检索结果-内蒙古大学图书馆

data-driven analysis of the Causal Chain of Waterborne Traffic Accidents: A Hybrid Framework Based on an Improved Human Factors analysis and Classification System with a Bayesian Network

引用

JOURNAL OF MARINE SCIENCE AND ENGINEERING 2025年第3期13卷

作者： Yin, Xiangyu Yan, Yan Wang, Jiahao Zhao, Hongzhuan Wu, Qingyan Xu, Qi China Waterborne Transport Res Inst Beijing 100088 Peoples R China Guilin Univ Elect Technol Guangxi Key Lab ITS Guilin 541000 Peoples R China Guilin Univ Elect Technol Sch Architecture & Transportat Engn Guilin 541004 Peoples R China Guilin Univ Elect Technol Dept Infrastruct Guilin 541004 Peoples R China

In the context of economic globalization, waterborne transportation plays an important role in international trade and logistics. However, waterborne traffic accidents pose a severe threat to life, property safety, and the environment. To gain a deeper understanding of the causal mechanisms behind waterborne traffic accidents, we conducted a data-driven analysis of the causal chain of waterborne traffic accidents. By constructing a hybrid framework integrating an improved HFACS (Human Factors analysis and Classification System) with a Bayesian network model, we conducted a multi-dimensional analysis of accident causes. The constructed model was quantitatively analyzed by applying genie software to the accident samples collected from the China MSA. The results indicate that there are 12, 3, 6, 2, 4, and 7 causal chains leading to collisions, contact, fires/explosions, windstorm accidents, sinking, and other types of accidents, respectively. These research results can serve as a reference for the enhancement of the safety of waterborne transportation.

关键词： waterborne traffic accidents causal chain analysis HFACS Bayesian network data-driven analysis

来源：评论

学校读者我要写书评

暂无评论

Proposal for a Novel Classification of Patients With Enlarged Ventricles and Cognitive Impairment Based on data-driven analysis of Neuroimaging Results in Patients With Psychiatric Disorders

引用

NEUROPSYCHOPHARMACOLOGY REPORTS 2025年第1期45卷 e70010页

作者： Yasuda, Yuka Ito, Satsuki Matsumoto, Junya Okada, Naohiro Onitsuka, Toshiaki Ikeda, Masashi Kushima, Itaru Sumiyoshi, Chika Fukunaga, Masaki Nemoto, Kiyotaka Miura, Kenichiro Hashimoto, Naoki Ohi, Kazutaka Takahashi, Tsutomu Sasabayashi, Daiki Koeda, Michihiko Yamamori, Hidenaga Fujimoto, Michiko Takano, Harumasa Hasegawa, Naomi Narita, Hisashi Yamamoto, Maeri Tha, Khin Khin Kikuchi, Masataka Kamishikiryo, Toshiharu Itai, Eri Okubo, Yoshiro Tateno, Amane Nakamura, Motoaki Kubota, Manabu Igarashi, Hiroyuki Hirano, Yoji Okada, Go Miyata, Jun Numata, Shusuke Abe, Osamu Yoshimura, Reiji Nakagawa, Shin Yamasue, Hidenori Ozaki, Norio Kasai, Kiyoto Hashimoto, Ryota Med Corp Foster Life Grow Brilliant Mental Clin Osaka Japan Natl Ctr Neurol & Psychiat Natl Inst Mental Hlth Dept Pathol Mental Dis Kodaira Tokyo Japan Univ Tokyo Grad Sch Med Dept Neuropsychiat Bunkyo Ku Tokyo Japan Univ Tokyo Int Res Ctr Neurointelligence WPI IRCN Inst Adv Study UTIAS Tokyo Japan NHO Sakakibara Natl Hosp Tsu Mie Japan Nagoya Univ Grad Sch Med Dept Psychiat Nagoya Aichi Japan Nagoya Univ Hosp Med Genom Ctr Nagoya Aichi Japan Fukushima Univ Fac Human Dev & Culture Fukushima Japan Natl Ctr Neurol & Psychiat Natl Inst Mental Hlth Dept Prevent Intervent Psychiat Disorders Kodaira Tokyo Japan Natl Inst Physiol Sci Sect Brain Funct Informat Okazaki Aichi Japan Grad Univ Adv Studies Physiol Sci Program Okazaki Aichi Japan Univ Tsukuba Inst Med Dept Psychiat Tsukuba Ibaraki Japan Hokkaido Univ Grad Sch Med Dept Psychiat Sapporo Hokkaido Japan Gifu Univ Grad Sch Med Dept Psychiat Gifu Japan Kanazawa Med Univ Dept Gen Internal Med Uchinada Ishikawa Japan Univ Toyama Grad Sch Med & Pharmaceut Sci Dept Neuropsychiat Toyama Japan Univ Toyama Res Ctr Idling Brain Sci Toyama Japan Tama Nagayama Hosp Nippon Med Sch Dept Neuropsychiat Tama Tokyo Japan Nippon Med Sch Dept Neuropsychiat Grad Sch Med Bunkyo Ku Tokyo Japan Osaka Univ Grad Sch Med Dept Psychiat Suita Osaka Japan Japan Community Hlth Care Org Osaka Hosp Osaka Japan Natl Ctr Neurol & Psychiat Dept Clin Neuroimaging Integrat Brain Imaging Ctr Kodaira Tokyo Japan Hokkaido Univ Hosp Dept Psychiat & Neurol Sapporo Hokkaido Japan Hokkaido Univ Fac Med Global Ctr Biomed Sci & Engn Sapporo Hokkaido Japan Univ Tokyo Grad Sch Frontier Sci Dept Computat Biol & Med Sci Kashiwa Chiba Japan Hiroshima Univ Grad Sch Biomed & Hlth Sci Dept Psychiat & Neurosci Hiroshima Japan Showa Univ Med Inst Dev Disabil Res Tokyo Japan Kyoto Univ Grad Sch Med Dept Psychiat Sakyo Ku Kyoto 6068507 Japan Univ Miyazaki Fac Med Dept Psychiat Div Clin Neurosci Kiyotak

