检索结果-内蒙古大学图书馆

SSRN 2025年

作者： Yu, Qiong Niu, Jiageng Ou, Jushang Bai, Wei Wang, Nengfeng Jiang, Xinguo College of Civil Aviation Safety Engineering Civil Aviation Flight University of China Guanghan China School of Transportation and Logistics Southwest Jiaotong University Chengdu China Department of Road Traffic Management Sichuan Police College Sichuan Luzhou China POWERCHINA Chengdu Engineering Corporation Limited Chengdu China National Engineering Laboratory of Integrated Transportation Big Data Application Technology West Park High-Tech District Chengdu China School of Transportation Fujian University of Technology Fuzhou China

Hazardous actions are the critical contributor to motorcyclist injury severity, which are typically treated in parallel with other causal factors in crash severity models. However, hazardous actions may be the direct outcome of road users’ interaction with the roadway and environment. Consequently, in addition to direct effects, there may also be indirect effects of causal factors on motorcyclist injury severity as a result of hazardous actions. The research attempts to investigate both the direct, indirect, and total effects of causal factors on motorcyclist injury severity. A path analysis approach is employed to model the inter-relationship among hazardous actions, other causal factors, and motorcyclist injury severity. Specifically, with motorcycle crash data in Michigan from 2015 to 2018, two models are developed, namely, a random parameters logit model to examine the relationship between contributing factors and hazardous actions, and a correlated random parameters logit model with heterogeneity in means to assess the correlation between contributing factors and motorcyclist injury severity. Results indicate that factors such as stop/yield signs, intersections, one-way traffic, two-lane roads, midnight/early morning, weekends, and dawn/dusk, while not having a significantly direct impact on motorcyclist injury severity, indirectly increase the risk of injury severity through hazardous actions. Furthermore, under the influence of indirect effects, alcohol or drug use, speed limits of 55 mph or higher, and motorcycle age of six years or older are associated with a greater likelihood of increasing injury severity. Additionally, divided median strips with or without traffic barriers, rain/snow weather, and darkness with streetlights directly reduce motorcyclist injury severity but indirectly increase it through hazardous actions. The study reveals the complex underlying relationship among hazardous actions, other causal factors, and motorcyclist injury severity, w

关键词： Motorcycles

来源：评论

学校读者我要写书评

暂无评论

Collaborative optimization of vehicle formation and timetable for modular autonomous bus considering demand uncertainty:A data-driven continuous approximate method

引用

transportation Research Part E: Logistics and transportation Review 2025年 200卷

作者： Yao, Zhihong Zhang, Qi Fu, Chengxin Wu, Yunxia Jiang, Yangsheng School of Transportation and Logistics National Engineering Laboratory of Integrated Transportation Big Data Application Technology National United Engineering Laboratory of Integrated and Intelligent Transportation Southwest Jiaotong University Chengdu Sichuan610031 China

The emerging modular autonomous vehicle (MAV) provides new opportunities to address the imbalance between supply and demand in the public transportation system. The continuous approximation (CA) model can efficiently solve the optimal time-varying headway of bus corridors, but the current CA model for MAV corridors does not consider the demand uncertainty, and its vehicle formation method still has limitations. To solve these gaps, this paper proposes collaborative optimization of vehicle formation and timetable for modular autonomous bus considering demand uncertainty based on a data-driven continuous approximate method. First, a time-dependent passenger flow disturbance parameter is introduced to capture the uncertainty demand, and the CA model is extended under demand uncertainty. Second, data-driven stochastic optimization methods (i.e., stochastic programming and distributed robust optimization) are developed to address the loss function term with the random passenger flow in the CA model. Then, based on the proposed CA model, a mixed integer linear programming (MILP) model is developed to obtain the optimal vehicle formation. Finally, two numerical experiments were conducted to verify the effectiveness and superiority of the proposed model. Results show that, (1) the proposed vehicle formation model achieves up to a 9.8% reduction in average total system cost compared to the benchmark model. (2) stochastic programming and distributed robust optimization do not significantly reduce the average system total cost when demand is uncertain, but can significantly improve the robustness of timetables and vehicle formation. Compared to the deterministic model, the proposed method achieves a reduction of over 90% in both the sample standard deviation and the interquartile range on the test dataset. In summary, the proposed method can provide theoretical support for modular bus operation and scheduling under passenger flow uncertainty. © 2025 Elsevier Ltd

