检索结果-内蒙古大学图书馆

Journal of Network Intelligence 2023年第2期8卷 347-363页

作者： Liao, Lyuchao Chen, Ruixiang Shi, Jinjin Zheng, Qi Xiong, Rong Zeng, Jiemao Fujian Provincial Universities Key Laboratory of Industrial Control and Data Analysis Fujian Provincial Universities Engineering Research Center for Intelligent Driving Technology Fujian University of Technology Fuzhou350118 China Fujian Provincial Universities Engineering Research Center for Intelligent Driving Technology Fujian University of Technology Fuzhou350118 China

Object identification is a significant computer vision issue with a growing number of applications in the area of autonomous driving. In order to solve the problem of difficult detection of small objects and dense objects in the target detection algorithm in the autonomous driving scenarios,we propose an object detection method with a hybrid domain attention mechanism. In the model, the Neck network is integrated with a parallel mixed-domain attention mechanism to increase the usable features in the feature map from both channel and spatial aspects. Then, we improve the Spatial Pyramid Pooling (SPP) module with dilated convolutions to limit the loss of important information in the feature map after max pooling, which further optimizes the detector performance. Finally, a fusion approach is proposed to improve the detection layer and enhance the capability of detecting tiny objects. Extensive experiments on the BDD100k dataset show that the proposed model outperforms the state-of-the-art YOLOv5s model with an average accuracy increase of 6.22%(mAP @0.5). © 2023, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Fusion Visual Saliency with Dual-Spectral Saliency of Anomaly Detection for Hyperspectral Herbal Oral Liquid 9

Fusion Visual Saliency with Dual-Spectral Saliency of Anomal...

引用

9th Symposium on Novel Photoelectronic Detection Technology and Applications

作者： Yin, Ating Mao, Jianxu Wang, Yaonan Zeng, Kai Zhang, Hui Li, Yaping College of Electrical and Information Engineering Hunan University Changsha China National Engineering Research Center of Robot Vision Perception and Control Technology Changsha China

ISBN: (纸本)9781510664432

Chinese herbal oral liquid can leach a variety of effective ingredients from herbs and has become a major drug for clinical application. However, it is easy to produce or introduce foreign matters that are very faint in the automatic filling production process. To solve the challenge of low accuracy of faint foreign matter detection, in this paper, we proposed a salient-based anomaly detection method which is fuses visual saliency with dual-spectral saliency (VDS) for the hyperspectral herbal oral liquid. Specifically, we first select the most discriminative bands via the band selection method to generate the pseudo-color map. Subsequently, the histogram-based contrast method is introduced to select the saliency feature map with the largest variance of color features, while fusing the multi-scale gradient features to obtain the preliminary vision-based anomaly detection map. After that, the spectral angles and spectral Euclidean distances are calculated separately based on the oral liquid hyperspectral images to fused into dual-spectral saliency maps. Finally, the dual-spectral saliency map is employed to suppress the background information of the preliminary anomaly detection map. The experimental results show that our proposed method outperforms the state-of-the-art anomaly detection methods, which accurately and quickly achieve the detection of faint foreign matter in the hyperspectral herbal oral liquid. It will accelerate the process of automated filling production lines for oral liquid in the pharmaceutical industry. © 2023 SPIE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Method for Leakage Location Detection of Pneumatic Systems Based on Infrared Thermal Image Evaluation 24

Deep Learning Method for Leakage Location Detection of Pneum...

