检索结果-内蒙古大学图书馆

MBNN: A Multi-Branch Neural Network Capable of Utilizing industrial Sample Unbalance for Fast Inference

IEEE SENSORS JOURNAL 2021年第2期21卷 1809-1819页

作者： Wang, Qizhao Wang, Kai Li, Qing Yang, Zuye Jin, Guangshu Wang, Hong Chinese Acad Sci Key Lab Networked Control Syst Shenyang 110169 Peoples R China Chinese Acad Sci Shenyang Inst Automat Shenyang 110169 Peoples R China Chinese Acad Sci Inst Robot & Intelligent Mfg Shenyang 110169 Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Microcyber Corp Ind Cloud Div Res & Dev Prod Direct Cloud Comp Big Data & Artif Shenyang 110179 Peoples R China Microcyber Corp Prod Div Ind Commun Prod & Instruments Shenyang 110179 Peoples R China

Deep neural networks has been widely used in industrial equipment fault diagnosis. The accuracy of deep neural network is usually proportional to the complexity, but the high inference delay and energy consumption caused by the complex model make it difficult to be applied in the industrial environment of real-time demand. At the same time, in the diagnosis of industrial equipment, different categories of samples have unbalanced characteristics in terms of number, difficulty of identification, and demand of identification. In order to solve this problem, this paper designs Multi-Branch Neural Network (MBNN), which is a new type neural network architecture that can use the unbalance of sample categories in industrial equipment fault diagnosis for fast inference. MBNN has multiple sub-networks with different complexity, and each branch is responsible for processing different categories of samples. Categories with large numbers, easy to process, and high demand of identification are processed through simple branches, such as normal samples. Categories with small numbers, difficult to identification, and low demand of identification are processed through complex branches, such as potential failure samples. The feasibility of MBNN has been verified on motor bearing fault diagnosis and gearbox fault diagnosis, and its performance has been evaluated on multiple computing platforms. The results show that MBNN can greatly improve the inference speed while ensuring the recognition accuracy, especially on resource-constrained platforms.

关键词： Fault diagnosis Neural networks Complexity theory Computational modeling Sensors Optimization Real-time systems Neural network architecture fault diagnosis fast inference unbalance sample

来源：评论

学校读者我要写书评

暂无评论

Smaller and Faster robotic Grasp Detection Model via Knowledge Distillation and Unequal Feature Encoding

引用

IEEE robotICS AND AUTOMATION LETTERS 2024年第8期9卷 7206-7213页

作者： Nie, Hong Zhao, Zhou Chen, Lu Lu, Zhenyu Li, Zhuomao Yang, Jing Shanxi Univ Inst Big Data Sci & Ind Sch Comp & Informat Technol Taiyuan 030006 Peoples R China Shanxi Univ Minist Educ Key Lab Computat Intelligence & Chinese Informat P Taiyuan 030006 Peoples R China Cent China Normal Univ Sch Comp Sci Wuhan 430079 Peoples R China Hubei Engn Res Ctr Intelligent Detect & Identifica Wuhan 430079 Peoples R China Univ West England Bristol Robot Lab Bristol BS16 1QY England Shanxi Univ Sch Automat & Software Engn Taiyuan 030031 Peoples R China

In order to achieve higher accuracy, the complexity of grasp detection network increases accordingly with complicated model structures and tremendous parameters. Although various light-weight strategies are adopted, directly designing the compact network can be sub-optimal and difficult to strike the balance between accuracy and model size. To solve this problem, we explore a more efficient grasp detection model from two aspects: elaborately designing a light-weight network and performing knowledge distillation on the designed network. Specifically, based on the designed light-weight backbone, the features from RGB and D images with unequal effective grasping information rates are fully utilized and the information compensation strategies are adopted to make the model small enough while maintaining its accuracy. Then, the grasping features contained in the large teacher model are adaptively and effectively learned by our proposed method via knowledge distillation. Experimental results indicate that the proposed method is able to achieve comparable performance (98.9%, 93.1%, 82.3%, and 90.0% on Cornell, Jacquard, GraspNet, and MultiObj datasets, respectively) with more complicate models while reducing the parameters from MBs to KBs. Real-world robotic grasping experiment in an embedded AI computing device also prove the effectiveness of this approach.