One of the challenges in diagnosing psychiatric disorders is that the results of biological and neuroscience research are not reflected in the diagnostic criteria. Thus, data-driven analyses incorporating biological and cross-disease perspectives, regardless of the diagnostic category, have recently been proposed. A data-driven clustering study based on subcortical volumes in 5604 subjects classified into four brain biotypes associated with cognitive/social functioning. Among the four brain biotypes identified in controls and patients with schizophrenia, bipolar disorder, major depressive disorder, autism spectrum disorder, and other psychiatric disorders, we further analyzed the brain biotype 1 subjects, those with an extremely small limbic region, for clinical utility. We found that the representative feature of brain biotype 1 is enlarged lateral ventricles. An enlarged ventricle, defined by an average z-score of left and right lateral ventricle volumes > 3, had a sensitivity of 99.1% and a specificity of 98.1% for discriminating brain biotype 1. However, the presence of an enlarged ventricle was not sufficient to classify patient subgroups, as 1% of the controls also had enlarged ventricles. Reclassification of patients with enlarged ventricles according to cognitive impairment resulted in a stratified subgroup that included patients with a high proportion of schizophrenia diagnoses, electroencephalography abnormalities, and rare pathological genetic copy number variations. data-driven clustering analysis of neuroimaging data revealed subgroups with enlarged ventricles and cognitive impairment. This subgroup could be a new diagnostic candidate for psychiatric disorders. This concept and strategy may be useful for identifying biologically defined psychiatric disorders in the future.

关键词： cognitive impairment copy number variation data-driven analysis enlarged ventricles schizophrenia

来源：评论

学校读者我要写书评

暂无评论

Influence of distracted institutional investors on corporate green innovation: A data-driven analysis from China

引用

Journal of data, Information and Management 2025年 1-30页

作者： Chen, Yingying Cao, Chongyan School of Management University of Science and Technology of China Anhui 230026 China

With the proliferation of big data and advanced analytical methodologies, understanding the complex dynamics influencing corporate behavior has become increasingly feasible. In the era of information-intensive management, this study leverages data-driven approaches to explore the role of institutional investor distraction in promoting corporate green innovation—a key driver for sustainable economic growth in China. Utilizing a comprehensive dataset of A-listed Chinese firms from 2013 to 2022, we apply a double fixed-effects model and data mining techniques to analyze how distractions among institutional investors impact both substantive and strategic green innovation. Our findings reveal that investor distraction serves as a catalyst for green innovation, particularly enhancing substantive innovations. This relationship is mediated by the exit propensity enhancement and negative media coverage, while redundant resources act as a moderating factor. Furthermore, the influence is more pronounced in non-resource-based cities, highly competitive markets, non-state-owned enterprises, and firms with lower ESG ratings. By integrating data analysis with management science, this study provides actionable insights for policymakers and corporations, contributing to the interdisciplinary discourse on sustainable development and offering a balanced perspective between theoretical rigor and practical application. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： data-driven analysis Double fixed-effects model G23 G34 Green innovation Institutional investor distraction O31 O32 Sustainable management