引用

7th International Conference on Software engineering and Information Management, ICSIM 2024

作者： Chang, Jiaqi Shi, Yan Yang, Liman Niu, Yanxia Nie, Yulong Yang, Zhiguo Li, Lei Zhang, Wenchao School of Automation Science and Electrical Engineering Beihang University China Engineering Training Center Beihang University China Guangzhou Industrial Control Environmental Protection Technology Co. Ltd China

ISBN: (纸本)9798400709197

Pneumatic systems are an essential fluid transmission method in the industrial field, which can achieve the transmission and control of power or signals. Leakage in pneumatic systems is challenging to detect and is a highly harmful fault. Most existing leak detection methods use flow or pressure sensors to detect specific leakage amounts, while leak localization is still in the traditional manual detection, which significantly restricts localization efficiency. This article establishes a deep learning framework-based thermal image localization method for pneumatic system leak detection. Infrared images captured in the pneumatic system were collected, and then a deep-learning localization method based on the YOLO framework was established. Then, the recognition accuracy of this method was calculated. The results indicate that the accuracy has reached 99.5% of mAP_0.5 and 86.27% of mAP_0.5:0.95, indicating that this work is a meaningful study that can apply intelligent computing to engineering. © 2024 ACM.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

MATS-DROP: A HIGHLY SENSITIVE HIGH-THROUGHPUT SINGLE-CELL WHOLE TRANSCRIPTOMIC SEQUENCING METHOD 26

MATS-DROP: A HIGHLY SENSITIVE HIGH-THROUGHPUT SINGLE-CELL WH...

引用

26th International Conference on Miniaturized Systems for Chemistry and Life sciences, MicroTAS 2022

作者： Cao, Wenjian Pan, Yating Mu, Ying Zhu, Qiangyuan Research Center for Analytical Instrumentation College of Control Science and Engineering State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China Research Center for Analytical Instrumentation College of Life Sciences State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China

ISBN: (纸本)9781733419048

The unprecedented single-cell resolution provided by single-cell RNA sequencing (scRNA-seq) powered the progress of biomedical research, leading to revolutionary discoveries. However, current high-throughput scRNA-seq methods are limited by sensitivity and can only detect polyadenylated transcripts. Utilizing polymer-tethered degenerate primer and droplet-based microfluidics, we developed a high-throughput scRNA-seq method with high sensitivity and whole transcriptomic detection capability. © 2022 MicroTAS 2022 - 26th International Conference on Miniaturized Systems for Chemistry and Life sciences. All rights reserved.

关键词： Microfluidics

来源：评论

学校读者我要写书评

暂无评论

Double-layer Descriptors and High-dimensional Search Mechanisms for Partial Point Cloud Registration

Double-layer Descriptors and High-dimensional Search Mechani...

引用

2023 China Automation Congress, CAC 2023

作者： Wang, Zhiyu Fang, Qiu Wang, Yaonan Lu, Hong Ye, Jun National Engineering Research Center for Robot Visual Perception and Control Technology School of Electrical and Information Engineering Hunan University Hunan Changsha410082 China

ISBN: (纸本)9798350303759

Partial point cloud registration is an essential preprocessing technique to generate complete 3D shapes that aim to transform partial scans into a common coordinate system. Existing methods that utilize geometric alignment rarely combine local and global information, which results in many incorrect correspondences. In the paper, a two-layer descriptor and a high-dimension searching approach (DDHSM) are utilized to extract and select the correct correspondences. Firstly, in the first layer, the Fast Point Feature Histogram (FPFH) is used to describe the feature of every point with high-dimension information based on its robustness and fastness. Then a high-dimensional search is considered to extract the initial corresponding set. In the second layer, global information is introduced to find the correct correspondences. For each point pair in the initial corresponding set, the normal angles are compared for all remaining points that satisfy the distance requirement. Finally, the singular value decomposition (SVD) method is implemented to compute the rigid transformation based on the updated corresponding set. Experimental results and comparisons with state-of-the-art methods demonstrate the effectiveness and feasibility of our approach. © 2023 IEEE.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

A Torque Ripple Suppression Method of Sensorless control for Five-phase PMSM Based on High-frequency Signal Injection 7

A Torque Ripple Suppression Method of Sensorless Control for...

