检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Li, Xiaojian Li, Tongtong Ma, Xiang Li, Ling Mo, Hangjie Zheng, Jieyu School of Management Hefei University of Technology Hefei China Hefei University of Technology Key Laboratory of Process Optimization and Intelligent Decision-Making Hefei China

ISBN: (纸本)9781665481090

Points tracking provides target guidance for the basic tasks of robotic surgery, such as autonomous cutting, autonomous suturing, and surgical navigation. Existing invivo tracking algorithms mainly consider region-level tracking, making it difficult to achieve pixel-level accuracy. This paper proposes a multi-keyframe guided tracking method (MKTracking) for robotic surgery, which achieves long-term dynamic tracking of any point on endoscopic images. An incremental keyframe pool building block based on time interval and image appearance is proposed, which contains keyframe basic information, tracking patch and tracking points. Besides, an online multi-keyframe query mechanism is designed to efficiently retrieves the three most similar templates from the keyframe pool based on the number of feature matches within the target patch. This mechanism can realize the identification of target moving out and the re-tracking of target reappearance. Points tracking result is obtained by fusing the optical flow results within the target patch across multiple frames. We evaluated MKTracking using ground-truth data, and the results demonstrated that our approach achieved superior tracking performance. © 2024 IEEE.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Two-stage charge and discharge optimization of battery energy storage systems in microgrids considering battery state of health 8

Two-stage charge and discharge optimization of battery energ...

引用

8th International Conference on Power and Renewable Energy, ICPRE 2023

作者： Zhang, Zenghui Zhou, Kaile Yang, Shanlin Hefei University of Technology Key Laboratory of Process Optimization and Intelligent Decision-Making School of Management Hefei230009 China

ISBN: (纸本)9798350328813

An important figure-of-merit for battery energy storage systems (BESSs) is their battery life, which is measured by the state of health (SOH). In this study, we propose a two-stage model to optimize the charging and discharging process of BESS in an industrial park microgrid (IPM). The first stage is used to optimize the charging and discharging time and the corresponding amount of the charging and discharging energy from the BESS, in which the SOH is considered. Subsequently, all battery packs need to be coordinated to ensure a reasonable BESS operation. In order to prolong the service life of the BESS, the second stage of the model allocates the charging and discharging of all battery packs on the basis of the first stage scheduling results. The proposed loss-calculation method is used to calculate the battery pack loss and then to calculate the SOHs of battery packs. It can be seen from the simulation results that the scheduling results considering the SOH are more realistic. Furthermore, the proposed charging and discharging allocation strategy can effectively coordinate the SOH change of all battery packs without causing a significant increase in the battery pack loss of the battery packs. © 2023 IEEE.

关键词： Battery energy storage system Charging and discharging optimization Industrial park microgrid State of health

来源：评论

学校读者我要写书评

暂无评论

Extreme Risk Measurement of Carbon Market Considering Multifractal Characteristics

引用

Journal of Systems Science & Complexity 2023年第6期36卷 2497-2514页

作者： ZHU Dandan ZHANG Chen PAN Di School of Management Hefei University of TechnologyHefei230009China School of Economics and Management Shanghai University of Political Science and LawShanghai201701China Key Laboratory of Process Optimization and Intelligent Decision-Making Hefei University of TechnologyHefei230009China

Influenced by the global economy,politics,energy and other factors,the price of carbon market fluctuates *** is of great practical significance to explore a suitable measurement method of extreme risk of carbon *** that the return series of carbon market has the characteristics of leptokurtosis,fat tail,skewness and multifractal,and there maybe many extreme risk values in the carbon market,this paper introduces the Skewed-t distribution which can describe the characteristics of leptokurtosis,fat tail and skewness of return series into MSM model which can describe multifractal characteristic of return series to model volatility of carbon *** the basis,based on the extreme value theory,this paper constructs Skewed-t-MSM-EVT model to measure extreme risk of carbon *** paper chooses EUA market as the object to study extreme risk of carbon market,and draws the following conclusions:Skewed-t-MSM-EVT model has significantly higher prediction accuracy for carbon market's Va R than MSM-EVT models under other distributions(including normal distribution,t distribution,GED distribution);Skewed-t-MSM-EVT model is superior to traditional Skewed-t-FIGARCH-EVT and Skewed-t-GARCH-EVT models in predicting carbon market's Va *** research has important practical significance for accurately grasping the risk of carbon market and promoting energy conservation and emission reduction.