关键词： robotic grasping light-weight modelling knowledge distillation generative network attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Crack formation of camshaft castings: Hot tearing susceptibility and root causes

引用

ENGINEERING FAILURE ANALYSIS 2023年第1期147卷

作者： Zhu, Yankang Zhou, Kangkang Xu, Gangqiang Xu, Cangsu Li, Xiaolu Li, Yuntang Wang, Bingqing Oppong, Francis China Jiliang Univ Coll Mech & Elect Engn Key Lab Intelligent Mfg Qual Big Data Tracing & An Hangzhou 310018 Peoples R China Zhejiang Boxing Ind & Trade Co Ltd Ctr Enterprise Technol Jinhua 321016 Peoples R China Zhejiang Univ Coll Energy Engn State Key Lab Clean Energy Utilizat Hangzhou 310027 Peoples R China

As a widely used cyclical motion component, the camshaft plays a key role in the accuracy and stability of the whole machine. Micro hot cracks in the camshaft casting process are an important cause of failure in subsequent machining and operation. In this paper, the hot tearing suscepti-bility of the camshaft in the casting process was studied using the alloy composition (carbon equivalent and Mn/S ratio) and mold preheating temperature. The formation mechanism of the hot tear source was analyzed through the microscopic morphology of the fracture-sensitive cross-section. Using the improved Clyne-Davies model and the newly proposed hot tearing suscepti-bility (HTS) model, the results show that as the carbon equivalent and Mn/S ratio increase, the hot tearing susceptibility of the camshaft first decreases and then increases. The hot tearing tendency of the casting can be reduced by appropriately increasing the mold preheating tem-perature. The microscopic morphology indicates that the initiation and propagation of the crack source are caused by the excessively serious non-equilibrium solidification of the camshaft metal fluid. Finally, potential countermeasures are proposed to decrease micro hot cracks in camshaft castings, including the adjustment of alloy composition, optimization of casting process param-eters, and improvement of system solidification conditions.

关键词： Camshaft Casting process Crack formation Hot tearing susceptibility (HTS) Clyne -Davies model

来源：评论

学校读者我要写书评

暂无评论

Weight change across adulthood and accelerated biological aging in middle-aged and older adults

引用

AMERICAN JOURNAL OF CLINICAL NUTRITION 2023年第1期117卷 1-11页

作者： Cao, Xingqi Yang, Gan Li, Xueqin Fu, Jinjing Mohedaner, Mayila Danzengzhuoga Jorgensen, Terese Sara Hoj Agogo, George O. Wang, Liang Zhang, Xuehong Zhang, Tao Han, Liyuan Gao, Xiang Liu, Zuyun Zhejiang Univ Sch Med Affiliated Hosp 2 Ctr Clin Big Data & Analyt Hangzhou Zhejiang Peoples R China Zhejiang Univ Sch Med Dept Big Data Hlth SciSch Publ Hlth Key Lab Intelligent Prevent Med Zhejiang Prov Hangzhou Zhejiang Peoples R China Univ Copenhagen Fac Hlth & Med Sci Sect Social Med Dept Publ Hlth Copenhagen Denmark StatsDecide Analyt & Consulting Ltd Nakuru Kenya Baylor Univ Dept Publ Hlth Robbins Coll Human Hlth & Sci Waco TX 76798 USA Brigham & Womens Hosp Dept Med Channing Div Network Med 75 Francis St Boston MA 02115 USA Harvard Med Sch Boston MA 02115 USA Shandong Univ Cheeloo Coll Med Sch Publ Hlth Dept Biostat Jinan Shandong Peoples R China Univ Chinese Acad Sci Ningbo Inst Life & Hlth Ind Dept Global Hlth Ningbo Zhejiang Peoples R China Univ Chinese Acad Sci Hwa Mei Hosp Ningbo Zhejiang Peoples R China Fudan Univ Sch Publ Hlth Dept Nutr & Food Hyg Shanghai Peoples R China