来源：评论

学校读者我要写书评

暂无评论

data-driven analysis for disturbance amplification in car-following behavior of automated vehicles

引用

TRANSPORTATION RESEARCH PART B-METHODOLOGICAL 2023年 174卷

作者： Zhou, Yang Zhong, Xinzhi Chen, Qian Ahn, Soyoung Jiang, Jiwan Jafarsalehi, Ghazaleh Texas A&M Zachry Dept Civil & Environm Engn 199 Spence StRoom 301A College Stn TX 53706 USA Univ Wisconsin Madison Dept Civil & Environm Engn 1415 Engn Dr Madison WI 53706 USA Southeast Univ Sch Automat Nanjing Peoples R China Univ Calif Davis Dept Civil & Environm Engn Davis 1 Shields Ave Davis CA 95616 USA

This paper presents a data-driven framework to quantitatively analyze the disturbance amplification behavior of automated vehicles in car-following (CF). The data-driven framework can be applied to unknown CF controllers based on the concept of empirical frequency response function (FRF). Specifically, a well-known signal processing method, Welch's method, together with a short time Fourier transformation is developed to extract the empirical transfer functions from vehicle trajectories. The method is first developed assuming a generic linear controller with time -invariant CF control features (e.g., control gains) and later extended to capture time -variant features. The proposed methods are evaluated for estimation consistencies via synthetic data-based simulations. The evaluation includes the performances of the linear approximation accuracy for a linear time-invariant controller, a nonlinear controller, and a linear time-variant controller. Results indicate that our framework can provide reasonably consistent results as theoretical ones in terms of disturbance amplification. Further it can perform better than a linear theoretical analysis of disturbance amplification, particularly when nonlinearity in CF behavior is present. The methods are applied to existing field data collected from vehicles with adaptive cruise control (ACC) on the market. Findings reveal that all tested vehicles tend to amplify disturbances, particularly in low frequency (< 0.5 Hz). Further, the results demonstrate that these ACC vehicles exhibit time-varying features in terms of disturbance amplification ratio depending on the leading vehicle trajectories.

关键词： Adaptive cruise control Disturbance amplification data-driven analysis Carfollowing Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

data-driven analysis of medium-term wave-seabed interactions at a non-tidal beach with multiple bars

引用

MARINE GEOLOGY 2013年 344卷 144-154页

作者： Valsamidis, Antonios Rozynski, Grzegorz Reeve, Dominic E. Univ Coll Swansea Coll Engn Swansea SA2 8PP W Glam Wales Polish Acad Sci Inst Hydroengn IBW PAN Gdansk Poland

The main scope of this paper is the analysis of wave-seabed interactions which play a significant role during the morphological evolution of a non-tidal sandy beach with multiple bars. The primary technique employed in our analysis was the Canonical Correlation analysis (CCA). A large amount of field data is necessary in order to use a statistical method such as the CCA to produce reliable results. However, our study area, a non-tidal beach with multiple bars located at IBW PAN Coastal Research Station at Lubiatowo, Poland has been the subject of numerous surveys during the last couple of decades, providing valuable information regarding both the bathymetry and the wave climate in the nearshore area. To that end, key wave transformation patterns were identified. The division of the original data set of consecutive seabed surveys, complemented by wave measurements, into summer and winter subsets, and the separate application of the CCA to each one of them, produced relatively high skill predictions and provides insight into noticeably different patterns of wave transformation in both seasons. Finally, the results and the experience gained by the application of the CCA are discussed and summarized to highlight research potential of the CCA method. (C) 2013 Elsevier B.V. All rights reserved.

关键词： Canonical Correlation analysis multi-barred beach data-driven analysis beach morphodynamics

来源：评论

学校读者我要写书评

暂无评论

data-driven analysis of the kinetics of the JAK2V617F allele burden and blood cell counts during hydroxyurea treatment of patients with polycythemia vera, essential thrombocythemia, and primary myelofibrosis

引用

EUROPEAN JOURNAL OF HAEMATOLOGY 2021年第6期107卷 624-633页

作者： Dam, Marc J. B. Pedersen, Rasmus K. Knudsen, Trine A. Andersen, Morten Skov, Vibe Kjaer, Lasse Hasselbalch, Hans C. Ottesen, Johnny T. Roskilde Univ Dept Sci & Environm Ctr Math Modeling Human Hlth & Dis IMFUFA Roskilde Denmark Zealand Univ Hosp Dept Haematol Roskilde Denmark