关键词： Carbon market extreme value theory multifractal Skewed-t distribution VaR

来源：评论

学校读者我要写书评

暂无评论

Joint optimization of Production and Shipping for Small Orders Considering Less-Than-Container Loading 4th

Joint Optimization of Production and Shipping for Small Orde...

引用

4th International Conference on Resources and Environmental Research, ICRER 2022

作者： Tian, Yajing Wang, Guoqiang Chen, Yingying Luo, He School of Management Hefei University of Technology Hefei China Key Laboratory of Process Optimization & Intelligent Decision-Making Ministry of Education Hefei China

ISBN: (纸本)9783031318078

This paper introduces a joint optimization problem of production and shipping for overseas small orders considering less-than-container loading (LCL) in manufacturing enterprises. The problem consists of finding a production schedule together with a LCL shipping scheme simultaneously to minimize the total cost. An integer programming model is developed, and the genetic algorithm of enhanced elite reservation (SEGA) is used to solve large-sized instances. Besides, the performance of SEGA is compared with the classical genetic algorithm (SGA) and stallion genetic algorithm (stud GA). It is statistically shown that SEGA outperforms other algorithms in finding near-optimal solutions. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Loading

来源：评论

学校读者我要写书评

暂无评论

Multi-sensor Deep Clustering Networks with Joint Learning Strategy for Fault Diagnosis Considering Consensus-specific Constraint

引用

IEEE Sensors Journal 2025年第11期25卷 19921-19936页

作者： Xu, Yihao Lu, Mingfeng Wang, Gang Fang, Fang University of Science and Technology of China School of Management Hefei230026 China Hefei University of Technology School of Management Hefei230009 China Hefei University of Technology School of Management Key Laboratory of Process Optimization and Intelligent Decision-Making of the Ministry of Education Ministry of Education Engineering Research Center for Intelligent Decision-Making and Information System Technologies Hefei230009 China

The deep clustering method has been successfully employed for fault diagnosis due to its remarkable ability to extract deep representation features, particularly in scenarios where labeled data is unavailable. However, the separate learning strategy utilized in deep clustering-based fault diagnosis methods leads to sub-optimal fault diagnosis results, and the consensus representation feature present in multi-sensor industrial data is not fully explored to improve the effectiveness of fault diagnosis. To address the above problems, a novel deep clustering method named Multi-sensor Deep Clustering Networks with joint learning strategy (MsDCN) is proposed for fault diagnosis, which can comprehensively utilize the industrial multi-sensor data and enable joint optimization. First, the Commonality-net uses a sensor-aware attentive encoder (SaAE) to integrate multi-sensor industrial data and extract the consensus representation feature. Second, the Individuality-net is established to extract the specific representation features of multi-sensor industrial data. Finally, a joint multisensor deep clustering learning strategy including consensus-specific constraints is designed to optimize the networks jointly and learn the consensus representation feature with consistent and complementary information. Extensive experiments on the gearbox and bearing datasets validate the proposed MsDCN. The results indicate that the proposed MsDCN can generate a reliable consensus representation feature to achieve better fault diagnosis performance than other benchmark methods. Moreover, its capability to enhance multi-sensor fault diagnosis with unlabeled data highlights its potential for real-world applications. © 2001-2012 IEEE.