Background: Little is known regarding the association between weight change and accelerated aging. Objectives: This study aimed to estimate the influence of weight change across adulthood on biological aging acceleration in middle-aged and older adults in the United States. Methods: We used data of 5553 adults (40-84 y) from the National Health and Nutrition Examination Survey 1999-2010. Weight change patterns (i.e., stable normal, maximal overweight, obese to nonobese, nonobese to obese, and stable obese) and absolute weight change groups across adulthood (i.e., from young to middle adulthood, young to late adulthood, and middle to late adulthood) were defined. A biological aging measure (i.e., phenotypic age acceleration [PhenoAgeAccel]) at late adulthood was calculated. Survey analysis procedures with the survey weights were performed. Results: Across adulthood, maximal overweight, nonobese to obese, and stable obesity were consistently associated with higher PhenoAgeAccel. For instance, from young to middle adulthood, compared with participants who had stable normal weight, participants experiencing maximal overweight, moving from the nonobese to obese, and maintaining obesity had 1.71 (standard error [SE], 0.21;P < 0.001), 3.62 (SE, 0.28;P < 0.001), and 6.61 (SE, 0.58;P < 0.001) higher PhenoAgeAccel values, respectively. From young to middle adulthood, relative to absolute weight loss or gain of <2.5 kg, weight loss of similar to 2.5 kg was marginally associated with lower PhenoAgeAccel (P = 0.054), whereas an obese to nonobese pattern from middle to late adulthood was associated with higher PhenoAgeAccel (P < 0.001). Conclusions: Maximal overweight, nonobese to obese, and stable obesity across adulthood, as well as an obese to nonobese pattern from middle to late adulthood, were associated with accelerated biological aging. In contrast, weight loss from young to middle adulthood was associated with decelerated biological aging. The findings highlight the poten

关键词： biological aging body mass index body weight changes obesity phenotypic age acceleration