Background Hydroxyurea (HU) treatment of patients with essential thrombocythemia (ET), polycythemia vera (PV), and primary myelofibrosis (PMF) (MPNs) normalizes elevated blood cell counts within weeks in the large majority of patients. Studies on the impact of HU upon the kinetics of the JAK2V617F allele burden, leukocyte, and platelet counts over time are scarce. Purpose Using data-driven analysis as a novel tool to model the kinetics of the JAK2V617F allele burden and blood cell counts over time during treatment with HU. Material and methods Using serial measurements of JAK2V617F and correlation analysis of routine hematological values (the Hb-concentration, leukocyte count, platelet count, and lactic dehydrogenase), we present a detailed description and analysis of the kinetics of the JAK2V617F, leukocyte, and platelet counts and lactic dehydrogenase in 27 patients (PV = 18;ET = 7;PMF = 2), who were followed in the Danish randomized trial (DALIAH). To further analyze the JAK2V617F kinetics, we use a machine learning clustering algorithm to group the response patterns. Results Response patterns were highly heterogeneous, with clustering resulting in 3 groups and 3 outliers. In the large majority of patients, HU treatment was initially associated with a modest decline in the JAK2V617F allele burden in concert with a decline in leukocyte and platelet counts. However, HU did not induce a sustained and continuous decrease in the JAK2V617F allele burden. Conclusion Using data-driven analysis of the JAK2V617F allele burden, leukocyte, and platelet kinetics during treatment with HU, we have shown that HU does not induce a sustained decrease in the JAK2V617F allele burden and neither induces sustained normalization of elevated cell counts in MPN patients. Our results may explain why MPN patients during treatment with HU still have a substantially increased risk of thrombosis.

关键词： data-driven analysis essential thrombocythemia polycythemia vera hydroxyurea interferon kinetics mathematical modeling MPN myelofibrosis myeloproliferative neoplasms

来源：评论

学校读者我要写书评

暂无评论

data-driven analysis of Virtual 3D Exploration of a Large Sculpture Collection in Real-World Museum Exhibitions

引用

ACM JOURNAL ON COMPUTING AND CULTURAL HERITAGE 2018年第1期11卷 1–20页

作者： Agus, Marco Marton, Fabio Bettio, Fabio Hadwiger, Markus Gobbetti, Enrico King Abdullah Univ Sci & Technol Visual Comp Ctr Bldg 1 Thuwal 239556900 Saudi Arabia CRS4 Pula CA Italy CRS4 POLARIS Ed 1 I-09010 Pula CA Italy

We analyze use of an interactive system for the exploration of highly detailed three-dimensional (3D) models of a collection of protostoric Mediterranean sculptures. In this system, when the object of interest is selected, its detailed 3D model and associated information are presented at high resolution on a large display controlled by a touch-enabled horizontal surface at a suitable distance. The user interface combines an object-aware interactive camera controller with an interactive point-of-interest selector and is implemented within a scalable implementation based on multiresolution structures shared between the rendering and user interaction subsystems. The system was installed in several temporary and permanent exhibitions and was extensively used by tens of thousands of visitors. We provide a data-driven analysis of usage experience based on logs gathered during a 27-month period at four exhibitions in archeological museums for a total of more than 75K exploration sessions. We focus on discerning the main visitor behaviors during 3D exploration by employing tools for deriving interest measures on surfaces and tools for clustering and knowledge discovery from high-dimensional data. The results highlight the main trends in visitor behavior during the interactive sessions. These results provide useful insights for the design of 3D exploration user interfaces in future digital installations.

关键词： Cultural Heritage Digital heritage virtual museums data-driven analysis user study

来源：评论

学校读者我要写书评

暂无评论

Subpercent Local Strains Due to the Shapes of Gold Nanorods Revealed by data-driven analysis

引用

ACS NANO 2021年第7期15卷 12077-12085页

作者： Aso, Kohei Maebe, Jens Tran, Xuan Quy Yamamoto, Tomokazu Oshima, Yoshifumi Matsumura, Syo Univ Ghent Fac Sci B-9000 Ghent Belgium Kyushu Univ Dept Appl Quantum Phys & Nucl Engn Fukuoka 8190395 Japan Kyushu Univ Ultramicroscopy Res Ctr Fukuoka 8190395 Japan Japan Adv Inst Sci & Technol Sch Mat Sci Nomi Ishikawa 9231292 Japan