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

Agile Earth Observation Satellite Scheduling Algorithm for Emergency Tasks Based on Multiple Strategies

引用

Journal of Systems Science and Systems Engineering 2021年第5期30卷 626-646页

作者： Haiquan Sun Wei Xia Zhilong Wang Xiaoxuan Hu aSchool of Management Hefei University of TechnologyHefeiChina Key Laboratory of Process Optimization and Intelligent Decision-making Ministry of EducationHefeiChina

During the execution of imaging tasks,satellites are often required to observe natural disasters,local wars,and other emergencies,which regularly interferes with the execution of existing ***,rapid satellite scheduling is urgently *** a new generation of three degree-of-freedom(roll,pitch,and yaw)satellites,agile earth observation satellites(AEOSs)have longer variable-pitch visible time windows for ground targets and are capable of observing at any time within the time ***,they are very suitable for emergency ***,current task scheduling models and algorithms ignore the time,storage and energy consumed by ***,these cannot make full use of the AEOS capabilities to optimize the scheduling for emergency *** this study,we present a fine scheduling model and algorithm to realize the AEOS scheduling for emergency ***,a novel time window division method is proposed to convert a variable-pitch visible time window to multiple fixed-pitch visible time ***,a model that considers flexible pitch and roll capabilities is ***,a scheduling algorithm based on merging insertion,direct insertion,shifting insertion,deleting insertion,and reinsertion strategies is proposed to solve conflicting problems *** verify the effectiveness of the algorithm,48 groups of comparative experiments are carried *** experimental results show that the model and algorithm can improve the emergency task completion efficiency of AEOSs and reduce the disturbance measure of the ***,the proposed method can support hybrid satellite resource scheduling for emergency tasks.

关键词： Agile earth observation satellites emergency tasks merging insertion shifting insertion

来源：评论

学校读者我要写书评

暂无评论

3DGS-based Tracking of Articulated Instruments for Instruments-Tissue Interaction Estimation in Robot-assisted Minimally Invasive Surgery

3DGS-based Tracking of Articulated Instruments for Instrumen...

引用

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Li, Xiaojian Shen, Lili Li, Ling Mo, Hangjie Wang, Xin Ma, Xiang Zheng, Jieyu School of Management Hefei University of Technology Hefei China Hefei University of Technology Key Laboratory of Process Optimization and Intelligent Decision-Making Hefei China West China Hospital Sichuan University Sichuan China

ISBN: (纸本)9781665481090

3D information of surgical scene potentially enhances the accuracy of surgical navigation and facilitate the automation of robot-assisted surgery. However, current research seldom considers the relative 3D position between instruments and tissue. In this paper, the instruments-tissue interaction estimation method is proposed to obtain the relative distance between instruments and tissue. The 3D Gaussian representation of instruments is established preoperatively, making the pose of instruments the only parameter to be learned and updated. Based on this, the instrument pose estimation method is proposed, which applies 3DGS (3D Gaussian Splatting) to the instrument Gaussian model to obtain rendered color images, projection masks, and depth maps. These are aligned with the input images, segmented masks and depth from stereo depth estimation to construct the target loss. By backpropagating through the target loss, the optimal instrument pose is obtained. The L1 loss and smooth loss based on TPS (the Thin Plate Spline) are used to complete the depth of tissue occluded by instruments. The instruments-tissue interaction is estimated by the nearest distance between instrument and tissue. The experimental results indicate an average error of 0.94 mm and an accuracy of 90.40% with an error less than 2mm in estimating relative 3D distance between instruments and tissue. © 2024 IEEE.

关键词： Robotic surgery

来源：评论

学校读者我要写书评

暂无评论

Learning Adaptive Mapless Navigation Skills Through Evidential Deep Learning

Learning Adaptive Mapless Navigation Skills Through Evidenti...

引用

2023 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2023

作者： Zhao, Cancan Yan, Yufeng Liu, Xuhao Zhang, Shuai Ouyang, Bo Hefei University of Technology School of Management Hefei China Hefei University of Technology The Key Laboratory of Process Optimization and Intelligent Decision-Making Ministry of Education Hefei China