来源：评论

学校读者我要写书评

暂无评论

MedShapeNet - a large-scale dataset of 3D medical shapes for computer vision

引用

BIOMEDICAL ENGINEERING-BIOMEDIZINISCHE TECHNIK 2025年第1期70卷 71-90页

作者： Li, Jianning Zhou, Zongwei Yang, Jiancheng Pepe, Antonio Gsaxner, Christina Luijten, Gijs Qu, Chongyu Zhang, Tiezheng Chen, Xiaoxi Li, Wenxuan Wodzinski, Marek Friedrich, Paul Xie, Kangxian Jin, Yuan Ambigapathy, Narmada Nasca, Enrico Solak, Naida Melito, Gian Marco Viet Duc Vu Memon, Afaque R. Schlachta, Christopher De Ribaupierre, Sandrine Patel, Rajnikant Eagleson, Roy Chen, Xiaojun Maechler, Heinrich Kirschke, Jan Stefan de la Rosa, Ezequiel Christ, Patrick Ferdinand Li, Hongwei Bran Ellis, David G. Aizenberg, Michele R. Gatidis, Sergios Kuestner, Thomas Shusharina, Nadya Heller, Nicholas Andrearczyk, Vincent Depeursinge, Adrien Hatt, Mathieu Sekuboyina, Anjany Loeffler, Maximilian T. Liebl, Hans Dorent, Reuben Vercauteren, Tom Shapey, Jonathan Kujawa, Aaron Cornelissen, Stefan Langenhuizen, Patrick Ben-Hamadou, Achraf Rekik, Ahmed Pujades, Sergi Boyer, Edmond Bolelli, Federico Grana, Costantino Lumetti, Luca Salehi, Hamidreza Ma, Jun Zhang, Yao Gharleghi, Ramtin Beier, Susann Sowmya, Arcot Garza-Villarreal, Eduardo A. Balducci, Thania Angeles-Valdez, Diego Souza, Roberto Rittner, Leticia Frayne, Richard Ji, Yuanfeng Ferrari, Vincenzo Chatterjee, Soumick Dubost, Florian Schreiber, Stefanie Mattern, Hendrik Speck, Oliver Haehn, Daniel John, Christoph Nuernberger, Andreas Pedrosa, Joo Ferreira, Carlos Aresta, Guilherme Cunha, Antonio Campilho, Aurelio Suter, Yannick Garcia, Jose Lalande, Alain Vandenbossche, Vicky Van Oevelen, Aline Duquesne, Kate Mekhzoum, Hamza Vandemeulebroucke, Jef Audenaert, Emmanuel Krebs, Claudia van Leeuwen, Timo Vereecke, Evie Heidemeyer, Hauke Roehrig, Rainer Hoelzle, Frank Badeli, Vahid Krieger, Kathrin Gunzer, Matthias Chen, Jianxu van Meegdenburg, Timo Dada, Amin Balzer, Miriam Fragemann, Jana Jonske, Frederic Rempe, Moritz Malorodov, Stanislav Bahnsen, Fin H. Seibold, Constantin Jaus, Alexander Marinov, Zdravko Jaeger, Paul F. Stiefelhagen, Rainer Santos, Ana Sofia Lindo, Mariana Ferreira, Andre Alves, Victor Kamp, Michael Abourayya, Amr Nensa, Felix Hoerst, Fabian Brehmer, Alexan Univ Hosp Essen AoR Inst Artificial Intelligence Med IKIM Girardetstr 2 D-45131 Essen Germany Graz Univ Technol Inst Comp Graph & Vis ICG Inffeldgasse 16c A-8010 Graz Austria Comp Algorithms Med Lab Cafe Graz Austria Univ Med Essen AoR Canc Res Ctr Cologne Essen CCCE Hufelandstr 55 D-45147 Essen Germany Univ Med Essen Univ Hosp Essen Ctr Virtual & Extended Real Med ZvRM Hufelandstr 55 D-45147 Essen Germany Johns Hopkins Univ Dept Comp Sci Baltimore MD 21218 USA Swiss Fed Inst Technol Lausanne EPFL Comp Vis Lab Lausanne Switzerland Univ Hosp RWTH Aachen Dept Oral & Maxillofacial Surg Aachen Germany Shanghai Jiao Tong Univ Renji Hosp Sch Med Dept Radiol Shanghai Peoples R China AGH Univ Sci & Technol Dept Measurement & Elect Krakow Poland Univ Appl Sci Western Switzerland HES SO Valais Inst Informat Syst Sierre Switzerland Univ Basel Dept Biomed Engn Ctr Med Image Anal & Nav CIAN Allschwil Switzerland Univ Buffalo Dept Comp Sci & Engn Buffalo NY 14260 USA ZhejiangLab Res Ctr Connected Healthcare Big Data Hangzhou Zhejiang Peoples R China Graz Univ Technol Inst Mech Graz Austria Justus Liebig Univ Giessen Univ Hosp Giessen Dept Diagnost & Intervent Radiol Giessen Germany Mehran Univ Engn & Technol Dept Mech Engn Jamshoro Sindh Pakistan Shanghai Jiao Tong Univ Inst Med Robot Shanghai Peoples R China Univ Hosp Canadian Surg Technol & Adv Robot CSTAR London ON Canada Shanghai Jiao Tong Univ Inst Biomed Mfg & Life Qual Engn Sch Mech Engn State Key Lab Mech Syst & Vibrat Shanghai Peoples R China Med Univ Graz Dept Cardiac Surg Graz Austria Techn Univ Munchen Univ Klinikum Geschaftsfuhrender Oberarzt Abt Intervent & Diagn Munich Germany Icometrix Leuven Belgium Tech Univ Munich Dept Informat Garching Germany Univ Zurich Dept Quantitat Biomed Zurich Switzerland Tech Univ Dortmund Fac Stat Dortmund Germany Shanghai Jiao Tong Univ Inst Med Robot Shanghai Peoples R China Univ Techn Univ Munchen Geschaftsfuhrender Oberarzt Abt Interv