关键词： Stochastic programming

来源：评论

学校读者我要写书评

暂无评论

GDKansformer: A group-wise dynamic Kolmogorov–Arnold transformer with multi-view gated attention for pathological image diagnosis

引用

Expert Systems with applications 2025年 286卷

作者： Lu, Xiaoyan Gong, Xun Chen, Yuanyuan School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology and Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Chengdu611756 China Department of Pathology The Third People's Hospital of Chengdu Affiliated Hospital of Southwest Jiaotong University Chengdu610031 China

Pathological image diagnosis is a fundamental and critical component of precision medicine, playing a pivotal role in clinical decision-making. However, due to the high heterogeneity of pathological images, existing models still face the challenges of insufficient feature representation, poor interpretability, and high computational costs. To address these issues, we propose a novel pathological image diagnosis model called GDKansformer, which integrates the Group-wise Dynamic Kolmogorov–Arnold Network with a Vision Transformer (ViT) architecture. Specifically, this model employs adaptive dynamic fitting and group-wise computation strategies to seamlessly embed an improved Kolmogorov–Arnold Network (KAN) into ViTs, thereby boosting pathological representation and interpretability. The proposed group-wise computation strategy effectively mitigates the distribution overfitting caused by the KAN structure and significantly reduces the computational costs. Furthermore, a Multi-view Gated Attention (MVGA) block comprising pixel-level non-local neighborhoods and adaptive local perception is designed to eliminate redundant non-feature information and enhance contextual interactions, thereby improving the feature discrimination of the model for high heterogeneity data distributions. Experimental results demonstrate that GDKansformer achieves high accuracy with lower parameters, highlighting the significant potential in facilitating pathological diagnosis. © 2025

关键词： Pathology

来源：评论

学校读者我要写书评

暂无评论

PseudoSC: A Binary Approximation to Stochastic Computing within Latent Operation-Space for Ultra-Lightweight on-Edge DNNs 23

PseudoSC: A Binary Approximation to Stochastic Computing wit...

引用

Proceedings of the 60th Annual ACM/IEEE Design Automation Conference

作者： Jihe Wang Zhaoqing Wang Danghui Wang School of Computer Science Northwestern Polytechnical University Xi'an China Engineering Research Center of Embedded System Integration Ministry of Education Northwestern Polytechnical University Xi'an China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9798350323481

Recently, stochastic computing (SC) is increasingly popular in constructing MAC for on-edge DNNs benefiting from its outstanding energy-efficiency, including its adequate precision and gatelevel operation. However, current SC-DNN systems always include a lot of costly SNGs/APCs for inevitably switches between binary and stochastic domains, which mortgages incongruous resources to pay the "bill" of the domain-switches and impedes highly-concurrent deployments. In this work, PseudoSC, a binary approximation to low-discrepancy SC, is proposed to totally remove the domain-switch for SNG/APC-free SC-DNNs. Its basic idea is to virtually re-arrange a couple of stochastic operands into a 2-D latent op-space, in which, original Monte Carlo sampling can be partitioned into three sub-ops, i.e., two fixed binary-ops and a fractal recursion. In theory, the recursion forms an isomorphic partition of the sampling repeated in smaller scales until the binary base-case achieved, as a result, a SC-op is well approximated only with binary-ops. Based on above theory, a multi-lane micro-architecture is designed to unroll the recursion within a few cycles and its advantages on hardware saving is verified under popular DNNs. The evaluation shows that the DNN-models with our schemes achieve 98.7% accuracy of the fixed-point implementations, which significantly outperform other SOTA methods. In addition, its reduced structure improves the power efficiency by 3.67 times on average.