ISBN: (纸本)9798350327182

Traditional navigation methods tend to design and train navigation skills based on the consideration of multi-scenario applicability and perform well in general scenarios. However, this results in sub-optimal navigation performance in some context-specific scenarios, such as navigating through open or crowded scenarios. While some existing navigation skills can achieve satisfactory performance in context-specific scenarios, e.g., using PID in open scenarios and reinforcement learning-based training methods in crowded scenarios. Most methods currently do without consideration of the integration of navigation skills and contextual understanding. To address this gap, we propose an adaptive mapless navigation method to utilize the optimal capabilities of each skill corresponding to the context-specific scenario. Specifically, we package several existing navigation skills and train a scenario classifier to enable the agent to automatically select the most appropriate skill based on the current scenario. Furthermore, we incorporate evidential deep learning (EDL) to assess classification uncertainty and ensure the safe switching of navigation skills. Our method was tested in both simulated and real scenarios, and the results of the experiments confirmed the effectiveness and generalization of our method. Moreover, the proposed method exhibits notably enhanced, context-sensitive efficiency within a hybrid multi-scenario setting, in comparison to a single navigation skill. © 2023 IEEE.

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

Ensemble Classifier Design Based on Perturbation Binary Salp Swarm Algorithm for Classification

引用

Computer Modeling in Engineering & Sciences 2023年第4期135卷 653-671页

作者： Xuhui Zhu Pingfan Xia Qizhi He Zhiwei Ni Liping Ni School of Management Hefei University of TechnologyHefei230009China School of Statistics Zhejiang Gongshang UniversityHangzhou310018China Key Laboratory of Process Optimization and Intelligent Decision-Making Ministry of EducationHefei230009China Collaborative Innovation Center for Statistical Data Engineering Technology and Application ZhejiangGongshang UniversityHangzhou310018China

Multiple classifier system exhibits strong classification capacity compared with single classifiers,but they require significant computational *** ensemble system aims to attain equivalent or better classification accuracy with fewer ***,current methods fail to identify precise solutions for constructing an ensemble *** this study,we propose an ensemble classifier design technique based on the perturbation binary salp swarm algorithm(ECDPB).Considering that extreme learning machines(ELMs)have rapid learning rates and good generalization ability,they can serve as the basic classifier for creating multiple candidates while using fewer computational ***,we introduce a combined diversity measure by taking the complementarity and accuracy of ELMs into account;it is used to identify the ELMs that have good diversity and low *** addition,we propose an ECDPB with powerful optimizing ability;it is employed to find the optimal subset of *** selected ELMs can then be used to forman ensemble *** on 10 benchmark datasets have been conducted,and the results demonstrate that the proposed ECDPB delivers superior classification capacity when compared with alternative methods.

关键词： Ensemble classifier salp swarmalgorithm diversity measure multiple classifiers system extreme learning machine

来源：评论

学校读者我要写书评

暂无评论

Energy storage resources management:Planning,operation,and business model

引用

Frontiers of Engineering Management 2022年第3期9卷 373-391页

作者： Kaile ZHOU Zenghui ZHANG Lu LIU Shanlin YANG School of Management Hefei University of TechnologyHefei 230009China Key Laboratory of Process Optimization and Intelligent Decision-making of Ministry of Education Hefei University of TechnologyHefei 230009China

With the acceleration of supply-side renewable energy penetration rate and the increasingly diversified and complex demand-side loads,how to maintain the stable,reliable,and efficient operation of the power system has become a challenging issue requiring *** of the feasible solutions is deploying the energy storage system(ESS)to integrate with the energy system to stabilize ***,considering the costs and the input/output characteristics of ESS,both theinitial configuration process and the actual operation process require efficient *** study presents a comprehensive reviewof managing ESs from the perspectives of planning,operation,and business *** of all,in terms of planning and configuration,it is investigated from capacity planning,location planning,as well as capacity and location combined *** process is generally the first step in deploying ***,it explores operation management of ESS from the perspectives of state assessment and operation *** so-called state assessment refers to the assessment of three aspects:The state of charge(SOC),the state of health(SOH),and the remaining useful life(RUL).The operation optimization includes ESS operation strategy optimization and joint operation ***,it discusses the business models of *** business models involve ancillary services and load transfer,while emerging business models include electric vehicle(EV)as energy storage and shared energy storage.

关键词： energy storage system energy storage resources management planning configuration operational management business model

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：