Objectives: The shape is commonly used to describe the objects. State-of-the-art algorithms in medical imaging are predominantly diverging from computer vision, where voxel grids, meshes, point clouds, and implicit surface models are used. This is seen from the growing popularity of ShapeNet (51,300 models) and Princeton ModelNet (127,915 models). However, a large collection of anatomical shapes (e.g., bones, organs, vessels) and 3D models of surgical instruments is missing. Methods: We present MedShapeNet to translate data-driven vision algorithms to medical applications and to adapt state-of-the-art vision algorithms to medical problems. As a unique feature, we directly model the majority of shapes on the imaging data of real patients. We present use cases in classifying brain tumors, skull reconstructions, multi-class anatomy completion, education, and 3D printing. Results: By now, MedShapeNet includes 23 datasets with more than 100,000 shapes that are paired with annotations (ground truth). Our data is freely accessible via a web interface and a Python application programming interface and can be used for discriminative, reconstructive, and variational benchmarks as well as various applications in virtual, augmented, or mixed reality, and 3D printing. Conclusions: MedShapeNet contains medical shapes from anatomy and surgical instruments and will continue to collect data for benchmarks and applications. The project page is: https://***/.

关键词： 3D medical shapes benchmark anatomy education shapeomics augmented reality virtual reality

来源：评论

学校读者我要写书评

暂无评论

Tracking Object's Pose via Dynamic Tactile Interaction

引用

INTERNATIONAL JOURNAL OF HUMANOID robotICS 2024年第3期21卷

作者： Lin, Qiguang Yan, Chaojie Li, Qiang Ling, Yonggen Lee, Wangwei Zheng, Yu Wan, Zhaoliang Huang, Bidan Liu, Xiaofeng Hohai Univ Coll IoT Engn Jiangsu Key Lab Special Robot Technol Changzhou 213022 Jiangsu Peoples R China Zhejiang Univ Inst Cyber Syst & Control State Key Lab Ind Control & Technol R China Hangzhou Peoples R China Shenzhen Technol Univ Coll Big Data & Internet Shenzhen 518118 Peoples R China Tencent Robot X Shenzhen Peoples R China Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou Peoples R China

It is a challenging task to localize and track an in-hand object in robotic domain. Researchers were mainly using the vision as major modality for extracting object's pose. The vision approaches are fragile when the object is occluded by the robotic arm and hand. To this end, we propose a tactile-based DTI-Tracker (tracking object's pose via Dynamic Tactile Interaction) approach and formalize the object's tracking as a filter problem. An Extended Kalman Filter (EKF) is used to estimate the in-hand object pose exploiting the high spatial resolution tactile feedback. Given the initial estimation error, the proposed approach rapidly converges the estimation result to the real pose and the statistic evaluation shows the robustness of the proposed approach. We evaluate this method in physics simulation and real multi-fingered grasping setup while the object is static and movable. The proposed method is a potential tool to foster future research on dexterous manipulation using multifingered robotic hand.

关键词： Tactile perception robotic grasping extended Kalman filter

来源：评论

学校读者我要写书评

暂无评论

DHESN: A deep hierarchical echo state network approach for algal bloom prediction

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年 239卷

作者： Hu, Bo Zhang, Huiyan Wang, Xiaoyi Wang, Li Xu, Jiping Sun, Qian Zhao, Zhiyao Zhang, Lei Beijing Technol & Business Univ Sch Artificial Intelligence Beijing 100048 Peoples R China Beijing Inst Fash Technol Beijing 100029 Peoples R China Nankai Univ Inst Robot & Automat Informat Syst IRAIS Tianjin 300350 Peoples R China Nankai Univ Tianjin Key Lab Intelligent Robot tjKLIR Tianjin 300350 Peoples R China Beijing Technol & Business Univ China Light Ind Key Lab Ind Internet & Big Data Beijing 100048 Peoples R China Daxing Water Environm Monitoring Ctr Beijing 102600 Peoples R China