analysis of subpercent local strain is important for a deeper understanding of nanomaterials, whose properties often depend on the strain. Conventional strain analysis has been performed by measuring interatomic distances from scanning transmission electron microscopy (STEM) images. However, measuring subpercent strain remains a challenge because the peak positions in STEM images do not precisely correspond to the real atomic positions due to disturbing influences, such as random noise and image distortion. Here, we utilized an advanced datadriven analysis method, Gaussian process regression, to predict the true strain distribution by reconstructing the true atomic positions. As a result, a precision of 0.2% was achieved in strain measurement at the atomic scale. The method was applied to gold nanoparticles of different shapes to reveal the shape dependence of the strain distribution. A spherical gold nanoparticle showed a symmetric strain distribution with a contraction of similar to 1% near the surface owing to surface relaxation. By contrast, a gold nanorod, which is a cylinder terminated by hemispherical caps on both sides, showed nonuniform strain distributions with lattice expansions of similar to 0.5% along the longitudinal axis around the caps except for the contraction at the surface. Our results indicate that the strain distribution depends on the shape of the nanomaterials. The proposed data-driven analysis is a convenient and powerful tool to measure the strain distribution with high precision at the atomic scale.

关键词： metal nanoparticles lattice strain data-driven analysis shape effect subpercent strain analysis

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Wheelset Health Status of Rail Transit Vehicles: Synthesis of Wear Mechanism and data-driven analysis

引用

JOURNAL OF TRANSPORTATION ENGINEERING PART A-SYSTEMS 2020年第12期146卷

作者： Zhu, Wei Xiao, Xin Huang, Zhaodong Fan, Wei Tongji Univ Shanghai Key Lab Rail Infrastruct Durabil & Syst Coll Transportat Engn Key Lab Rd & Traff EngnMinist Educ Shanghai 201804 Peoples R China Tongji Univ Minist Educ Coll Transportat Engn Key Lab Rd & Traff Engn Shanghai 201804 Peoples R China Ningbo Univ Coll Maritime & Transportat Ningbo 315211 Zhejiang Peoples R China Univ N Carolina USDOT Ctr Adv Multimodal Mobil Solut & Educ 9201 Univ City Blvd Charlotte NC 28223 USA Univ N Carolina Dept Civil & Environm Engn 9201 Univ City Blvd Charlotte NC 28223 USA

The security and reliability of rail transit vehicles in service are greatly affected by their wheel-rail contact. Thus, modeling the wear of wheelsets and monitoring their status is important for improving safety and reducing costs. A key issue involves evaluating the wheelset status accurately and using this as the basis for developing effective maintenance strategies and measures. However, the open nature of actual wheel-rail systems and their inconsistent environmental conditions make it difficult to construct a precise theoretical model that covers both wheelset wear and status evaluation. In this paper, a synthesis approach for evaluating the wheelset health status of rail transit vehicles is proposed. The wheelset health status is defined, and then a data-driven wheelset health evaluation model is developed. Potential causes of deviations between the model and reality are analyzed based on a theoretical wear mechanism, and application prerequisites for the proposed model are given. A case study involving the Shanghai Metro shows that the proposed approach operates well and can, therefore, be applied in practice. (c) 2020 American Society of Civil Engineers.

关键词： Rail transit vehicle Maintenance Wheelset health status Evaluation model data-driven analysis Wear mechanism

来源：评论

学校读者我要写书评

暂无评论

A data-driven analysis for Operational Vehicle Performance of Public Transport Network

引用

IEEE ACCESS 2019年 7卷 96404-96413页

作者： Zhang, Hui Cui, Houdun Shi, Baiying Shandong Jianzhu Univ Sch Transportat Engn Jinan 250101 Shandong Peoples R China Shandong Hispeed Grp Co Ltd Jinan 250098 Shandong Peoples R China

The operational stability of public transport is significant for both passengers and operators. Affected by many stochastic factors, such as traffic congestion, traffic signals and passenger demand at stops, the headway always become uneven, which greatly reduces the service quality. This paper used the big global positioning systems (GPS) trajectory data to analyze the headway stability of bus system from the perspective of network. A statistical method is proposed to analyze the operational vehicle performance of bus network. The GPS trajectory data of Jinan is used to test the model. The results show that the average dwell time, actual headway, and headway stability index of stations follow lognormal distributions with obvious right tails. Moreover, the seriously unstable situations do not appear in the peak hours, but in the time periods before peak hours. In addition, the stations with most unstable headway are located in the suburbs and the fringe area of downtown. The outcomes suggest that operators should pay more attention to the suburbs and the fringe area of downtown, and the time periods before peak hours to efficiently improve the service quality.

关键词： Public transport network stability of headway GPS trajectory data data-driven analysis

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：