引用

7th International Symposium on Autonomous Systems, ISAS 2024

作者： Wang, Bingxue Sun, Guodong Li, Bingjing Liaoning Petrochemical University College of Information and Control Engineering Fushun China Institute of Intelligence Science and Engineering Shenzhen China China Mining Products Safety Approval and Certification Center Beijing China

ISBN: (纸本)9798350363173

To effectively tackle the issue of high-frequency torque ripple in five-phase motors, this paper presents a novel method for suppressing high-frequency torque ripple through sensorless control in five-phase permanent magnet synchronous motors. This innovative approach is specifically designed to address the problem of high-frequency torque ripple and ensure its suppression in the motor. Compared with traditional methods, this strategy chooses to inject two high-frequency voltage signals with the same frequency but different amplitudes simultaneously on the d-axis and q-axis. Through this scheme, the optimal ratio of these two voltage amplitudes is determined to ensure that the electromagnetic torque remains stable during the signal injection process. Through this method, a constant d-axis and q-axis currents can be achieved, thereby minimizing high-frequency torque fluctuations. Through simulation verification, this strategy has shown significant effectiveness in solving the problem of high-frequency torque fluctuations in five phase motors. This optimized high-frequency signal injection method provides a new approach for optimizing the transmission performance of sensorless five phase motor, significantly reducing the vibration and noise generated by the driving system and improving overall operating efficiency. © 2024 IEEE.

关键词： Sensorless control

来源：评论

学校读者我要写书评

暂无评论

Seek-and-Take Games of Heterogeneous Agent Teams With Large Language Model

Seek-and-Take Games of Heterogeneous Agent Teams With Large ...

引用

2024 China Automation Congress, CAC 2024

作者： Li, Haolin Yi, Peng Wei, Dixiao Bai, Wenyan The Department of Control Science and Engineering Tongji University Shanghai201804 China Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai201203 China National Key Laboratory of Autonomous Intelligent Unmanned Systems Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education China Beijing Aerospace Automatic Control Institute Beijing100854 China

ISBN: (纸本)9798350368604

The problem of confrontation games between multi-agent teams has attracted considerable interest, and the question of how to ensure effective coordination of heterogeneous agents in dynamic and adversarial environments remains a significant challenge. In this paper, we present a decision-making methodology for a confrontation game between two teams, which is based on large language models (LLMs). The game is designed as a competitive Seek-and-Take task comprising three distinct robot types: reconnaissance, grabbing, and blocking robots. The LLMs enhance the robot team’s decision-making efficiency, delivering high-level commands that significantly improve coordination and adversarial performance. The game is initially formalized as a partially observable Markov decision process. Subsequently, a systematic construction of the LLM agents is provided, enabling real-time decisions based on the state information of a heterogeneous robot team (HRT). Detailed prompt design and the "Zero-shot-CoT" procedure are provided, and a cue word iteration method with reflections is proposed as a means of enhancing the decision-making efficiency of the LLMs and generating optimal collaboration strategies. Finally, the efficacy of the methodology is validated through experimentation with multiple LLMs in a multi-robot simulation environment. The results demonstrate that LLMs improve the efficiency and adaptability of decision-making in dynamic environments by serving as a core decision module, generating optimal strategies through real-time analysis. © 2024 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Stress-unloading and gas migration improvement mechanism in the soft and hard interbedded coal seam using directional hydraulic flushing technology

引用

International Journal of Mining science and Technology 2023年第9期33卷 1165-1179页

作者： Hao Zhang Yuanping Cheng Cunbao Deng Jingyu Jiang Lei Zhang Xiaoyu Yan Junwei Guo Suifang Wang College of Safety&Emergency Management Engineering Taiyuan University of TechnologyTaiyuan 030024China Datong Coal Mine Group Co. LtdDatong 037037China Key Laboratory of Coal Methane and Fire Control Ministry of EducationChina University of Mining and TechnologyXuzhou 221116China National Engineering Research Center for Coal and Gas Control China University of Mining and TechnologyXuzhou 221116China School of Safety Engineering China University of Mining and TechnologyXuzhou 221116China

