks while maintaining prior knowledge in real-world challenging continual learning scenarios, e.g., class-incremental learning on ImageNet1. This study demonstrates that emulating biological intelligence provides a promising path to enable deep neural networks with continual learning capabilities. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A novel underwater image synthesis method based on a pixel-level self-supervised training strategy

A novel underwater image synthesis method based on a pixel-l...

引用

2021 IEEE International Conference on Real-Time Computing and robotics, RCAR 2021

作者： Wu, Zhiheng Wu, Zhengxing Lu, Yue Wang, Jian Yu, Junzhi Institute of Automation Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China State Key Laboratory for Turbulence and Complex Systems Department of Advanced Manufacturing and Robotics BIC-ESAT College of Engineering Peking University Beijing100871 China

ISBN: (纸本)9781665436786

With the rapid development of deep neural networks, underwater vision plays an increasingly important role in the underwater robotic operation. However, the scarce underwater datasets greatly limit the performance of deep learning on underwater visual tasks, further hindering the applications of underwater operation. To solve this problem, we propose an underwater image synthesis method, which can directly convert the natural light image into the synthetic underwater image end-to-end. Particularly, a pixel-level self-supervised training strategy is designed to maximize the structural similarity between the synthesized and real images, through training the real underwater images. Finally, extensive experiments are carried out, and the obtained results demonstrate the effectiveness and superiority of our methods by quantitative and qualitative comparisons. The proposed underwater image synthesis method offers a valuable sight for underwater vision and manipulating control. © 2021 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhanced Wi-Fi indoor positioning real application based on access points optimization ensemble model

Enhanced Wi-Fi indoor positioning real application based on ...

引用

第34届中国控制与决策会议

作者： Zheng Yao Huaiyu Wu Yang Chen Engineering Research Center for Metallurgical Automation and Measurement Technology of Ministry of Education Institute of Robotics and Intelligent Systems Wuhan University of Science and Technology School of Information Science and Engineering Wuhan University of Science and TechnologyWuhan University of Science and Technology

When designing a Wi-Fi indoor positioning system in large,real-world environments,the problem we have to face is that available access points of indoor location scenes are very extensive,and the signal interference is very serious,leading to weak positioning ***,too many access points also increase the computation complexity and the storage size of the fingerprint *** remedy those problems,we propose a new ensemble model consisting of Gaussian Mixture Model(GMM) region classifier and Random Forest feature learner using best-discriminating access points optimization to enhance Wi-Fi indoor positioning real *** GMM classifier is applied to get better regional classification,and for the same area,the Random Forest feature learner is trained to obtain best-discriminating access points *** fully reflect the performance of the proposed method,experiments have been carried out in the real environment of indoor parking lots and the performance of the proposed algorithm was compared with the other three existing access points optimization *** results show that the proposed access points optimization ensemble model successfully enhances Wi-Fi indoor positioning real application of indoor parking lots.

关键词： Wi-Fi positioning AP optimization region classifier feature learner

来源：评论

学校读者我要写书评

暂无评论

BLIP-Adapter: Bridging Vision-Language Models with Adapters for Generalizable Face Anti-spoofing

BLIP-Adapter: Bridging Vision-Language Models with Adapters ...

引用

IEEE International Joint Conference on Biometrics (IJCB)

作者： Bin Zhang Xiangyu Zhu Li Gao Xiaoyu Zhang Zhen Lei Institute of Information Engineering Chinese Academy of Sciences China School of Cyber Security University of Chinese Academy of Sciences China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China China Mobile Financial Technology Co. Ltd. China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences China

ISBN: (数字)9798350364132

ISBN: (纸本)9798350364149

Face anti-spoofing is essential for ensuring the security of facial recognition systems against spoofing attacks. Recent methods have transferred Vision-Language models to face anti-spoofing (e.g., FLIP and CLIPC8), demonstrating that learning perception from supervision in natural language can enhance the model’s detection performance. However, such methods exhibit limited depth in the interaction between images and texts, resulting in poor performance on fine-grained understanding tasks such as face anti-spoofing. Besides, the lack of diversity in image-text pairs for face anti-spoofing further hinders such methods from playing their best. To address these issues, we propose a novel fine-tuning strategy for Vision-Language models in face anti-spoofing. This strategy introduces the Bootstrapping Language-Image Pre-training model (BLIP), known for its novel interaction mechanisms and superior image-text comprehension, to construct a more generalized feature representation for face anti-spoofing. Furthermore, we propose an Adapter module for the text branch to reduce the negative impact of insufficient data diversity and catastrophic forgetting. Extensive experiments conducted on various cross-domain testing benchmarks demonstrate the significant superiority of our method over the state-of-the-art, highlighting its effectiveness and robustness.

关键词： Adaptation models Analytical models Face recognition Biological system modeling Transfer learning Natural languages Benchmark testing Robustness Security Visual perception

来源：评论

学校读者我要写书评

暂无评论

Towards Automated Ultrasound Scanning Using Vision-Based Navigation: From Physician Skill Learning to Robotic Reproduction

Towards Automated Ultrasound Scanning Using Vision-Based Nav...