A deep hierarchical echo state network (DHESN) is designed for rectifying the shortcomings of the shallow coupled structure with less reservoir dynamics. This design is with reference to algal bloom which is a complex ecological phenomenon. Accurate prediction of algal bloom can reduce the environmental impact and economic loss. Since the formation of algal bloom has chaotic characteristics, the ESN has been employed to realize its prediction function. First, the candidate variables with strong causal relationship have been screened by transfer entropy, and the redundant variables is eliminated. Then, a hierarchical reservoir structure is established that is inspired by the hierarchical characteristics from the brain. The hierarchical reservoir has realized the connection between the representative nodes of each subreservoir, and improved the information processing ability of the reservoir. Finally, the pruning and compression of the output weights have been realized by the elastic regularization method, which improves the robustness of the prediction model. The simulation results demonstrate that the DHESN has appreciable prediction accuracy in both the chaotic and the public algal bloom datasets. The DHESN contains richer dynamic characteristics, and can realize the self-organization of the network structure. It provides a novel idea to realize the prediction model of algal bloom with a high accuracy and low complexity.

关键词： Algal bloom prediction Deep echo state network Hierarchical reservoir Elastic regularization

来源：评论

学校读者我要写书评

暂无评论

Framework of rod-like crops sorting based on multi-object oriented detection and analysis

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2024年 216卷

作者： Zhou, Shuo Zhong, Ming Chai, Xiujuan Zhang, Ning Zhang, Yubin Sun, Qixin Sun, Tan Chinese Acad Agr Sci Agr Informat Inst Beijing 100081 Peoples R China Minist Agr & Rural Affairs Key Lab Agr Big Data Beijing 100081 Peoples R China Harbin Inst Technol Ind Res Inst Robot & Intelligent Equipment Weihai 264209 Peoples R China Zibo Inst Digital Agr & Rural Res Zibo 255000 Peoples R China

Quality grading and sorting are crucial post-harvest procedures to increase the market value of crops. To reduce the over-dependence on manual work for these tasks, automated sorting methods have been studied. However, we find existing research focuses mainly on round-like fruits and vegetables, and most machines can only grade one object at a time in their vision pipeline. To address these limitations, this paper proposes a comprehensive framework specifically for detecting and analyzing rod-like crops based on multi-object oriented detection. Zizania shoots are primarily used to validate our methods. To implement the deep learning models, an efficient oriented bounding box label software called OBBlabel is developed, and several large-scale image datasets are constructed. Both of the software and datasets are open-sourced for the community. Based on YOLOv8 architecture, the proposed YOLO-OBB model predicts oriented bounding boxes to extract all rod-like targets in image with 0.903 mAP@0.5. A multi-label recognition model YOLO-MLD then conducts quality grading and posture perception on individual target with 93.4% mean accuracy. Thus, precise position and quality information for all objects can be obtained in near real-time for subsequent suction cup-based sorting operations. Furthermore, according to the framework, this paper designs and manufactures a prototype sorting machine with edge intelligence for rod-like crops.

关键词： Rod-like crops Quality grading Sorting machine Oriented object detection Multi-label recognition

来源：评论

学校读者我要写书评

暂无评论

Novel intelligent grazing strategy based on remote sensing, herd perception and UAVs monitoring

引用

COMPUTERS AND ELECTRONICS IN AGRICULTURE 2024年 219卷

作者： Chen, Tao Zheng, Han Chen, Jian Zhang, Zichao Huang, Xinhang China Agr Univ Coll Engn Beijing 100083 Peoples R China Minist Agr & Rural Affairs Key Lab Smart Agr Technol Trop South China Guangzhou 510642 Peoples R China Zhejiang Univ Coll Biosyst Engn & Food Sci Key Lab Intelligent Equipment & Robot Agr Zhejiang Hangzhou 310058 Peoples R China Beihang Univ State Key Lab Virtual Real Technol & Syst Beijing 100191 Peoples R China MNR Key Lab Spatial temporal Big Data Anal & Applicat Shanghai 200063 Peoples R China Minist Agr & Rural Affairs Key Lab Smart Agr Technol Yangtze River Delta Nanjing 210044 Peoples R China Zhejiang Univ State Key Lab Clean Energy Utilizat Hangzhou 310013 Peoples R China