To enhance gas drainage in the soft and hard interbedded(SHI)coal seam,it’s necessary to unload the insitu stress and improve its gas migration *** this research,a directional hydraulic flushing(DHF)technology was carried *** stress-unloading and gas migration improvement mechanism was analyzed through numerical simulation,and systematic engineering tests were conducted to verify the gas drainage *** results show that the improvement of gas migration performance in the SHI coal seam is caused by a combined effect of seepage-improving and *** DHF,stress-unloading and plastic failure could be achieved both in the soft coal(SC)sublayer and in the hard coal(HC)***,the gas diffusion capacity improves significantly in the SC sublayer,while the gas seepage capacity improves notably in the HC ***,the stress-unloading and gas migration improvement effect improves with the flushing radius and the thickness of the SC ***,after adopting the DHF technology,the gas drainage effect improved *** borehole number dropped by 49%,the gas drainage ratio increased from 26.0%to 48.2%,and the average coal roadway excavation speed increased from 2.4 to 5.6 m/d.

关键词： Hydraulic flushing Stress-unloading Plastic failure Permeability-increasing Gas migration

来源：评论

学校读者我要写书评

暂无评论

The Group Behavioral Characteristics in a Mean Field Game Model with a Turnpike Effect

引用

Lobachevskii Journal of Mathematics 2025年第1期46卷 341-350页

作者： Trusov, N.V. Federal Research Center ‘‘Computer Science and Control’’ of the Russian Academy of Sciences Moscow 119333 Russian Federation

We describe the agents’ group behavior by the concept of mean field games with a turnpike effect. The problem is formalized by a system of PDEs: a Kolmogorov–Fokker–Planck equation that describes the evolution of the agents’ density distribution, and a Hamilton–Jacobi–Bellman equation that describes the optimal strategy of the agents. The boundary conditions pose at the initial moment of time for a Kolmogorov–Fokker–Planck equation and at the final moment of time for a Hamilton–Jacobi–Bellman equation. The considered system of PDEs is coupled due to the imitation behavior of the agents. To solve the boundary value problem of PDEs, we use a reduction to an extremal problem and present its numerical solution. In numerical results we examine the optimal strategies of the agents considering different behavioral characteristics. © Pleiades Publishing, Ltd. 2025.

关键词： mean field games numerical solution optimal control turnpike effect

来源：评论

学校读者我要写书评

暂无评论

Autonomous landing scene recognition based on transfer learning for drones

引用

Journal of Systems engineering and Electronics 2023年第1期34卷 28-35页

作者： DU Hao WANG Wei WANG Xuerao WANG Yuanda School of Automation Southeast UniversityNanjing 210096China Autonomous Control Robot Laboratory Jiangsu Zhongke Institute of Applied Research on Intelligent Science and TechnologyChangzhou 213164China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science and TechnologyNanjing 210044China

In this paper, we study autonomous landing scene recognition with knowledge transfer for drones. Considering the difficulties in aerial remote sensing, especially that some scenes are extremely similar, or the same scene has different representations in different altitudes, we employ a deep convolutional neural network(CNN) based on knowledge transfer and fine-tuning to solve the problem. Then, LandingScenes-7 dataset is established and divided into seven classes. Moreover, there is still a novelty detection problem in the classifier, and we address this by excluding other landing scenes using the approach of thresholding in the prediction stage. We employ the transfer learning method based on ResNeXt-50 backbone with the adaptive momentum(ADAM) optimization algorithm. We also compare ResNet-50 backbone and the momentum stochastic gradient descent(SGD) optimizer. Experiment results show that ResNeXt-50 based on the ADAM optimization algorithm has better performance. With a pre-trained model and fine-tuning, it can achieve 97.845 0% top-1 accuracy on the LandingScenes-7dataset, paving the way for drones to autonomously learn landing scenes.

关键词： landing scene recognition convolutional neural network(CNN) transfer learning remote sensing image

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：