引用

WRC Symposium on Advanced robotics and automation (WRC SARA)

作者： Mingrui Hao Pengcheng Zhang Chen Chen Shuangyi Wang School of Artificial Intelligence University of Chinese Academy of Sciences 19 Yuquan Road Beijing China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences 95 Zhongguancun East Road Beijing China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Sciences Hong Kong China

Ultrasound scanning is widely employed for disease diagnosis and procedure guidance. However, conventional ultrasound depends on the sonographer’s manual operation, resulting in poor repeatability. Although robot-assisted ultrasound has been extensively studied, it has been a challenge in the field to further automate the examination and make the robotic system more practical for primary use. In this study, we propose a visual navigation method based on the skill learning of the sonographer. The key information about the probe’s movement, including position and angle, was recorded using vision-based methods on 14 cases based on a professional sonographer’s practice. Then, an automatic scanning method based on visual guidance, human-machine collaboration, and path planning was designed using a novel parallel mechanismbased ultrasound robot. The strategy of traversal scanning is a key consideration in facilitating efficient coverage of desired ranges and involves two primary steps: waypoint selection and waypoint planning. To compare the efficiency of different schemes proposed for these two respective stages, a simulation study and an actual running time test of the robot were conducted to assess the weighted coverage, energy, and time consumption. The results demonstrate that the proposed traversal strategy can effectively cover the statistical area formed by the physician’s scanning experience, and the new workflow is promising to be tested in-vivo in our future work.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of Individually Demagnetized Power Converter for Switched Reluctance Motors

引用

IEEE Transactions on Transportation Electrification 2025年第3期11卷 8439-8449页

作者： Liu, Hemiao Chen, Hao Wang, Xing Gorbounov, Yassen Wheeler, Patrick Anuchin, Alecksey Demidova, Galina Korovkin, Nikolay Liudmila, Sakhno Shenzhen Research Institute China University of Mining and Technology Shenzhen515100 China China University of Mining and Technology School of Electrical Engineering Xuzhou221116 China Xinjiang Institute of Engineering Ürümqi830000 China International Joint Research Center of Central and Eastern European Countries on New Energy Electric Vehicle Technology and Equipment Xuzhou221008 China International Cooperation Joint Laboratory of New Energy Power Generation and Electric Vehicles of Jiangsu Province Colleges and Universities Xuzhou221008 China Xuzhou Key Laboratory of New Energy Electric Vehicle Technology and Equipment Xuzhou221008 China Mining Production University of Mining and Geology "St. Ivan Rilski " Department of Automation Sofia1700 Bulgaria The University of Nottingham Power Electronics Machines and Control Group NottinghamNG7 2RD United Kingdom Electric Drives Department Moscow111250 Russia Saint-Petersburg National Research University of Information Technologies Mechanics and Optics Faculty of Control Systems and Robotics Engineer Saint Petersburg197101 Russia Peter the Great St. Petersburg Polytechnic University Institute of Energy Saint Petersburg195251 Russia

Switched reluctance motors (SRMs) are capable of operating at high speeds and high loads. The large back EMF results in the excitation winding current being demagnetized more slowly, which, in turn, reduces the efficiency and output of the motor system. This study proposes a novel individually demagnetization power converter (IDPC) specifically designed for SRMs to effectively use the demagnetization energy through an independent demagnetization circuit. Compared with traditional converters, the IDPC can accept direct current (dc) and high-frequency ac inputs while achieving fast demagnetization and energy recovery. The topology and working principle of the IDPC are analyzed in detail in this article using a three-phase 12/8 SRM as the research object. In addition, the influence of the winding demagnetization voltage on the negative torque during the demagnetization phase was studied, as well as the functional implementation and logic control strategy of the IDPC. Simulation and experimental results confirm the validity of the proposed topology and high-frequency ac drive characteristics, as well as their advantages in terms of efficiency, output capacity, and dynamic performance. © 2015 IEEE.

关键词： Reluctance motors

来源：评论

学校读者我要写书评

暂无评论

Educational robotics as a Teaching Field and Technology Integration: Application of CAD, CAM and 3D printing in structural robot construction 4

Educational Robotics as a Teaching Field and Technology Inte...

引用

4th IEEE World Engineering Education Conference, EDUNINE 2020

作者： De Souza Almeida, Marcus Vinicius Junior, Armano Barros Alves Junior, Ermilton Souza Carvalho Da Silva, Emilly Cristine Costa De Mesquita, Brehme D'Napoli Reis Federal Institute of Maranhão Campus Açailândia Açailândia Brazil Federal Institute of Maranhão Campus Açailândia Laboratory of Automation Robotics and Systems Açailândia Brazil

ISBN: (纸本)9781728166384

Educational robotics has become a field of possibilities for teaching technologies, adding students new challenges that lead to professional practice. Therefore, the Açaímov robotics Team from the Federal institute of Education, Science and Technology of Maranhão - Campus Açailândia, Brazil, consisting of high school students integrated with the technical courses in electromechanics and industrial automation, included the technologies of Computer Aided Design (CAD), Computer Aided Manufacturing (CAM) and 3D Print in the development stages of robot structures. Through a group dynamic among the students to enhance results, the robot's structural specifications were determined based on the characteristics of the Journey to the Center if the Earth Challenge and the arrangement of controller board, sensors and actuators. This work demonstrates the efficiency of this methodology applied to the robotics group by presenting as a result the structure developed for the robot using Fusion 360 (CAD technology), Repetier Host (CAM technology) and 3D printing with biodegradable material. © 2020 IEEE.

关键词： 3D printers

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：