关键词： stochastic computing

来源：评论

学校读者我要写书评

暂无评论

FedDAG: Federated Domain Adversarial Generation Towards Generalizable Medical Image Analysis

arXiv

引用

arXiv 2025年

作者： Che, Haoxuan Wu, Yifei Jin, Haibo Xia, Yong Chen, Hao Department of Computer Science and Engineering Hong Kong University of Science and Technology University Hong Kong National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an710072 China Department of Computer Science and Engineering Department of Chemical and Biological Engineering Division of Life Science Hong Kong University of Science and Technology Hong Kong

Federated domain generalization aims to train a global model from multiple source domains and ensure its generalization ability to unseen target domains. Due to the target domain being with unknown domain shifts, attempting to approximate these gaps by source domains may be the key to improving model generalization capability. Existing works mainly focus on sharing and recombining local domain-specific attributes to increase data diversity and simulate potential domain shifts. However, these methods may be insufficient since only the local attribute recombination can be hard to touch the out-of-distribution of global data. In this paper, we propose a simple-yet-efficient framework named Federated Domain Adversarial Generation (FedDAG). It aims to simulate the domain shift and improve the model generalization by adversarially generating novel domains different from local and global source domains. Specifically, it generates novel-style images by maximizing the instance-level feature discrepancy between original and generated images and trains a generalizable task model by minimizing their feature discrepancy. Further, we observed that FedDAG could cause different performance improvements for local models. It may be due to inherent data isolation and heterogeneity among clients, exacerbating the imbalance in their generalization contributions to the global model. Ignoring this imbalance can lead the global model’s generalization ability to be sub-optimal, further limiting the novel domain generation procedure. Thus, to mitigate this imbalance, FedDAG hierarchically aggregates local models at the within-client and across-client levels by using the sharpness concept to evaluate client model generalization contributions. Extensive experiments across four medical benchmarks demonstrate FedDAG’s ability to enhance generalization in federated medical scenarios. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

LLM Knows Geometry Better than Algebra: Numerical Understanding of LLM-Based Agents in A Trading Arena

arXiv

引用

arXiv 2025年

作者： Ma, Tianmi Du, Jiawei Huang, Wenxin Wang, Wenjie Xie, Liang Zhong, Xian Zhou, Joey Tianyi Hubei Key Laboratory of Transportation Internet of Things Wuhan University of Technology China Hubei Key Laboratory of Big Data Intelligent Analysis and Application Hubei University China Centre for Frontier AI Research Agency for Science Technology and Research Singapore Institute of High Performance Computing Agency for Science Technology and Research Singapore School of Computing National University of Singapore Singapore School of Science Wuhan University of Technology China

Recent advancements in large language models (LLMs) have significantly improved performance in natural language processing tasks. However, their ability to generalize to dynamic, unseen tasks, particularly in numerical reasoning, remains a challenge. Existing benchmarks mainly evaluate LLMs on problems with predefined optimal solutions, which may not align with real-world scenarios where clear answers are absent. To bridge this gap, we design the Agent Trading Arena, a virtual numerical game simulating complex economic systems through zero-sum games, where agents invest in stock portfolios. Our experiments reveal that LLMs, including GPT-4o, struggle with algebraic reasoning when dealing with plain-text stock data, often focusing on local details rather than global trends. In contrast, LLMs perform significantly better with geometric reasoning when presented with visual data, such as scatter plots or K-line charts, suggesting that visual representations enhance numerical reasoning. This capability is further improved by incorporating the reflection module, which aids in the analysis and interpretation of complex data. We validate our findings on NASDAQ STOCK dataset, where LLMs demonstrate stronger reasoning with visual data compared to text. Our code and data are publicly available at https://***/wekjsdvnm/***. © 2025, CC BY.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Visible-Infrared Person Re-identification with Modality- and Instance-aware Adaptation Learning