intelligent grazing is a new livestock husbandry development mode based on obtaining the multi-source information, ecological balance is the goal. This paper focuses on intelligent grazing, reviews from grass remote sensing and aerial seeding, unmanned aerial vehicles (UAVs) monitoring and intelligent grazing robot, and summarizing the development of intelligent grazing elements at this stage, exploring the new development direction of automatic grazing management with grazing robot at this stage, and proposes a novel intelligent grazing strategy based on remote sensing, herd perception and UAVs monitoring. Furthermore, focusing on the intelligent grazing needs, the digital twin pasture is built in this paper mainly serves the technical verification and data acquisition based on machine vision, simulating the behavior of the herd during grazing.

关键词： intelligent grazing Remote sensing Herd perception UAVs

来源：评论

学校读者我要写书评

暂无评论

Exploring competitiveness of taxis to ride-hailing services from a multidimensional spatio-temporal perspective: A case study in Beijing, China

引用

JOURNAL OF TRANSPORT GEOGRAPHY 2024年 118卷

作者： Luo, Yihao Huang, Ailing He, Zhengbing Zeng, Jiaqi Wang, Dianhai Zhejiang Univ Polytech Inst B820 Anzhong BldgZijingang Campus866 Yuhangtang Hangzhou 310058 Peoples R China Zhejiang Univ Inst Intelligent Transportat Syst Hangzhou 310058 Peoples R China Beijing Jiaotong Univ Key Lab Transport Ind Big Data Applicat Technol Co Minist Transport Beijing 100044 Peoples R China MIT Senseable City Lab 77 Massachusetts Ave9-216 Cambridge MA 02139 USA Zhejiang Univ Inst Intelligent Transportat Syst Coll Civil Engn & Architecture Hangzhou 310058 Peoples R China Beijing Jiaotong Univ Sch Traff & Transportat Traff Syst Engn Shangyuancun 3 Beijing 100044 Peoples R China Zhejiang Univ Coll Civil Engn & Architecture B820 Anzhong BldgZijingang Campus866 Yuhangtang Hangzhou 310058 Peoples R China Zhejiang Univ Coll Civil Engn & Architecture B720 Anzhong BldgZijingang Campus866 Yuhangtang Hangzhou 310058 Peoples R China

As the sharing economy expands in China, the emergence of ride-hailing services has diminished the market share of the taxi industry. As a regulated and publicly convenient service with a dedicated customer base, traditional taxi industry needs to improve its own competitiveness and maintain its market share. However, the specific circumstances under which taxis can gain a competitive edge over ride-hailing services are not wellunderstood. Aiming to uncover the competitive potential of taxis in the ride-source market, this study proposes a methodology to explore the Competition and Cooperation Relationship (CCR) between taxis and ridehailing services on a multidimensional spatio-temporal scale. By taking Beijing, China as a case study, we first compare different impacts of Points of Interest (POI) on the traffic volume of taxis/ride-hailing services through Geographically and Temporally Weighted Regression (GTWR) models, and explore the corresponding times and locations where taxis/ride-hailing services are more likely to attract passengers. Based on the findings that there are strong correlations between traffic volume and spatio-temporal conditions, we establish the CompetitionCooperation index (CCI) as a quantitative measure to characterize the CCR and then analyze the spatiotemporal distribution of CCI to identify the times and locations where taxis hold advantages in cooperative or competitive relationship relative to ride-hailing services. Furthermore, we investigate the underlying reasons for these patterns, discovering that CCI has a close connection with land use. The results of our analysis show that taxis exhibit competitive advantages over ride-hailing services under some specific circumstances and can further enhance their competitiveness by proposed targeted measures. The findings of this study provide valuable insights for both industries in formulating growth strategies and for governmental agencies in setting policies.

关键词： Taxis Ride-hailing services Competition Cooperation GTWR Traffic volume

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：