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Wu, Ruiqi Jiao, Bingliang Liu, Meng Wang, Shining Wang, Wenxuan Wang, Peng Northwestern Polytechnical University School of Computer Science Xi'an710072 China Ningbo Institute Northwestern Polytechnical University Ningbo315000 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi'an710072 China Northwestern Polytechnical University School of Electronics and Information Xi'an710072 China Shenzhen Research Institute of Northwestern Polytechnical University Shenzhen518057 China

The Visible-Infrared Person Re-identification (VI ReID) aims to achieve cross-modality re-identification by matching pedestrian images from visible and infrared illumination. A crucial challenge in this task is mitigating the impact of modality divergence to enable the VI ReID model to learn cross-modality correspondence. Regarding this challenge, existing methods primarily focus on eliminating the information gap between different modalities by extracting modality-invariant information or supplementing inputs with specific information from another modality. However, these methods may overly focus on bridging the information gap, a challenging issue that could potentially overshadow the inherent complexities of cross-modality ReID itself. Based on this insight, we propose a straightforward yet effective strategy to empower the VI ReID model with sufficient flexibility to adapt diverse modality inputs to achieve cross-modality ReID effectively. Specifically, we introduce a Modality-aware and Instance-aware Visual Prompts (MIP) network, leveraging transformer architecture with customized visual prompts. In our MIP, a set of modality-aware prompts is designed to enable our model to dynamically adapt diverse modality inputs and effectively extract information for identification, thereby alleviating the interference of modality divergence. Besides, we also propose the instance-aware prompts, which are responsible for guiding the model to adapt individual pedestrians and capture discriminative clues for accurate identification. Through extensive experiments on four mainstream VI ReID datasets, the effectiveness of our designed modules is evaluated. Furthermore, our proposed MIP network outperforms most current state-of-the-art methods. © 1991-2012 IEEE.

关键词： Infrared devices

来源：评论

学校读者我要写书评

暂无评论

Leapfrog Polymorphic Neural Ordinary Differential Equation

引用

IEEE Signal Processing Letters 2025年 32卷 2139-2143页

作者： Zhang, Xiao Wei, Wei Zhang, Zhen Zhang, Lei Northwestern Polytechnical University School of Software Xi'an710072 China Northwestern Polytechnical University Shaanxi Provincial Key Laboratory of Speech and Image Information Processing School of Computer Science Xi'an710072 China Northwestern Polytechnical University National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science Xi'an710072 China The University of Adelaide school of computer science AdelaideSA5005 Australia

Neural Ordinary Differential Equations (NODEs) revolutionize the way we view residual networks as solvers for initial value problems (IVPs), with layer depth serving as the time step. In this study, we propose a more efficient extension of NODEs called Leap-Frog Polymorphic Neural ODEs (LF-NODEs). LF-NODEs introduce the leap-frog updating scheme, breaking free from the specific structure of time-evolving mixtures of multiple dynamical systems. In each time step (corresponding to each residual network layer), LF-NODEs integrate the features of multiple dynamical systems (residual network layers) by employing time-variant weights from different dynamical systems. Our LF-NODEs not only overcome the limitations in the representation power of individual residual networks but also provide a more flexible and effective structure for residual networks based on multiple dynamical systems. The efficiency of the leap-frog updating scheme is theoretically derived and demonstrated. Furthermore, we expand the model by incorporating a multi-scale approach (LF-MSNODEs) to achieve even more accurate model representations. Empirical results showcase the improvements provided by our proposed methods in 2D concentric spheres task, irregularly sampled time series prediction, and classification tasks. Additionally, the results provide empirical evidence that the learned feature space enhances system efficiency with fewer parameters and function evaluations compared to the baseline methods. © 1994-2012 IEEE.

关键词： Ordinary differential equations

来源：评论

学校读者我要写书评

暂无评论

Road rage patterns in Nigeria: A multi-level latent class analysis

引用

Case Studies on Transport Policy 2025年 20卷

作者： Labbo, Muwaffaq Safiyanu Jiang, Xinguo Wada, Surajo Abubakar de Dieu, Gatesi Jean Bala, Nuhu D. Management Science and Engineering Post-Doctoral Research Station China Three Gorges University Yichang 443002 China Department of Civil Engineering Aliko Dangote University of Science and Technology Kano Wudil Nigeria School of Transportation and Logistics Southwest Jiaotong University West Park High-Tech District Chengdu 611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology West Park High-Tech District Chengdu 611756 China Department of Civil Engineering Ahmadu Bello University Kaduna State Zaria 810107 Nigeria

Road crashes remain a serious concern in Nigeria, and road user behavior is a significant contributing factor. This study explores the relationship between risky driving behaviors and emotional experiences among Nigerian drivers, with a specific focus on anger expression patterns and their association with anger-induced situations. Employing a nuanced approach through multilevel latent class analysis (MLCA), the research identifies three high-level groups and four low-level classes of drivers. Among the low-level classes, Easily Angered Drivers, Travel Impatience Drivers, Prudent Drivers, and Calm Drivers exhibit distinct characteristics, while the high-level groups encompass the Physical and Verbal anger expression group, the Anger Control group, and the Use of Vehicle to express anger group. Multinomial regression results reveal that male drivers are more likely to belong to the Physical and Verbal anger expression group, aligning with prior research. Travel Impatience Drivers demonstrate a tendency to express anger physically or verbally, especially amid travel-related frustrations. Easily Angered Drivers, particularly in younger age groups, are more likely to exhibit physical and verbal anger expression and vehicular aggression. This tendency may stem from deficiencies in driver training systems, which often fail to equip novice drivers with adequate emotional regulation strategies and conflict management skills on the road. Proposed interventions include improving driver training, rigorous traffic law enforcement, and public awareness campaigns to foster responsible driving. © 2025 World Conference on Transport Research Society

关键词： Anger Expression Anger Induced Situations Multi Level Latent Class Analysis Risky Driving Behavior Road Rage Road Safety

来源：评论

学校读者我要写书评

暂无评论

Role of mountains and rivers in the formation of logistics enterprises'spatial pattern in the central urban areas of Chongqing

引用

Journal of Mountain Science 2022年第7期19卷 2060-2074页

作者： LIU Si-jing ZHU Cheng-jia HE Nan-nan LI Guo-qi School of Transportation and Logistics Southwest Jiaotong UniversityChengdu611756China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Chengdu611756China National United Engineering Laboratory of Integrated and Intelligent Transportation Chengdu611756China

The complex landforms of a Shan-shui City(Shan-shui refers to mountains and rivers)significantly impact the selection of locations for logistics *** paper takes Chongqing,one of the most typical Shan-shui Cities in China,as the research object,and adopts spatial analysis methods and a mediating effect model,to explore the role of mountains and rivers in the formation of logistics enterprises’spatial pattern on the street *** study results reveal that 90% of the logistics enterprises in the central urban areas of Chongqing are located in the low-altitude area below 353m above sea level,and distributed in a north-south direction along the mountains,as a result of blockage by mountain ranges,such as those of Zhongliang Mountain and Tongluo *** than 70% of the logistics enterprises are located less than 5 km from either the Yangtze River or Jialing River,spreading along the *** addition,more than half of the logistics enterprises in commercial and financial,and residential land are located within the urban core area,while 80.83% of the logistics enterprises located in warehousing land and industrial land are concentrated in the urban expansion *** areas with high land prices,the negative effect of altitude on logistics enterprise agglomeration is weakened,while the promotion effect of river proximity on logistics enterprise agglomeration is *** the urban core area with the advantage of low altitude and proximity to the Jialing and Yangtze Rivers,the role of mountains and rivers on logistics enterprises is not apparent;in contrast,in the urban expansion area with more complex landforms,land price can be an effective means for the government to macro-manage the spatial pattern of logistics enterprises in a Shan-shui City.

关键词： Logistics enterprise Spatial pattern Influencing factors Driving mechanism Chongqing

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：